google register code to crawl and index

CODE_OF_CONDUCT.md

@@ -1,9 +0,0 @@
-# Microsoft Open Source Code of Conduct
-
-This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
-
-Resources:
-
-- [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/)
-- [Microsoft Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/)
-- Contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with questions or concerns

Dockerfiles/1.0.23/Dockerfile

@@ -1,29 +0,0 @@
-FROM continuumio/miniconda:4.5.11
-
-# install git
-RUN apt-get update && apt-get upgrade -y && apt-get install -y git
-
-# create a new conda environment named azureml
-RUN conda create -n azureml -y -q Python=3.6
-
-# install additional packages used by sample notebooks. this is optional
-RUN ["/bin/bash", "-c", "source activate azureml && conda install -y tqdm cython matplotlib scikit-learn"]
-
-# install azurmel-sdk components
-RUN ["/bin/bash", "-c", "source activate azureml && pip install azureml-sdk[notebooks]==1.0.23"]
-
-# clone Azure ML GitHub sample notebooks
-RUN cd /home && git clone -b "azureml-sdk-1.0.23" --single-branch https://github.com/Azure/MachineLearningNotebooks.git
-
-# generate jupyter configuration file
-RUN ["/bin/bash", "-c", "source activate azureml && mkdir ~/.jupyter && cd ~/.jupyter && jupyter notebook --generate-config"]
-
-# set an emtpy token for Jupyter to remove authentication. 
-# this is NOT recommended for production environment
-RUN echo "c.NotebookApp.token = ''" >> ~/.jupyter/jupyter_notebook_config.py
-
-# open up port 8887 on the container
-EXPOSE 8887
-
-# start Jupyter notebook server on port 8887 when the container starts
-CMD /bin/bash -c "cd /home/MachineLearningNotebooks && source activate azureml && jupyter notebook --port 8887 --no-browser --ip 0.0.0.0 --allow-root"

Dockerfiles/1.0.30/Dockerfile

@@ -1,29 +0,0 @@
-FROM continuumio/miniconda:4.5.11
-
-# install git
-RUN apt-get update && apt-get upgrade -y && apt-get install -y git
-
-# create a new conda environment named azureml
-RUN conda create -n azureml -y -q Python=3.6
-
-# install additional packages used by sample notebooks. this is optional
-RUN ["/bin/bash", "-c", "source activate azureml && conda install -y tqdm cython matplotlib scikit-learn"]
-
-# install azurmel-sdk components
-RUN ["/bin/bash", "-c", "source activate azureml && pip install azureml-sdk[notebooks]==1.0.30"]
-
-# clone Azure ML GitHub sample notebooks
-RUN cd /home && git clone -b "azureml-sdk-1.0.30" --single-branch https://github.com/Azure/MachineLearningNotebooks.git
-
-# generate jupyter configuration file
-RUN ["/bin/bash", "-c", "source activate azureml && mkdir ~/.jupyter && cd ~/.jupyter && jupyter notebook --generate-config"]
-
-# set an emtpy token for Jupyter to remove authentication. 
-# this is NOT recommended for production environment
-RUN echo "c.NotebookApp.token = ''" >> ~/.jupyter/jupyter_notebook_config.py
-
-# open up port 8887 on the container
-EXPOSE 8887
-
-# start Jupyter notebook server on port 8887 when the container starts
-CMD /bin/bash -c "cd /home/MachineLearningNotebooks && source activate azureml && jupyter notebook --port 8887 --no-browser --ip 0.0.0.0 --allow-root"

Dockerfiles/1.0.33/Dockerfile

@@ -1,29 +0,0 @@
-FROM continuumio/miniconda:4.5.11
-
-# install git
-RUN apt-get update && apt-get upgrade -y && apt-get install -y git
-
-# create a new conda environment named azureml
-RUN conda create -n azureml -y -q Python=3.6
-
-# install additional packages used by sample notebooks. this is optional
-RUN ["/bin/bash", "-c", "source activate azureml && conda install -y tqdm cython matplotlib scikit-learn"]
-
-# install azurmel-sdk components
-RUN ["/bin/bash", "-c", "source activate azureml && pip install azureml-sdk[notebooks]==1.0.33"]
-
-# clone Azure ML GitHub sample notebooks
-RUN cd /home && git clone -b "azureml-sdk-1.0.33" --single-branch https://github.com/Azure/MachineLearningNotebooks.git
-
-# generate jupyter configuration file
-RUN ["/bin/bash", "-c", "source activate azureml && mkdir ~/.jupyter && cd ~/.jupyter && jupyter notebook --generate-config"]
-
-# set an emtpy token for Jupyter to remove authentication. 
-# this is NOT recommended for production environment
-RUN echo "c.NotebookApp.token = ''" >> ~/.jupyter/jupyter_notebook_config.py
-
-# open up port 8887 on the container
-EXPOSE 8887
-
-# start Jupyter notebook server on port 8887 when the container starts
-CMD /bin/bash -c "cd /home/MachineLearningNotebooks && source activate azureml && jupyter notebook --port 8887 --no-browser --ip 0.0.0.0 --allow-root"

Dockerfiles/1.0.41/Dockerfile

@@ -1,29 +0,0 @@
-FROM continuumio/miniconda:4.5.11
-
-# install git
-RUN apt-get update && apt-get upgrade -y && apt-get install -y git
-
-# create a new conda environment named azureml
-RUN conda create -n azureml -y -q Python=3.6
-
-# install additional packages used by sample notebooks. this is optional
-RUN ["/bin/bash", "-c", "source activate azureml && conda install -y tqdm cython matplotlib scikit-learn"]
-
-# install azurmel-sdk components
-RUN ["/bin/bash", "-c", "source activate azureml && pip install azureml-sdk[notebooks]==1.0.41"]
-
-# clone Azure ML GitHub sample notebooks
-RUN cd /home && git clone -b "azureml-sdk-1.0.41" --single-branch https://github.com/Azure/MachineLearningNotebooks.git
-
-# generate jupyter configuration file
-RUN ["/bin/bash", "-c", "source activate azureml && mkdir ~/.jupyter && cd ~/.jupyter && jupyter notebook --generate-config"]
-
-# set an emtpy token for Jupyter to remove authentication. 
-# this is NOT recommended for production environment
-RUN echo "c.NotebookApp.token = ''" >> ~/.jupyter/jupyter_notebook_config.py
-
-# open up port 8887 on the container
-EXPOSE 8887
-
-# start Jupyter notebook server on port 8887 when the container starts
-CMD /bin/bash -c "cd /home/MachineLearningNotebooks && source activate azureml && jupyter notebook --port 8887 --no-browser --ip 0.0.0.0 --allow-root"

Dockerfiles/1.0.43/Dockerfile

@@ -1,29 +0,0 @@
-FROM continuumio/miniconda:4.5.11
-
-# install git
-RUN apt-get update && apt-get upgrade -y && apt-get install -y git
-
-# create a new conda environment named azureml
-RUN conda create -n azureml -y -q Python=3.6
-
-# install additional packages used by sample notebooks. this is optional
-RUN ["/bin/bash", "-c", "source activate azureml && conda install -y tqdm cython matplotlib scikit-learn"]
-
-# install azurmel-sdk components
-RUN ["/bin/bash", "-c", "source activate azureml && pip install azureml-sdk[notebooks]==1.0.43"]
-
-# clone Azure ML GitHub sample notebooks
-RUN cd /home && git clone -b "azureml-sdk-1.0.43" --single-branch https://github.com/Azure/MachineLearningNotebooks.git
-
-# generate jupyter configuration file
-RUN ["/bin/bash", "-c", "source activate azureml && mkdir ~/.jupyter && cd ~/.jupyter && jupyter notebook --generate-config"]
-
-# set an emtpy token for Jupyter to remove authentication. 
-# this is NOT recommended for production environment
-RUN echo "c.NotebookApp.token = ''" >> ~/.jupyter/jupyter_notebook_config.py
-
-# open up port 8887 on the container
-EXPOSE 8887
-
-# start Jupyter notebook server on port 8887 when the container starts
-CMD /bin/bash -c "cd /home/MachineLearningNotebooks && source activate azureml && jupyter notebook --port 8887 --no-browser --ip 0.0.0.0 --allow-root"

NBSETUP.md

@@ -1,4 +1,6 @@
-# Set up your notebook environment for Azure Machine Learning
+# Setting up environment
+
+---
 
 To run the notebooks in this repository use one of following options.
 
@@ -10,7 +12,9 @@ Azure Notebooks is a hosted Jupyter-based notebook service in the Azure cloud. A
 1. Follow the instructions in the [Configuration](configuration.ipynb) notebook to create and connect to a workspace
 1. Open one of the sample notebooks
 
-    **Make sure the Azure Notebook kernel is set to `Python 3.6`** when you open a notebook by choosing Kernel > Change Kernel > Python 3.6 from the menus.
+    **Make sure the Azure Notebook kernel is set to `Python 3.6`** when you open a notebook
+
+    ![set kernel to Python 3.6](images/python36.png)
 
 ## **Option 2: Use your own notebook server**
 
@@ -24,11 +28,14 @@ pip install azureml-sdk
 git clone https://github.com/Azure/MachineLearningNotebooks.git
 
 # below steps are optional
-# install the base SDK, Jupyter notebook server and tensorboard
-pip install azureml-sdk[notebooks,tensorboard]
+# install the base SDK and a Jupyter notebook server
+pip install azureml-sdk[notebooks]
+
+# install the data prep component
+pip install azureml-dataprep
 
 # install model explainability component
-pip install azureml-sdk[interpret]
+pip install azureml-sdk[explain]
 
 # install automated ml components
 pip install azureml-sdk[automl]
@@ -51,7 +58,8 @@ Please make sure you start with the [Configuration](configuration.ipynb) noteboo
 
 ### Video walkthrough:
 
-[!VIDEO https://youtu.be/VIsXeTuW3FU]
+[![Get Started video](images/yt_cover.png)](https://youtu.be/VIsXeTuW3FU)
+
 
 ## **Option 3: Use Docker**
 
@@ -82,11 +90,14 @@ Now you can point your browser to http://localhost:8887. We recommend that you s
 If you need additional Azure ML SDK components, you can either modify the Docker files before you build the Docker images to add additional steps, or install them through command line in the live container after you build the Docker image. For example:
 
 ```sh
+# install dataprep components
+pip install azureml-dataprep
+
 # install the core SDK and automated ml components
 pip install azureml-sdk[automl]
 
 # install the core SDK and model explainability component
-pip install azureml-sdk[interpret]
+pip install azureml-sdk[explain]
 
 # install the core SDK and experimental components
 pip install azureml-sdk[contrib]

README.md

@@ -1,43 +1,56 @@
-# Azure Machine Learning Python SDK notebooks
+# Azure Machine Learning service example notebooks
 
-### **With the introduction of AzureML SDK v2, this samples repository for the v1 SDK is now deprecated and will not be monitored or updated. Users are encouraged to visit the [v2 SDK samples repository](https://github.com/Azure/azureml-examples) instead for up-to-date and enhanced examples of how to build, train, and deploy machine learning models with AzureML's newest features.**
+This repository contains example notebooks demonstrating the [Azure Machine Learning](https://azure.microsoft.com/en-us/services/machine-learning-service/) Python SDK which allows you to build, train, deploy and manage machine learning solutions using Azure.  The AML SDK allows you the choice of using local or cloud compute resources, while managing and maintaining the complete data science workflow from the cloud.
 
-Welcome to the Azure Machine Learning Python SDK notebooks repository!
-
-## Getting started
-
-These notebooks are recommended for use in an Azure Machine Learning [Compute Instance](https://docs.microsoft.com/azure/machine-learning/concept-compute-instance), where you can run them without any additional set up.
-
-However, the notebooks can be run in any development environment with the correct `azureml` packages installed.
-
-Install the `azureml.core` Python package:
+![Azure ML workflow](https://raw.githubusercontent.com/MicrosoftDocs/azure-docs/master/articles/machine-learning/service/media/overview-what-is-azure-ml/aml.png)
 
+## Quick installation
 ```sh
-pip install azureml-core
+pip install azureml-sdk
 ```
+Read more detailed instructions on [how to set up your environment](./NBSETUP.md) using Azure Notebook service, your own Jupyter notebook server, or Docker.
 
-Install additional packages as needed:
+## How to navigate and use the example notebooks?
+You should always run the [Configuration](./configuration.ipynb) notebook first when setting up a notebook library on a new machine or in a new environment. It configures your notebook library to connect to an Azure Machine Learning workspace, and sets up your workspace and compute to be used by many of the other examples. 
 
-```sh
-pip install azureml-mlflow
-pip install azureml-dataset-runtime
-pip install azureml-automl-runtime
-pip install azureml-pipeline
-pip install azureml-pipeline-steps
-...
-```
+If you want to...
 
-We recommend starting with one of the [quickstarts](tutorials/compute-instance-quickstarts).
+ * ...try out and explore Azure ML, start with image classification tutorials: [Part 1 (Training)](./tutorials/img-classification-part1-training.ipynb) and [Part 2 (Deployment)](./tutorials/img-classification-part2-deploy.ipynb).
+ * ...prepare your data and do automated machine learning, start with regression tutorials: [Part 1 (Data Prep)](./tutorials/regression-part1-data-prep.ipynb) and [Part 2 (Automated ML)](./tutorials/regression-part2-automated-ml.ipynb).
+ * ...learn about experimentation and tracking run history, first [train within Notebook](./how-to-use-azureml/training/train-within-notebook/train-within-notebook.ipynb), then try [training on remote VM](./how-to-use-azureml/training/train-on-remote-vm/train-on-remote-vm.ipynb) and [using logging APIs](./how-to-use-azureml/training/logging-api/logging-api.ipynb).
+ * ...train deep learning models at scale, first learn about [Machine Learning Compute](./how-to-use-azureml/training/train-on-amlcompute/train-on-amlcompute.ipynb), and then try [distributed hyperparameter tuning](./how-to-use-azureml/training-with-deep-learning/train-hyperparameter-tune-deploy-with-pytorch/train-hyperparameter-tune-deploy-with-pytorch.ipynb) and [distributed training](./how-to-use-azureml/training-with-deep-learning/distributed-pytorch-with-horovod/distributed-pytorch-with-horovod.ipynb).
+ * ...deploy models as a realtime scoring service, first learn the basics by [training within Notebook and deploying to Azure Container Instance](./how-to-use-azureml/training/train-within-notebook/train-within-notebook.ipynb), then learn how to [register and manage models, and create Docker images](./how-to-use-azureml/deployment/register-model-create-image-deploy-service/register-model-create-image-deploy-service.ipynb), and [production deploy models on Azure Kubernetes Cluster](./how-to-use-azureml/deployment/production-deploy-to-aks/production-deploy-to-aks.ipynb).
+ * ...deploy models as a batch scoring service, first [train a model within Notebook](./how-to-use-azureml/training/train-within-notebook/train-within-notebook.ipynb), learn how to [register and manage models](./how-to-use-azureml/deployment/register-model-create-image-deploy-service/register-model-create-image-deploy-service.ipynb), then [create Machine Learning Compute for scoring compute](./how-to-use-azureml/training/train-on-amlcompute/train-on-amlcompute.ipynb), and [use Machine Learning Pipelines to deploy your model](./how-to-use-azureml/machine-learning-pipelines/pipeline-mpi-batch-prediction.ipynb).
+ * ...monitor your deployed models, learn about using [App Insights](./how-to-use-azureml/deployment/enable-app-insights-in-production-service/enable-app-insights-in-production-service.ipynb) and [model data collection](./how-to-use-azureml/deployment/enable-data-collection-for-models-in-aks/enable-data-collection-for-models-in-aks.ipynb).
 
-## Contributing
+## Tutorials
 
-This repository is a push-only mirror. Pull requests are ignored.
+The [Tutorials](./tutorials) folder contains notebooks for the tutorials described in the [Azure Machine Learning documentation](https://aka.ms/aml-docs).
+  
+## How to use Azure ML
 
-## Code of Conduct
+The [How to use Azure ML](./how-to-use-azureml) folder contains specific examples demonstrating the features of the Azure Machine Learning SDK
 
-This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/). Please see the [code of conduct](CODE_OF_CONDUCT.md) for details.
+- [Training](./how-to-use-azureml/training) - Examples of how to build models using Azure ML's logging and execution capabilities on local and remote compute targets
+- [Training with Deep Learning](./how-to-use-azureml/training-with-deep-learning) - Examples demonstrating how to build deep learning models using estimators and parameter sweeps
+- [Manage Azure ML Service](./how-to-use-azureml/manage-azureml-service) - Examples how to perform tasks, such as authenticate against Azure ML service in different ways.
+- [Automated Machine Learning](./how-to-use-azureml/automated-machine-learning) - Examples using Automated Machine Learning to automatically generate optimal machine learning pipelines and models
+- [Machine Learning Pipelines](./how-to-use-azureml/machine-learning-pipelines) - Examples showing how to create and use reusable pipelines for training and batch scoring
+- [Deployment](./how-to-use-azureml/deployment) - Examples showing how to deploy and manage machine learning models and solutions
+- [Azure Databricks](./how-to-use-azureml/azure-databricks) - Examples showing how to use Azure ML with Azure Databricks
 
-## Reference
+---
+## Documentation
 
-- [Documentation](https://docs.microsoft.com/azure/machine-learning)
+ * Quickstarts, end-to-end tutorials, and how-tos on the [official documentation site for Azure Machine Learning service](https://docs.microsoft.com/en-us/azure/machine-learning/service/).
+ * [Python SDK reference](https://docs.microsoft.com/en-us/python/api/overview/azure/ml/intro?view=azure-ml-py)
+ * Azure ML Data Prep SDK [overview](https://aka.ms/data-prep-sdk), [Python SDK reference](https://aka.ms/aml-data-prep-apiref), and [tutorials and how-tos](https://aka.ms/aml-data-prep-notebooks).
 
+---
+
+## Projects using Azure Machine Learning
+
+Visit following repos to see projects contributed by Azure ML users:
+
+ - [Fine tune natural language processing models using Azure Machine Learning service](https://github.com/Microsoft/AzureML-BERT)
+ - [Fashion MNIST with Azure ML SDK](https://github.com/amynic/azureml-sdk-fashion)

SECURITY.md

@@ -1,41 +0,0 @@
-<!-- BEGIN MICROSOFT SECURITY.MD V0.0.7 BLOCK -->
-
-## Security
-
-Microsoft takes the security of our software products and services seriously, which includes all source code repositories managed through our GitHub organizations, which include [Microsoft](https://github.com/Microsoft), [Azure](https://github.com/Azure), [DotNet](https://github.com/dotnet), [AspNet](https://github.com/aspnet), [Xamarin](https://github.com/xamarin), and [our GitHub organizations](https://opensource.microsoft.com/).
-
-If you believe you have found a security vulnerability in any Microsoft-owned repository that meets [Microsoft's definition of a security vulnerability](https://aka.ms/opensource/security/definition), please report it to us as described below.
-
-## Reporting Security Issues
-
-**Please do not report security vulnerabilities through public GitHub issues.**
-
-Instead, please report them to the Microsoft Security Response Center (MSRC) at [https://msrc.microsoft.com/create-report](https://aka.ms/opensource/security/create-report).
-
-If you prefer to submit without logging in, send email to [secure@microsoft.com](mailto:secure@microsoft.com).  If possible, encrypt your message with our PGP key; please download it from the [Microsoft Security Response Center PGP Key page](https://aka.ms/opensource/security/pgpkey).
-
-You should receive a response within 24 hours. If for some reason you do not, please follow up via email to ensure we received your original message. Additional information can be found at [microsoft.com/msrc](https://aka.ms/opensource/security/msrc). 
-
-Please include the requested information listed below (as much as you can provide) to help us better understand the nature and scope of the possible issue:
-
-  * Type of issue (e.g. buffer overflow, SQL injection, cross-site scripting, etc.)
-  * Full paths of source file(s) related to the manifestation of the issue
-  * The location of the affected source code (tag/branch/commit or direct URL)
-  * Any special configuration required to reproduce the issue
-  * Step-by-step instructions to reproduce the issue
-  * Proof-of-concept or exploit code (if possible)
-  * Impact of the issue, including how an attacker might exploit the issue
-
-This information will help us triage your report more quickly.
-
-If you are reporting for a bug bounty, more complete reports can contribute to a higher bounty award. Please visit our [Microsoft Bug Bounty Program](https://aka.ms/opensource/security/bounty) page for more details about our active programs.
-
-## Preferred Languages
-
-We prefer all communications to be in English.
-
-## Policy
-
-Microsoft follows the principle of [Coordinated Vulnerability Disclosure](https://aka.ms/opensource/security/cvd).
-
-<!-- END MICROSOFT SECURITY.MD BLOCK -->

configuration.ipynb

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/configuration.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -58,7 +51,7 @@
         "\n",
         "### What is an Azure Machine Learning workspace\n",
         "\n",
-        "An Azure ML Workspace is an Azure resource that organizes and coordinates the actions of many other Azure resources to assist in executing and sharing machine learning workflows.  In particular, an Azure ML Workspace coordinates storage, databases, and compute resources providing added functionality for machine learning experimentation, deployment, inference, and the monitoring of deployed models."
+        "An Azure ML Workspace is an Azure resource that organizes and coordinates the actions of many other Azure resources to assist in executing and sharing machine learning workflows.  In particular, an Azure ML Workspace coordinates storage, databases, and compute resources providing added functionality for machine learning experimentation, deployment, inferencing, and the monitoring of deployed models."
       ]
     },
     {
@@ -103,7 +96,7 @@
       "source": [
         "import azureml.core\n",
         "\n",
-        "print(\"This notebook was created using version 1.59.0 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version 1.0.21 of the Azure ML SDK\")\n",
         "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },
@@ -214,10 +207,7 @@
         "* You do not have permission to create a resource group if it's non-existing.\n",
         "* You are not a subscription owner or contributor and no Azure ML workspaces have ever been created in this subscription\n",
         "\n",
-        "If workspace creation fails, please work with your IT admin to provide you with the appropriate permissions or to provision the required resources.\n",
-        "\n",
-        "**Note**: A Basic workspace is created by default. If you would like to create an Enterprise workspace, please specify sku = 'enterprise'.\n",
-        "Please visit our [pricing page](https://azure.microsoft.com/en-us/pricing/details/machine-learning/) for more details on our Enterprise edition.\n"
+        "If workspace creation fails, please work with your IT admin to provide you with the appropriate permissions or to provision the required resources."
       ]
     },
     {
@@ -238,7 +228,6 @@
         "                      resource_group = resource_group, \n",
         "                      location = workspace_region,\n",
         "                      create_resource_group = True,\n",
-        "                      sku = 'basic',\n",
         "                      exist_ok = True)\n",
         "ws.get_details()\n",
         "\n",
@@ -254,8 +243,6 @@
         "\n",
         "Many of the sample notebooks use Azure ML managed compute (AmlCompute) to train models using a dynamically scalable pool of compute. In this section you will create default compute clusters for use by the other notebooks and any other operations you choose.\n",
         "\n",
-        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
-        "\n",
         "To create a cluster, you need to specify a compute configuration that specifies the type of machine to be used and the scalability behaviors.  Then you choose a name for the cluster that is unique within the workspace that can be used to address the cluster later.\n",
         "\n",
         "The cluster parameters are:\n",
@@ -264,7 +251,7 @@
         "```shell\n",
         "az vm list-skus -o tsv\n",
         "```\n",
-        "* min_nodes - this sets the minimum size of the cluster.  If you set the minimum to 0 the cluster will shut down all nodes while not in use.  Setting this number to a value higher than 0 will allow for faster start-up times, but you will also be billed when the cluster is not in use.\n",
+        "* min_nodes - this sets the minimum size of the cluster.  If you set the minimum to 0 the cluster will shut down all nodes while note in use.  Setting this number to a value higher than 0 will allow for faster start-up times, but you will also be billed when the cluster is not in use.\n",
         "* max_nodes - this sets the maximum size of the cluster.  Setting this to a larger number allows for more concurrency and a greater distributed processing of scale-out jobs.\n",
         "\n",
         "\n",
@@ -281,14 +268,14 @@
         "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# Choose a name for your CPU cluster\n",
-        "cpu_cluster_name = \"cpu-cluster\"\n",
+        "cpu_cluster_name = \"cpucluster\"\n",
         "\n",
         "# Verify that cluster does not exist already\n",
         "try:\n",
         "    cpu_cluster = ComputeTarget(workspace=ws, name=cpu_cluster_name)\n",
-        "    print(\"Found existing cpu-cluster\")\n",
+        "    print(\"Found existing cpucluster\")\n",
         "except ComputeTargetException:\n",
-        "    print(\"Creating new cpu-cluster\")\n",
+        "    print(\"Creating new cpucluster\")\n",
         "    \n",
         "    # Specify the configuration for the new cluster\n",
         "    compute_config = AmlCompute.provisioning_configuration(vm_size=\"STANDARD_D2_V2\",\n",
@@ -319,17 +306,17 @@
         "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# Choose a name for your GPU cluster\n",
-        "gpu_cluster_name = \"gpu-cluster\"\n",
+        "gpu_cluster_name = \"gpucluster\"\n",
         "\n",
         "# Verify that cluster does not exist already\n",
         "try:\n",
         "    gpu_cluster = ComputeTarget(workspace=ws, name=gpu_cluster_name)\n",
         "    print(\"Found existing gpu cluster\")\n",
         "except ComputeTargetException:\n",
-        "    print(\"Creating new gpu-cluster\")\n",
+        "    print(\"Creating new gpucluster\")\n",
         "    \n",
         "    # Specify the configuration for the new cluster\n",
-        "    compute_config = AmlCompute.provisioning_configuration(vm_size=\"Standard_NC6s_v3\",\n",
+        "    compute_config = AmlCompute.provisioning_configuration(vm_size=\"STANDARD_NC6\",\n",
         "                                                           min_nodes=0,\n",
         "                                                           max_nodes=4)\n",
         "    # Create the cluster with the specified name and configuration\n",
@@ -363,13 +350,13 @@
   "metadata": {
     "authors": [
       {
-        "name": "ninhu"
+        "name": "roastala"
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.8 - AzureML",
+      "display_name": "Python 3.6",
       "language": "python",
-      "name": "python38-azureml"
+      "name": "python36"
     },
     "language_info": {
       "codemirror_mode": {

configuration.yml

@@ -1,4 +0,0 @@
-name: configuration
-dependencies:
-- pip:
-  - azureml-sdk

contrib/RAPIDS/process_data.py

@@ -15,6 +15,21 @@ from glob import glob
 import os
 import argparse
 
+def initialize_rmm_pool():
+    from librmm_cffi import librmm_config as rmm_cfg
+
+    rmm_cfg.use_pool_allocator = True
+    #rmm_cfg.initial_pool_size = 2<<30 # set to 2GiB. Default is 1/2 total GPU memory
+    import cudf
+    return cudf._gdf.rmm_initialize()
+
+def initialize_rmm_no_pool():
+    from librmm_cffi import librmm_config as rmm_cfg
+    
+    rmm_cfg.use_pool_allocator = False
+    import cudf
+    return cudf._gdf.rmm_initialize()
+
 def run_dask_task(func, **kwargs):
     task = func(**kwargs)
     return task
@@ -192,26 +207,26 @@ def gpu_load_names(col_path):
 
 def create_ever_features(gdf, **kwargs):
     everdf = gdf[['loan_id', 'current_loan_delinquency_status']]
-    everdf = everdf.groupby('loan_id', method='hash').max().reset_index()
+    everdf = everdf.groupby('loan_id', method='hash').max()
     del(gdf)
-    everdf['ever_30'] = (everdf['current_loan_delinquency_status'] >= 1).astype('int8')
-    everdf['ever_90'] = (everdf['current_loan_delinquency_status'] >= 3).astype('int8')
-    everdf['ever_180'] = (everdf['current_loan_delinquency_status'] >= 6).astype('int8')
-    everdf.drop_column('current_loan_delinquency_status')
+    everdf['ever_30'] = (everdf['max_current_loan_delinquency_status'] >= 1).astype('int8')
+    everdf['ever_90'] = (everdf['max_current_loan_delinquency_status'] >= 3).astype('int8')
+    everdf['ever_180'] = (everdf['max_current_loan_delinquency_status'] >= 6).astype('int8')
+    everdf.drop_column('max_current_loan_delinquency_status')
     return everdf
 
 def create_delinq_features(gdf, **kwargs):
     delinq_gdf = gdf[['loan_id', 'monthly_reporting_period', 'current_loan_delinquency_status']]
     del(gdf)
-    delinq_30 = delinq_gdf.query('current_loan_delinquency_status >= 1')[['loan_id', 'monthly_reporting_period']].groupby('loan_id', method='hash').min().reset_index()
-    delinq_30['delinquency_30'] = delinq_30['monthly_reporting_period']
-    delinq_30.drop_column('monthly_reporting_period')
-    delinq_90 = delinq_gdf.query('current_loan_delinquency_status >= 3')[['loan_id', 'monthly_reporting_period']].groupby('loan_id', method='hash').min().reset_index()
-    delinq_90['delinquency_90'] = delinq_90['monthly_reporting_period']
-    delinq_90.drop_column('monthly_reporting_period')
-    delinq_180 = delinq_gdf.query('current_loan_delinquency_status >= 6')[['loan_id', 'monthly_reporting_period']].groupby('loan_id', method='hash').min().reset_index()
-    delinq_180['delinquency_180'] = delinq_180['monthly_reporting_period']
-    delinq_180.drop_column('monthly_reporting_period')
+    delinq_30 = delinq_gdf.query('current_loan_delinquency_status >= 1')[['loan_id', 'monthly_reporting_period']].groupby('loan_id', method='hash').min()
+    delinq_30['delinquency_30'] = delinq_30['min_monthly_reporting_period']
+    delinq_30.drop_column('min_monthly_reporting_period')
+    delinq_90 = delinq_gdf.query('current_loan_delinquency_status >= 3')[['loan_id', 'monthly_reporting_period']].groupby('loan_id', method='hash').min()
+    delinq_90['delinquency_90'] = delinq_90['min_monthly_reporting_period']
+    delinq_90.drop_column('min_monthly_reporting_period')
+    delinq_180 = delinq_gdf.query('current_loan_delinquency_status >= 6')[['loan_id', 'monthly_reporting_period']].groupby('loan_id', method='hash').min()
+    delinq_180['delinquency_180'] = delinq_180['min_monthly_reporting_period']
+    delinq_180.drop_column('min_monthly_reporting_period')
     del(delinq_gdf)
     delinq_merge = delinq_30.merge(delinq_90, how='left', on=['loan_id'], type='hash')
     delinq_merge['delinquency_90'] = delinq_merge['delinquency_90'].fillna(np.dtype('datetime64[ms]').type('1970-01-01').astype('datetime64[ms]'))
@@ -264,15 +279,16 @@ def create_joined_df(gdf, everdf, **kwargs):
 def create_12_mon_features(joined_df, **kwargs):
     testdfs = []
     n_months = 12
-
     for y in range(1, n_months + 1):
         tmpdf = joined_df[['loan_id', 'timestamp_year', 'timestamp_month', 'delinquency_12', 'upb_12']]
         tmpdf['josh_months'] = tmpdf['timestamp_year'] * 12 + tmpdf['timestamp_month']
         tmpdf['josh_mody_n'] = ((tmpdf['josh_months'].astype('float64') - 24000 - y) / 12).floor()
-        tmpdf = tmpdf.groupby(['loan_id', 'josh_mody_n'], method='hash').agg({'delinquency_12': 'max','upb_12': 'min'}).reset_index()
-        tmpdf['delinquency_12'] = (tmpdf['delinquency_12']>3).astype('int32')
-        tmpdf['delinquency_12'] +=(tmpdf['upb_12']==0).astype('int32')
-        tmpdf['upb_12'] = tmpdf['upb_12']
+        tmpdf = tmpdf.groupby(['loan_id', 'josh_mody_n'], method='hash').agg({'delinquency_12': 'max','upb_12': 'min'})
+        tmpdf['delinquency_12'] = (tmpdf['max_delinquency_12']>3).astype('int32')
+        tmpdf['delinquency_12'] +=(tmpdf['min_upb_12']==0).astype('int32')
+        tmpdf.drop_column('max_delinquency_12')
+        tmpdf['upb_12'] = tmpdf['min_upb_12']
+        tmpdf.drop_column('min_upb_12')
         tmpdf['timestamp_year'] = (((tmpdf['josh_mody_n'] * n_months) + 24000 + (y - 1)) / 12).floor().astype('int16')
         tmpdf['timestamp_month'] = np.int8(y)
         tmpdf.drop_column('josh_mody_n')
@@ -313,7 +329,6 @@ def last_mile_cleaning(df, **kwargs):
         'delinquency_30', 'delinquency_90', 'delinquency_180', 'upb_12',
         'zero_balance_effective_date','foreclosed_after', 'disposition_date','timestamp'
     ]
-
     for column in drop_list:
         df.drop_column(column)
     for col, dtype in df.dtypes.iteritems():
@@ -327,6 +342,7 @@ def last_mile_cleaning(df, **kwargs):
     return df.to_arrow(preserve_index=False)
 
 def main():
+    #print('XGBOOST_BUILD_DOC is ' + os.environ['XGBOOST_BUILD_DOC'])
     parser = argparse.ArgumentParser("rapidssample")
     parser.add_argument("--data_dir", type=str, help="location of data")
     parser.add_argument("--num_gpu", type=int, help="Number of GPUs to use", default=1)
@@ -348,6 +364,7 @@ def main():
     print('data_dir = {0}'.format(data_dir))
     print('num_gpu = {0}'.format(num_gpu))
     print('part_count = {0}'.format(part_count))
+    #part_count = part_count + 1 # adding one because the usage below is not inclusive
     print('end_year = {0}'.format(end_year))
     print('cpu_predictor = {0}'.format(cpu_predictor))
     
@@ -363,17 +380,19 @@ def main():
     client
     print(client.ncores())
 
-    # to download data for this notebook, visit https://rapidsai.github.io/demos/datasets/mortgage-data and update the following paths accordingly
+# to download data for this notebook, visit https://rapidsai.github.io/demos/datasets/mortgage-data and update the following paths accordingly
     acq_data_path = "{0}/acq".format(data_dir) #"/rapids/data/mortgage/acq"
     perf_data_path = "{0}/perf".format(data_dir) #"/rapids/data/mortgage/perf"
     col_names_path = "{0}/names.csv".format(data_dir) # "/rapids/data/mortgage/names.csv"
     start_year = 2000
+#end_year = 2000 # end_year is inclusive -- converted to parameter
+#part_count = 2 # the number of data files to train against -- converted to parameter
 
+    client.run(initialize_rmm_pool)
     client
-    print('--->>> Workers used: {0}'.format(client.ncores()))
-
-    # NOTE: The ETL calculates additional features which are then dropped before creating the XGBoost DMatrix.
-    # This can be optimized to avoid calculating the dropped features.
+    print(client.ncores())
+# NOTE: The ETL calculates additional features which are then dropped before creating the XGBoost DMatrix.
+# This can be optimized to avoid calculating the dropped features.
     print("Reading ...")
     t1 = datetime.datetime.now()
     gpu_dfs = []
@@ -395,9 +414,14 @@ def main():
             
     wait(gpu_dfs)
     t2 = datetime.datetime.now()
-    print("Reading time: {0}".format(str(t2-t1)))
-    print('--->>> Number of data parts: {0}'.format(len(gpu_dfs)))
-
+    print("Reading time ...")
+    print(t2-t1)
+    print('len(gpu_dfs) is {0}'.format(len(gpu_dfs)))
+    
+    client.run(cudf._gdf.rmm_finalize)
+    client.run(initialize_rmm_no_pool)
+    client
+    print(client.ncores())
     dxgb_gpu_params = {
         'nround':            100,
         'max_depth':         8,
@@ -414,7 +438,7 @@ def main():
         'n_gpus':            1, 
         'distributed_dask':  True,
         'loss':              'ls',
-        'objective':         'reg:squarederror',
+        'objective':         'gpu:reg:linear',
         'max_features':      'auto',
         'criterion':         'friedman_mse',
         'grow_policy':       'lossguide',
@@ -422,13 +446,13 @@ def main():
     }
       
     if cpu_predictor:
-        print('\n---->>>> Training using CPUs <<<<----\n')
+        print('Training using CPUs')
         dxgb_gpu_params['predictor'] = 'cpu_predictor'
         dxgb_gpu_params['tree_method'] = 'hist'
         dxgb_gpu_params['objective'] = 'reg:linear'
         
     else:
-        print('\n---->>>> Training using GPUs <<<<----\n')
+        print('Training using GPUs')
     
     print('Training parameters are {0}'.format(dxgb_gpu_params))
     
@@ -457,13 +481,14 @@ def main():
     gpu_dfs = [gpu_df.persist() for gpu_df in gpu_dfs]
     gc.collect()
     wait(gpu_dfs)
-
-    # TRAIN THE MODEL
+    
     labels = None
     t1 = datetime.datetime.now()
     bst = dxgb_gpu.train(client, dxgb_gpu_params, gpu_dfs, labels, num_boost_round=dxgb_gpu_params['nround'])
     t2 = datetime.datetime.now()
-    print('\n---->>>> Training time: {0} <<<<----\n'.format(str(t2-t1)))
+    print("Training time ...")
+    print(t2-t1)
+    print('str(bst) is {0}'.format(str(bst)))
     print('Exiting script')
 
 if __name__ == '__main__':

contrib/RAPIDS/rapids.yml

@@ -0,0 +1,35 @@
+name: rapids
+channels:
+- nvidia
+- numba
+- conda-forge
+- rapidsai
+- defaults
+- pytorch
+
+dependencies:
+- arrow-cpp=0.12.0
+- bokeh
+- cffi=1.11.5
+- cmake=3.12
+- cuda92
+- cython==0.29
+- dask=1.1.1
+- distributed=1.25.3
+- faiss-gpu=1.5.0
+- numba=0.42
+- numpy=1.15.4
+- nvstrings
+- pandas=0.23.4
+- pyarrow=0.12.0
+- scikit-learn
+- scipy
+- cudf
+- cuml
+- python=3.6.2
+- jupyterlab
+- pip:
+  - file:/rapids/xgboost/python-package/dist/xgboost-0.81-py3-none-any.whl
+  - git+https://github.com/rapidsai/dask-xgboost@dask-cudf
+  - git+https://github.com/rapidsai/dask-cudf@master
+  - git+https://github.com/rapidsai/dask-cuda@master

googled8147fb6c0788258.html

@@ -0,0 +1 @@
+google-site-verification: googled8147fb6c0788258.html

how-to-use-azureml/README.md

@@ -4,11 +4,14 @@ Learn how to use Azure Machine Learning services for experimentation and model m
 
 As a pre-requisite, run the [configuration Notebook](../configuration.ipynb) notebook first to set up your Azure ML Workspace. Then, run the notebooks in following recommended order.
 
-* [train-within-notebook](./training/train-within-notebook): Train a model while tracking run history, and learn how to deploy the model as web service to Azure Container Instance.
+* [train-within-notebook](./training/train-within-notebook): Train a model hile tracking run history, and learn how to deploy the model as web service to Azure Container Instance.
 * [train-on-local](./training/train-on-local): Learn how to submit a run to local computer and use Azure ML managed run configuration.
 * [train-on-amlcompute](./training/train-on-amlcompute): Use a 1-n node Azure ML managed compute cluster for remote runs on Azure CPU or GPU infrastructure.
 * [train-on-remote-vm](./training/train-on-remote-vm): Use Data Science Virtual Machine as a target for remote runs.
-* [logging-api](./track-and-monitor-experiments/logging-api): Learn about the details of logging metrics to run history.
+* [logging-api](./training/logging-api): Learn about the details of logging metrics to run history.
+* [register-model-create-image-deploy-service](./deployment/register-model-create-image-deploy-service): Learn about the details of model management.
+* [production-deploy-to-aks](./deployment/production-deploy-to-aks) Deploy a model to production at scale on Azure Kubernetes Service.
+* [enable-data-collection-for-models-in-aks](./deployment/enable-data-collection-for-models-in-aks) Learn about data collection APIs for deployed model.
 * [enable-app-insights-in-production-service](./deployment/enable-app-insights-in-production-service) Learn how to use App Insights with production web service.
  
 Find quickstarts, end-to-end tutorials, and how-tos on the [official documentation site for Azure Machine Learning service](https://docs.microsoft.com/en-us/azure/machine-learning/service/).

how-to-use-azureml/automated-machine-learning/README.md

@@ -1,8 +1,8 @@
 # Table of Contents
 1. [Automated ML Introduction](#introduction)
-1. [Setup using Compute Instances](#jupyter)
-1. [Setup using a Local Conda environment](#localconda)
-1. [Setup using Azure Databricks](#databricks)
+1. [Running samples in Azure Notebooks](#jupyter)
+1. [Running samples in Azure Databricks](#databricks)
+1. [Running samples in a Local Conda environment](#localconda)
 1. [Automated ML SDK Sample Notebooks](#samples)
 1. [Documentation](#documentation)
 1. [Running using python command](#pythoncommand)
@@ -13,25 +13,33 @@
 Automated machine learning (automated ML) builds high quality machine learning models for you by automating model and hyperparameter selection. Bring a labelled dataset that you want to build a model for, automated ML will give you a high quality machine learning model that you can use for predictions.
 
 
-If you are new to Data Science, automated ML will help you get jumpstarted by simplifying machine learning model building. It abstracts you from needing to perform model selection, hyperparameter selection and in one step creates a high quality trained model for you to use.
+If you are new to Data Science, AutoML will help you get jumpstarted by simplifying machine learning model building. It abstracts you from needing to perform model selection, hyperparameter selection and in one step creates a high quality trained model for you to use.
 
-If you are an experienced data scientist, automated ML will help increase your productivity by intelligently performing the model and hyperparameter selection for your training and generates high quality models much quicker than manually specifying several combinations of the parameters and running training jobs. Automated ML provides visibility and access to all the training jobs and the performance characteristics of the models to help you further tune the pipeline if you desire.
+If you are an experienced data scientist, AutoML will help increase your productivity by intelligently performing the model and hyperparameter selection for your training and generates high quality models much quicker than manually specifying several combinations of the parameters and running training jobs. AutoML provides visibility and access to all the training jobs and the performance characteristics of the models to help you further tune the pipeline if you desire.
 
-Below are the three execution environments supported by automated ML.
+Below are the three execution environments supported by AutoML.
 
 
  <a name="jupyter"></a>
-## Setup using Compute Instances - Jupyter based notebooks from a Azure Virtual Machine
+## Running samples in Azure Notebooks - Jupyter based notebooks in the Azure cloud
 
-1. Open the [ML Azure portal](https://ml.azure.com)
-1. Select Compute
-1. Select Compute Instances
-1. Click New
-1. Type a Compute Name, select a Virtual Machine type and select a Virtual Machine size
-1. Click Create
+1. [![Azure Notebooks](https://notebooks.azure.com/launch.png)](https://aka.ms/aml-clone-azure-notebooks)
+[Import sample notebooks ](https://aka.ms/aml-clone-azure-notebooks) into Azure Notebooks.
+1. Follow the instructions in the [configuration](../../configuration.ipynb) notebook to create and connect to a workspace.
+1. Open one of the sample notebooks.
+
+ <a name="databricks"></a>
+## Running samples in Azure Databricks
+
+**NOTE**: Please create your Azure Databricks cluster as v4.x (high concurrency preferred) with **Python 3** (dropdown).
+**NOTE**: You should at least have contributor access to your Azure subcription to run the notebook.
+- Please remove the previous SDK version if there is any and install the latest SDK by installing **azureml-sdk[automl_databricks]** as a PyPi library in Azure Databricks workspace.
+- You can find the detail Readme instructions at [GitHub](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/azure-databricks).
+- Download the sample notebook automl-databricks-local-01.ipynb from [GitHub](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/azure-databricks) and import into the Azure databricks workspace.
+- Attach the notebook to the cluster.
 
 <a name="localconda"></a>
-## Setup using a Local Conda environment
+## Running samples in a Local Conda environment
 
 To run these notebook on your own notebook server, use these installation instructions.
 The instructions below will install everything you need and then start a Jupyter notebook.
@@ -41,15 +49,11 @@ The instructions below will install everything you need and then start a Jupyter
 There's no need to install mini-conda specifically.
 
 ### 2. Downloading the sample notebooks
-- Download the sample notebooks from [GitHub](https://github.com/Azure/MachineLearningNotebooks) as zip and extract the contents to a local directory.  The automated ML sample notebooks are in the "automated-machine-learning" folder.
+- Download the sample notebooks from [GitHub](https://github.com/Azure/MachineLearningNotebooks) as zip and extract the contents to a local directory.  The AutoML sample notebooks are in the "automl" folder.
 
 ### 3. Setup a new conda environment
-The **automl_setup** script creates a new conda environment, installs the necessary packages, configures the widget and starts a jupyter notebook. It takes the conda environment name as an optional parameter.  The default conda environment name is azure_automl.  The exact command depends on the operating system.  See the specific sections below for Windows, Mac and Linux.  It can take about 10 minutes to execute.
-
-Packages installed by the **automl_setup** script:
-    <ul><li>python</li><li>nb_conda</li><li>matplotlib</li><li>numpy</li><li>cython</li><li>urllib3</li><li>scipy</li><li>scikit-learn</li><li>pandas</li><li>tensorflow</li><li>py-xgboost</li><li>azureml-sdk</li><li>azureml-widgets</li><li>pandas-ml</li></ul>
-
-For more details refer to the [automl_env.yml](./automl_env.yml)
+The **automl/automl_setup** script creates a new conda environment, installs the necessary packages, configures the widget and starts a jupyter notebook.
+It takes the conda environment name as an optional parameter.  The default conda environment name is azure_automl.  The exact command depends on the operating system.  See the specific sections below for Windows, Mac and Linux.  It can take about 10 minutes to execute.
 ## Windows
 Start an **Anaconda Prompt** window, cd to the **how-to-use-azureml/automated-machine-learning** folder where the sample notebooks were extracted and then run:
 ```
@@ -77,7 +81,7 @@ bash automl_setup_linux.sh
 
 ### 5. Running Samples
 - Please make sure you use the Python [conda env:azure_automl] kernel when trying the sample Notebooks.
-- Follow the instructions in the individual notebooks to explore various features in automated ML.
+- Follow the instructions in the individual notebooks to explore various features in AutoML
 
 ### 6. Starting jupyter notebook manually
 To start your Jupyter notebook manually, use:
@@ -94,99 +98,96 @@ source activate azure_automl
 jupyter notebook
 ```
 
- <a name="databricks"></a>
-## Setup using Azure Databricks
-
-**NOTE**: Please create your Azure Databricks cluster as v7.1 (high concurrency preferred) with **Python 3** (dropdown).
-**NOTE**: You should at least have contributor access to your Azure subcription to run the notebook.
-- You can find the detail Readme instructions at [GitHub](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/azure-databricks/automl).
-- Download the sample notebook automl-databricks-local-01.ipynb from [GitHub](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/azure-databricks/automl) and import into the Azure databricks workspace.
-- Attach the notebook to the cluster.
-
 <a name="samples"></a>
 # Automated ML SDK Sample Notebooks
 
-## Classification
-- **Classify Credit Card Fraud**
-    - Dataset: [Kaggle's credit card fraud detection dataset](https://www.kaggle.com/mlg-ulb/creditcardfraud)
-      - **[Jupyter Notebook (remote run)](classification-credit-card-fraud/auto-ml-classification-credit-card-fraud.ipynb)**
-          - run the experiment remotely on AML Compute cluster
-          - test the performance of the best model in the local environment
-      - **[Jupyter Notebook (local run)](local-run-classification-credit-card-fraud/auto-ml-classification-credit-card-fraud-local.ipynb)**
-          - run experiment in the local environment
-          - use Mimic Explainer for computing feature importance
-          - deploy the best model along with the explainer to an Azure Kubernetes (AKS) cluster, which will compute the raw and engineered feature importances at inference time
-- **Predict Term Deposit Subscriptions in a Bank**
-    - Dataset: [UCI's bank marketing dataset](https://www.kaggle.com/janiobachmann/bank-marketing-dataset)
-        - **[Jupyter Notebook](classification-bank-marketing-all-features/auto-ml-classification-bank-marketing-all-features.ipynb)**
-          - run experiment remotely on AML Compute cluster to generate ONNX compatible models
-          - view the featurization steps that were applied during training
-          - view feature importance for the best model
-          - download the best model in ONNX format and use it for inferencing using ONNXRuntime
-          - deploy the best model in PKL format to Azure Container Instance (ACI)
-- **Predict Newsgroup based on Text from News Article**
-    - Dataset: [20 newsgroups text dataset](https://scikit-learn.org/0.19/datasets/twenty_newsgroups.html)
-        - **[Jupyter Notebook](classification-text-dnn/auto-ml-classification-text-dnn.ipynb)**
-          - AutoML highlights here include using deep neural networks (DNNs) to create embedded features from text data
-          - AutoML will use Bidirectional Encoder Representations from Transformers (BERT) when a GPU compute is used
-          - Bidirectional Long-Short Term neural network (BiLSTM) will be utilized when a CPU compute is used, thereby optimizing the choice of DNN
+- [auto-ml-classification.ipynb](classification/auto-ml-classification.ipynb)
+    - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
+    - Simple example of using Auto ML for classification
+    - Uses local compute for training
 
-## Regression
-- **Predict Performance of Hardware Parts**
-    - Dataset: Hardware Performance Dataset
-        - **[Jupyter Notebook](regression/auto-ml-regression.ipynb)**
-            - run the experiment remotely on AML Compute cluster
-            - get best trained model for a different metric than the one the experiment was optimized for
-            - test the performance of the best model in the local environment
-        - **[Jupyter Notebook (advanced)](regression/auto-ml-regression.ipynb)**
-            - run the experiment remotely on AML Compute cluster
-            - customize featurization: override column purpose within the dataset, configure transformer parameters
-            - get best trained model for a different metric than the one the experiment was optimized for
-            - run a model explanation experiment on the remote cluster
-            - deploy the model along the explainer and run online inferencing
+- [auto-ml-regression.ipynb](regression/auto-ml-regression.ipynb)
+    - Dataset: scikit learn's [diabetes dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_diabetes.html)
+    - Simple example of using Auto ML for regression
+    - Uses local compute for training
 
-## Time Series Forecasting
-- **Forecast Energy Demand**
-    - Dataset: [NYC energy demand data](http://mis.nyiso.com/public/P-58Blist.htm)
-        - **[Jupyter Notebook](forecasting-energy-demand/auto-ml-forecasting-energy-demand.ipynb)**
-          - run experiment remotely on AML Compute cluster
-          - use lags and rolling window features
-          - view the featurization steps that were applied during training
-          - get the best model, use it to forecast on test data and compare the accuracy of predictions against real data
-- **Forecast Orange Juice Sales (Multi-Series)**
-    - Dataset: [Dominick's grocery sales of orange juice](forecasting-orange-juice-sales/dominicks_OJ.csv)
-        - **[Jupyter Notebook](forecasting-orange-juice-sales/dominicks_OJ.csv)**
-          - run experiment remotely on AML Compute cluster
-          - customize time-series featurization, change column purpose and override transformer hyper parameters
-          - evaluate locally the performance of the generated best model
-          - deploy the best model as a webservice on Azure Container Instance (ACI)
-          - get online predictions from the deployed model
-- **Forecast Demand of a Bike-Sharing Service**
-    - Dataset: [Bike demand data](forecasting-bike-share/bike-no.csv)
-        - **[Jupyter Notebook](forecasting-bike-share/auto-ml-forecasting-bike-share.ipynb)**
-          - run experiment remotely on AML Compute cluster
-          - integrate holiday features
-          - run rolling forecast for test set that is longer than the forecast horizon
-          - compute metrics on the predictions from the remote forecast
-- **The Forecast Function Interface**
-    - Dataset: Generated for sample purposes
-        - **[Jupyter Notebook](forecasting-forecast-function/auto-ml-forecasting-function.ipynb)**
-          - train a forecaster using a remote AML Compute cluster
-          - capabilities of forecast function (e.g. forecast farther into the horizon)
-          - generate confidence intervals
-- **Forecast Beverage Production**
-    - Dataset: [Monthly beer production data](forecasting-beer-remote/Beer_no_valid_split_train.csv)
-        - **[Jupyter Notebook](forecasting-beer-remote/auto-ml-forecasting-beer-remote.ipynb)**
-          - train using a remote AML Compute cluster
-          - enable the DNN learning model
-          - forecast on a remote compute cluster and compare different model performance
-- **Continuous Retraining with NOAA Weather Data**
-    - Dataset: [NOAA weather data from Azure Open Datasets](https://azure.microsoft.com/en-us/services/open-datasets/)
-        - **[Jupyter Notebook](continuous-retraining/auto-ml-continuous-retraining.ipynb)**
-          - continuously retrain a model using Pipelines and AutoML
-          - create a Pipeline to upload a time series dataset to an Azure blob
-          - create a Pipeline to run an AutoML experiment and register the best resulting model in the Workspace
-          - publish the training pipeline created and schedule it to run daily
+- [auto-ml-remote-execution.ipynb](remote-execution/auto-ml-remote-execution.ipynb)
+    - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
+    - Example of using Auto ML for classification using a remote linux DSVM for training
+    - Parallel execution of iterations
+    - Async tracking of progress
+    - Cancelling individual iterations or entire run
+    - Retrieving models for any iteration or logged metric
+    - Specify automl settings as kwargs
+
+- [auto-ml-remote-amlcompute.ipynb](remote-batchai/auto-ml-remote-amlcompute.ipynb)
+    - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
+    - Example of using automated ML for classification using remote AmlCompute for training
+    - Parallel execution of iterations
+    - Async tracking of progress
+    - Cancelling individual iterations or entire run
+    - Retrieving models for any iteration or logged metric
+    - Specify automl settings as kwargs
+
+- [auto-ml-remote-attach.ipynb](remote-attach/auto-ml-remote-attach.ipynb)
+    - Dataset: Scikit learn's [20newsgroup](http://scikit-learn.org/stable/datasets/twenty_newsgroups.html)
+    - handling text data with preprocess flag
+    - Reading data from a blob store for remote executions
+    - using pandas dataframes for reading data
+
+- [auto-ml-missing-data-blacklist-early-termination.ipynb](missing-data-blacklist-early-termination/auto-ml-missing-data-blacklist-early-termination.ipynb)
+    - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
+    - Blacklist certain pipelines
+    - Specify a target metrics to indicate stopping criteria
+    - Handling Missing Data in the input
+
+- [auto-ml-sparse-data-train-test-split.ipynb](sparse-data-train-test-split/auto-ml-sparse-data-train-test-split.ipynb)
+    - Dataset: Scikit learn's [20newsgroup](http://scikit-learn.org/stable/datasets/twenty_newsgroups.html)
+    - Handle sparse datasets
+    - Specify custom train and validation set
+
+- [auto-ml-exploring-previous-runs.ipynb](exploring-previous-runs/auto-ml-exploring-previous-runs.ipynb)
+    - List all projects for the workspace
+    - List all AutoML Runs for a given project
+    - Get details for a AutoML Run. (Automl settings, run widget & all metrics)
+    - Download fitted pipeline for any iteration
+
+- [auto-ml-remote-execution-with-datastore.ipynb](remote-execution-with-datastore/auto-ml-remote-execution-with-datastore.ipynb)
+    - Dataset: Scikit learn's [20newsgroup](http://scikit-learn.org/stable/datasets/twenty_newsgroups.html)
+    - Download the data and store it in DataStore.
+
+- [auto-ml-classification-with-deployment.ipynb](classification-with-deployment/auto-ml-classification-with-deployment.ipynb)
+    - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
+    - Simple example of using Auto ML for classification
+    - Registering the model
+    - Creating Image and creating aci service
+    - Testing the aci service
+
+- [auto-ml-sample-weight.ipynb](sample-weight/auto-ml-sample-weight.ipynb)
+    - How to specifying sample_weight
+    - The difference that it makes to test results
+
+- [auto-ml-subsampling-local.ipynb](subsampling/auto-ml-subsampling-local.ipynb)
+    - How to enable subsampling
+
+- [auto-ml-dataprep.ipynb](dataprep/auto-ml-dataprep.ipynb)
+    - Using DataPrep for reading data
+
+- [auto-ml-dataprep-remote-execution.ipynb](dataprep-remote-execution/auto-ml-dataprep-remote-execution.ipynb)
+    - Using DataPrep for reading data with remote execution
+
+- [auto-ml-classification-with-whitelisting.ipynb](classification-with-whitelisting/auto-ml-classification-with-whitelisting.ipynb)
+    - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
+    - Simple example of using Auto ML for classification with whitelisting tensorflow models.
+    - Uses local compute for training
+
+- [auto-ml-forecasting-energy-demand.ipynb](forecasting-energy-demand/auto-ml-forecasting-energy-demand.ipynb)
+    - Dataset: [NYC energy demand data](forecasting-a/nyc_energy.csv)
+    - Example of using AutoML for training a forecasting model
+
+- [auto-ml-forecasting-orange-juice-sales.ipynb](forecasting-orange-juice-sales/auto-ml-forecasting-orange-juice-sales.ipynb)
+    - Dataset: [Dominick's grocery sales of orange juice](forecasting-b/dominicks_OJ.csv)
+    - Example of training an AutoML forecasting model on multiple time-series
 
 <a name="documentation"></a>
 See [Configure automated machine learning experiments](https://docs.microsoft.com/azure/machine-learning/service/how-to-configure-auto-train) to learn how more about the the settings and features available for automated machine learning experiments.
@@ -205,18 +206,10 @@ The main code of the file must be indented so that it is under this condition.
 <a name="troubleshooting"></a>
 # Troubleshooting
 ## automl_setup fails
-1. On Windows, make sure that you are running automl_setup from an Anconda Prompt window rather than a regular cmd window.  You can launch the "Anaconda Prompt" window by hitting the Start button and typing "Anaconda Prompt".  If you don't see the application "Anaconda Prompt", you might not have conda or mini conda installed.  In that case, you can install it [here](https://conda.io/miniconda.html)
+1. On windows, make sure that you are running automl_setup from an Anconda Prompt window rather than a regular cmd window.  You can launch the "Anaconda Prompt" window by hitting the Start button and typing "Anaconda Prompt".  If you don't see the application "Anaconda Prompt", you might not have conda or mini conda installed.  In that case, you can install it [here](https://conda.io/miniconda.html)
 2. Check that you have conda 64-bit installed rather than 32-bit.  You can check this with the command `conda info`.  The `platform` should be `win-64` for Windows or `osx-64` for Mac.
-3. Check that you have conda 4.7.8 or later.  You can check the version with the command `conda -V`.  If you have a previous version installed, you can update it using the command: `conda update conda`.
-4. On Linux, if the error is `gcc: error trying to exec 'cc1plus': execvp: No such file or directory`, install build essentials using the command `sudo apt-get install build-essential`.
-5. Pass a new name as the first parameter to automl_setup so that it creates a new conda environment. You can view existing conda environments using `conda env list` and remove them with `conda env remove -n <environmentname>`.
-
-## automl_setup_linux.sh fails
-If automl_setup_linux.sh fails on Ubuntu Linux with the error: `unable to execute 'gcc': No such file or directory`
-1. Make sure that outbound ports 53 and 80 are enabled.  On an Azure VM, you can do this from the Azure Portal by selecting the VM and clicking on Networking.
-2. Run the command: `sudo apt-get update`
-3. Run the command: `sudo apt-get install build-essential --fix-missing`
-4. Run `automl_setup_linux.sh` again.
+3. Check that you have conda 4.4.10 or later.  You can check the version with the command `conda -V`.  If you have a previous version installed, you can update it using the command: `conda update conda`.
+4. Pass a new name as the first parameter to automl_setup so that it creates a new conda environment. You can view existing conda environments using `conda env list` and remove them with `conda env remove -n <environmentname>`. 
 
 ## configuration.ipynb fails
 1) For local conda, make sure that you have susccessfully run automl_setup first.
@@ -225,17 +218,6 @@ If automl_setup_linux.sh fails on Ubuntu Linux with the error: `unable to execut
 4) Check that the region is one of the supported regions: `eastus2`, `eastus`, `westcentralus`, `southeastasia`, `westeurope`, `australiaeast`, `westus2`, `southcentralus`
 5) Check that you have access to the region using the Azure Portal.
 
-## import AutoMLConfig fails after upgrade from before 1.0.76 to 1.0.76 or later
-There were package changes in automated machine learning version 1.0.76, which require the previous version to be uninstalled before upgrading to the new version.
-If you have manually upgraded from a version of automated machine learning before 1.0.76 to 1.0.76 or later, you may get the error:
-`ImportError: cannot import name 'AutoMLConfig'`
-
-This can be resolved by running:
-`pip uninstall azureml-train-automl` and then 
-`pip install azureml-train-automl`
-
-The automl_setup.cmd script does this automatically.
-
 ## workspace.from_config fails
 If the call `ws = Workspace.from_config()` fails:
 1) Make sure that you have run the `configuration.ipynb` notebook successfully.
@@ -251,29 +233,13 @@ If a sample notebook fails with an error that property, method or library does n
 ## Numpy import fails on Windows
 Some Windows environments see an error loading numpy with the latest Python version 3.6.8.  If you see this issue, try with Python version 3.6.7.
 
-## Numpy import fails
-Check the tensorflow version in the automated ml conda environment. Supported versions are < 1.13. Uninstall tensorflow from the environment if version is >= 1.13
-You may check the version of tensorflow and uninstall as follows
-1) start a command shell, activate conda environment where automated ml packages are installed
-2) enter `pip freeze` and look for `tensorflow` , if found, the version listed should be < 1.13
-3) If the listed version is a not a supported version,  `pip uninstall tensorflow` in the command shell and enter y for confirmation.
-
-## KeyError: 'brand' when running AutoML on local compute or Azure Databricks cluster**
-If a new environment was created after 10 June 2020 using SDK 1.7.0 or lower, training may fail with the above error due to an update in the py-cpuinfo package. (Environments created on or before 10 June 2020 are unaffected, as well as experiments run on remote compute as cached training images are used.) To work around this issue, either of the two following steps can be taken:
-
-1) Update the SDK version to 1.8.0 or higher (this will also downgrade py-cpuinfo to 5.0.0):
-`pip install --upgrade azureml-sdk[automl]`
-
-2) Downgrade the installed version of py-cpuinfo to 5.0.0:
-`pip install py-cpuinfo==5.0.0`
-
-## Remote run: DsvmCompute.create fails
+## Remote run: DsvmCompute.create fails 
 There are several reasons why the DsvmCompute.create can fail.  The reason is usually in the error message but you have to look at the end of the error message for the detailed reason.  Some common reasons are:
 1) `Compute name is invalid, it should start with a letter, be between 2 and 16 character, and only include letters (a-zA-Z), numbers (0-9) and \'-\'.`  Note that underscore is not allowed in the name.
-2) `The requested VM size xxxxx is not available in the current region.`  You can select a different region or vm_size.
+2) `The requested VM size xxxxx is not available in the current region.`  You can select a different region or vm_size. 
 
 ## Remote run: Unable to establish SSH connection
-Automated ML uses the SSH protocol to communicate with remote DSVMs.  This defaults to port 22.  Possible causes for this error are:
+AutoML uses the SSH protocol to communicate with remote DSVMs.  This defaults to port 22.  Possible causes for this error are:
 1) The DSVM is not ready for SSH connections.  When DSVM creation completes, the DSVM might still not be ready to acceept SSH connections.  The sample notebooks have a one minute delay to allow for this.
 2) Your Azure Subscription may restrict the IP address ranges that can access the DSVM on port 22.  You can check this in the Azure Portal by selecting the Virtual Machine and then clicking Networking.  The Virtual Machine name is the name that you provided in the notebook plus 10 alpha numeric characters to make the name unique.  The Inbound Port Rules define what can access the VM on specific ports.  Note that there is a priority priority order.  So, a Deny entry with a low priority number will override a Allow entry with a higher priority number.
 
@@ -284,16 +250,16 @@ This is often an issue with the `get_data` method.
 3) You can get to the error log for the setup iteration by clicking the `Click here to see the run in Azure portal` link, click `Back to Experiment`, click on the highest run number and then click on Logs.
 
 ## Remote run: disk full
-Automated ML creates files under /tmp/azureml_runs for each iteration that it runs.  It creates a folder with the iteration id.  For example: AutoML_9a038a18-77cc-48f1-80fb-65abdbc33abe_93.  Under this, there is a azureml-logs folder, which contains logs.  If you run too many iterations on the same DSVM, these files can fill the disk.
+AutoML creates files under /tmp/azureml_runs for each iteration that it runs.  It creates a folder with the iteration id.  For example: AutoML_9a038a18-77cc-48f1-80fb-65abdbc33abe_93.  Under this, there is a azureml-logs folder, which contains logs.  If you run too many iterations on the same DSVM, these files can fill the disk.
 You can delete the files under /tmp/azureml_runs or just delete the VM and create a new one.
 If your get_data downloads files, make sure the delete them or they can use disk space as well.
 When using DataStore, it is good to specify an absolute path for the files so that they are downloaded just once.  If you specify a relative path, it will download a file for each iteration.
 
 ## Remote run: Iterations fail and the log contains "MemoryError"
-This can be caused by insufficient memory on the DSVM.  Automated ML loads all training data into memory.  So, the available memory should be more than the training data size.
+This can be caused by insufficient memory on the DSVM.  AutoML loads all training data into memory.  So, the available memory should be more than the training data size.
 If you are using a remote DSVM, memory is needed for each concurrent iteration.  The max_concurrent_iterations setting specifies the maximum concurrent iterations.  For example, if the training data size is 8Gb and max_concurrent_iterations is set to 10, the minimum memory required is at least 80Gb.
 To resolve this issue, allocate a DSVM with more memory or reduce the value specified for max_concurrent_iterations.
 
 ## Remote run: Iterations show as "Not Responding" in the RunDetails widget.
 This can be caused by too many concurrent iterations for a remote DSVM.  Each concurrent iteration usually takes 100% of a core when it is running.  Some iterations can use multiple cores.  So, the max_concurrent_iterations setting should always be less than the number of cores of the DSVM.
-To resolve this issue, try reducing the value specified for the max_concurrent_iterations setting.
+To resolve this issue, try reducing the value specified for the max_concurrent_iterations setting.

how-to-use-azureml/automated-machine-learning/automl_env.yml

@@ -1,26 +1,22 @@
-name: azure_automl
-channels:
-  - conda-forge
-  - pytorch
-  - main
-dependencies:
-  # The python interpreter version.
-  # Azure ML only supports 3.8 and later.
-- pip==22.3.1
-- python>=3.10,<3.11
-- holidays==0.29
-- scipy==1.10.1
-- tqdm==4.66.1
-
-- pip:
-  # Required packages for AzureML execution, history, and data preparation.
-  - azureml-widgets~=1.59.0
-  - azureml-defaults~=1.59.0
-  - -r https://automlcesdkdataresources.blob.core.windows.net/validated-requirements/1.59.0/validated_win32_requirements.txt [--no-deps]
-  - matplotlib==3.7.1
-  - xgboost==1.5.2
-  - prophet==1.1.4
-  - onnx==1.16.1
-  - setuptools-git==1.2
-  - spacy==3.7.4
-  - https://aka.ms/automl-resources/packages/en_core_web_sm-3.7.1.tar.gz
+name: azure_automl
+dependencies:
+  # The python interpreter version.
+  # Currently Azure ML only supports 3.5.2 and later.
+- python>=3.5.2,<3.6.8
+- nb_conda
+- matplotlib==2.1.0
+- numpy>=1.11.0,<1.15.0
+- cython
+- urllib3<1.24
+- scipy>=1.0.0,<=1.1.0
+- scikit-learn>=0.18.0,<=0.19.1
+- pandas>=0.22.0,<0.23.0
+- tensorflow>=1.12.0
+- py-xgboost<=0.80
+
+- pip:
+  # Required packages for AzureML execution, history, and data preparation.
+  - azureml-sdk[automl,explain]
+  - azureml-widgets
+  - pandas_ml
+  

how-to-use-azureml/automated-machine-learning/automl_env_linux.yml

@@ -1,30 +0,0 @@
-name: azure_automl
-channels:
-  - conda-forge
-  - pytorch
-  - main
-dependencies:
-  # The python interpreter version.
-  # Azure ML only supports 3.7 and later.
-- pip==22.3.1
-- python>=3.10,<3.11
-- matplotlib==3.7.1
-- numpy>=1.21.6,<=1.23.5
-- urllib3==1.26.7
-- scipy==1.10.1
-- scikit-learn==1.5.1
-- holidays==0.29
-- pytorch::pytorch=1.11.0
-- cudatoolkit=10.1.243
-- notebook
-
-- pip:
-  # Required packages for AzureML execution, history, and data preparation.
-  - azureml-widgets~=1.59.0
-  - azureml-defaults~=1.59.0
-  - pytorch-transformers==1.0.0
-  - spacy==3.7.4
-  - xgboost==1.5.2
-  - prophet==1.1.4
-  - https://aka.ms/automl-resources/packages/en_core_web_sm-3.7.1.tar.gz
-  - -r https://automlcesdkdataresources.blob.core.windows.net/validated-requirements/1.59.0/validated_linux_requirements.txt [--no-deps]

how-to-use-azureml/automated-machine-learning/automl_env_mac.yml

@@ -1,26 +1,23 @@
-name: azure_automl
-channels:
-  - conda-forge
-  - pytorch
-  - main
-dependencies:
-  # The python interpreter version.
-  # Currently Azure ML only supports 3.7 and later.
-- pip==22.3.1
-- python>=3.10,<3.11
-- numpy>=1.21.6,<=1.23.5
-- scipy==1.10.1
-- scikit-learn==1.5.1
-- holidays==0.29
-
-- pip:
-  # Required packages for AzureML execution, history, and data preparation.
-  - azureml-widgets~=1.59.0
-  - azureml-defaults~=1.59.0
-  - pytorch-transformers==1.0.0
-  - prophet==1.1.4
-  - xgboost==1.5.2
-  - spacy==3.7.4
-  - matplotlib==3.7.1
-  - https://aka.ms/automl-resources/packages/en_core_web_sm-3.7.1.tar.gz
-  - -r https://automlcesdkdataresources.blob.core.windows.net/validated-requirements/1.59.0/validated_darwin_requirements.txt [--no-deps]
+name: azure_automl
+dependencies:
+  # The python interpreter version.
+  # Currently Azure ML only supports 3.5.2 and later.
+- python>=3.5.2,<3.6.8
+- nb_conda
+- matplotlib==2.1.0
+- numpy>=1.15.3
+- cython
+- urllib3<1.24
+- scipy>=1.0.0,<=1.1.0
+- scikit-learn>=0.18.0,<=0.19.1
+- pandas>=0.22.0,<0.23.0
+- tensorflow>=1.12.0
+- py-xgboost<=0.80
+
+- pip:
+  # Required packages for AzureML execution, history, and data preparation.
+  - azureml-sdk[automl,explain]
+  - azureml-widgets
+  - pandas_ml
+  
+

how-to-use-azureml/automated-machine-learning/automl_setup.cmd

@@ -1,80 +1,51 @@
-@echo off
-set conda_env_name=%1
-set automl_env_file=%2
-set options=%3
-set PIP_NO_WARN_SCRIPT_LOCATION=0
-
-IF "%conda_env_name%"=="" SET conda_env_name="azure_automl"
-IF "%automl_env_file%"=="" SET automl_env_file="automl_env.yml"
-SET check_conda_version_script="check_conda_version.py"
-
-IF NOT EXIST %automl_env_file% GOTO YmlMissing
-
-IF "%CONDA_EXE%"=="" GOTO CondaMissing
-
-IF NOT EXIST %check_conda_version_script% GOTO VersionCheckMissing
-
-python "%check_conda_version_script%"
-IF errorlevel 1 GOTO ErrorExit:
-
-SET replace_version_script="replace_latest_version.ps1"
-IF EXIST %replace_version_script% (
-  powershell -file %replace_version_script% %automl_env_file%
-)
-
-call conda activate %conda_env_name% 2>nul:
-
-if not errorlevel 1 (
-  echo Upgrading existing conda environment %conda_env_name%
-  call pip uninstall azureml-train-automl -y -q
-  call conda env update --name %conda_env_name% --file %automl_env_file%
-  if errorlevel 1 goto ErrorExit
-) else (
-  call conda env create -f %automl_env_file% -n %conda_env_name%
-)
-
-python "%conda_prefix%\scripts\pywin32_postinstall.py" -install
-
-call conda activate %conda_env_name% 2>nul:
-if errorlevel 1 goto ErrorExit
-
-call python -m ipykernel install --user --name %conda_env_name% --display-name "Python (%conda_env_name%)"
-
-REM azureml.widgets is now installed as part of the pip install under the conda env.
-REM Removing the old user install so that the notebooks will use the latest widget.
-call jupyter nbextension uninstall --user --py azureml.widgets
-
-echo.
-echo.
-echo ***************************************
-echo * AutoML setup completed successfully *
-echo ***************************************
-IF NOT "%options%"=="nolaunch" (
-  echo.
-  echo Starting jupyter notebook - please run the configuration notebook 
-  echo.
-  jupyter notebook --log-level=50 --notebook-dir='..\..'
-)
-
-goto End
-
-:CondaMissing
-echo Please run this script from an Anaconda Prompt window.
-echo You can start an Anaconda Prompt window by
-echo typing Anaconda Prompt on the Start menu.
-echo If you don't see the Anaconda Prompt app, install Miniconda.
-echo If you are running an older version of Miniconda or Anaconda,
-echo you can upgrade using the command: conda update conda
-goto End
-
-:VersionCheckMissing
-echo File %check_conda_version_script% not found.
-goto End
-
-:YmlMissing
-echo File %automl_env_file% not found.
-
-:ErrorExit
-echo Install failed
-
+@echo off
+set conda_env_name=%1
+set automl_env_file=%2
+set options=%3
+set PIP_NO_WARN_SCRIPT_LOCATION=0
+
+IF "%conda_env_name%"=="" SET conda_env_name="azure_automl"
+IF "%automl_env_file%"=="" SET automl_env_file="automl_env.yml"
+
+IF NOT EXIST %automl_env_file% GOTO YmlMissing
+
+call conda activate %conda_env_name% 2>nul:
+
+if not errorlevel 1 (
+  echo Upgrading azureml-sdk[automl,notebooks,explain] in existing conda environment %conda_env_name%
+  call pip install --upgrade azureml-sdk[automl,notebooks,explain]
+  if errorlevel 1 goto ErrorExit
+) else (
+  call conda env create -f %automl_env_file% -n %conda_env_name%
+)
+
+call conda activate %conda_env_name% 2>nul:
+if errorlevel 1 goto ErrorExit
+
+call python -m ipykernel install --user --name %conda_env_name% --display-name "Python (%conda_env_name%)"
+
+REM azureml.widgets is now installed as part of the pip install under the conda env.
+REM Removing the old user install so that the notebooks will use the latest widget.
+call jupyter nbextension uninstall --user --py azureml.widgets
+
+echo.
+echo.
+echo ***************************************
+echo * AutoML setup completed successfully *
+echo ***************************************
+IF NOT "%options%"=="nolaunch" (
+  echo.
+  echo Starting jupyter notebook - please run the configuration notebook 
+  echo.
+  jupyter notebook --log-level=50 --notebook-dir='..\..'
+)
+
+goto End
+
+:YmlMissing
+echo File %automl_env_file% not found.
+
+:ErrorExit
+echo Install failed
+
 :End

how-to-use-azureml/automated-machine-learning/automl_setup_linux.sh

@@ -4,7 +4,6 @@ CONDA_ENV_NAME=$1
 AUTOML_ENV_FILE=$2
 OPTIONS=$3
 PIP_NO_WARN_SCRIPT_LOCATION=0
-CHECK_CONDA_VERSION_SCRIPT="check_conda_version.py"
 
 if [ "$CONDA_ENV_NAME" == "" ]
 then
@@ -13,7 +12,7 @@ fi
 
 if [ "$AUTOML_ENV_FILE" == "" ]
 then
-  AUTOML_ENV_FILE="automl_env_linux.yml"
+  AUTOML_ENV_FILE="automl_env.yml"
 fi
 
 if [ ! -f $AUTOML_ENV_FILE ]; then
@@ -21,23 +20,10 @@ if [ ! -f $AUTOML_ENV_FILE ]; then
     exit 1
 fi
 
-if [ ! -f $CHECK_CONDA_VERSION_SCRIPT ]; then
-    echo "File $CHECK_CONDA_VERSION_SCRIPT not found"
-    exit 1
-fi
-
-python "$CHECK_CONDA_VERSION_SCRIPT"
-if [ $? -ne 0 ]; then
-    exit 1
-fi
-
-sed -i 's/AZUREML-SDK-VERSION/latest/' $AUTOML_ENV_FILE
-
 if source activate $CONDA_ENV_NAME 2> /dev/null
 then
-   echo "Upgrading existing conda environment" $CONDA_ENV_NAME
-   pip uninstall azureml-train-automl -y -q
-   conda env update --name $CONDA_ENV_NAME --file $AUTOML_ENV_FILE &&
+   echo "Upgrading azureml-sdk[automl,notebooks,explain] in existing conda environment" $CONDA_ENV_NAME
+   pip install --upgrade azureml-sdk[automl,notebooks,explain] &&
    jupyter nbextension uninstall --user --py azureml.widgets
 else
    conda env create -f $AUTOML_ENV_FILE -n $CONDA_ENV_NAME &&

how-to-use-azureml/automated-machine-learning/automl_setup_mac.sh

@@ -4,7 +4,6 @@ CONDA_ENV_NAME=$1
 AUTOML_ENV_FILE=$2
 OPTIONS=$3
 PIP_NO_WARN_SCRIPT_LOCATION=0
-CHECK_CONDA_VERSION_SCRIPT="check_conda_version.py"
 
 if [ "$CONDA_ENV_NAME" == "" ]
 then
@@ -21,24 +20,10 @@ if [ ! -f $AUTOML_ENV_FILE ]; then
     exit 1
 fi
 
-if [ ! -f $CHECK_CONDA_VERSION_SCRIPT ]; then
-    echo "File $CHECK_CONDA_VERSION_SCRIPT not found"
-    exit 1
-fi
-
-python "$CHECK_CONDA_VERSION_SCRIPT"
-if [ $? -ne 0 ]; then
-    exit 1
-fi
-
-sed -i '' 's/AZUREML-SDK-VERSION/latest/' $AUTOML_ENV_FILE
-brew install libomp
-
 if source activate $CONDA_ENV_NAME 2> /dev/null
 then
-   echo "Upgrading existing conda environment" $CONDA_ENV_NAME
-   pip uninstall azureml-train-automl -y -q
-   conda env update --name $CONDA_ENV_NAME --file $AUTOML_ENV_FILE &&
+   echo "Upgrading azureml-sdk[automl,notebooks,explain] in existing conda environment" $CONDA_ENV_NAME
+   pip install --upgrade azureml-sdk[automl,notebooks,explain] &&
    jupyter nbextension uninstall --user --py azureml.widgets
 else
    conda env create -f $AUTOML_ENV_FILE -n $CONDA_ENV_NAME &&
@@ -46,6 +31,7 @@ else
    conda install lightgbm -c conda-forge -y &&
    python -m ipykernel install --user --name $CONDA_ENV_NAME --display-name "Python ($CONDA_ENV_NAME)" &&
    jupyter nbextension uninstall --user --py azureml.widgets &&
+   pip install numpy==1.15.3 &&
    echo "" &&
    echo "" &&
    echo "***************************************" &&

how-to-use-azureml/automated-machine-learning/check_conda_version.py

@@ -1,26 +0,0 @@
-from setuptools._vendor.packaging import version
-import platform
-
-try:
-    import conda
-except Exception:
-    print('Failed to import conda.')
-    print('This setup is usually run from the base conda environment.')
-    print('You can activate the base environment using the command "conda activate base"')
-    exit(1)
-
-architecture = platform.architecture()[0]
-
-if architecture != "64bit":
-    print('This setup requires 64bit Anaconda or Miniconda.  Found: ' + architecture)
-    exit(1)
-
-minimumVersion = "4.7.8"
-
-versionInvalid = (version.parse(conda.__version__) < version.parse(minimumVersion))
-
-if versionInvalid:
-    print('Setup requires conda version ' + minimumVersion + ' or higher.')
-    print('You can use the command "conda update conda" to upgrade conda.')
-
-exit(versionInvalid)

how-to-use-azureml/automated-machine-learning/classification-credit-card-fraud/auto-ml-classification-credit-card-fraud.ipynb

@@ -1,504 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/classification-credit-card-fraud/auto-ml-classification-credit-card-fraud.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Automated Machine Learning\n",
-        "_**Classification of credit card fraudulent transactions on remote compute **_\n",
-        "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Train](#Train)\n",
-        "1. [Results](#Results)\n",
-        "1. [Test](#Test)\n",
-        "1. [Acknowledgements](#Acknowledgements)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
-        "\n",
-        "In this example we use the associated credit card dataset to showcase how you can use AutoML for a simple classification problem. The goal is to predict if a credit card transaction is considered a fraudulent charge.\n",
-        "\n",
-        "This notebook is using remote compute to train the model.\n",
-        "\n",
-        "If you are using an Azure Machine Learning Compute Instance, you are all set. Otherwise, go through the [configuration](../../../configuration.ipynb) notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
-        "\n",
-        "In this notebook you will learn how to:\n",
-        "1. Create an experiment using an existing workspace.\n",
-        "2. Configure AutoML using `AutoMLConfig`.\n",
-        "3. Train the model using remote compute.\n",
-        "4. Explore the results.\n",
-        "5. Test the fitted model."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Setup\n",
-        "\n",
-        "As part of the setup you have already created an Azure ML `Workspace` object. For Automated ML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import logging\n",
-        "\n",
-        "from matplotlib import pyplot as plt\n",
-        "import pandas as pd\n",
-        "import os\n",
-        "\n",
-        "import azureml.core\n",
-        "from azureml.core.experiment import Experiment\n",
-        "from azureml.core.workspace import Workspace\n",
-        "from azureml.core.dataset import Dataset\n",
-        "from azureml.train.automl import AutoMLConfig"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ws = Workspace.from_config()\n",
-        "\n",
-        "# choose a name for experiment\n",
-        "experiment_name = \"automl-classification-ccard-remote\"\n",
-        "\n",
-        "experiment = Experiment(ws, experiment_name)\n",
-        "\n",
-        "output = {}\n",
-        "output[\"Subscription ID\"] = ws.subscription_id\n",
-        "output[\"Workspace\"] = ws.name\n",
-        "output[\"Resource Group\"] = ws.resource_group\n",
-        "output[\"Location\"] = ws.location\n",
-        "output[\"Experiment Name\"] = experiment.name\n",
-        "output[\"SDK Version\"] = azureml.core.VERSION\n",
-        "pd.set_option(\"display.max_colwidth\", None)\n",
-        "outputDf = pd.DataFrame(data=output, index=[\"\"])\n",
-        "outputDf.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Create or Attach existing AmlCompute\n",
-        "A compute target is required to execute the Automated ML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
-        "\n",
-        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
-        "\n",
-        "#### Creation of AmlCompute takes approximately 5 minutes. \n",
-        "If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
-        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
-        "from azureml.core.compute_target import ComputeTargetException\n",
-        "\n",
-        "# Choose a name for your CPU cluster\n",
-        "cpu_cluster_name = \"cpu-cluster-1\"\n",
-        "\n",
-        "# Verify that cluster does not exist already\n",
-        "try:\n",
-        "    compute_target = ComputeTarget(workspace=ws, name=cpu_cluster_name)\n",
-        "    print(\"Found existing cluster, use it.\")\n",
-        "except ComputeTargetException:\n",
-        "    compute_config = AmlCompute.provisioning_configuration(\n",
-        "        vm_size=\"STANDARD_DS12_V2\", max_nodes=6\n",
-        "    )\n",
-        "    compute_target = ComputeTarget.create(ws, cpu_cluster_name, compute_config)\n",
-        "compute_target.wait_for_completion(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Data"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Load Data\n",
-        "\n",
-        "Load the credit card dataset from a csv file containing both training features and labels. The features are inputs to the model, while the training labels represent the expected output of the model. Next, we'll split the data using random_split and extract the training data for the model."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "name": "load-data"
-      },
-      "outputs": [],
-      "source": [
-        "data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/creditcard.csv\"\n",
-        "dataset = Dataset.Tabular.from_delimited_files(data)\n",
-        "training_data, validation_data = dataset.random_split(percentage=0.8, seed=223)\n",
-        "label_column_name = \"Class\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Train\n",
-        "\n",
-        "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
-        "\n",
-        "|Property|Description|\n",
-        "|-|-|\n",
-        "|**task**|classification or regression|\n",
-        "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
-        "|**enable_early_stopping**|Stop the run if the metric score is not showing improvement.|\n",
-        "|**n_cross_validations**|Number of cross validation splits.|\n",
-        "|**training_data**|Input dataset, containing both features and label column.|\n",
-        "|**label_column_name**|The name of the label column.|\n",
-        "\n",
-        "**_You can find more information about primary metrics_** [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#primary-metric)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "name": "automl-config"
-      },
-      "outputs": [],
-      "source": [
-        "automl_settings = {\n",
-        "    \"n_cross_validations\": 3,\n",
-        "    \"primary_metric\": \"average_precision_score_weighted\",\n",
-        "    \"enable_early_stopping\": True,\n",
-        "    \"max_concurrent_iterations\": 2,  # This is a limit for testing purpose, please increase it as per cluster size\n",
-        "    \"experiment_timeout_hours\": 0.25,  # This is a time limit for testing purposes, remove it for real use cases, this will drastically limit ablity to find the best model possible\n",
-        "    \"verbosity\": logging.INFO,\n",
-        "}\n",
-        "\n",
-        "automl_config = AutoMLConfig(\n",
-        "    task=\"classification\",\n",
-        "    debug_log=\"automl_errors.log\",\n",
-        "    compute_target=compute_target,\n",
-        "    training_data=training_data,\n",
-        "    label_column_name=label_column_name,\n",
-        "    **automl_settings,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Call the `submit` method on the experiment object and pass the run configuration. Depending on the data and the number of iterations this can run for a while. Validation errors and current status will be shown when setting `show_output=True` and the execution will be synchronous."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run = experiment.submit(automl_config, show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# If you need to retrieve a run that already started, use the following code\n",
-        "# from azureml.train.automl.run import AutoMLRun\n",
-        "# remote_run = AutoMLRun(experiment = experiment, run_id = '<replace with your run id>')"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Results"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Widget for Monitoring Runs\n",
-        "\n",
-        "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
-        "\n",
-        "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "tags": [
-          "widget-rundetails-sample"
-        ]
-      },
-      "outputs": [],
-      "source": [
-        "from azureml.widgets import RunDetails\n",
-        "\n",
-        "RunDetails(remote_run).show()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run.wait_for_completion(show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Explain model\n",
-        "\n",
-        "Automated ML models can be explained and visualized using the SDK Explainability library. "
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Analyze results\n",
-        "\n",
-        "### Retrieve the Best Model\n",
-        "\n",
-        "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "best_run, fitted_model = remote_run.get_output()\n",
-        "fitted_model"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Print the properties of the model\n",
-        "The fitted_model is a python object and you can read the different properties of the object.\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Test the fitted model\n",
-        "\n",
-        "Now that the model is trained, split the data in the same way the data was split for training (The difference here is the data is being split locally) and then run the test data through the trained model to get the predicted values."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# convert the test data to dataframe\n",
-        "X_test_df = validation_data.drop_columns(\n",
-        "    columns=[label_column_name]\n",
-        ").to_pandas_dataframe()\n",
-        "y_test_df = validation_data.keep_columns(\n",
-        "    columns=[label_column_name], validate=True\n",
-        ").to_pandas_dataframe()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# call the predict functions on the model\n",
-        "y_pred = fitted_model.predict(X_test_df)\n",
-        "y_pred"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Calculate metrics for the prediction\n",
-        "\n",
-        "Now visualize the data on a scatter plot to show what our truth (actual) values are compared to the predicted values \n",
-        "from the trained model that was returned."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from sklearn.metrics import confusion_matrix\n",
-        "import numpy as np\n",
-        "import itertools\n",
-        "\n",
-        "cf = confusion_matrix(y_test_df.values, y_pred)\n",
-        "plt.imshow(cf, cmap=plt.cm.Blues, interpolation=\"nearest\")\n",
-        "plt.colorbar()\n",
-        "plt.title(\"Confusion Matrix\")\n",
-        "plt.xlabel(\"Predicted\")\n",
-        "plt.ylabel(\"Actual\")\n",
-        "class_labels = [\"False\", \"True\"]\n",
-        "tick_marks = np.arange(len(class_labels))\n",
-        "plt.xticks(tick_marks, class_labels)\n",
-        "plt.yticks([-0.5, 0, 1, 1.5], [\"\", \"False\", \"True\", \"\"])\n",
-        "# plotting text value inside cells\n",
-        "thresh = cf.max() / 2.0\n",
-        "for i, j in itertools.product(range(cf.shape[0]), range(cf.shape[1])):\n",
-        "    plt.text(\n",
-        "        j,\n",
-        "        i,\n",
-        "        format(cf[i, j], \"d\"),\n",
-        "        horizontalalignment=\"center\",\n",
-        "        color=\"white\" if cf[i, j] > thresh else \"black\",\n",
-        "    )\n",
-        "plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Acknowledgements"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "This Credit Card fraud Detection dataset is made available under the Open Database License: http://opendatacommons.org/licenses/odbl/1.0/. Any rights in individual contents of the database are licensed under the Database Contents License: http://opendatacommons.org/licenses/dbcl/1.0/ and is available at: https://www.kaggle.com/mlg-ulb/creditcardfraud\n",
-        "\n",
-        "The dataset has been collected and analysed during a research collaboration of Worldline and the Machine Learning Group (http://mlg.ulb.ac.be) of ULB (Universit\u00c3\u00a9 Libre de Bruxelles) on big data mining and fraud detection.\n",
-        "More details on current and past projects on related topics are available on https://www.researchgate.net/project/Fraud-detection-5 and the page of the DefeatFraud project\n",
-        "\n",
-        "Please cite the following works:\n",
-        "\n",
-        "Andrea Dal Pozzolo, Olivier Caelen, Reid A. Johnson and Gianluca Bontempi. Calibrating Probability with Undersampling for Unbalanced Classification. In Symposium on Computational Intelligence and Data Mining (CIDM), IEEE, 2015\n",
-        "\n",
-        "Dal Pozzolo, Andrea; Caelen, Olivier; Le Borgne, Yann-Ael; Waterschoot, Serge; Bontempi, Gianluca. Learned lessons in credit card fraud detection from a practitioner perspective, Expert systems with applications,41,10,4915-4928,2014, Pergamon\n",
-        "\n",
-        "Dal Pozzolo, Andrea; Boracchi, Giacomo; Caelen, Olivier; Alippi, Cesare; Bontempi, Gianluca. Credit card fraud detection: a realistic modeling and a novel learning strategy, IEEE transactions on neural networks and learning systems,29,8,3784-3797,2018,IEEE\n",
-        "\n",
-        "Dal Pozzolo, Andrea Adaptive Machine learning for credit card fraud detection ULB MLG PhD thesis (supervised by G. Bontempi)\n",
-        "\n",
-        "Carcillo, Fabrizio; Dal Pozzolo, Andrea; Le Borgne, Yann-A\u00c3\u00abl; Caelen, Olivier; Mazzer, Yannis; Bontempi, Gianluca. Scarff: a scalable framework for streaming credit card fraud detection with Spark, Information fusion,41, 182-194,2018,Elsevier\n",
-        "\n",
-        "Carcillo, Fabrizio; Le Borgne, Yann-A\u00c3\u00abl; Caelen, Olivier; Bontempi, Gianluca. Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization, International Journal of Data Science and Analytics, 5,4,285-300,2018,Springer International Publishing\n",
-        "\n",
-        "Bertrand Lebichot, Yann-A\u00c3\u00abl Le Borgne, Liyun He, Frederic Obl\u00c3\u00a9, Gianluca Bontempi Deep-Learning Domain Adaptation Techniques for Credit Cards Fraud Detection, INNSBDDL 2019: Recent Advances in Big Data and Deep Learning, pp 78-88, 2019\n",
-        "\n",
-        "Fabrizio Carcillo, Yann-A\u00c3\u00abl Le Borgne, Olivier Caelen, Frederic Obl\u00c3\u00a9, Gianluca Bontempi Combining Unsupervised and Supervised Learning in Credit Card Fraud Detection Information Sciences, 2019"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "ratanase"
-      }
-    ],
-    "category": "tutorial",
-    "compute": [
-      "AML Compute"
-    ],
-    "datasets": [
-      "Creditcard"
-    ],
-    "deployment": [
-      "None"
-    ],
-    "exclude_from_index": false,
-    "file_extension": ".py",
-    "framework": [
-      "None"
-    ],
-    "friendly_name": "Classification of credit card fraudulent transactions using Automated ML",
-    "index_order": 5,
-    "kernelspec": {
-      "display_name": "Python 3.8 - AzureML",
-      "language": "python",
-      "name": "python38-azureml"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.6.7"
-    },
-    "mimetype": "text/x-python",
-    "name": "python",
-    "nbconvert_exporter": "python",
-    "pygments_lexer": "ipython3",
-    "tags": [
-      "remote_run",
-      "AutomatedML"
-    ],
-    "task": "Classification",
-    "version": "3.6.7"
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

how-to-use-azureml/automated-machine-learning/classification-with-deployment/auto-ml-classification-with-deployment.ipynb

@@ -0,0 +1,503 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "_**Classification with Deployment**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Train](#Train)\n",
+        "1. [Deploy](#Deploy)\n",
+        "1. [Test](#Test)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "\n",
+        "In this example we use the scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) to showcase how you can use AutoML for a simple classification problem and deploy it to an Azure Container Instance (ACI).\n",
+        "\n",
+        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+        "\n",
+        "In this notebook you will learn how to:\n",
+        "1. Create an experiment using an existing workspace.\n",
+        "2. Configure AutoML using `AutoMLConfig`.\n",
+        "3. Train the model using local compute.\n",
+        "4. Explore the results.\n",
+        "5. Register the model.\n",
+        "6. Create a container image.\n",
+        "7. Create an Azure Container Instance (ACI) service.\n",
+        "8. Test the ACI service."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup\n",
+        "\n",
+        "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import json\n",
+        "import logging\n",
+        "\n",
+        "from matplotlib import pyplot as plt\n",
+        "import numpy as np\n",
+        "import pandas as pd\n",
+        "from sklearn import datasets\n",
+        "\n",
+        "import azureml.core\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "from azureml.train.automl import AutoMLConfig\n",
+        "from azureml.train.automl.run import AutoMLRun"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "# choose a name for experiment\n",
+        "experiment_name = 'automl-classification-deployment'\n",
+        "# project folder\n",
+        "project_folder = './sample_projects/automl-classification-deployment'\n",
+        "\n",
+        "experiment=Experiment(ws, experiment_name)\n",
+        "\n",
+        "output = {}\n",
+        "output['SDK version'] = azureml.core.VERSION\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace'] = ws.name\n",
+        "output['Resource Group'] = ws.resource_group\n",
+        "output['Location'] = ws.location\n",
+        "output['Project Directory'] = project_folder\n",
+        "output['Experiment Name'] = experiment.name\n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
+        "outputDf.T"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train\n",
+        "\n",
+        "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
+        "\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**task**|classification or regression|\n",
+        "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
+        "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+        "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
+        "|**n_cross_validations**|Number of cross validation splits.|\n",
+        "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+        "|**y**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|\n",
+        "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "digits = datasets.load_digits()\n",
+        "X_train = digits.data[10:,:]\n",
+        "y_train = digits.target[10:]\n",
+        "\n",
+        "automl_config = AutoMLConfig(task = 'classification',\n",
+        "                             name = experiment_name,\n",
+        "                             debug_log = 'automl_errors.log',\n",
+        "                             primary_metric = 'AUC_weighted',\n",
+        "                             iteration_timeout_minutes = 20,\n",
+        "                             iterations = 10,\n",
+        "                             n_cross_validations = 2,\n",
+        "                             verbosity = logging.INFO,\n",
+        "                             X = X_train, \n",
+        "                             y = y_train,\n",
+        "                             path = project_folder)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
+        "In this example, we specify `show_output = True` to print currently running iterations to the console."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run = experiment.submit(automl_config, show_output = True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Deploy\n",
+        "\n",
+        "### Retrieve the Best Model\n",
+        "\n",
+        "Below we select the best pipeline from our iterations. The `get_output` method on `automl_classifier` returns the best run and the fitted model for the last invocation. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run, fitted_model = local_run.get_output()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Register the Fitted Model for Deployment\n",
+        "If neither `metric` nor `iteration` are specified in the `register_model` call, the iteration with the best primary metric is registered."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "description = 'AutoML Model'\n",
+        "tags = None\n",
+        "model = local_run.register_model(description = description, tags = tags)\n",
+        "\n",
+        "print(local_run.model_id) # This will be written to the script file later in the notebook."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create Scoring Script"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%writefile score.py\n",
+        "import pickle\n",
+        "import json\n",
+        "import numpy\n",
+        "import azureml.train.automl\n",
+        "from sklearn.externals import joblib\n",
+        "from azureml.core.model import Model\n",
+        "\n",
+        "\n",
+        "def init():\n",
+        "    global model\n",
+        "    model_path = Model.get_model_path(model_name = '<<modelid>>') # this name is model.id of model that we want to deploy\n",
+        "    # deserialize the model file back into a sklearn model\n",
+        "    model = joblib.load(model_path)\n",
+        "\n",
+        "def run(rawdata):\n",
+        "    try:\n",
+        "        data = json.loads(rawdata)['data']\n",
+        "        data = numpy.array(data)\n",
+        "        result = model.predict(data)\n",
+        "    except Exception as e:\n",
+        "        result = str(e)\n",
+        "        return json.dumps({\"error\": result})\n",
+        "    return json.dumps({\"result\":result.tolist()})"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create a YAML File for the Environment"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "To ensure the fit results are consistent with the training results, the SDK dependency versions need to be the same as the environment that trains the model. Details about retrieving the versions can be found in notebook [12.auto-ml-retrieve-the-training-sdk-versions](12.auto-ml-retrieve-the-training-sdk-versions.ipynb)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "experiment = Experiment(ws, experiment_name)\n",
+        "ml_run = AutoMLRun(experiment = experiment, run_id = local_run.id)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "dependencies = ml_run.get_run_sdk_dependencies(iteration = 7)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "for p in ['azureml-train-automl', 'azureml-sdk', 'azureml-core']:\n",
+        "    print('{}\\t{}'.format(p, dependencies[p]))"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.conda_dependencies import CondaDependencies\n",
+        "\n",
+        "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn'], pip_packages=['azureml-sdk[automl]'])\n",
+        "\n",
+        "conda_env_file_name = 'myenv.yml'\n",
+        "myenv.save_to_file('.', conda_env_file_name)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Substitute the actual version number in the environment file.\n",
+        "# This is not strictly needed in this notebook because the model should have been generated using the current SDK version.\n",
+        "# However, we include this in case this code is used on an experiment from a previous SDK version.\n",
+        "\n",
+        "with open(conda_env_file_name, 'r') as cefr:\n",
+        "    content = cefr.read()\n",
+        "\n",
+        "with open(conda_env_file_name, 'w') as cefw:\n",
+        "    cefw.write(content.replace(azureml.core.VERSION, dependencies['azureml-sdk']))\n",
+        "\n",
+        "# Substitute the actual model id in the script file.\n",
+        "\n",
+        "script_file_name = 'score.py'\n",
+        "\n",
+        "with open(script_file_name, 'r') as cefr:\n",
+        "    content = cefr.read()\n",
+        "\n",
+        "with open(script_file_name, 'w') as cefw:\n",
+        "    cefw.write(content.replace('<<modelid>>', local_run.model_id))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create a Container Image"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.image import Image, ContainerImage\n",
+        "\n",
+        "image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
+        "                                 execution_script = script_file_name,\n",
+        "                                 conda_file = conda_env_file_name,\n",
+        "                                 tags = {'area': \"digits\", 'type': \"automl_classification\"},\n",
+        "                                 description = \"Image for automl classification sample\")\n",
+        "\n",
+        "image = Image.create(name = \"automlsampleimage\",\n",
+        "                     # this is the model object \n",
+        "                     models = [model],\n",
+        "                     image_config = image_config, \n",
+        "                     workspace = ws)\n",
+        "\n",
+        "image.wait_for_creation(show_output = True)\n",
+        "\n",
+        "if image.creation_state == 'Failed':\n",
+        "    print(\"Image build log at: \" + image.image_build_log_uri)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Deploy the Image as a Web Service on Azure Container Instance"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.webservice import AciWebservice\n",
+        "\n",
+        "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
+        "                                               memory_gb = 1, \n",
+        "                                               tags = {'area': \"digits\", 'type': \"automl_classification\"}, \n",
+        "                                               description = 'sample service for Automl Classification')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.webservice import Webservice\n",
+        "\n",
+        "aci_service_name = 'automl-sample-01'\n",
+        "print(aci_service_name)\n",
+        "aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
+        "                                           image = image,\n",
+        "                                           name = aci_service_name,\n",
+        "                                           workspace = ws)\n",
+        "aci_service.wait_for_deployment(True)\n",
+        "print(aci_service.state)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Delete a Web Service"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "#aci_service.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Get Logs from a Deployed Web Service"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "#aci_service.get_logs()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Test"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "#Randomly select digits and test\n",
+        "digits = datasets.load_digits()\n",
+        "X_test = digits.data[:10, :]\n",
+        "y_test = digits.target[:10]\n",
+        "images = digits.images[:10]\n",
+        "\n",
+        "for index in np.random.choice(len(y_test), 3, replace = False):\n",
+        "    print(index)\n",
+        "    test_sample = json.dumps({'data':X_test[index:index + 1].tolist()})\n",
+        "    predicted = aci_service.run(input_data = test_sample)\n",
+        "    label = y_test[index]\n",
+        "    predictedDict = json.loads(predicted)\n",
+        "    title = \"Label value = %d  Predicted value = %s \" % ( label,predictedDict['result'][0])\n",
+        "    fig = plt.figure(1, figsize = (3,3))\n",
+        "    ax1 = fig.add_axes((0,0,.8,.8))\n",
+        "    ax1.set_title(title)\n",
+        "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
+        "    plt.show()"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "savitam"
+      }
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "python",
+      "name": "python36"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.6"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/classification-with-whitelisting/auto-ml-classification-with-whitelisting.ipynb

@@ -0,0 +1,387 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "_**Classification using whitelist models**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Data](#Data)\n",
+        "1. [Train](#Train)\n",
+        "1. [Results](#Results)\n",
+        "1. [Test](#Test)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "\n",
+        "In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset) to showcase how you can use AutoML for a simple classification problem.\n",
+        "\n",
+        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+        "This notebooks shows how can automl can be trained on a a selected list of models,see the readme.md for the models.\n",
+        "This trains the model exclusively on tensorflow based models.\n",
+        "\n",
+        "In this notebook you will learn how to:\n",
+        "1. Create an `Experiment` in an existing `Workspace`.\n",
+        "2. Configure AutoML using `AutoMLConfig`.\n",
+        "3. Train the model on a whilelisted models using local compute. \n",
+        "4. Explore the results.\n",
+        "5. Test the best fitted model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup\n",
+        "\n",
+        "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "#Note: This notebook will install tensorflow if not already installed in the enviornment..\n",
+        "import logging\n",
+        "\n",
+        "from matplotlib import pyplot as plt\n",
+        "import numpy as np\n",
+        "import pandas as pd\n",
+        "from sklearn import datasets\n",
+        "\n",
+        "import azureml.core\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "try:\n",
+        "    import tensorflow as tf1\n",
+        "except ImportError:\n",
+        "    from pip._internal import main\n",
+        "    main(['install', 'tensorflow>=1.10.0,<=1.12.0'])\n",
+        "from azureml.train.automl import AutoMLConfig"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "# Choose a name for the experiment and specify the project folder.\n",
+        "experiment_name = 'automl-local-whitelist'\n",
+        "project_folder = './sample_projects/automl-local-whitelist'\n",
+        "\n",
+        "experiment = Experiment(ws, experiment_name)\n",
+        "\n",
+        "output = {}\n",
+        "output['SDK version'] = azureml.core.VERSION\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace Name'] = ws.name\n",
+        "output['Resource Group'] = ws.resource_group\n",
+        "output['Location'] = ws.location\n",
+        "output['Project Directory'] = project_folder\n",
+        "output['Experiment Name'] = experiment.name\n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
+        "outputDf.T"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Data\n",
+        "\n",
+        "This uses scikit-learn's [load_digits](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) method."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "digits = datasets.load_digits()\n",
+        "\n",
+        "# Exclude the first 100 rows from training so that they can be used for test.\n",
+        "X_train = digits.data[100:,:]\n",
+        "y_train = digits.target[100:]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train\n",
+        "\n",
+        "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
+        "\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**task**|classification or regression|\n",
+        "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i>|\n",
+        "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+        "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
+        "|**n_cross_validations**|Number of cross validation splits.|\n",
+        "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+        "|**y**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|\n",
+        "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|\n",
+        "|**whitelist_models**|List of models that AutoML should use.  The possible values are listed [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#configure-your-experiment-settings).|"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "automl_config = AutoMLConfig(task = 'classification',\n",
+        "                             debug_log = 'automl_errors.log',\n",
+        "                             primary_metric = 'AUC_weighted',\n",
+        "                             iteration_timeout_minutes = 60,\n",
+        "                             iterations = 10,\n",
+        "                             n_cross_validations = 3,\n",
+        "                             verbosity = logging.INFO,\n",
+        "                             X = X_train, \n",
+        "                             y = y_train,\n",
+        "                             enable_tf=True,\n",
+        "                             whitelist_models=[\"TensorFlowLinearClassifier\", \"TensorFlowDNN\"],\n",
+        "                             path = project_folder)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
+        "In this example, we specify `show_output = True` to print currently running iterations to the console."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run = experiment.submit(automl_config, show_output = True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Results"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Widget for Monitoring Runs\n",
+        "\n",
+        "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+        "\n",
+        "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.widgets import RunDetails\n",
+        "RunDetails(local_run).show() "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "\n",
+        "#### Retrieve All Child Runs\n",
+        "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "children = list(local_run.get_children())\n",
+        "metricslist = {}\n",
+        "for run in children:\n",
+        "    properties = run.get_properties()\n",
+        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+        "    metricslist[int(properties['iteration'])] = metrics\n",
+        "\n",
+        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+        "rundata"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Retrieve the Best Model\n",
+        "\n",
+        "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run, fitted_model = local_run.get_output()\n",
+        "print(best_run)\n",
+        "print(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Best Model Based on Any Other Metric\n",
+        "Show the run and the model that has the smallest `log_loss` value:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "lookup_metric = \"log_loss\"\n",
+        "best_run, fitted_model = local_run.get_output(metric = lookup_metric)\n",
+        "print(best_run)\n",
+        "print(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Model from a Specific Iteration\n",
+        "Show the run and the model from the third iteration:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "iteration = 3\n",
+        "third_run, third_model = local_run.get_output(iteration = iteration)\n",
+        "print(third_run)\n",
+        "print(third_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Test\n",
+        "\n",
+        "#### Load Test Data"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "digits = datasets.load_digits()\n",
+        "X_test = digits.data[:10, :]\n",
+        "y_test = digits.target[:10]\n",
+        "images = digits.images[:10]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Testing Our Best Fitted Model\n",
+        "We will try to predict 2 digits and see how our model works."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Randomly select digits and test.\n",
+        "for index in np.random.choice(len(y_test), 2, replace = False):\n",
+        "    print(index)\n",
+        "    predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
+        "    label = y_test[index]\n",
+        "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
+        "    fig = plt.figure(1, figsize = (3,3))\n",
+        "    ax1 = fig.add_axes((0,0,.8,.8))\n",
+        "    ax1.set_title(title)\n",
+        "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
+        "    plt.show()"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "savitam"
+      }
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "python",
+      "name": "python36"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.6"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/classification/auto-ml-classification.ipynb

@@ -0,0 +1,443 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "_**Classification with Local Compute**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Data](#Data)\n",
+        "1. [Train](#Train)\n",
+        "1. [Results](#Results)\n",
+        "1. [Test](#Test)\n",
+        "\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "\n",
+        "In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset) to showcase how you can use AutoML for a simple classification problem.\n",
+        "\n",
+        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+        "\n",
+        "In this notebook you will learn how to:\n",
+        "1. Create an `Experiment` in an existing `Workspace`.\n",
+        "2. Configure AutoML using `AutoMLConfig`.\n",
+        "3. Train the model using local compute.\n",
+        "4. Explore the results.\n",
+        "5. Test the best fitted model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup\n",
+        "\n",
+        "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import logging\n",
+        "\n",
+        "from matplotlib import pyplot as plt\n",
+        "import numpy as np\n",
+        "import pandas as pd\n",
+        "from sklearn import datasets\n",
+        "\n",
+        "import azureml.core\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "from azureml.train.automl import AutoMLConfig"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "# Choose a name for the experiment and specify the project folder.\n",
+        "experiment_name = 'automl-classification'\n",
+        "project_folder = './sample_projects/automl-classification'\n",
+        "\n",
+        "experiment = Experiment(ws, experiment_name)\n",
+        "\n",
+        "output = {}\n",
+        "output['SDK version'] = azureml.core.VERSION\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace Name'] = ws.name\n",
+        "output['Resource Group'] = ws.resource_group\n",
+        "output['Location'] = ws.location\n",
+        "output['Project Directory'] = project_folder\n",
+        "output['Experiment Name'] = experiment.name\n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
+        "outputDf.T"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Data\n",
+        "\n",
+        "This uses scikit-learn's [load_digits](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) method."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "digits = datasets.load_digits()\n",
+        "\n",
+        "# Exclude the first 100 rows from training so that they can be used for test.\n",
+        "X_train = digits.data[100:,:]\n",
+        "y_train = digits.target[100:]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train\n",
+        "\n",
+        "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
+        "\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**task**|classification or regression|\n",
+        "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
+        "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+        "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
+        "|**n_cross_validations**|Number of cross validation splits.|\n",
+        "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+        "|**y**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|\n",
+        "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "automl_config = AutoMLConfig(task = 'classification',\n",
+        "                             debug_log = 'automl_errors.log',\n",
+        "                             primary_metric = 'AUC_weighted',\n",
+        "                             iteration_timeout_minutes = 60,\n",
+        "                             iterations = 25,\n",
+        "                             n_cross_validations = 3,\n",
+        "                             verbosity = logging.INFO,\n",
+        "                             X = X_train, \n",
+        "                             y = y_train,\n",
+        "                             path = project_folder)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
+        "In this example, we specify `show_output = True` to print currently running iterations to the console."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run = experiment.submit(automl_config, show_output = True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Optionally, you can continue an interrupted local run by calling `continue_experiment` without the `iterations` parameter, or run more iterations for a completed run by specifying the `iterations` parameter:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run = local_run.continue_experiment(X = X_train, \n",
+        "                                          y = y_train, \n",
+        "                                          show_output = True,\n",
+        "                                          iterations = 5)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Results"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Widget for Monitoring Runs\n",
+        "\n",
+        "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+        "\n",
+        "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.widgets import RunDetails\n",
+        "RunDetails(local_run).show() "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "\n",
+        "#### Retrieve All Child Runs\n",
+        "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "children = list(local_run.get_children())\n",
+        "metricslist = {}\n",
+        "for run in children:\n",
+        "    properties = run.get_properties()\n",
+        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+        "    metricslist[int(properties['iteration'])] = metrics\n",
+        "\n",
+        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+        "rundata"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Retrieve the Best Model\n",
+        "\n",
+        "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run, fitted_model = local_run.get_output()\n",
+        "print(best_run)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Print the properties of the model\n",
+        "The fitted_model is a python object and you can read the different properties of the object.\n",
+        "The following shows printing hyperparameters for each step in the pipeline."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from pprint import pprint\n",
+        "\n",
+        "def print_model(model, prefix=\"\"):\n",
+        "    for step in model.steps:\n",
+        "        print(prefix + step[0])\n",
+        "        if hasattr(step[1], 'estimators') and hasattr(step[1], 'weights'):\n",
+        "            pprint({'estimators': list(e[0] for e in step[1].estimators), 'weights': step[1].weights})\n",
+        "            print()\n",
+        "            for estimator in step[1].estimators:\n",
+        "                print_model(estimator[1], estimator[0]+ ' - ')\n",
+        "        else:\n",
+        "            pprint(step[1].get_params())\n",
+        "            print()\n",
+        "            \n",
+        "print_model(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Best Model Based on Any Other Metric\n",
+        "Show the run and the model that has the smallest `log_loss` value:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "lookup_metric = \"log_loss\"\n",
+        "best_run, fitted_model = local_run.get_output(metric = lookup_metric)\n",
+        "print(best_run)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print_model(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Model from a Specific Iteration\n",
+        "Show the run and the model from the third iteration:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "iteration = 3\n",
+        "third_run, third_model = local_run.get_output(iteration = iteration)\n",
+        "print(third_run)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print_model(third_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Test \n",
+        "\n",
+        "#### Load Test Data"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "digits = datasets.load_digits()\n",
+        "X_test = digits.data[:10, :]\n",
+        "y_test = digits.target[:10]\n",
+        "images = digits.images[:10]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Testing Our Best Fitted Model\n",
+        "We will try to predict 2 digits and see how our model works."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Randomly select digits and test.\n",
+        "for index in np.random.choice(len(y_test), 2, replace = False):\n",
+        "    print(index)\n",
+        "    predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
+        "    label = y_test[index]\n",
+        "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
+        "    fig = plt.figure(1, figsize = (3,3))\n",
+        "    ax1 = fig.add_axes((0,0,.8,.8))\n",
+        "    ax1.set_title(title)\n",
+        "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
+        "    plt.show()"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "savitam"
+      }
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "python",
+      "name": "python36"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.6"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/continuous-retraining/auto-ml-continuous-retraining.ipynb

@@ -1,602 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/continuous-retraining/auto-ml-continuous-retraining.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Automated Machine Learning \n",
-        "**Continuous retraining using Pipelines and Time-Series TabularDataset**\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "2. [Setup](#Setup)\n",
-        "3. [Compute](#Compute)\n",
-        "4. [Run Configuration](#Run-Configuration)\n",
-        "5. [Data Ingestion Pipeline](#Data-Ingestion-Pipeline)\n",
-        "6. [Training Pipeline](#Training-Pipeline)\n",
-        "7. [Publish Retraining Pipeline and Schedule](#Publish-Retraining-Pipeline-and-Schedule)\n",
-        "8. [Test Retraining](#Test-Retraining)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
-        "In this example we use AutoML and Pipelines to enable contious retraining of a model based on updates to the training dataset. We will create two pipelines, the first one to demonstrate a training dataset that gets updated over time. We leverage time-series capabilities of `TabularDataset` to achieve this. The second pipeline utilizes pipeline `Schedule` to trigger continuous retraining. \n",
-        "Make sure you have executed the [configuration notebook](../../../configuration.ipynb) before running this notebook.\n",
-        "In this notebook you will learn how to:\n",
-        "* Create an Experiment in an existing Workspace.\n",
-        "* Configure AutoML using AutoMLConfig.\n",
-        "* Create data ingestion pipeline to update a time-series based TabularDataset\n",
-        "* Create training pipeline to prepare data, run AutoML, register the model and setup pipeline triggers.\n",
-        "\n",
-        "## Setup\n",
-        "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import logging\n",
-        "\n",
-        "from matplotlib import pyplot as plt\n",
-        "import numpy as np\n",
-        "import pandas as pd\n",
-        "from sklearn import datasets\n",
-        "\n",
-        "import azureml.core\n",
-        "from azureml.core.experiment import Experiment\n",
-        "from azureml.core.workspace import Workspace\n",
-        "from azureml.train.automl import AutoMLConfig"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Accessing the Azure ML workspace requires authentication with Azure.\n",
-        "\n",
-        "The default authentication is interactive authentication using the default tenant. Executing the ws = Workspace.from_config() line in the cell below will prompt for authentication the first time that it is run.\n",
-        "\n",
-        "If you have multiple Azure tenants, you can specify the tenant by replacing the ws = Workspace.from_config() line in the cell below with the following:\n",
-        "```\n",
-        "from azureml.core.authentication import InteractiveLoginAuthentication\n",
-        "auth = InteractiveLoginAuthentication(tenant_id = 'mytenantid')\n",
-        "ws = Workspace.from_config(auth = auth)\n",
-        "```\n",
-        "If you need to run in an environment where interactive login is not possible, you can use Service Principal authentication by replacing the ws = Workspace.from_config() line in the cell below with the following:\n",
-        "```\n",
-        "from azureml.core.authentication import ServicePrincipalAuthentication\n",
-        "auth = auth = ServicePrincipalAuthentication('mytenantid', 'myappid', 'mypassword')\n",
-        "ws = Workspace.from_config(auth = auth)\n",
-        "```\n",
-        "For more details, see aka.ms/aml-notebook-auth"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ws = Workspace.from_config()\n",
-        "dstor = ws.get_default_datastore()\n",
-        "\n",
-        "# Choose a name for the run history container in the workspace.\n",
-        "experiment_name = \"retrain-noaaweather\"\n",
-        "experiment = Experiment(ws, experiment_name)\n",
-        "\n",
-        "output = {}\n",
-        "output[\"Subscription ID\"] = ws.subscription_id\n",
-        "output[\"Workspace\"] = ws.name\n",
-        "output[\"Resource Group\"] = ws.resource_group\n",
-        "output[\"Location\"] = ws.location\n",
-        "output[\"Run History Name\"] = experiment_name\n",
-        "output[\"SDK Version\"] = azureml.core.VERSION\n",
-        "pd.set_option(\"display.max_colwidth\", None)\n",
-        "outputDf = pd.DataFrame(data=output, index=[\"\"])\n",
-        "outputDf.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Compute \n",
-        "\n",
-        "#### Create or Attach existing AmlCompute\n",
-        "\n",
-        "You will need to create a compute target for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
-        "\n",
-        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
-        "\n",
-        "#### Creation of AmlCompute takes approximately 5 minutes. \n",
-        "If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
-        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
-        "from azureml.core.compute_target import ComputeTargetException\n",
-        "\n",
-        "# Choose a name for your CPU cluster\n",
-        "amlcompute_cluster_name = \"cont-cluster\"\n",
-        "\n",
-        "# Verify that cluster does not exist already\n",
-        "try:\n",
-        "    compute_target = ComputeTarget(workspace=ws, name=amlcompute_cluster_name)\n",
-        "    print(\"Found existing cluster, use it.\")\n",
-        "except ComputeTargetException:\n",
-        "    compute_config = AmlCompute.provisioning_configuration(\n",
-        "        vm_size=\"STANDARD_DS12_V2\", max_nodes=4\n",
-        "    )\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, compute_config)\n",
-        "compute_target.wait_for_completion(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Run Configuration"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.runconfig import CondaDependencies, RunConfiguration\n",
-        "\n",
-        "# create a new RunConfig object\n",
-        "conda_run_config = RunConfiguration(framework=\"python\")\n",
-        "\n",
-        "# Set compute target to AmlCompute\n",
-        "conda_run_config.target = compute_target\n",
-        "\n",
-        "conda_run_config.environment.docker.enabled = True\n",
-        "\n",
-        "cd = CondaDependencies.create(\n",
-        "    pip_packages=[\n",
-        "        \"azureml-sdk[automl]\",\n",
-        "        \"applicationinsights\",\n",
-        "        \"azureml-opendatasets\",\n",
-        "        \"azureml-defaults\",\n",
-        "    ],\n",
-        "    conda_packages=[\"numpy==1.19.5\"],\n",
-        "    pin_sdk_version=False,\n",
-        ")\n",
-        "conda_run_config.environment.python.conda_dependencies = cd\n",
-        "\n",
-        "print(\"run config is ready\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Data Ingestion Pipeline \n",
-        "For this demo, we will use NOAA weather data from [Azure Open Datasets](https://azure.microsoft.com/services/open-datasets/). You can replace this with your own dataset, or you can skip this pipeline if you already have a time-series based `TabularDataset`.\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# The name and target column of the Dataset to create\n",
-        "dataset = \"NOAA-Weather-DS4\"\n",
-        "target_column_name = \"temperature\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "\n",
-        "### Upload Data Step\n",
-        "The data ingestion pipeline has a single step with a script to query the latest weather data and upload it to the blob store. During the first run, the script will create and register a time-series based `TabularDataset` with the past one week of weather data. For each subsequent run, the script will create a partition in the blob store by querying NOAA for new weather data since the last modified time of the dataset (`dataset.data_changed_time`) and creating a data.csv file."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.pipeline.core import Pipeline, PipelineParameter\n",
-        "from azureml.pipeline.steps import PythonScriptStep\n",
-        "\n",
-        "ds_name = PipelineParameter(name=\"ds_name\", default_value=dataset)\n",
-        "upload_data_step = PythonScriptStep(\n",
-        "    script_name=\"upload_weather_data.py\",\n",
-        "    allow_reuse=False,\n",
-        "    name=\"upload_weather_data\",\n",
-        "    arguments=[\"--ds_name\", ds_name],\n",
-        "    compute_target=compute_target,\n",
-        "    runconfig=conda_run_config,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Submit Pipeline Run"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "data_pipeline = Pipeline(\n",
-        "    description=\"pipeline_with_uploaddata\", workspace=ws, steps=[upload_data_step]\n",
-        ")\n",
-        "data_pipeline_run = experiment.submit(\n",
-        "    data_pipeline, pipeline_parameters={\"ds_name\": dataset}\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "data_pipeline_run.wait_for_completion(show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Training Pipeline\n",
-        "### Prepare Training Data Step\n",
-        "\n",
-        "Script to check if new data is available since the model was last trained. If no new data is available, we cancel the remaining pipeline steps. We need to set allow_reuse flag to False to allow the pipeline to run even when inputs don't change. We also need the name of the model to check the time the model was last trained."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.pipeline.core import PipelineData\n",
-        "\n",
-        "# The model name with which to register the trained model in the workspace.\n",
-        "model_name = PipelineParameter(\"model_name\", default_value=\"noaaweatherds\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "data_prep_step = PythonScriptStep(\n",
-        "    script_name=\"check_data.py\",\n",
-        "    allow_reuse=False,\n",
-        "    name=\"check_data\",\n",
-        "    arguments=[\"--ds_name\", ds_name, \"--model_name\", model_name],\n",
-        "    compute_target=compute_target,\n",
-        "    runconfig=conda_run_config,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core import Dataset\n",
-        "\n",
-        "train_ds = Dataset.get_by_name(ws, dataset)\n",
-        "train_ds = train_ds.drop_columns([\"partition_date\"])"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### AutoMLStep\n",
-        "Create an AutoMLConfig and a training step."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.train.automl import AutoMLConfig\n",
-        "from azureml.pipeline.steps import AutoMLStep\n",
-        "\n",
-        "automl_settings = {\n",
-        "    \"iteration_timeout_minutes\": 10,\n",
-        "    \"experiment_timeout_hours\": 0.25,\n",
-        "    \"n_cross_validations\": 3,\n",
-        "    \"primary_metric\": \"r2_score\",\n",
-        "    \"max_concurrent_iterations\": 3,\n",
-        "    \"max_cores_per_iteration\": -1,\n",
-        "    \"verbosity\": logging.INFO,\n",
-        "    \"enable_early_stopping\": True,\n",
-        "}\n",
-        "\n",
-        "automl_config = AutoMLConfig(\n",
-        "    task=\"regression\",\n",
-        "    debug_log=\"automl_errors.log\",\n",
-        "    path=\".\",\n",
-        "    compute_target=compute_target,\n",
-        "    training_data=train_ds,\n",
-        "    label_column_name=target_column_name,\n",
-        "    **automl_settings,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.pipeline.core import PipelineData, TrainingOutput\n",
-        "\n",
-        "metrics_output_name = \"metrics_output\"\n",
-        "best_model_output_name = \"best_model_output\"\n",
-        "\n",
-        "metrics_data = PipelineData(\n",
-        "    name=\"metrics_data\",\n",
-        "    datastore=dstor,\n",
-        "    pipeline_output_name=metrics_output_name,\n",
-        "    training_output=TrainingOutput(type=\"Metrics\"),\n",
-        ")\n",
-        "model_data = PipelineData(\n",
-        "    name=\"model_data\",\n",
-        "    datastore=dstor,\n",
-        "    pipeline_output_name=best_model_output_name,\n",
-        "    training_output=TrainingOutput(type=\"Model\"),\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "automl_step = AutoMLStep(\n",
-        "    name=\"automl_module\",\n",
-        "    automl_config=automl_config,\n",
-        "    outputs=[metrics_data, model_data],\n",
-        "    allow_reuse=False,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Register Model Step\n",
-        "Script to register the model to the workspace. "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "register_model_step = PythonScriptStep(\n",
-        "    script_name=\"register_model.py\",\n",
-        "    name=\"register_model\",\n",
-        "    allow_reuse=False,\n",
-        "    arguments=[\n",
-        "        \"--model_name\",\n",
-        "        model_name,\n",
-        "        \"--model_path\",\n",
-        "        model_data,\n",
-        "        \"--ds_name\",\n",
-        "        ds_name,\n",
-        "    ],\n",
-        "    inputs=[model_data],\n",
-        "    compute_target=compute_target,\n",
-        "    runconfig=conda_run_config,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Submit Pipeline Run"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "training_pipeline = Pipeline(\n",
-        "    description=\"training_pipeline\",\n",
-        "    workspace=ws,\n",
-        "    steps=[data_prep_step, automl_step, register_model_step],\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "training_pipeline_run = experiment.submit(\n",
-        "    training_pipeline,\n",
-        "    pipeline_parameters={\"ds_name\": dataset, \"model_name\": \"noaaweatherds\"},\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "training_pipeline_run.wait_for_completion(show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Publish Retraining Pipeline and Schedule\n",
-        "Once we are happy with the pipeline, we can publish the training pipeline to the workspace and create a schedule to trigger on blob change. The schedule polls the blob store where the data is being uploaded and runs the retraining pipeline if there is a data change. A new version of the model will be registered to the workspace once the run is complete."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "pipeline_name = \"Retraining-Pipeline-NOAAWeather\"\n",
-        "\n",
-        "published_pipeline = training_pipeline.publish(\n",
-        "    name=pipeline_name, description=\"Pipeline that retrains AutoML model\"\n",
-        ")\n",
-        "\n",
-        "published_pipeline"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.pipeline.core import Schedule\n",
-        "\n",
-        "schedule = Schedule.create(\n",
-        "    workspace=ws,\n",
-        "    name=\"RetrainingSchedule\",\n",
-        "    pipeline_parameters={\"ds_name\": dataset, \"model_name\": \"noaaweatherds\"},\n",
-        "    pipeline_id=published_pipeline.id,\n",
-        "    experiment_name=experiment_name,\n",
-        "    datastore=dstor,\n",
-        "    wait_for_provisioning=True,\n",
-        "    polling_interval=1440,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Test Retraining\n",
-        "Here we setup the data ingestion pipeline to run on a schedule, to verify that the retraining pipeline runs as expected. \n",
-        "\n",
-        "Note: \n",
-        "* Azure NOAA Weather data is updated daily and retraining will not trigger if there is no new data available. \n",
-        "* Depending on the polling interval set in the schedule, the retraining may take some time trigger after data ingestion pipeline completes."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "pipeline_name = \"DataIngestion-Pipeline-NOAAWeather\"\n",
-        "\n",
-        "published_pipeline = training_pipeline.publish(\n",
-        "    name=pipeline_name, description=\"Pipeline that updates NOAAWeather Dataset\"\n",
-        ")\n",
-        "\n",
-        "published_pipeline"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.pipeline.core import Schedule\n",
-        "\n",
-        "schedule = Schedule.create(\n",
-        "    workspace=ws,\n",
-        "    name=\"RetrainingSchedule-DataIngestion\",\n",
-        "    pipeline_parameters={\"ds_name\": dataset},\n",
-        "    pipeline_id=published_pipeline.id,\n",
-        "    experiment_name=experiment_name,\n",
-        "    datastore=dstor,\n",
-        "    wait_for_provisioning=True,\n",
-        "    polling_interval=1440,\n",
-        ")"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "vivijay"
-      }
-    ],
-    "kernelspec": {
-      "display_name": "Python 3.8 - AzureML",
-      "language": "python",
-      "name": "python38-azureml"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.6.6"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

how-to-use-azureml/automated-machine-learning/continuous-retraining/check_data.py

@@ -1,49 +0,0 @@
-import argparse
-import os
-import azureml.core
-from datetime import datetime
-import pandas as pd
-import pytz
-from azureml.core import Dataset, Model
-from azureml.core.run import Run, _OfflineRun
-from azureml.core import Workspace
-
-run = Run.get_context()
-ws = None
-if type(run) == _OfflineRun:
-    ws = Workspace.from_config()
-else:
-    ws = run.experiment.workspace
-
-print("Check for new data.")
-
-parser = argparse.ArgumentParser("split")
-parser.add_argument("--ds_name", help="input dataset name")
-parser.add_argument("--model_name", help="name of the deployed model")
-
-args = parser.parse_args()
-
-print("Argument 1(ds_name): %s" % args.ds_name)
-print("Argument 2(model_name): %s" % args.model_name)
-
-# Get the latest registered model
-try:
-    model = Model(ws, args.model_name)
-    last_train_time = model.created_time
-    print("Model was last trained on {0}.".format(last_train_time))
-except Exception:
-    print("Could not get last model train time.")
-    last_train_time = datetime.min.replace(tzinfo=pytz.UTC)
-
-train_ds = Dataset.get_by_name(ws, args.ds_name)
-dataset_changed_time = train_ds.data_changed_time.replace(tzinfo=pytz.UTC)
-
-print("dataset_changed_time=" + str(dataset_changed_time))
-print("last_train_time=" + str(last_train_time))
-
-if not dataset_changed_time > last_train_time:
-    print("Cancelling run since there is no new data.")
-    run.parent.cancel()
-else:
-    # New data is available since the model was last trained
-    print("Dataset was last updated on {0}. Retraining...".format(dataset_changed_time))

how-to-use-azureml/automated-machine-learning/continuous-retraining/register_model.py

@@ -1,35 +0,0 @@
-from azureml.core.model import Model, Dataset
-from azureml.core.run import Run, _OfflineRun
-from azureml.core import Workspace
-import argparse
-
-parser = argparse.ArgumentParser()
-parser.add_argument("--model_name")
-parser.add_argument("--model_path")
-parser.add_argument("--ds_name")
-args = parser.parse_args()
-
-print("Argument 1(model_name): %s" % args.model_name)
-print("Argument 2(model_path): %s" % args.model_path)
-print("Argument 3(ds_name): %s" % args.ds_name)
-
-run = Run.get_context()
-ws = None
-if type(run) == _OfflineRun:
-    ws = Workspace.from_config()
-else:
-    ws = run.experiment.workspace
-
-train_ds = Dataset.get_by_name(ws, args.ds_name)
-datasets = [(Dataset.Scenario.TRAINING, train_ds)]
-
-# Register model with training dataset
-
-model = Model.register(
-    workspace=ws,
-    model_path=args.model_path,
-    model_name=args.model_name,
-    datasets=datasets,
-)
-
-print("Registered version {0} of model {1}".format(model.version, model.name))

how-to-use-azureml/automated-machine-learning/continuous-retraining/upload_weather_data.py

@@ -1,161 +0,0 @@
-import argparse
-import os
-from datetime import datetime
-from dateutil.relativedelta import relativedelta
-import pandas as pd
-import traceback
-from azureml.core import Dataset
-from azureml.core.run import Run, _OfflineRun
-from azureml.core import Workspace
-from azureml.opendatasets import NoaaIsdWeather
-
-run = Run.get_context()
-ws = None
-if type(run) == _OfflineRun:
-    ws = Workspace.from_config()
-else:
-    ws = run.experiment.workspace
-
-usaf_list = [
-    "725724",
-    "722149",
-    "723090",
-    "722159",
-    "723910",
-    "720279",
-    "725513",
-    "725254",
-    "726430",
-    "720381",
-    "723074",
-    "726682",
-    "725486",
-    "727883",
-    "723177",
-    "722075",
-    "723086",
-    "724053",
-    "725070",
-    "722073",
-    "726060",
-    "725224",
-    "725260",
-    "724520",
-    "720305",
-    "724020",
-    "726510",
-    "725126",
-    "722523",
-    "703333",
-    "722249",
-    "722728",
-    "725483",
-    "722972",
-    "724975",
-    "742079",
-    "727468",
-    "722193",
-    "725624",
-    "722030",
-    "726380",
-    "720309",
-    "722071",
-    "720326",
-    "725415",
-    "724504",
-    "725665",
-    "725424",
-    "725066",
-]
-
-
-def get_noaa_data(start_time, end_time):
-    columns = [
-        "usaf",
-        "wban",
-        "datetime",
-        "latitude",
-        "longitude",
-        "elevation",
-        "windAngle",
-        "windSpeed",
-        "temperature",
-        "stationName",
-        "p_k",
-    ]
-    isd = NoaaIsdWeather(start_time, end_time, cols=columns)
-    noaa_df = isd.to_pandas_dataframe()
-    df_filtered = noaa_df[noaa_df["usaf"].isin(usaf_list)]
-    df_filtered.reset_index(drop=True)
-    print(
-        "Received {0} rows of training data between {1} and {2}".format(
-            df_filtered.shape[0], start_time, end_time
-        )
-    )
-    return df_filtered
-
-
-print("Check for new data and prepare the data")
-
-parser = argparse.ArgumentParser("split")
-parser.add_argument("--ds_name", help="name of the Dataset to update")
-args = parser.parse_args()
-
-print("Argument 1(ds_name): %s" % args.ds_name)
-
-dstor = ws.get_default_datastore()
-register_dataset = False
-end_time = datetime.utcnow()
-
-try:
-    ds = Dataset.get_by_name(ws, args.ds_name)
-    end_time_last_slice = ds.data_changed_time.replace(tzinfo=None)
-    print("Dataset {0} last updated on {1}".format(args.ds_name, end_time_last_slice))
-except Exception:
-    print(traceback.format_exc())
-    print(
-        "Dataset with name {0} not found, registering new dataset.".format(args.ds_name)
-    )
-    register_dataset = True
-    end_time = datetime(2021, 5, 1, 0, 0)
-    end_time_last_slice = end_time - relativedelta(weeks=2)
-
-try:
-    train_df = get_noaa_data(end_time_last_slice, end_time)
-except Exception as ex:
-    print("get_noaa_data failed:", ex)
-    train_df = None
-
-if train_df is not None and train_df.size > 0:
-    print(
-        "Received {0} rows of new data after {1}.".format(
-            train_df.shape[0], end_time_last_slice
-        )
-    )
-    folder_name = "{}/{:04d}/{:02d}/{:02d}/{:02d}/{:02d}/{:02d}".format(
-        args.ds_name,
-        end_time.year,
-        end_time.month,
-        end_time.day,
-        end_time.hour,
-        end_time.minute,
-        end_time.second,
-    )
-    file_path = "{0}/data.csv".format(folder_name)
-
-    # Add a new partition to the registered dataset
-    os.makedirs(folder_name, exist_ok=True)
-    train_df.to_csv(file_path, index=False)
-
-    dstor.upload_files(
-        files=[file_path], target_path=folder_name, overwrite=True, show_progress=True
-    )
-else:
-    print("No new data since {0}.".format(end_time_last_slice))
-
-if register_dataset:
-    ds = Dataset.Tabular.from_delimited_files(
-        dstor.path("{}/**/*.csv".format(args.ds_name)),
-        partition_format="/{partition_date:yyyy/MM/dd/HH/mm/ss}/data.csv",
-    )
-    ds.register(ws, name=args.ds_name)

how-to-use-azureml/automated-machine-learning/dataprep-remote-execution/auto-ml-dataprep-remote-execution.ipynb

@@ -0,0 +1,498 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "_**Prepare Data using `azureml.dataprep` for Remote Execution (DSVM)**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Data](#Data)\n",
+        "1. [Train](#Train)\n",
+        "1. [Results](#Results)\n",
+        "1. [Test](#Test)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "In this example we showcase how you can use the `azureml.dataprep` SDK to load and prepare data for AutoML. `azureml.dataprep` can also be used standalone; full documentation can be found [here](https://github.com/Microsoft/PendletonDocs).\n",
+        "\n",
+        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+        "\n",
+        "In this notebook you will learn how to:\n",
+        "1. Define data loading and preparation steps in a `Dataflow` using `azureml.dataprep`.\n",
+        "2. Pass the `Dataflow` to AutoML for a local run.\n",
+        "3. Pass the `Dataflow` to AutoML for a remote run."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup\n",
+        "\n",
+        "Currently, Data Prep only supports __Ubuntu 16__ and __Red Hat Enterprise Linux 7__. We are working on supporting more linux distros."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import logging\n",
+        "import time\n",
+        "\n",
+        "import pandas as pd\n",
+        "\n",
+        "import azureml.core\n",
+        "from azureml.core.compute import DsvmCompute\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "import azureml.dataprep as dprep\n",
+        "from azureml.train.automl import AutoMLConfig"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        " \n",
+        "# choose a name for experiment\n",
+        "experiment_name = 'automl-dataprep-remote-dsvm'\n",
+        "# project folder\n",
+        "project_folder = './sample_projects/automl-dataprep-remote-dsvm'\n",
+        " \n",
+        "experiment = Experiment(ws, experiment_name)\n",
+        " \n",
+        "output = {}\n",
+        "output['SDK version'] = azureml.core.VERSION\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace Name'] = ws.name\n",
+        "output['Resource Group'] = ws.resource_group\n",
+        "output['Location'] = ws.location\n",
+        "output['Project Directory'] = project_folder\n",
+        "output['Experiment Name'] = experiment.name\n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
+        "outputDf.T"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Data"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# You can use `auto_read_file` which intelligently figures out delimiters and datatypes of a file.\n",
+        "# The data referenced here was pulled from `sklearn.datasets.load_digits()`.\n",
+        "simple_example_data_root = 'https://dprepdata.blob.core.windows.net/automl-notebook-data/'\n",
+        "X = dprep.auto_read_file(simple_example_data_root + 'X.csv').skip(1)  # Remove the header row.\n",
+        "\n",
+        "# You can also use `read_csv` and `to_*` transformations to read (with overridable delimiter)\n",
+        "# and convert column types manually.\n",
+        "# Here we read a comma delimited file and convert all columns to integers.\n",
+        "y = dprep.read_csv(simple_example_data_root + 'y.csv').to_long(dprep.ColumnSelector(term='.*', use_regex = True))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can peek the result of a Dataflow at any range using `skip(i)` and `head(j)`. Doing so evaluates only `j` records for all the steps in the Dataflow, which makes it fast even against large datasets."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X.skip(1).head(5)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train\n",
+        "\n",
+        "This creates a general AutoML settings object applicable for both local and remote runs."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "automl_settings = {\n",
+        "    \"iteration_timeout_minutes\" : 10,\n",
+        "    \"iterations\" : 2,\n",
+        "    \"primary_metric\" : 'AUC_weighted',\n",
+        "    \"preprocess\" : False,\n",
+        "    \"verbosity\" : logging.INFO,\n",
+        "    \"n_cross_validations\": 3\n",
+        "}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create or Attach a Remote Linux DSVM"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "dsvm_name = 'mydsvmc'\n",
+        "\n",
+        "try:\n",
+        "    while ws.compute_targets[dsvm_name].provisioning_state == 'Creating':\n",
+        "        time.sleep(1)\n",
+        "        \n",
+        "    dsvm_compute = DsvmCompute(ws, dsvm_name)\n",
+        "    print('Found existing DVSM.')\n",
+        "except:\n",
+        "    print('Creating a new DSVM.')\n",
+        "    dsvm_config = DsvmCompute.provisioning_configuration(vm_size = \"Standard_D2_v2\")\n",
+        "    dsvm_compute = DsvmCompute.create(ws, name = dsvm_name, provisioning_configuration = dsvm_config)\n",
+        "    dsvm_compute.wait_for_completion(show_output = True)\n",
+        "    print(\"Waiting one minute for ssh to be accessible\")\n",
+        "    time.sleep(90) # Wait for ssh to be accessible"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.runconfig import RunConfiguration\n",
+        "from azureml.core.conda_dependencies import CondaDependencies\n",
+        "\n",
+        "conda_run_config = RunConfiguration(framework=\"python\")\n",
+        "\n",
+        "conda_run_config.target = dsvm_compute\n",
+        "\n",
+        "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy','py-xgboost<=0.80'])\n",
+        "conda_run_config.environment.python.conda_dependencies = cd"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Pass Data with `Dataflow` Objects\n",
+        "\n",
+        "The `Dataflow` objects captured above can also be passed to the `submit` method for a remote run. AutoML will serialize the `Dataflow` object and send it to the remote compute target. The `Dataflow` will not be evaluated locally."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "automl_config = AutoMLConfig(task = 'classification',\n",
+        "                             debug_log = 'automl_errors.log',\n",
+        "                             path = project_folder,\n",
+        "                             run_configuration=conda_run_config,\n",
+        "                             X = X,\n",
+        "                             y = y,\n",
+        "                             **automl_settings)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run = experiment.submit(automl_config, show_output = True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Results"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Widget for Monitoring Runs\n",
+        "\n",
+        "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+        "\n",
+        "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.widgets import RunDetails\n",
+        "RunDetails(remote_run).show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Retrieve All Child Runs\n",
+        "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "children = list(remote_run.get_children())\n",
+        "metricslist = {}\n",
+        "for run in children:\n",
+        "    properties = run.get_properties()\n",
+        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+        "    metricslist[int(properties['iteration'])] = metrics\n",
+        "    \n",
+        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+        "rundata"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Retrieve the Best Model\n",
+        "\n",
+        "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run, fitted_model = remote_run.get_output()\n",
+        "print(best_run)\n",
+        "print(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Best Model Based on Any Other Metric\n",
+        "Show the run and the model that has the smallest `log_loss` value:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "lookup_metric = \"log_loss\"\n",
+        "best_run, fitted_model = remote_run.get_output(metric = lookup_metric)\n",
+        "print(best_run)\n",
+        "print(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Model from a Specific Iteration\n",
+        "Show the run and the model from the first iteration:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "iteration = 0\n",
+        "best_run, fitted_model = remote_run.get_output(iteration = iteration)\n",
+        "print(best_run)\n",
+        "print(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Test\n",
+        "\n",
+        "#### Load Test Data"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from sklearn import datasets\n",
+        "\n",
+        "digits = datasets.load_digits()\n",
+        "X_test = digits.data[:10, :]\n",
+        "y_test = digits.target[:10]\n",
+        "images = digits.images[:10]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Testing Our Best Fitted Model\n",
+        "We will try to predict 2 digits and see how our model works."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "#Randomly select digits and test\n",
+        "from matplotlib import pyplot as plt\n",
+        "import numpy as np\n",
+        "\n",
+        "for index in np.random.choice(len(y_test), 2, replace = False):\n",
+        "    print(index)\n",
+        "    predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
+        "    label = y_test[index]\n",
+        "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
+        "    fig = plt.figure(1, figsize=(3,3))\n",
+        "    ax1 = fig.add_axes((0,0,.8,.8))\n",
+        "    ax1.set_title(title)\n",
+        "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
+        "    plt.show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Appendix"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Capture the `Dataflow` Objects for Later Use in AutoML\n",
+        "\n",
+        "`Dataflow` objects are immutable and are composed of a list of data preparation steps. A `Dataflow` object can be branched at any point for further usage."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# sklearn.digits.data + target\n",
+        "digits_complete = dprep.auto_read_file('https://dprepdata.blob.core.windows.net/automl-notebook-data/digits-complete.csv')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "`digits_complete` (sourced from `sklearn.datasets.load_digits()`) is forked into `dflow_X` to capture all the feature columns and `dflow_y` to capture the label column."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(digits_complete.to_pandas_dataframe().shape)\n",
+        "labels_column = 'Column64'\n",
+        "dflow_X = digits_complete.drop_columns(columns = [labels_column])\n",
+        "dflow_y = digits_complete.keep_columns(columns = [labels_column])"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "savitam"
+      }
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "python",
+      "name": "python36"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.5"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/dataprep/auto-ml-dataprep.ipynb

@@ -0,0 +1,449 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "_**Prepare Data using `azureml.dataprep` for Local Execution**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Data](#Data)\n",
+        "1. [Train](#Train)\n",
+        "1. [Results](#Results)\n",
+        "1. [Test](#Test)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "In this example we showcase how you can use the `azureml.dataprep` SDK to load and prepare data for AutoML. `azureml.dataprep` can also be used standalone; full documentation can be found [here](https://github.com/Microsoft/PendletonDocs).\n",
+        "\n",
+        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+        "\n",
+        "In this notebook you will learn how to:\n",
+        "1. Define data loading and preparation steps in a `Dataflow` using `azureml.dataprep`.\n",
+        "2. Pass the `Dataflow` to AutoML for a local run.\n",
+        "3. Pass the `Dataflow` to AutoML for a remote run."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup\n",
+        "\n",
+        "Currently, Data Prep only supports __Ubuntu 16__ and __Red Hat Enterprise Linux 7__. We are working on supporting more linux distros."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import logging\n",
+        "\n",
+        "import pandas as pd\n",
+        "\n",
+        "import azureml.core\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "import azureml.dataprep as dprep\n",
+        "from azureml.train.automl import AutoMLConfig"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        " \n",
+        "# choose a name for experiment\n",
+        "experiment_name = 'automl-dataprep-local'\n",
+        "# project folder\n",
+        "project_folder = './sample_projects/automl-dataprep-local'\n",
+        " \n",
+        "experiment = Experiment(ws, experiment_name)\n",
+        " \n",
+        "output = {}\n",
+        "output['SDK version'] = azureml.core.VERSION\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace Name'] = ws.name\n",
+        "output['Resource Group'] = ws.resource_group\n",
+        "output['Location'] = ws.location\n",
+        "output['Project Directory'] = project_folder\n",
+        "output['Experiment Name'] = experiment.name\n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
+        "outputDf.T"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Data"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# You can use `auto_read_file` which intelligently figures out delimiters and datatypes of a file.\n",
+        "# The data referenced here was pulled from `sklearn.datasets.load_digits()`.\n",
+        "simple_example_data_root = 'https://dprepdata.blob.core.windows.net/automl-notebook-data/'\n",
+        "X = dprep.auto_read_file(simple_example_data_root + 'X.csv').skip(1)  # Remove the header row.\n",
+        "\n",
+        "# You can also use `read_csv` and `to_*` transformations to read (with overridable delimiter)\n",
+        "# and convert column types manually.\n",
+        "# Here we read a comma delimited file and convert all columns to integers.\n",
+        "y = dprep.read_csv(simple_example_data_root + 'y.csv').to_long(dprep.ColumnSelector(term='.*', use_regex = True))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Review the Data Preparation Result\n",
+        "\n",
+        "You can peek the result of a Dataflow at any range using `skip(i)` and `head(j)`. Doing so evaluates only `j` records for all the steps in the Dataflow, which makes it fast even against large datasets."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X.skip(1).head(5)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train\n",
+        "\n",
+        "This creates a general AutoML settings object applicable for both local and remote runs."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "automl_settings = {\n",
+        "    \"iteration_timeout_minutes\" : 10,\n",
+        "    \"iterations\" : 2,\n",
+        "    \"primary_metric\" : 'AUC_weighted',\n",
+        "    \"preprocess\" : False,\n",
+        "    \"verbosity\" : logging.INFO,\n",
+        "    \"n_cross_validations\": 3\n",
+        "}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Pass Data with `Dataflow` Objects\n",
+        "\n",
+        "The `Dataflow` objects captured above can be passed to the `submit` method for a local run. AutoML will retrieve the results from the `Dataflow` for model training."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "automl_config = AutoMLConfig(task = 'classification',\n",
+        "                             debug_log = 'automl_errors.log',\n",
+        "                             X = X,\n",
+        "                             y = y,\n",
+        "                             **automl_settings)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run = experiment.submit(automl_config, show_output = True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Results"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Widget for Monitoring Runs\n",
+        "\n",
+        "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+        "\n",
+        "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.widgets import RunDetails\n",
+        "RunDetails(local_run).show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Retrieve All Child Runs\n",
+        "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "children = list(local_run.get_children())\n",
+        "metricslist = {}\n",
+        "for run in children:\n",
+        "    properties = run.get_properties()\n",
+        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+        "    metricslist[int(properties['iteration'])] = metrics\n",
+        "    \n",
+        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+        "rundata"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Retrieve the Best Model\n",
+        "\n",
+        "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run, fitted_model = local_run.get_output()\n",
+        "print(best_run)\n",
+        "print(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Best Model Based on Any Other Metric\n",
+        "Show the run and the model that has the smallest `log_loss` value:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "lookup_metric = \"log_loss\"\n",
+        "best_run, fitted_model = local_run.get_output(metric = lookup_metric)\n",
+        "print(best_run)\n",
+        "print(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Model from a Specific Iteration\n",
+        "Show the run and the model from the first iteration:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "iteration = 0\n",
+        "best_run, fitted_model = local_run.get_output(iteration = iteration)\n",
+        "print(best_run)\n",
+        "print(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Test\n",
+        "\n",
+        "#### Load Test Data"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from sklearn import datasets\n",
+        "\n",
+        "digits = datasets.load_digits()\n",
+        "X_test = digits.data[:10, :]\n",
+        "y_test = digits.target[:10]\n",
+        "images = digits.images[:10]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Testing Our Best Fitted Model\n",
+        "We will try to predict 2 digits and see how our model works."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "#Randomly select digits and test\n",
+        "from matplotlib import pyplot as plt\n",
+        "import numpy as np\n",
+        "\n",
+        "for index in np.random.choice(len(y_test), 2, replace = False):\n",
+        "    print(index)\n",
+        "    predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
+        "    label = y_test[index]\n",
+        "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
+        "    fig = plt.figure(1, figsize=(3,3))\n",
+        "    ax1 = fig.add_axes((0,0,.8,.8))\n",
+        "    ax1.set_title(title)\n",
+        "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
+        "    plt.show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Appendix"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Capture the `Dataflow` Objects for Later Use in AutoML\n",
+        "\n",
+        "`Dataflow` objects are immutable and are composed of a list of data preparation steps. A `Dataflow` object can be branched at any point for further usage."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# sklearn.digits.data + target\n",
+        "digits_complete = dprep.auto_read_file('https://dprepdata.blob.core.windows.net/automl-notebook-data/digits-complete.csv')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "`digits_complete` (sourced from `sklearn.datasets.load_digits()`) is forked into `dflow_X` to capture all the feature columns and `dflow_y` to capture the label column."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(digits_complete.to_pandas_dataframe().shape)\n",
+        "labels_column = 'Column64'\n",
+        "dflow_X = digits_complete.drop_columns(columns = [labels_column])\n",
+        "dflow_y = digits_complete.keep_columns(columns = [labels_column])"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "savitam"
+      }
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "python",
+      "name": "python36"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.5"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/experimental/README.md

@@ -1,92 +0,0 @@
-# Experimental Notebooks for Automated ML
-Notebooks listed in this folder are leveraging experimental features. Namespaces or function signitures may change in future SDK releases. The notebooks published here will reflect the latest supported APIs. All of these notebooks can run on a client-only installation of the Automated ML SDK.
-The client only installation doesn't contain any of the machine learning libraries, such as scikit-learn, xgboost, or tensorflow, making it much faster to install and is less likely to conflict with any packages in an existing environment. However, since the ML libraries are not available locally, models cannot be downloaded and loaded directly in the client. To replace the functionality of having models locally, these notebooks also demonstrate the ModelProxy feature which will allow you to submit a predict/forecast to the training environment. 
-
-<a name="localconda"></a>
-## Setup using a Local Conda environment
-
-To run these notebook on your own notebook server, use these installation instructions.
-The instructions below will install everything you need and then start a Jupyter notebook.
-If you would like to use a lighter-weight version of the client that does not install all of the machine learning libraries locally, you can leverage the [experimental notebooks.](experimental/README.md)
-
-### 1. Install mini-conda from [here](https://conda.io/miniconda.html), choose 64-bit Python 3.8 or higher.
-- **Note**: if you already have conda installed, you can keep using it but it should be version 4.4.10 or later (as shown by: conda -V).  If you have a previous version installed, you can update it using the command: conda update conda.
-There's no need to install mini-conda specifically.
-
-### 2. Downloading the sample notebooks
-- Download the sample notebooks from [GitHub](https://github.com/Azure/MachineLearningNotebooks) as zip and extract the contents to a local directory.  The automated ML sample notebooks are in the "automated-machine-learning" folder.
-
-### 3. Setup a new conda environment
-The **automl_setup_thin_client** script creates a new conda environment, installs the necessary packages, configures the widget and starts a jupyter notebook. It takes the conda environment name as an optional parameter.  The default conda environment name is azure_automl_experimental.  The exact command depends on the operating system.  See the specific sections below for Windows, Mac and Linux.  It can take about 10 minutes to execute.
-
-Packages installed by the **automl_setup** script:
-    <ul><li>python</li><li>nb_conda</li><li>matplotlib</li><li>numpy</li><li>cython</li><li>urllib3</li><li>pandas</li><li>azureml-sdk</li><li>azureml-widgets</li><li>pandas-ml</li></ul>
-
-For more details refer to the [automl_env_thin_client.yml](./automl_env_thin_client.yml)
-## Windows
-Start an **Anaconda Prompt** window, cd to the **how-to-use-azureml/automated-machine-learning/experimental** folder where the sample notebooks were extracted and then run:
-```
-automl_setup_thin_client
-```
-## Mac
-Install "Command line developer tools" if it is not already installed (you can use the command: `xcode-select --install`).
-
-Start a Terminal windows, cd to the **how-to-use-azureml/automated-machine-learning/experimental** folder where the sample notebooks were extracted and then run:
-
-```
-bash automl_setup_thin_client_mac.sh
-```
-
-## Linux
-cd to the **how-to-use-azureml/automated-machine-learning/experimental** folder where the sample notebooks were extracted and then run:
-
-```
-bash automl_setup_thin_client_linux.sh
-```
-
-### 4. Running configuration.ipynb
-- Before running any samples you next need to run the configuration notebook. Click on [configuration](../../configuration.ipynb) notebook
-- Execute the cells in the notebook to Register Machine Learning Services Resource Provider and create a workspace. (*instructions in notebook*)
-
-### 5. Running Samples
-- Please make sure you use the Python [conda env:azure_automl_experimental] kernel when trying the sample Notebooks.
-- Follow the instructions in the individual notebooks to explore various features in automated ML.
-
-### 6. Starting jupyter notebook manually
-To start your Jupyter notebook manually, use:
-
-```
-conda activate azure_automl
-jupyter notebook
-```
-
-or on Mac or Linux:
-
-```
-source activate azure_automl
-jupyter notebook
-```
-
-
-<a name="samples"></a>
-# Automated ML SDK Sample Notebooks
-
-- [auto-ml-regression-model-proxy.ipynb](regression-model-proxy/auto-ml-regression-model-proxy.ipynb)
-    - Dataset: Hardware Performance Dataset
-    - Simple example of using automated ML for regression
-    - Uses azure compute for training
-    - Uses ModelProxy for submitting prediction to training environment on azure compute
-
-<a name="documentation"></a>
-See [Configure automated machine learning experiments](https://docs.microsoft.com/azure/machine-learning/service/how-to-configure-auto-train) to learn how more about the the settings and features available for automated machine learning experiments.
-
-<a name="pythoncommand"></a>
-# Running using python command
-Jupyter notebook provides a File / Download as / Python (.py) option for saving the notebook as a Python file.
-You can then run this file using the python command.
-However, on Windows the file needs to be modified before it can be run.
-The following condition must be added to the main code in the file:
-
-    if __name__ == "__main__":
-
-The main code of the file must be indented so that it is under this condition.

how-to-use-azureml/automated-machine-learning/experimental/autofeaturization-codegen/codegen-for-autofeaturization.ipynb

@@ -1,346 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/classification-credit-card-fraud/custom-model-training-from-autofeaturization-run.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Automated Machine Learning - Codegen for AutoFeaturization \n",
-        "_**Autofeaturization of credit card fraudulent transactions dataset on remote compute and codegen functionality**_\n",
-        "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Data](#Data)\n",
-        "1. [Autofeaturization](#Autofeaturization)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id='Introduction'></a>\n",
-        "## Introduction"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "**Autofeaturization** lets you run an AutoML experiment to only featurize the datasets. These datasets along with the transformer are stored in AML Storage and linked to the run which can later be retrieved and used to train models. \n",
-        "\n",
-        "**To run Autofeaturization, set the number of iterations to zero and featurization as auto.**\n",
-        "\n",
-        "Please refer to [Autofeaturization and custom model training](../autofeaturization-custom-model-training/custom-model-training-from-autofeaturization-run.ipynb) for more details on the same.\n",
-        "\n",
-        "[Codegen](https://github.com/Azure/automl-codegen-preview) is a feature, which when enabled, provides a user with the script of the underlying functionality and a notebook to tweak inputs or code and rerun the same.\n",
-        "\n",
-        "In this example we use the credit card fraudulent transactions dataset to showcase how you can use AutoML for autofeaturization and further how you can enable the `Codegen` feature.\n",
-        "\n",
-        "This notebook is using remote compute to complete the featurization.\n",
-        "\n",
-        "If you are using an Azure Machine Learning Compute Instance, you are all set. Otherwise, go through the [configuration](../../configuration.ipynb) notebook first if you haven't already, to establish your connection to the AzureML Workspace. \n",
-        "\n",
-        "Here you will learn how to create an autofeaturization experiment using an existing workspace with codegen feature enabled."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id='Setup'></a>\n",
-        "## Setup\n",
-        "\n",
-        "As part of the setup you have already created an Azure ML `Workspace` object. For Automated ML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import logging\n",
-        "import pandas as pd\n",
-        "import azureml.core\n",
-        "from azureml.core.experiment import Experiment\n",
-        "from azureml.core.workspace import Workspace\n",
-        "from azureml.core.dataset import Dataset\n",
-        "from azureml.train.automl import AutoMLConfig"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "print(\"This notebook was created using version 1.59.0 of the Azure ML SDK\")\n",
-        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ws = Workspace.from_config()\n",
-        "\n",
-        "# choose a name for experiment\n",
-        "experiment_name = 'automl-autofeaturization-ccard-codegen-remote'\n",
-        "\n",
-        "experiment=Experiment(ws, experiment_name)\n",
-        "\n",
-        "output = {}\n",
-        "output['Subscription ID'] = ws.subscription_id\n",
-        "output['Workspace'] = ws.name\n",
-        "output['Resource Group'] = ws.resource_group\n",
-        "output['Location'] = ws.location\n",
-        "output['Experiment Name'] = experiment.name\n",
-        "outputDf = pd.DataFrame(data = output, index = [''])\n",
-        "outputDf.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Create or Attach existing AmlCompute\n",
-        "A compute target is required to execute the Automated ML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
-        "\n",
-        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
-        "\n",
-        "#### Creation of AmlCompute takes approximately 5 minutes. \n",
-        "If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
-        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
-        "from azureml.core.compute_target import ComputeTargetException\n",
-        "\n",
-        "# Choose a name for your CPU cluster\n",
-        "cpu_cluster_name = \"cpu-codegen\"\n",
-        "\n",
-        "# Verify that cluster does not exist already\n",
-        "try:\n",
-        "    compute_target = ComputeTarget(workspace=ws, name=cpu_cluster_name)\n",
-        "    print('Found existing cluster, use it.')\n",
-        "except ComputeTargetException:\n",
-        "    compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_DS12_V2',\n",
-        "                                                           max_nodes=6)\n",
-        "    compute_target = ComputeTarget.create(ws, cpu_cluster_name, compute_config)\n",
-        "\n",
-        "compute_target.wait_for_completion(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id='Data'></a>\n",
-        "## Data"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Load Data\n",
-        "\n",
-        "Load the credit card fraudulent transactions dataset from a CSV file, containing both training features and labels. The features are inputs to the model, while the training labels represent the expected output of the model. \n",
-        "\n",
-        "Here the autofeaturization run will featurize the training data passed in."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "##### Training Dataset"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "training_data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/creditcard_train.csv\"\n",
-        "training_dataset = Dataset.Tabular.from_delimited_files(training_data) # Tabular dataset\n",
-        "\n",
-        "label_column_name = 'Class' # output label"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id='Autofeaturization'></a>\n",
-        "## AutoFeaturization\n",
-        "\n",
-        "Instantiate an AutoMLConfig object. This defines the settings and data used to run the autofeaturization experiment.\n",
-        "\n",
-        "|Property|Description|\n",
-        "|-|-|\n",
-        "|**task**|classification or regression or forecasting|\n",
-        "|**training_data**|Input training dataset, containing both features and label column.|\n",
-        "|**iterations**|For an autofeaturization run, iterations will be 0.|\n",
-        "|**featurization**|For an autofeaturization run, featurization can be 'auto' or 'custom'.|\n",
-        "|**label_column_name**|The name of the label column.|\n",
-        "|**enable_code_generation**|For enabling codegen for the run, value would be True|\n",
-        "\n",
-        "**_You can find more information about primary metrics_** [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#primary-metric)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "automl_config = AutoMLConfig(task = 'classification',\n",
-        "                             debug_log = 'automl_errors.log',\n",
-        "                             iterations = 0, # autofeaturization run can be triggered by setting iterations to 0\n",
-        "                             compute_target = compute_target,\n",
-        "                             training_data = training_dataset,\n",
-        "                             label_column_name = label_column_name,\n",
-        "                             featurization = 'auto',\n",
-        "                             verbosity = logging.INFO,\n",
-        "                             enable_code_generation = True # enable codegen\n",
-        "                            )"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Call the `submit` method on the experiment object and pass the run configuration. Depending on the data this can run for a while. Validation errors and current status will be shown when setting `show_output=True` and the execution will be synchronous."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run = experiment.submit(automl_config, show_output = False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Results"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Widget for Monitoring Runs\n",
-        "\n",
-        "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
-        "\n",
-        "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.widgets import RunDetails\n",
-        "RunDetails(remote_run).show()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run.wait_for_completion(show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Codegen Script and Notebook"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Codegen script and notebook can be found under the `Outputs + logs` section from the details page of the remote run. Please check for the `autofeaturization_notebook.ipynb` under `/outputs/generated_code`. To modify the featurization code, open `script.py` and make changes. The codegen notebook can be run with the same environment configuration as the above AutoML run."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Experiment Complete!"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "bhavanatumma"
-      }
-    ],
-    "interpreter": {
-      "hash": "adb464b67752e4577e3dc163235ced27038d19b7d88def00d75d1975bde5d9ab"
-    },
-    "kernelspec": {
-      "display_name": "Python 3.8 - AzureML",
-      "language": "python",
-      "name": "python38-azureml"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.6.9"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

how-to-use-azureml/automated-machine-learning/experimental/autofeaturization-custom-model-training/custom-model-training-from-autofeaturization-run.ipynb

@@ -1,729 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/classification-credit-card-fraud/custom-model-training-from-autofeaturization-run.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Automated Machine Learning - AutoFeaturization (Part 1)\n",
-        "_**Autofeaturization of credit card fraudulent transactions dataset on remote compute**_\n",
-        "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Data](#Data)\n",
-        "1. [Autofeaturization](#Autofeaturization)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id='Introduction'></a>\n",
-        "## Introduction"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Autofeaturization is a new feature to let you as the user run an AutoML experiment to only featurize the datasets. These datasets along with the transformer will be stored in the experiment which can later be retrieved and used to train models, either via AutoML or custom training. \n",
-        "\n",
-        "**To run Autofeaturization, pass in zero iterations and featurization as auto. This will featurize the datasets and terminate the experiment. Training will not occur.**\n",
-        "\n",
-        "*Limitations - Sparse data cannot be supported at the moment. Any dataset that has extensive categorical data might be featurized into sparse data which will not be allowed as input to AutoML. Efforts are underway to support sparse data and will be updated soon.* \n",
-        "\n",
-        "In this example we use the credit card fraudulent transactions dataset to showcase how you can use AutoML for autofeaturization. The goal is to clean and featurize the training dataset.\n",
-        "\n",
-        "This notebook is using remote compute to complete the featurization.\n",
-        "\n",
-        "If you are using an Azure Machine Learning Compute Instance, you are all set. Otherwise, go through the [configuration](../../configuration.ipynb) notebook first if you haven't already, to establish your connection to the AzureML Workspace. \n",
-        "\n",
-        "In the below steps, you will learn how to:\n",
-        "1. Create an autofeaturization experiment using an existing workspace.\n",
-        "2. View the featurized datasets and transformer"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id='Setup'></a>\n",
-        "## Setup\n",
-        "\n",
-        "As part of the setup you have already created an Azure ML `Workspace` object. For Automated ML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import logging\n",
-        "import pandas as pd\n",
-        "import azureml.core\n",
-        "from azureml.core.experiment import Experiment\n",
-        "from azureml.core.workspace import Workspace\n",
-        "from azureml.core.dataset import Dataset\n",
-        "from azureml.train.automl import AutoMLConfig"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "print(\"This notebook was created using version 1.59.0 of the Azure ML SDK\")\n",
-        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ws = Workspace.from_config()\n",
-        "\n",
-        "# choose a name for experiment\n",
-        "experiment_name = 'automl-autofeaturization-ccard-remote'\n",
-        "\n",
-        "experiment=Experiment(ws, experiment_name)\n",
-        "\n",
-        "output = {}\n",
-        "output['Subscription ID'] = ws.subscription_id\n",
-        "output['Workspace'] = ws.name\n",
-        "output['Resource Group'] = ws.resource_group\n",
-        "output['Location'] = ws.location\n",
-        "output['Experiment Name'] = experiment.name\n",
-        "outputDf = pd.DataFrame(data = output, index = [''])\n",
-        "outputDf.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Create or Attach existing AmlCompute\n",
-        "A compute target is required to execute the Automated ML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
-        "\n",
-        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
-        "\n",
-        "#### Creation of AmlCompute takes approximately 5 minutes. \n",
-        "If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
-        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
-        "from azureml.core.compute_target import ComputeTargetException\n",
-        "\n",
-        "# Choose a name for your CPU cluster\n",
-        "cpu_cluster_name = \"cpu-cluster\"\n",
-        "\n",
-        "# Verify that cluster does not exist already\n",
-        "try:\n",
-        "    compute_target = ComputeTarget(workspace=ws, name=cpu_cluster_name)\n",
-        "    print('Found existing cluster, use it.')\n",
-        "except ComputeTargetException:\n",
-        "    compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_DS12_V2',\n",
-        "                                                           max_nodes=6)\n",
-        "    compute_target = ComputeTarget.create(ws, cpu_cluster_name, compute_config)\n",
-        "\n",
-        "compute_target.wait_for_completion(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id='Data'></a>\n",
-        "## Data"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Load Data\n",
-        "\n",
-        "Load the credit card fraudulent transactions dataset from a CSV file, containing both training features and labels. The features are inputs to the model, while the training labels represent the expected output of the model. \n",
-        "\n",
-        "Here the autofeaturization run will featurize the training data passed in."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "##### Training Dataset"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "training_data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/creditcard_train.csv\"\n",
-        "training_dataset = Dataset.Tabular.from_delimited_files(training_data) # Tabular dataset\n",
-        "\n",
-        "label_column_name = 'Class' # output label"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id='Autofeaturization'></a>\n",
-        "## AutoFeaturization\n",
-        "\n",
-        "Instantiate an AutoMLConfig object. This defines the settings and data used to run the autofeaturization experiment.\n",
-        "\n",
-        "|Property|Description|\n",
-        "|-|-|\n",
-        "|**task**|classification or regression|\n",
-        "|**training_data**|Input training dataset, containing both features and label column.|\n",
-        "|**iterations**|For an autofeaturization run, iterations will be 0.|\n",
-        "|**featurization**|For an autofeaturization run, featurization will be 'auto'.|\n",
-        "|**label_column_name**|The name of the label column.|\n",
-        "\n",
-        "**_You can find more information about primary metrics_** [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#primary-metric)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "automl_config = AutoMLConfig(task = 'classification',\n",
-        "                             debug_log = 'automl_errors.log',\n",
-        "                             iterations = 0, # autofeaturization run can be triggered by setting iterations to 0\n",
-        "                             compute_target = compute_target,\n",
-        "                             training_data = training_dataset,\n",
-        "                             label_column_name = label_column_name,\n",
-        "                             featurization = 'auto',\n",
-        "                             verbosity = logging.INFO\n",
-        "                            )"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Call the `submit` method on the experiment object and pass the run configuration. Depending on the data this can run for a while. Validation errors and current status will be shown when setting `show_output=True` and the execution will be synchronous."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run = experiment.submit(automl_config, show_output = False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Transformer and Featurized Datasets\n",
-        "The given datasets have been featurized and stored under `Outputs + logs` from the details page of the remote run. The structure is shown below. The featurized dataset is stored under `/outputs/featurization/data` and the transformer is saved under `/outputs/featurization/pipeline` \n",
-        "\n",
-        "Below you will learn how to refer to the data saved in your run and retrieve the same."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Featurized Data](https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/autofeaturization_img.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Results"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Widget for Monitoring Runs\n",
-        "\n",
-        "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
-        "\n",
-        "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.widgets import RunDetails\n",
-        "RunDetails(remote_run).show()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run.wait_for_completion(show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Automated Machine Learning - AutoFeaturization (Part 2)\n",
-        "_**Training using a custom model with the featurized data from Autofeaturization run of credit card fraudulent transactions dataset**_\n",
-        "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Data Setup](#DataSetup)\n",
-        "1. [Autofeaturization Data](#AutofeaturizationData)\n",
-        "1. [Train](#Train)\n",
-        "1. [Results](#Results)\n",
-        "1. [Test](#Test)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id='Introduction'></a>\n",
-        "## Introduction\n",
-        "\n",
-        "Here we use the featurized dataset saved in the above run to showcase how you can perform custom training by using the transformer from an autofeaturization run to transform validation / test datasets. \n",
-        "\n",
-        "The goal is to use autofeaturized run data and transformer to transform and run a custom training experiment independently\n",
-        "\n",
-        "In the below steps, you will learn how to:\n",
-        "1. Read transformer from a completed autofeaturization run and transform data\n",
-        "2. Pull featurized data from a completed autofeaturization run\n",
-        "3. Run a custom training experiment with the above data\n",
-        "4. Check results"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id='DataSetup'></a>\n",
-        "## Data Setup"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "We will load the featurized training data and also load the transformer from the above autofeaturized run. This transformer can then be used to transform the test data to check the accuracy of the custom model after training."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Load Test Data"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "load test dataset from CSV and split into X and y columns to featurize with the transformer going forward."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "test_data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/creditcard_test.csv\"\n",
-        "\n",
-        "test_dataset = pd.read_csv(test_data)\n",
-        "label_column_name = 'Class'\n",
-        "\n",
-        "X_test_data = test_dataset[test_dataset.columns.difference([label_column_name])]\n",
-        "y_test_data = test_dataset[label_column_name].values\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Load data_transformer from the above remote run artifact"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### (Method 1)\n",
-        "\n",
-        "Method 1 allows you to read the transformer from the remote storage."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import mlflow\n",
-        "mlflow.set_tracking_uri(ws.get_mlflow_tracking_uri())\n",
-        "\n",
-        "# Set uri to fetch data transformer from remote parent run.\n",
-        "artifact_path = \"/outputs/featurization/pipeline/\"\n",
-        "uri = \"runs:/\" + remote_run.id + artifact_path\n",
-        "\n",
-        "print(uri)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### (Method 2)\n",
-        "\n",
-        "Method 2 downloads the transformer to the local directory and then can be used to transform the data. Uncomment to use."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "''' import pathlib\n",
-        "\n",
-        "# Download the transformer to the local directory\n",
-        "transformers_file_path = \"/outputs/featurization/pipeline/\"\n",
-        "local_path = \"./transformer\"\n",
-        "remote_run.download_files(prefix=transformers_file_path, output_directory=local_path, batch_size=500)\n",
-        "\n",
-        "path = pathlib.Path(\"transformer\") \n",
-        "path = str(path.absolute()) + transformers_file_path\n",
-        "str_uri = \"file:///\" + path\n",
-        "\n",
-        "print(str_uri) '''"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Transform Data"
-      ]
-    },
-    {
-      "attachments": {},
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "**Note:** Not all datasets produce a y_transformer. The dataset used in the current notebook requires a transformer as the y column data is categorical. \n",
-        "\n",
-        "We will go ahead and download the mlflow transformer model and use it to transform test data that can be used for further experimentation below. To run the commented code, make sure the environment requirement is satisfied. You can go ahead and create the environment from the `conda.yaml` file under `/outputs/featurization/pipeline/` and run the given code in it."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "''' from azureml.automl.core.shared.constants import Transformers\n",
-        "\n",
-        "transformers = mlflow.sklearn.load_model(uri) # Using method 1\n",
-        "data_transformers = transformers.get_transformers()\n",
-        "x_transformer = data_transformers[Transformers.X_TRANSFORMER]\n",
-        "y_transformer = data_transformers[Transformers.Y_TRANSFORMER]\n",
-        "\n",
-        "X_test = x_transformer.transform(X_test_data)\n",
-        "y_test = y_transformer.transform(y_test_data) '''"
-      ]
-    },
-    {
-      "attachments": {},
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Run the following cell to see the featurization summary of X and y transformers. Uncomment to use.  "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "''' X_data_summary = x_transformer.get_featurization_summary(is_user_friendly=False)\n",
-        "\n",
-        "summary_df = pd.DataFrame.from_records(X_data_summary)\n",
-        "summary_df '''"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Load Datastore\n",
-        "\n",
-        "The below data store holds the featurized datasets, hence we load and access the data. Check the path and file names according to the saved structure in your experiment `Outputs + logs` as seen in <i>Autofeaturization Part 1</i>"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.datastore import Datastore\n",
-        "\n",
-        "ds = Datastore.get(ws, \"workspaceartifactstore\")\n",
-        "experiment_loc = \"ExperimentRun/dcid.\" + remote_run.id\n",
-        "\n",
-        "remote_data_path = \"/outputs/featurization/data/\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id='AutofeaturizationData'></a>\n",
-        "## Autofeaturization Data\n",
-        "\n",
-        "We will load the training data from the previously completed Autofeaturization experiment. The resulting featurized dataframe can be passed into the custom model for training. Here we are saving the file to local from the experiment storage and reading the data."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "train_data_file_path = \"full_training_dataset.df.parquet\"\n",
-        "local_data_path = \"./data/\" + train_data_file_path\n",
-        "\n",
-        "remote_run.download_file(remote_data_path + train_data_file_path, local_data_path)\n",
-        "\n",
-        "full_training_data = pd.read_parquet(local_data_path)"
-      ]
-    },
-    {
-      "attachments": {},
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Another way to load the data is to go to the above autofeaturization experiment and check for the featurized dataset ids under `Output datasets`. Uncomment and replace them accordingly below, to use."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# train_data = Dataset.get_by_id(ws, 'cb4418ee-bac4-45ac-b055-600653bdf83a') # replace the featurized full_training_dataset id\n",
-        "# full_training_data = train_data.to_pandas_dataframe()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Training Data"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "We are dropping the y column and weights column from the featurized training dataset."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "Y_COLUMN = \"automl_y\"\n",
-        "SW_COLUMN = \"automl_weights\"\n",
-        "\n",
-        "X_train = full_training_data[full_training_data.columns.difference([Y_COLUMN, SW_COLUMN])]\n",
-        "y_train = full_training_data[Y_COLUMN].values\n",
-        "sample_weight = full_training_data[SW_COLUMN].values"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id='Train'></a>\n",
-        "## Train"
-      ]
-    },
-    {
-      "attachments": {},
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Here we are passing our training data to the lightgbm classifier, any custom model can be used with your data. Let us first install lightgbm."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "! pip install lightgbm"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import lightgbm as lgb\n",
-        "\n",
-        "model = lgb.LGBMClassifier(learning_rate=0.08,max_depth=-5,random_state=42)\n",
-        "model.fit(X_train, y_train, sample_weight=sample_weight)"
-      ]
-    },
-    {
-      "attachments": {},
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Once training is done, the test data obtained after transforming from the above downloaded transformer can be used to calculate the accuracy "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "print('Training accuracy {:.4f}'.format(model.score(X_train, y_train)))\n",
-        "\n",
-        "# Uncomment below to test the model on test data \n",
-        "# print('Testing accuracy {:.4f}'.format(model.score(X_test, y_test)))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id='Results'></a>\n",
-        "## Analyze results\n",
-        "\n",
-        "### Retrieve the Model"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "model"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id='Test'></a>\n",
-        "## Test the fitted model\n",
-        "\n",
-        "Now that the model is trained, split the data in the same way the data was split for training (The difference here is the data is being split locally) and then run the test data through the trained model to get the predicted values."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Uncomment below to test the model on test data\n",
-        "# y_pred = model.predict(X_test)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Experiment Complete!"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "bhavanatumma"
-      }
-    ],
-    "interpreter": {
-      "hash": "adb464b67752e4577e3dc163235ced27038d19b7d88def00d75d1975bde5d9ab"
-    },
-    "kernelspec": {
-      "display_name": "Python 3.8 - AzureML",
-      "language": "python",
-      "name": "python38-azureml"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.6.9"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

how-to-use-azureml/automated-machine-learning/experimental/automl_setup_thin_client.cmd

@@ -1,63 +0,0 @@
-@echo off
-set conda_env_name=%1
-set automl_env_file=%2
-set options=%3
-set PIP_NO_WARN_SCRIPT_LOCATION=0
-
-IF "%conda_env_name%"=="" SET conda_env_name="azure_automl_experimental"
-IF "%automl_env_file%"=="" SET automl_env_file="automl_thin_client_env.yml"
-
-IF NOT EXIST %automl_env_file% GOTO YmlMissing
-
-IF "%CONDA_EXE%"=="" GOTO CondaMissing
-
-call conda activate %conda_env_name% 2>nul:
-
-if not errorlevel 1 (
-  echo Upgrading existing conda environment %conda_env_name%
-  call pip uninstall azureml-train-automl -y -q
-  call conda env update --name %conda_env_name% --file %automl_env_file%
-  if errorlevel 1 goto ErrorExit
-) else (
-  call conda env create -f %automl_env_file% -n %conda_env_name%
-)
-
-call conda activate %conda_env_name% 2>nul:
-if errorlevel 1 goto ErrorExit
-
-call python -m ipykernel install --user --name %conda_env_name% --display-name "Python (%conda_env_name%)"
-
-REM azureml.widgets is now installed as part of the pip install under the conda env.
-REM Removing the old user install so that the notebooks will use the latest widget.
-call jupyter nbextension uninstall --user --py azureml.widgets
-
-echo.
-echo.
-echo ***************************************
-echo * AutoML setup completed successfully *
-echo ***************************************
-IF NOT "%options%"=="nolaunch" (
-  echo.
-  echo Starting jupyter notebook - please run the configuration notebook 
-  echo.
-  jupyter notebook --log-level=50 --notebook-dir='..\..'
-)
-
-goto End
-
-:CondaMissing
-echo Please run this script from an Anaconda Prompt window.
-echo You can start an Anaconda Prompt window by
-echo typing Anaconda Prompt on the Start menu.
-echo If you don't see the Anaconda Prompt app, install Miniconda.
-echo If you are running an older version of Miniconda or Anaconda,
-echo you can upgrade using the command: conda update conda
-goto End
-
-:YmlMissing
-echo File %automl_env_file% not found.
-
-:ErrorExit
-echo Install failed
-
-:End

how-to-use-azureml/automated-machine-learning/experimental/automl_setup_thin_client_linux.sh

@@ -1,53 +0,0 @@
-#!/bin/bash
-
-CONDA_ENV_NAME=$1
-AUTOML_ENV_FILE=$2
-OPTIONS=$3
-PIP_NO_WARN_SCRIPT_LOCATION=0
-
-if [ "$CONDA_ENV_NAME" == "" ]
-then
-  CONDA_ENV_NAME="azure_automl_experimental"
-fi
-
-if [ "$AUTOML_ENV_FILE" == "" ]
-then
-  AUTOML_ENV_FILE="automl_thin_client_env.yml"
-fi
-
-if [ ! -f $AUTOML_ENV_FILE ]; then
-    echo "File $AUTOML_ENV_FILE not found"
-    exit 1
-fi
-
-if source activate $CONDA_ENV_NAME 2> /dev/null
-then
-   echo "Upgrading existing conda environment" $CONDA_ENV_NAME
-   pip uninstall azureml-train-automl -y -q
-   conda env update --name $CONDA_ENV_NAME --file $AUTOML_ENV_FILE &&
-   jupyter nbextension uninstall --user --py azureml.widgets
-else
-   conda env create -f $AUTOML_ENV_FILE -n $CONDA_ENV_NAME &&
-   source activate $CONDA_ENV_NAME &&
-   python -m ipykernel install --user --name $CONDA_ENV_NAME --display-name "Python ($CONDA_ENV_NAME)" &&
-   jupyter nbextension uninstall --user --py azureml.widgets &&
-   echo "" &&
-   echo "" &&
-   echo "***************************************" &&
-   echo "* AutoML setup completed successfully *" &&
-   echo "***************************************" &&
-   if [ "$OPTIONS" != "nolaunch" ]
-   then
-      echo "" &&
-      echo "Starting jupyter notebook - please run the configuration notebook" &&
-      echo "" &&
-      jupyter notebook --log-level=50 --notebook-dir '../..'
-   fi
-fi
-
-if [ $? -gt 0 ]
-then
-   echo "Installation failed"
-fi
-
-

how-to-use-azureml/automated-machine-learning/experimental/automl_setup_thin_client_mac.sh

@@ -1,55 +0,0 @@
-#!/bin/bash
-
-CONDA_ENV_NAME=$1
-AUTOML_ENV_FILE=$2
-OPTIONS=$3
-PIP_NO_WARN_SCRIPT_LOCATION=0
-
-if [ "$CONDA_ENV_NAME" == "" ]
-then
-  CONDA_ENV_NAME="azure_automl_experimental"
-fi
-
-if [ "$AUTOML_ENV_FILE" == "" ]
-then
-  AUTOML_ENV_FILE="automl_thin_client_env_mac.yml"
-fi
-
-if [ ! -f $AUTOML_ENV_FILE ]; then
-    echo "File $AUTOML_ENV_FILE not found"
-    exit 1
-fi
-
-if source activate $CONDA_ENV_NAME 2> /dev/null
-then
-   echo "Upgrading existing conda environment" $CONDA_ENV_NAME
-   pip uninstall azureml-train-automl -y -q
-   conda env update --name $CONDA_ENV_NAME --file $AUTOML_ENV_FILE &&
-   jupyter nbextension uninstall --user --py azureml.widgets
-else
-   conda env create -f $AUTOML_ENV_FILE -n $CONDA_ENV_NAME &&
-   source activate $CONDA_ENV_NAME &&
-   conda install lightgbm -c conda-forge -y &&
-   python -m ipykernel install --user --name $CONDA_ENV_NAME --display-name "Python ($CONDA_ENV_NAME)" &&
-   jupyter nbextension uninstall --user --py azureml.widgets &&
-   echo "" &&
-   echo "" &&
-   echo "***************************************" &&
-   echo "* AutoML setup completed successfully *" &&
-   echo "***************************************" &&
-   if [ "$OPTIONS" != "nolaunch" ]
-   then
-      echo "" &&
-      echo "Starting jupyter notebook - please run the configuration notebook" &&
-      echo "" &&
-      jupyter notebook --log-level=50 --notebook-dir '../..'
-   fi
-fi
-
-if [ $? -gt 0 ]
-then
-   echo "Installation failed"
-fi
-
-
-

how-to-use-azureml/automated-machine-learning/experimental/automl_thin_client_env.yml

@@ -1,15 +0,0 @@
-name: azure_automl_experimental
-dependencies:
-  # The python interpreter version.
-  # Currently Azure ML only supports 3.7.0 and later.
-- pip<=22.3.1
-- python>=3.7.0,<3.11
-
-- pip:
-  # Required packages for AzureML execution, history, and data preparation.
-  - azureml-defaults
-  - azureml-sdk
-  - azureml-widgets
-  - azureml-mlflow
-  - pandas
-  - mlflow

how-to-use-azureml/automated-machine-learning/experimental/automl_thin_client_env_mac.yml

@@ -1,24 +0,0 @@
-name: azure_automl_experimental
-channels:
-  - conda-forge
-  - main
-dependencies:
-  # The python interpreter version.
-  # Currently Azure ML only supports 3.7.0 and later.
-- pip<=20.2.4
-- nomkl
-- python>=3.7.0,<3.11
-- urllib3==1.26.7
-- PyJWT < 2.0.0
-- numpy>=1.21.6,<=1.22.3
-
-- pip:
-  # Required packages for AzureML execution, history, and data preparation.
-  - azure-core==1.24.1
-  - azure-identity==1.7.0
-  - azureml-defaults
-  - azureml-sdk
-  - azureml-widgets
-  - azureml-mlflow
-  - pandas
-  - mlflow

how-to-use-azureml/automated-machine-learning/experimental/regression-model-proxy/auto-ml-regression-model-proxy.ipynb

@@ -1,470 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/experimental/regression-model-proxy/auto-ml-regression-model-proxy.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Automated Machine Learning\n",
-        "_**Regression with Aml Compute**_\n",
-        "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Data](#Data)\n",
-        "1. [Train](#Train)\n",
-        "1. [Results](#Results)\n",
-        "1. [Test](#Test)\n",
-        "\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
-        "In this example we use an experimental feature, Model Proxy, to do a predict on the best generated model without downloading the model locally. The prediction will happen on same compute and environment that was used to train the model. This feature is currently in the experimental state, which means that the API is prone to changing, please make sure to run on the latest version of this notebook if you face any issues.\n",
-        "This notebook will also leverage MLFlow for saving models, allowing for more portability of the resulting models. See https://docs.microsoft.com/en-us/azure/machine-learning/how-to-use-mlflow for more details around MLFlow is AzureML.\n",
-        "\n",
-        "If you are using an Azure Machine Learning Compute Instance, you are all set.  Otherwise, go through the [configuration](../../../../configuration.ipynb)  notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
-        "\n",
-        "In this notebook you will learn how to:\n",
-        "1. Create an `Experiment` in an existing `Workspace`.\n",
-        "2. Configure AutoML using `AutoMLConfig`.\n",
-        "3. Train the model using remote compute.\n",
-        "4. Explore the results.\n",
-        "5. Test the best fitted model."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Setup\n",
-        "\n",
-        "As part of the setup you have already created an Azure ML `Workspace` object. For Automated ML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import logging\n",
-        "\n",
-        "import json\n",
-        "\n",
-        "\n",
-        "import azureml.core\n",
-        "from azureml.core.experiment import Experiment\n",
-        "from azureml.core.workspace import Workspace\n",
-        "from azureml.core.dataset import Dataset\n",
-        "from azureml.train.automl import AutoMLConfig"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "print(\"This notebook was created using version 1.59.0 of the Azure ML SDK\")\n",
-        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ws = Workspace.from_config()\n",
-        "\n",
-        "# Choose a name for the experiment.\n",
-        "experiment_name = 'automl-regression-model-proxy'\n",
-        "\n",
-        "experiment = Experiment(ws, experiment_name)\n",
-        "\n",
-        "output = {}\n",
-        "output['Subscription ID'] = ws.subscription_id\n",
-        "output['Workspace'] = ws.name\n",
-        "output['Resource Group'] = ws.resource_group\n",
-        "output['Location'] = ws.location\n",
-        "output['Run History Name'] = experiment_name\n",
-        "output"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Using AmlCompute\n",
-        "You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) for your AutoML run. In this tutorial, you use `AmlCompute` as your training compute resource."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
-        "from azureml.core.compute_target import ComputeTargetException\n",
-        "\n",
-        "# Choose a name for your CPU cluster\n",
-        "# Try to ensure that the cluster name is unique across the notebooks\n",
-        "cpu_cluster_name = \"reg-model-proxy\"\n",
-        "\n",
-        "# Verify that cluster does not exist already\n",
-        "try:\n",
-        "    compute_target = ComputeTarget(workspace=ws, name=cpu_cluster_name)\n",
-        "    print('Found existing cluster, use it.')\n",
-        "except ComputeTargetException:\n",
-        "    compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_DS12_V2',\n",
-        "                                                           max_nodes=4)\n",
-        "    compute_target = ComputeTarget.create(ws, cpu_cluster_name, compute_config)\n",
-        "\n",
-        "compute_target.wait_for_completion(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Data\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Load Data\n",
-        "Load the hardware dataset from a csv file containing both training features and labels. The features are inputs to the model, while the training labels represent the expected output of the model. Next, we'll split the data using random_split and extract the training data for the model. "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/machineData.csv\"\n",
-        "dataset = Dataset.Tabular.from_delimited_files(data)\n",
-        "\n",
-        "# Split the dataset into train and test datasets\n",
-        "train_data, test_data = dataset.random_split(percentage=0.8, seed=223)\n",
-        "\n",
-        "label = \"ERP\"\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "The split data will be used in the remote compute by ModelProxy and locally to compare results.\n",
-        "So, we need to persist the split data to avoid descrepencies from different package versions in the local and remote."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ds = ws.get_default_datastore()\n",
-        "\n",
-        "train_data = Dataset.Tabular.register_pandas_dataframe(\n",
-        "    train_data.to_pandas_dataframe(), target=(ds, \"machineTrainData\"), name=\"train_data\")\n",
-        "\n",
-        "test_data = Dataset.Tabular.register_pandas_dataframe(\n",
-        "    test_data.to_pandas_dataframe(), target=(ds, \"machineTestData\"), name=\"test_data\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Train\n",
-        "\n",
-        "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
-        "\n",
-        "|Property|Description|\n",
-        "|-|-|\n",
-        "|**task**|classification, regression or forecasting|\n",
-        "|**primary_metric**|This is the metric that you want to optimize. Regression supports the following primary metrics: <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>|\n",
-        "|**n_cross_validations**|Number of cross validation splits.|\n",
-        "|**training_data**|(sparse) array-like, shape = [n_samples, n_features]|\n",
-        "|**label_column_name**|(sparse) array-like, shape = [n_samples, ], targets values.|\n",
-        "\n",
-        "**_You can find more information about primary metrics_** [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#primary-metric)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "tags": [
-          "automlconfig-remarks-sample"
-        ]
-      },
-      "outputs": [],
-      "source": [
-        "automl_settings = {\n",
-        "    \"n_cross_validations\": 3,\n",
-        "    \"primary_metric\": 'r2_score',\n",
-        "    \"enable_early_stopping\": True, \n",
-        "    \"experiment_timeout_hours\": 0.3, #for real scenarios we recommend a timeout of at least one hour \n",
-        "    \"max_concurrent_iterations\": 4,\n",
-        "    \"max_cores_per_iteration\": -1,\n",
-        "    \"verbosity\": logging.INFO,\n",
-        "    \"save_mlflow\": True,\n",
-        "}\n",
-        "\n",
-        "automl_config = AutoMLConfig(task = 'regression',\n",
-        "                             compute_target = compute_target,\n",
-        "                             training_data = train_data,\n",
-        "                             label_column_name = label,\n",
-        "                             **automl_settings\n",
-        "                            )"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Call the `submit` method on the experiment object and pass the run configuration. Execution of remote runs is asynchronous. Depending on the data and the number of iterations this can run for a while.  Validation errors and current status will be shown when setting `show_output=True` and the execution will be synchronous."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run = experiment.submit(automl_config, show_output = False)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# If you need to retrieve a run that already started, use the following code\n",
-        "#from azureml.train.automl.run import AutoMLRun\n",
-        "#remote_run = AutoMLRun(experiment = experiment, run_id = '<replace with your run id>')"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Results"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run.wait_for_completion(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Retrieve the Best Child Run\n",
-        "\n",
-        "Below we select the best pipeline from our iterations. The `get_best_child` method returns the best run. Overloads on `get_best_child` allow you to retrieve the best run for *any* logged metric."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "best_run = remote_run.get_best_child()\n",
-        "print(best_run)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Show hyperparameters\n",
-        "Show the model pipeline used for the best run with its hyperparameters.\n",
-        "For ensemble pipelines it shows the iterations and algorithms that are ensembled."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "run_properties = best_run.get_details()['properties']\n",
-        "pipeline_script = json.loads(run_properties['pipeline_script'])\n",
-        "print(json.dumps(pipeline_script, indent = 1)) \n",
-        "\n",
-        "if 'ensembled_iterations' in run_properties:\n",
-        "    print(\"\")\n",
-        "    print(\"Ensembled Iterations\")\n",
-        "    print(run_properties['ensembled_iterations'])\n",
-        "    \n",
-        "if 'ensembled_algorithms' in run_properties:\n",
-        "    print(\"\")\n",
-        "    print(\"Ensembled Algorithms\")\n",
-        "    print(run_properties['ensembled_algorithms'])"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Best Child Run Based on Any Other Metric\n",
-        "Show the run and the model that has the smallest `root_mean_squared_error` value (which turned out to be the same as the one with largest `spearman_correlation` value):"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "lookup_metric = \"root_mean_squared_error\"\n",
-        "best_run = remote_run.get_best_child(metric = lookup_metric)\n",
-        "print(best_run)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "y_test = test_data.keep_columns('ERP')\n",
-        "test_data = test_data.drop_columns('ERP')\n",
-        "\n",
-        "\n",
-        "y_train = train_data.keep_columns('ERP')\n",
-        "train_data = train_data.drop_columns('ERP')\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Creating ModelProxy for submitting prediction runs to the training environment.\n",
-        "We will create a ModelProxy for the best child run, which will allow us to submit a run that does the prediction in the training environment. Unlike the local client, which can have different versions of some libraries, the training environment will have all the compatible libraries for the model already."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.train.automl.model_proxy import ModelProxy\n",
-        "best_model_proxy = ModelProxy(best_run)\n",
-        "y_pred_train = best_model_proxy.predict(train_data)\n",
-        "y_pred_test = best_model_proxy.predict(test_data)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Exploring results"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "y_pred_train = y_pred_train.to_pandas_dataframe().values.flatten()\n",
-        "y_train = y_train.to_pandas_dataframe().values.flatten()\n",
-        "y_residual_train = y_train - y_pred_train\n",
-        "\n",
-        "y_pred_test = y_pred_test.to_pandas_dataframe().values.flatten()\n",
-        "y_test = y_test.to_pandas_dataframe().values.flatten()\n",
-        "y_residual_test = y_test - y_pred_test\n",
-        "print(y_residual_train)\n",
-        "print(y_residual_test)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": []
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "sekrupa"
-      }
-    ],
-    "categories": [
-      "how-to-use-azureml",
-      "automated-machine-learning"
-    ],
-    "kernelspec": {
-      "display_name": "Python 3.8 - AzureML",
-      "language": "python",
-      "name": "python38-azureml"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.6.2"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

how-to-use-azureml/automated-machine-learning/exploring-previous-runs/auto-ml-exploring-previous-runs.ipynb

@@ -0,0 +1,342 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "_**Exploring Previous Runs**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Explore](#Explore)\n",
+        "1. [Download](#Download)\n",
+        "1. [Register](#Register)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "In this example we present some examples on navigating previously executed runs. We also show how you can download a fitted model for any previous run.\n",
+        "\n",
+        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+        "\n",
+        "In this notebook you will learn how to:\n",
+        "1. List all experiments in a workspace.\n",
+        "2. List all AutoML runs in an experiment.\n",
+        "3. Get details for an AutoML run, including settings, run widget, and all metrics.\n",
+        "4. Download a fitted pipeline for any iteration."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import pandas as pd\n",
+        "import json\n",
+        "\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "from azureml.train.automl.run import AutoMLRun"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Explore"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### List Experiments"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "experiment_list = Experiment.list(workspace=ws)\n",
+        "\n",
+        "summary_df = pd.DataFrame(index = ['No of Runs'])\n",
+        "for experiment in experiment_list:\n",
+        "    automl_runs = list(experiment.get_runs(type='automl'))\n",
+        "    summary_df[experiment.name] = [len(automl_runs)]\n",
+        "    \n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "summary_df.T"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### List runs for an experiment\n",
+        "Set `experiment_name` to any experiment name from the result of the Experiment.list cell to load the AutoML runs."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "experiment_name = 'automl-local-classification' # Replace this with any project name from previous cell.\n",
+        "\n",
+        "proj = ws.experiments[experiment_name]\n",
+        "summary_df = pd.DataFrame(index = ['Type', 'Status', 'Primary Metric', 'Iterations', 'Compute', 'Name'])\n",
+        "automl_runs = list(proj.get_runs(type='automl'))\n",
+        "automl_runs_project = []\n",
+        "for run in automl_runs:\n",
+        "    properties = run.get_properties()\n",
+        "    tags = run.get_tags()\n",
+        "    amlsettings = json.loads(properties['AMLSettingsJsonString'])\n",
+        "    if 'iterations' in tags:\n",
+        "        iterations = tags['iterations']\n",
+        "    else:\n",
+        "        iterations = properties['num_iterations']\n",
+        "    summary_df[run.id] = [amlsettings['task_type'], run.get_details()['status'], properties['primary_metric'], iterations, properties['target'], amlsettings['name']]\n",
+        "    if run.get_details()['status'] == 'Completed':\n",
+        "        automl_runs_project.append(run.id)\n",
+        "    \n",
+        "from IPython.display import HTML\n",
+        "projname_html = HTML(\"<h3>{}</h3>\".format(proj.name))\n",
+        "\n",
+        "from IPython.display import display\n",
+        "display(projname_html)\n",
+        "display(summary_df.T)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Get details for a run\n",
+        "\n",
+        "Copy the project name and run id from the previous cell output to find more details on a particular run."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run_id = automl_runs_project[0]  # Replace with your own run_id from above run ids\n",
+        "assert (run_id in summary_df.keys()), \"Run id not found! Please set run id to a value from above run ids\"\n",
+        "\n",
+        "from azureml.widgets import RunDetails\n",
+        "\n",
+        "experiment = Experiment(ws, experiment_name)\n",
+        "ml_run = AutoMLRun(experiment = experiment, run_id = run_id)\n",
+        "\n",
+        "summary_df = pd.DataFrame(index = ['Type', 'Status', 'Primary Metric', 'Iterations', 'Compute', 'Name', 'Start Time', 'End Time'])\n",
+        "properties = ml_run.get_properties()\n",
+        "tags = ml_run.get_tags()\n",
+        "status = ml_run.get_details()\n",
+        "amlsettings = json.loads(properties['AMLSettingsJsonString'])\n",
+        "if 'iterations' in tags:\n",
+        "    iterations = tags['iterations']\n",
+        "else:\n",
+        "    iterations = properties['num_iterations']\n",
+        "start_time = None\n",
+        "if 'startTimeUtc' in status:\n",
+        "    start_time = status['startTimeUtc']\n",
+        "end_time = None\n",
+        "if 'endTimeUtc' in status:\n",
+        "    end_time = status['endTimeUtc']\n",
+        "summary_df[ml_run.id] = [amlsettings['task_type'], status['status'], properties['primary_metric'], iterations, properties['target'], amlsettings['name'], start_time, end_time]\n",
+        "display(HTML('<h3>Runtime Details</h3>'))\n",
+        "display(summary_df)\n",
+        "\n",
+        "#settings_df = pd.DataFrame(data = amlsettings, index = [''])\n",
+        "display(HTML('<h3>AutoML Settings</h3>'))\n",
+        "display(amlsettings)\n",
+        "\n",
+        "display(HTML('<h3>Iterations</h3>'))\n",
+        "RunDetails(ml_run).show() \n",
+        "\n",
+        "children = list(ml_run.get_children())\n",
+        "metricslist = {}\n",
+        "for run in children:\n",
+        "    properties = run.get_properties()\n",
+        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+        "    metricslist[int(properties['iteration'])] = metrics\n",
+        "\n",
+        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+        "display(HTML('<h3>Metrics</h3>'))\n",
+        "display(rundata)\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Download"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Download the Best Model for Any Given Metric"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "metric = 'AUC_weighted' # Replace with a metric name.\n",
+        "best_run, fitted_model = ml_run.get_output(metric = metric)\n",
+        "fitted_model"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Download the Model for Any Given Iteration"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "iteration = 1 # Replace with an iteration number.\n",
+        "best_run, fitted_model = ml_run.get_output(iteration = iteration)\n",
+        "fitted_model"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Register"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Register fitted model for deployment\n",
+        "If neither `metric` nor `iteration` are specified in the `register_model` call, the iteration with the best primary metric is registered."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "description = 'AutoML Model'\n",
+        "tags = None\n",
+        "ml_run.register_model(description = description, tags = tags)\n",
+        "print(ml_run.model_id) # Use this id to deploy the model as a web service in Azure."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Register the Best Model for Any Given Metric"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "metric = 'AUC_weighted' # Replace with a metric name.\n",
+        "description = 'AutoML Model'\n",
+        "tags = None\n",
+        "ml_run.register_model(description = description, tags = tags, metric = metric)\n",
+        "print(ml_run.model_id) # Use this id to deploy the model as a web service in Azure."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Register the Model for Any Given Iteration"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "iteration = 1 # Replace with an iteration number.\n",
+        "description = 'AutoML Model'\n",
+        "tags = None\n",
+        "ml_run.register_model(description = description, tags = tags, iteration = iteration)\n",
+        "print(ml_run.model_id) # Use this id to deploy the model as a web service in Azure."
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "savitam"
+      }
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "python",
+      "name": "python36"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.6"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/forecasting-backtest-many-models/assets/score.py

@@ -1,174 +0,0 @@
-from typing import Any, Dict, Optional, List
-
-import argparse
-import json
-import os
-import re
-
-import numpy as np
-import pandas as pd
-
-from matplotlib import pyplot as plt
-from matplotlib.backends.backend_pdf import PdfPages
-
-from azureml.automl.core.shared import constants
-from azureml.automl.core.shared.types import GrainType
-from azureml.automl.runtime.shared.score import scoring
-
-GRAIN = "time_series_id"
-BACKTEST_ITER = "backtest_iteration"
-ACTUALS = "actual_level"
-PREDICTIONS = "predicted_level"
-ALL_GRAINS = "all_sets"
-
-FORECASTS_FILE = "forecast.csv"
-SCORES_FILE = "scores.csv"
-PLOTS_FILE = "plots_fcst_vs_actual.pdf"
-RE_INVALID_SYMBOLS = re.compile("[: ]")
-
-
-def _compute_metrics(df: pd.DataFrame, metrics: List[str]):
-    """
-    Compute metrics for one data frame.
-
-    :param df: The data frame which contains actual_level and predicted_level columns.
-    :return: The data frame with two columns - metric_name and metric.
-    """
-    scores = scoring.score_regression(
-        y_test=df[ACTUALS], y_pred=df[PREDICTIONS], metrics=metrics
-    )
-    metrics_df = pd.DataFrame(list(scores.items()), columns=["metric_name", "metric"])
-    metrics_df.sort_values(["metric_name"], inplace=True)
-    metrics_df.reset_index(drop=True, inplace=True)
-    return metrics_df
-
-
-def _format_grain_name(grain: GrainType) -> str:
-    """
-    Convert grain name to string.
-
-    :param grain: the grain name.
-    :return: the string representation of the given grain.
-    """
-    if not isinstance(grain, tuple) and not isinstance(grain, list):
-        return str(grain)
-    grain = list(map(str, grain))
-    return "|".join(grain)
-
-
-def compute_all_metrics(
-    fcst_df: pd.DataFrame,
-    ts_id_colnames: List[str],
-    metric_names: Optional[List[set]] = None,
-):
-    """
-    Calculate metrics per grain.
-
-    :param fcst_df: forecast data frame. Must contain 2 columns: 'actual_level' and 'predicted_level'
-    :param metric_names: (optional) the list of metric names to return
-    :param ts_id_colnames: (optional) list of grain column names
-    :return: dictionary of summary table for all tests and final decision on stationary vs nonstaionary
-    """
-    if not metric_names:
-        metric_names = list(constants.Metric.SCALAR_REGRESSION_SET)
-
-    if ts_id_colnames is None:
-        ts_id_colnames = []
-
-    metrics_list = []
-    if ts_id_colnames:
-        for grain, df in fcst_df.groupby(ts_id_colnames):
-            one_grain_metrics_df = _compute_metrics(df, metric_names)
-            one_grain_metrics_df[GRAIN] = _format_grain_name(grain)
-            metrics_list.append(one_grain_metrics_df)
-
-    # overall metrics
-    one_grain_metrics_df = _compute_metrics(fcst_df, metric_names)
-    one_grain_metrics_df[GRAIN] = ALL_GRAINS
-    metrics_list.append(one_grain_metrics_df)
-
-    # collect into a data frame
-    return pd.concat(metrics_list)
-
-
-def _draw_one_plot(
-    df: pd.DataFrame,
-    time_column_name: str,
-    grain_column_names: List[str],
-    pdf: PdfPages,
-) -> None:
-    """
-    Draw the single plot.
-
-    :param df: The data frame with the data to build plot.
-    :param time_column_name: The name of a time column.
-    :param grain_column_names: The name of grain columns.
-    :param pdf: The pdf backend used to render the plot.
-    """
-    fig, _ = plt.subplots(figsize=(20, 10))
-    df = df.set_index(time_column_name)
-    plt.plot(df[[ACTUALS, PREDICTIONS]])
-    plt.xticks(rotation=45)
-    iteration = df[BACKTEST_ITER].iloc[0]
-    if grain_column_names:
-        grain_name = [df[grain].iloc[0] for grain in grain_column_names]
-        plt.title(f"Time series ID: {_format_grain_name(grain_name)} {iteration}")
-    plt.legend(["actual", "forecast"])
-    plt.close(fig)
-    pdf.savefig(fig)
-
-
-def calculate_scores_and_build_plots(
-    input_dir: str, output_dir: str, automl_settings: Dict[str, Any]
-):
-    os.makedirs(output_dir, exist_ok=True)
-    grains = automl_settings.get(
-        constants.TimeSeries.TIME_SERIES_ID_COLUMN_NAMES,
-        automl_settings.get(constants.TimeSeries.GRAIN_COLUMN_NAMES, None),
-    )
-    time_column_name = automl_settings.get(constants.TimeSeries.TIME_COLUMN_NAME)
-    if grains is None:
-        grains = []
-    if isinstance(grains, str):
-        grains = [grains]
-    while BACKTEST_ITER in grains:
-        grains.remove(BACKTEST_ITER)
-
-    dfs = []
-    for fle in os.listdir(input_dir):
-        file_path = os.path.join(input_dir, fle)
-        if os.path.isfile(file_path) and file_path.endswith(".csv"):
-            df_iter = pd.read_csv(file_path, parse_dates=[time_column_name])
-            for _, iteration in df_iter.groupby(BACKTEST_ITER):
-                dfs.append(iteration)
-    forecast_df = pd.concat(dfs, sort=False, ignore_index=True)
-    # To make sure plots are in order, sort the predictions by grain and iteration.
-    ts_index = grains + [BACKTEST_ITER]
-    forecast_df.sort_values(by=ts_index, inplace=True)
-    pdf = PdfPages(os.path.join(output_dir, PLOTS_FILE))
-    for _, one_forecast in forecast_df.groupby(ts_index):
-        _draw_one_plot(one_forecast, time_column_name, grains, pdf)
-    pdf.close()
-    forecast_df.to_csv(os.path.join(output_dir, FORECASTS_FILE), index=False)
-    # Remove np.NaN and np.inf from the prediction and actuals data.
-    forecast_df.replace([np.inf, -np.inf], np.nan, inplace=True)
-    forecast_df.dropna(subset=[ACTUALS, PREDICTIONS], inplace=True)
-    metrics = compute_all_metrics(forecast_df, grains + [BACKTEST_ITER])
-    metrics.to_csv(os.path.join(output_dir, SCORES_FILE), index=False)
-
-
-if __name__ == "__main__":
-    args = {"forecasts": "--forecasts", "scores_out": "--output-dir"}
-    parser = argparse.ArgumentParser("Parsing input arguments.")
-    for argname, arg in args.items():
-        parser.add_argument(arg, dest=argname, required=True)
-    parsed_args, _ = parser.parse_known_args()
-    input_dir = parsed_args.forecasts
-    output_dir = parsed_args.scores_out
-    with open(
-        os.path.join(
-            os.path.dirname(os.path.realpath(__file__)), "automl_settings.json"
-        )
-    ) as json_file:
-        automl_settings = json.load(json_file)
-    calculate_scores_and_build_plots(input_dir, output_dir, automl_settings)

how-to-use-azureml/automated-machine-learning/forecasting-backtest-many-models/auto-ml-forecasting-backtest-many-models.ipynb

@@ -1,779 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/forecasting-backtest-many-models/auto-ml-forecasting-backtest-many-models.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Many Models with Backtesting - Automated ML\n",
-        "**_Backtest many models time series forecasts with Automated Machine Learning_**\n",
-        "\n",
-        "---"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "For this notebook we are using a synthetic dataset to demonstrate the back testing in many model scenario. This allows us to check historical performance of AutoML on a historical data. To do that we step back on the backtesting period by the data set several times and split the data to train and test sets. Then these data sets are used for training and evaluation of model.<br>\n",
-        "\n",
-        "Thus, it is a quick way of evaluating AutoML as if it was in production. Here, we do not test historical performance of a particular model, for this see the [notebook](../forecasting-backtest-single-model/auto-ml-forecasting-backtest-single-model.ipynb). Instead, the best model for every backtest iteration can be different since AutoML chooses the best model for a given training set.\n",
-        "\n",
-        "![Backtesting](Backtesting.png)\n",
-        "\n",
-        "**NOTE: There are limits on how many runs we can do in parallel per workspace, and we currently recommend to set the parallelism to maximum of 320 runs per experiment per workspace. If users want to have more parallelism and increase this limit they might encounter Too Many Requests errors (HTTP 429).**"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Prerequisites\n",
-        "You'll need to create a compute Instance by following [these](https://learn.microsoft.com/en-us/azure/machine-learning/v1/how-to-create-manage-compute-instance?tabs=python) instructions."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## 1.0 Set up workspace, datastore, experiment"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "gather": {
-          "logged": 1613003526897
-        }
-      },
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "\n",
-        "import azureml.core\n",
-        "from azureml.core import Workspace, Datastore\n",
-        "import numpy as np\n",
-        "import pandas as pd\n",
-        "\n",
-        "from pandas.tseries.frequencies import to_offset\n",
-        "\n",
-        "# Set up your workspace\n",
-        "ws = Workspace.from_config()\n",
-        "ws.get_details()\n",
-        "\n",
-        "# Set up your datastores\n",
-        "dstore = ws.get_default_datastore()\n",
-        "\n",
-        "output = {}\n",
-        "output[\"SDK version\"] = azureml.core.VERSION\n",
-        "output[\"Subscription ID\"] = ws.subscription_id\n",
-        "output[\"Workspace\"] = ws.name\n",
-        "output[\"Resource Group\"] = ws.resource_group\n",
-        "output[\"Location\"] = ws.location\n",
-        "output[\"Default datastore name\"] = dstore.name\n",
-        "output[\"SDK Version\"] = azureml.core.VERSION\n",
-        "pd.set_option(\"display.max_colwidth\", None)\n",
-        "outputDf = pd.DataFrame(data=output, index=[\"\"])\n",
-        "outputDf.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "This notebook is compatible with Azure ML SDK version 1.35.1 or later."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Choose an experiment"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "gather": {
-          "logged": 1613003540729
-        }
-      },
-      "outputs": [],
-      "source": [
-        "from azureml.core import Experiment\n",
-        "\n",
-        "experiment = Experiment(ws, \"automl-many-models-backtest\")\n",
-        "\n",
-        "print(\"Experiment name: \" + experiment.name)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## 2.0 Data\n",
-        "\n",
-        "#### 2.1 Data generation\n",
-        "For this notebook we will generate the artificial data set with two [time series IDs](https://docs.microsoft.com/en-us/python/api/azureml-automl-core/azureml.automl.core.forecasting_parameters.forecastingparameters?view=azure-ml-py). Then we will generate backtest folds and will upload it to the default BLOB storage and create a [TabularDataset](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.tabular_dataset.tabulardataset?view=azure-ml-py)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# simulate data: 2 grains - 700\n",
-        "TIME_COLNAME = \"date\"\n",
-        "TARGET_COLNAME = \"value\"\n",
-        "TIME_SERIES_ID_COLNAME = \"ts_id\"\n",
-        "\n",
-        "sample_size = 700\n",
-        "# Set the random seed for reproducibility of results.\n",
-        "np.random.seed(20)\n",
-        "X1 = pd.DataFrame(\n",
-        "    {\n",
-        "        TIME_COLNAME: pd.date_range(start=\"2018-01-01\", periods=sample_size),\n",
-        "        TARGET_COLNAME: np.random.normal(loc=100, scale=20, size=sample_size),\n",
-        "        TIME_SERIES_ID_COLNAME: \"ts_A\",\n",
-        "    }\n",
-        ")\n",
-        "X2 = pd.DataFrame(\n",
-        "    {\n",
-        "        TIME_COLNAME: pd.date_range(start=\"2018-01-01\", periods=sample_size),\n",
-        "        TARGET_COLNAME: np.random.normal(loc=100, scale=20, size=sample_size),\n",
-        "        TIME_SERIES_ID_COLNAME: \"ts_B\",\n",
-        "    }\n",
-        ")\n",
-        "\n",
-        "X = pd.concat([X1, X2], ignore_index=True, sort=False)\n",
-        "print(\"Simulated dataset contains {} rows \\n\".format(X.shape[0]))\n",
-        "X.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Now we will generate 8 backtesting folds with backtesting period of 7 days and with the same forecasting horizon. We will add the column \"backtest_iteration\", which will identify the backtesting period by the last training date."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "offset_type = \"7D\"\n",
-        "NUMBER_OF_BACKTESTS = 8  # number of train/test sets to generate\n",
-        "\n",
-        "dfs_train = []\n",
-        "dfs_test = []\n",
-        "for ts_id, df_one in X.groupby(TIME_SERIES_ID_COLNAME):\n",
-        "\n",
-        "    data_end = df_one[TIME_COLNAME].max()\n",
-        "\n",
-        "    for i in range(NUMBER_OF_BACKTESTS):\n",
-        "        train_cutoff_date = data_end - to_offset(offset_type)\n",
-        "        df_one = df_one.copy()\n",
-        "        df_one[\"backtest_iteration\"] = \"iteration_\" + str(train_cutoff_date)\n",
-        "        train = df_one[df_one[TIME_COLNAME] <= train_cutoff_date]\n",
-        "        test = df_one[\n",
-        "            (df_one[TIME_COLNAME] > train_cutoff_date)\n",
-        "            & (df_one[TIME_COLNAME] <= data_end)\n",
-        "        ]\n",
-        "        data_end = train[TIME_COLNAME].max()\n",
-        "        dfs_train.append(train)\n",
-        "        dfs_test.append(test)\n",
-        "\n",
-        "X_train = pd.concat(dfs_train, sort=False, ignore_index=True)\n",
-        "X_test = pd.concat(dfs_test, sort=False, ignore_index=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### 2.2 Create the Tabular Data Set.\n",
-        "\n",
-        "A Datastore is a place where data can be stored that is then made accessible to a compute either by means of mounting or copying the data to the compute target.\n",
-        "\n",
-        "Please refer to [Datastore](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.datastore(class)?view=azure-ml-py) documentation on how to access data from Datastore.\n",
-        "\n",
-        "In this next step, we will upload the data and create a TabularDataset."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.data.dataset_factory import TabularDatasetFactory\n",
-        "\n",
-        "ds = ws.get_default_datastore()\n",
-        "# Upload saved data to the default data store.\n",
-        "train_data = TabularDatasetFactory.register_pandas_dataframe(\n",
-        "    X_train, target=(ds, \"data_mm\"), name=\"data_train\"\n",
-        ")\n",
-        "test_data = TabularDatasetFactory.register_pandas_dataframe(\n",
-        "    X_test, target=(ds, \"data_mm\"), name=\"data_test\"\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## 3.0 Build the training pipeline\n",
-        "Now that the dataset, WorkSpace, and datastore are set up, we can put together a pipeline for training.\n",
-        "\n",
-        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Choose a compute target\n",
-        "\n",
-        "You will need to create a [compute target](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-set-up-training-targets#amlcompute) for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
-        "\n",
-        "\\*\\*Creation of AmlCompute takes approximately 5 minutes.**\n",
-        "\n",
-        "If the AmlCompute with that name is already in your workspace this code will skip the creation process. As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read this [article](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-manage-quotas) on the default limits and how to request more quota."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "gather": {
-          "logged": 1613007037308
-        }
-      },
-      "outputs": [],
-      "source": [
-        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
-        "\n",
-        "# Name your cluster\n",
-        "compute_name = \"backtest-mm\"\n",
-        "\n",
-        "\n",
-        "if compute_name in ws.compute_targets:\n",
-        "    compute_target = ws.compute_targets[compute_name]\n",
-        "    if compute_target and type(compute_target) is AmlCompute:\n",
-        "        print(\"Found compute target: \" + compute_name)\n",
-        "else:\n",
-        "    print(\"Creating a new compute target...\")\n",
-        "    provisioning_config = AmlCompute.provisioning_configuration(\n",
-        "        vm_size=\"STANDARD_DS12_V2\", max_nodes=6\n",
-        "    )\n",
-        "    # Create the compute target\n",
-        "    compute_target = ComputeTarget.create(ws, compute_name, provisioning_config)\n",
-        "\n",
-        "    # Can poll for a minimum number of nodes and for a specific timeout.\n",
-        "    # If no min node count is provided it will use the scale settings for the cluster\n",
-        "    compute_target.wait_for_completion(\n",
-        "        show_output=True, min_node_count=None, timeout_in_minutes=20\n",
-        "    )\n",
-        "\n",
-        "    # For a more detailed view of current cluster status, use the 'status' property\n",
-        "    print(compute_target.status.serialize())"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Set up training parameters\n",
-        "\n",
-        "We need to provide ``ForecastingParameters``, ``AutoMLConfig`` and ``ManyModelsTrainParameters`` objects. For the forecasting task we also need to define several settings including the name of the time column, the maximum forecast horizon, and the partition column name(s) definition.\n",
-        "\n",
-        "#### ``ForecastingParameters`` arguments\n",
-        "| Property                           | Description|\n",
-        "| :---------------                   | :------------------- |\n",
-        "| **forecast_horizon**               | The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly). Periods are inferred from your data. |\n",
-        "| **time_column_name**               | The name of your time column. |\n",
-        "| **time_series_id_column_names**    | The column names used to uniquely identify timeseries in data that has multiple rows with the same timestamp. |\n",
-        "| **cv_step_size**                   | Number of periods between two consecutive cross-validation folds. The default value is \\\"auto\\\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value. |\n",
-        "\n",
-        "#### ``AutoMLConfig`` arguments\n",
-        "| Property                           | Description|\n",
-        "| :---------------                   | :------------------- |\n",
-        "| **task**                           | forecasting |\n",
-        "| **primary_metric**                 | This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i> |\n",
-        "| **blocked_models**                 | Blocked models won't be used by AutoML. |\n",
-        "| **iteration_timeout_minutes**      | Maximum amount of time in minutes that the model can train. This is optional but provides customers with greater control on exit criteria. |\n",
-        "| **iterations**                     | Number of models to train. This is optional but provides customers with greater control on exit criteria. |\n",
-        "| **experiment_timeout_hours**       | Maximum amount of time in hours that each experiment can take before it terminates. This is optional but provides customers with greater control on exit criteria. **It does not control the overall timeout for the pipeline run, instead controls the timeout for each training run per partitioned time series.** |\n",
-        "| **label_column_name**              | The name of the label column. |\n",
-        "| **n_cross_validations**            | Number of cross validation splits. The default value is \\\"auto\\\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
-        "| **enable_early_stopping**          | Flag to enable early termination if the primary metric is no longer improving. |\n",
-        "| **enable_engineered_explanations** | Engineered feature explanations will be downloaded if enable_engineered_explanations flag is set to True. By default it is set to False to save storage space. |\n",
-        "| **track_child_runs**               | Flag to disable tracking of child runs. Only best run is tracked if the flag is set to False (this includes the model and metrics of the run). |\n",
-        "| **pipeline_fetch_max_batch_size**  | Determines how many pipelines (training algorithms) to fetch at a time for training, this helps reduce throttling when training at large scale. |\n",
-        "\n",
-        "\n",
-        "#### ``ManyModelsTrainParameters`` arguments\n",
-        "| Property                           | Description|\n",
-        "| :---------------                   | :------------------- |\n",
-        "| **automl_settings**                | The ``AutoMLConfig`` object defined above. |\n",
-        "| **partition_column_names**         | The names of columns used to group your models. For timeseries, the groups must not split up individual time-series. That is, each group must contain one or more whole time-series. |"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "gather": {
-          "logged": 1613007061544
-        }
-      },
-      "outputs": [],
-      "source": [
-        "from azureml.train.automl.runtime._many_models.many_models_parameters import (\n",
-        "    ManyModelsTrainParameters,\n",
-        ")\n",
-        "from azureml.automl.core.forecasting_parameters import ForecastingParameters\n",
-        "from azureml.train.automl.automlconfig import AutoMLConfig\n",
-        "\n",
-        "partition_column_names = [TIME_SERIES_ID_COLNAME, \"backtest_iteration\"]\n",
-        "\n",
-        "forecasting_parameters = ForecastingParameters(\n",
-        "    time_column_name=TIME_COLNAME,\n",
-        "    forecast_horizon=6,\n",
-        "    time_series_id_column_names=partition_column_names,\n",
-        "    cv_step_size=\"auto\",\n",
-        ")\n",
-        "\n",
-        "automl_settings = AutoMLConfig(\n",
-        "    task=\"forecasting\",\n",
-        "    primary_metric=\"normalized_root_mean_squared_error\",\n",
-        "    iteration_timeout_minutes=10,\n",
-        "    iterations=15,\n",
-        "    experiment_timeout_hours=0.25,\n",
-        "    label_column_name=TARGET_COLNAME,\n",
-        "    n_cross_validations=\"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
-        "    track_child_runs=False,\n",
-        "    forecasting_parameters=forecasting_parameters,\n",
-        ")\n",
-        "\n",
-        "\n",
-        "mm_paramters = ManyModelsTrainParameters(\n",
-        "    automl_settings=automl_settings, partition_column_names=partition_column_names\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Set up many models pipeline"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Parallel run step is leveraged to train multiple models at once. To configure the ParallelRunConfig you will need to determine the appropriate number of workers and nodes for your use case. The process_count_per_node is based off the number of cores of the compute VM. The node_count will determine the number of master nodes to use, increasing the node count will speed up the training process.\n",
-        "\n",
-        "| Property                           | Description|\n",
-        "| :---------------                   | :------------------- |\n",
-        "| **experiment**                     | The experiment used for training. |\n",
-        "| **train_data**                     | The file dataset to be used as input to the training run. |\n",
-        "| **node_count**                     | The number of compute nodes to be used for running the user script. We recommend to start with 3 and increase the node_count if the training time is taking too long. |\n",
-        "| **process_count_per_node**         | Process count per node, we recommend 2:1 ratio for number of cores: number of processes per node. eg. If node has 16 cores then configure 8 or less process count per node or optimal performance. |\n",
-        "| **train_pipeline_parameters**      | The set of configuration parameters defined in the previous section. |\n",
-        "| **run_invocation_timeout**         | Maximum amount of time in seconds that the ``ParallelRunStep`` class is allowed. This is optional but provides customers with greater control on exit criteria. This must be greater than ``experiment_timeout_hours`` by at least 300 seconds. |\n",
-        "\n",
-        "Calling this method will create a new aggregated dataset which is generated dynamically on pipeline execution.\n",
-        "\n",
-        "**Note**: Total time taken for the **training step** in the pipeline to complete = $ \\frac{t}{ p \\times n } \\times ts $\n",
-        "where,\n",
-        "- $ t $ is time taken for training one partition (can be viewed in the training logs)\n",
-        "- $ p $ is ``process_count_per_node``\n",
-        "- $ n $ is ``node_count``\n",
-        "- $ ts $ is total number of partitions in time series based on ``partition_column_names``"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.contrib.automl.pipeline.steps import AutoMLPipelineBuilder\n",
-        "\n",
-        "\n",
-        "training_pipeline_steps = AutoMLPipelineBuilder.get_many_models_train_steps(\n",
-        "    experiment=experiment,\n",
-        "    train_data=train_data,\n",
-        "    compute_target=compute_target,\n",
-        "    node_count=2,\n",
-        "    process_count_per_node=2,\n",
-        "    run_invocation_timeout=1200,\n",
-        "    train_pipeline_parameters=mm_paramters,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.pipeline.core import Pipeline\n",
-        "\n",
-        "training_pipeline = Pipeline(ws, steps=training_pipeline_steps)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Submit the pipeline to run\n",
-        "Next we submit our pipeline to run. The whole training pipeline takes about 20 minutes using a STANDARD_DS12_V2 VM with our current ParallelRunConfig setting."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "training_run = experiment.submit(training_pipeline)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "training_run.wait_for_completion(show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Check the run status, if training_run is in completed state, continue to next section. Otherwise, check the portal for failures."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## 4.0 Backtesting\n",
-        "Now that we selected the best AutoML model for each backtest fold, we will use these models to generate the forecasts and compare with the actuals."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Set up output dataset for inference data\n",
-        "Output of inference can be represented as [OutputFileDatasetConfig](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.output_dataset_config.outputdatasetconfig?view=azure-ml-py) object and OutputFileDatasetConfig can be registered as a dataset. "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.data import OutputFileDatasetConfig\n",
-        "\n",
-        "output_inference_data_ds = OutputFileDatasetConfig(\n",
-        "    name=\"many_models_inference_output\",\n",
-        "    destination=(dstore, \"backtesting/inference_data/\"),\n",
-        ").register_on_complete(name=\"backtesting_data_ds\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "For many models we need to provide the ManyModelsInferenceParameters object.\n",
-        "\n",
-        "#### ``ManyModelsInferenceParameters`` arguments\n",
-        "| Property                           | Description|\n",
-        "| :---------------                   | :------------------- |\n",
-        "| **partition_column_names**         | List of column names that identifies groups. |\n",
-        "| **target_column_name**             | \\[Optional] Column name only if the inference dataset has the target. |\n",
-        "| **time_column_name**               | \\[Optional] Time column name only if it is timeseries. |\n",
-        "| **inference_type**                 | \\[Optional] Which inference method to use on the model. Possible values are 'forecast', 'predict_proba', and 'predict'. |\n",
-        "| **forecast_mode**                  | \\[Optional] The type of forecast to be used, either 'rolling' or 'recursive'; defaults to 'recursive'. |\n",
-        "| **step**                           | \\[Optional] Number of periods to advance the forecasting window in each iteration **(for rolling forecast only)**; defaults to 1. |\n",
-        "\n",
-        "#### ``get_many_models_batch_inference_steps`` arguments\n",
-        "| Property                           | Description|\n",
-        "| :---------------                   | :------------------- |\n",
-        "| **experiment**                     | The experiment used for inference run. |\n",
-        "| **inference_data**                 | The data to use for inferencing. It should be the same schema as used for training.\n",
-        "| **compute_target**                 | The compute target that runs the inference pipeline. |\n",
-        "| **node_count**                     | The number of compute nodes to be used for running the user script. We recommend to start with the number of cores per node (varies by compute sku). |\n",
-        "| **process_count_per_node**         | \\[Optional] The number of processes per node. By default it's 2 (should be at most half of the number of cores in a single node of the compute cluster that will be used for the experiment).\n",
-        "| **inference_pipeline_parameters**  | \\[Optional] The ``ManyModelsInferenceParameters`` object defined above. |\n",
-        "| **append_row_file_name**           | \\[Optional] The name of the output file (optional, default value is 'parallel_run_step.txt'). Supports 'txt' and 'csv' file extension. A 'txt' file extension generates the output in 'txt' format with space as separator without column names. A 'csv' file extension generates the output in 'csv' format with comma as separator and with column names. |\n",
-        "| **train_run_id**                   | \\[Optional] The run id of the **training pipeline**. By default it is the latest successful training pipeline run in the experiment. |\n",
-        "| **train_experiment_name**          | \\[Optional] The train experiment that contains the train pipeline. This one is only needed when the train pipeline is not in the same experiement as the inference pipeline. |\n",
-        "| **run_invocation_timeout**         | \\[Optional] Maximum amount of time in seconds that the ``ParallelRunStep`` class is allowed. This is optional but provides customers with greater control on exit criteria. |\n",
-        "| **output_datastore**               | \\[Optional] The ``Datastore`` or ``OutputDatasetConfig`` to be used for output. If specified any pipeline output will be written to that location. If unspecified the default datastore will be used. |\n",
-        "| **arguments**                      | \\[Optional] Arguments to be passed to inference script. Possible argument is '--forecast_quantiles' followed by quantile values. |"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.contrib.automl.pipeline.steps import AutoMLPipelineBuilder\n",
-        "from azureml.train.automl.runtime._many_models.many_models_parameters import (\n",
-        "    ManyModelsInferenceParameters,\n",
-        ")\n",
-        "\n",
-        "mm_parameters = ManyModelsInferenceParameters(\n",
-        "    partition_column_names=partition_column_names,\n",
-        "    time_column_name=TIME_COLNAME,\n",
-        "    target_column_name=TARGET_COLNAME,\n",
-        ")\n",
-        "\n",
-        "output_file_name = \"parallel_run_step.csv\"\n",
-        "\n",
-        "inference_steps = AutoMLPipelineBuilder.get_many_models_batch_inference_steps(\n",
-        "    experiment=experiment,\n",
-        "    inference_data=test_data,\n",
-        "    node_count=2,\n",
-        "    process_count_per_node=2,\n",
-        "    compute_target=compute_target,\n",
-        "    run_invocation_timeout=300,\n",
-        "    output_datastore=output_inference_data_ds,\n",
-        "    train_run_id=training_run.id,\n",
-        "    train_experiment_name=training_run.experiment.name,\n",
-        "    inference_pipeline_parameters=mm_parameters,\n",
-        "    append_row_file_name=output_file_name,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.pipeline.core import Pipeline\n",
-        "\n",
-        "inference_pipeline = Pipeline(ws, steps=inference_steps)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "inference_run = experiment.submit(inference_pipeline)\n",
-        "inference_run.wait_for_completion(show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## 5.0 Retrieve results and calculate metrics\n",
-        "\n",
-        "The pipeline returns one file with the predictions for each times series ID and outputs the result to the forecasting_output Blob container. The details of the blob container is listed in 'forecasting_output.txt' under Outputs+logs. \n",
-        "\n",
-        "The next code snippet does the following:\n",
-        "1. Downloads the contents of the output folder that is passed in the parallel run step \n",
-        "2. Reads the parallel_run_step.txt file that has the predictions as pandas dataframe \n",
-        "3. Saves the table in csv format and \n",
-        "4. Displays the top 10 rows of the predictions"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.contrib.automl.pipeline.steps.utilities import get_output_from_mm_pipeline\n",
-        "\n",
-        "PREDICTION_COLNAME = \"Predictions\"\n",
-        "forecasting_results_name = \"forecasting_results\"\n",
-        "forecasting_output_name = \"many_models_inference_output\"\n",
-        "forecast_file = get_output_from_mm_pipeline(\n",
-        "    inference_run, forecasting_results_name, forecasting_output_name, output_file_name\n",
-        ")\n",
-        "df = pd.read_csv(forecast_file, parse_dates=[0])\n",
-        "print(\n",
-        "    \"Prediction has \", df.shape[0], \" rows. Here the first 10 rows are being displayed.\"\n",
-        ")\n",
-        "# Save the csv file to read it in the next step.\n",
-        "df.rename(\n",
-        "    columns={TARGET_COLNAME: \"actual_level\", PREDICTION_COLNAME: \"predicted_level\"},\n",
-        "    inplace=True,\n",
-        ")\n",
-        "df.to_csv(os.path.join(forecasting_results_name, \"forecast.csv\"), index=False)\n",
-        "df.head(10)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## View metrics\n",
-        "We will read in the obtained results and run the helper script, which will generate metrics and create the plots of predicted versus actual values."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from assets.score import calculate_scores_and_build_plots\n",
-        "\n",
-        "backtesting_results = \"backtesting_mm_results\"\n",
-        "os.makedirs(backtesting_results, exist_ok=True)\n",
-        "calculate_scores_and_build_plots(\n",
-        "    forecasting_results_name,\n",
-        "    backtesting_results,\n",
-        "    automl_settings.as_serializable_dict(),\n",
-        ")\n",
-        "pd.DataFrame({\"File\": os.listdir(backtesting_results)})"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "The directory contains a set of files with results:\n",
-        "- forecast.csv contains forecasts for all backtest iterations. The backtest_iteration column contains iteration identifier with the last training date as a suffix\n",
-        "- scores.csv contains all metrics. If data set contains several time series, the metrics are given for all combinations of time series id and iterations, as well as scores for all iterations and time series ids, which are marked as \"all_sets\"\n",
-        "- plots_fcst_vs_actual.pdf contains the predictions vs forecast plots for each iteration and, eash time series is saved as separate plot.\n",
-        "\n",
-        "For demonstration purposes we will display the table of metrics for one of the time series with ID \"ts0\". We will create the utility function, which will build the table with metrics."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "def get_metrics_for_ts(all_metrics, ts):\n",
-        "    \"\"\"\n",
-        "    Get the metrics for the time series with ID ts and return it as pandas data frame.\n",
-        "\n",
-        "    :param all_metrics: The table with all the metrics.\n",
-        "    :param ts: The ID of a time series of interest.\n",
-        "    :return: The pandas DataFrame with metrics for one time series.\n",
-        "    \"\"\"\n",
-        "    results_df = None\n",
-        "    for ts_id, one_series in all_metrics.groupby(\"time_series_id\"):\n",
-        "        if not ts_id.startswith(ts):\n",
-        "            continue\n",
-        "        iteration = ts_id.split(\"|\")[-1]\n",
-        "        df = one_series[[\"metric_name\", \"metric\"]]\n",
-        "        df.rename({\"metric\": iteration}, axis=1, inplace=True)\n",
-        "        df.set_index(\"metric_name\", inplace=True)\n",
-        "        if results_df is None:\n",
-        "            results_df = df\n",
-        "        else:\n",
-        "            results_df = results_df.merge(\n",
-        "                df, how=\"inner\", left_index=True, right_index=True\n",
-        "            )\n",
-        "    results_df.sort_index(axis=1, inplace=True)\n",
-        "    return results_df\n",
-        "\n",
-        "\n",
-        "metrics_df = pd.read_csv(os.path.join(backtesting_results, \"scores.csv\"))\n",
-        "ts = \"ts_A\"\n",
-        "get_metrics_for_ts(metrics_df, ts)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Forecast vs actuals plots."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from IPython.display import IFrame\n",
-        "\n",
-        "IFrame(\"./backtesting_mm_results/plots_fcst_vs_actual.pdf\", width=800, height=300)"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "jialiu"
-      }
-    ],
-    "categories": [
-      "how-to-use-azureml",
-      "automated-machine-learning"
-    ],
-    "kernelspec": {
-      "display_name": "Python 3.8 - AzureML",
-      "language": "python",
-      "name": "python38-azureml"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.8.5"
-    },
-    "vscode": {
-      "interpreter": {
-        "hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
-      }
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 4
-}

how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/assets/data_split.py

@@ -1,45 +0,0 @@
-import argparse
-import os
-
-import pandas as pd
-
-import azureml.train.automl.runtime._hts.hts_runtime_utilities as hru
-
-from azureml.core import Run
-from azureml.core.dataset import Dataset
-
-# Parse the arguments.
-args = {
-    "step_size": "--step-size",
-    "step_number": "--step-number",
-    "time_column_name": "--time-column-name",
-    "time_series_id_column_names": "--time-series-id-column-names",
-    "out_dir": "--output-dir",
-}
-parser = argparse.ArgumentParser("Parsing input arguments.")
-for argname, arg in args.items():
-    parser.add_argument(arg, dest=argname, required=True)
-parsed_args, _ = parser.parse_known_args()
-step_number = int(parsed_args.step_number)
-step_size = int(parsed_args.step_size)
-# Create the working dirrectory to store the temporary csv files.
-working_dir = parsed_args.out_dir
-os.makedirs(working_dir, exist_ok=True)
-# Set input and output
-script_run = Run.get_context()
-input_dataset = script_run.input_datasets["training_data"]
-X_train = input_dataset.to_pandas_dataframe()
-# Split the data.
-for i in range(step_number):
-    file_name = os.path.join(working_dir, "backtest_{}.csv".format(i))
-    if parsed_args.time_series_id_column_names:
-        dfs = []
-        for _, one_series in X_train.groupby([parsed_args.time_series_id_column_names]):
-            one_series = one_series.sort_values(
-                by=[parsed_args.time_column_name], inplace=False
-            )
-            dfs.append(one_series.iloc[: len(one_series) - step_size * i])
-        pd.concat(dfs, sort=False, ignore_index=True).to_csv(file_name, index=False)
-    else:
-        X_train.sort_values(by=[parsed_args.time_column_name], inplace=True)
-        X_train.iloc[: len(X_train) - step_size * i].to_csv(file_name, index=False)

how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/assets/retrain_models.py

@@ -1,178 +0,0 @@
-# ---------------------------------------------------------
-# Copyright (c) Microsoft Corporation. All rights reserved.
-# ---------------------------------------------------------
-"""The batch script needed for back testing of models using PRS."""
-import argparse
-import json
-import logging
-import os
-import pickle
-import re
-
-import pandas as pd
-
-from azureml.core.experiment import Experiment
-from azureml.core.model import Model
-from azureml.core.run import Run
-from azureml.automl.core.shared import constants
-from azureml.automl.runtime.shared.score import scoring
-from azureml.train.automl import AutoMLConfig
-
-RE_INVALID_SYMBOLS = re.compile(r"[:\s]")
-
-model_name = None
-target_column_name = None
-current_step_run = None
-output_dir = None
-
-logger = logging.getLogger(__name__)
-
-
-def _get_automl_settings():
-    with open(
-        os.path.join(
-            os.path.dirname(os.path.realpath(__file__)), "automl_settings.json"
-        )
-    ) as json_file:
-        return json.load(json_file)
-
-
-def init():
-    global model_name
-    global target_column_name
-    global output_dir
-    global automl_settings
-    global model_uid
-    global forecast_quantiles
-
-    logger.info("Initialization of the run.")
-    parser = argparse.ArgumentParser("Parsing input arguments.")
-    parser.add_argument("--output-dir", dest="out", required=True)
-    parser.add_argument("--model-name", dest="model", default=None)
-    parser.add_argument("--model-uid", dest="model_uid", default=None)
-    parser.add_argument(
-        "--forecast_quantiles",
-        nargs="*",
-        type=float,
-        help="forecast quantiles list",
-        default=None,
-    )
-
-    parsed_args, _ = parser.parse_known_args()
-    model_name = parsed_args.model
-    automl_settings = _get_automl_settings()
-    target_column_name = automl_settings.get("label_column_name")
-    output_dir = parsed_args.out
-    model_uid = parsed_args.model_uid
-    forecast_quantiles = parsed_args.forecast_quantiles
-    os.makedirs(output_dir, exist_ok=True)
-    os.environ["AUTOML_IGNORE_PACKAGE_VERSION_INCOMPATIBILITIES".lower()] = "True"
-
-
-def get_run():
-    global current_step_run
-    if current_step_run is None:
-        current_step_run = Run.get_context()
-    return current_step_run
-
-
-def run_backtest(data_input_name: str, file_name: str, experiment: Experiment):
-    """Re-train the model and return metrics."""
-    data_input = pd.read_csv(
-        data_input_name,
-        parse_dates=[automl_settings[constants.TimeSeries.TIME_COLUMN_NAME]],
-    )
-    print(data_input.head())
-    if not automl_settings.get(constants.TimeSeries.GRAIN_COLUMN_NAMES):
-        # There is no grains.
-        data_input.sort_values(
-            [automl_settings[constants.TimeSeries.TIME_COLUMN_NAME]], inplace=True
-        )
-        X_train = data_input.iloc[: -automl_settings["max_horizon"]]
-        y_train = X_train.pop(target_column_name).values
-        X_test = data_input.iloc[-automl_settings["max_horizon"] :]
-        y_test = X_test.pop(target_column_name).values
-    else:
-        # The data contain grains.
-        dfs_train = []
-        dfs_test = []
-        for _, one_series in data_input.groupby(
-            automl_settings.get(constants.TimeSeries.GRAIN_COLUMN_NAMES)
-        ):
-            one_series.sort_values(
-                [automl_settings[constants.TimeSeries.TIME_COLUMN_NAME]], inplace=True
-            )
-            dfs_train.append(one_series.iloc[: -automl_settings["max_horizon"]])
-            dfs_test.append(one_series.iloc[-automl_settings["max_horizon"] :])
-        X_train = pd.concat(dfs_train, sort=False, ignore_index=True)
-        y_train = X_train.pop(target_column_name).values
-        X_test = pd.concat(dfs_test, sort=False, ignore_index=True)
-        y_test = X_test.pop(target_column_name).values
-
-    last_training_date = str(
-        X_train[automl_settings[constants.TimeSeries.TIME_COLUMN_NAME]].max()
-    )
-
-    if file_name:
-        # If file name is provided, we will load model and retrain it on backtest data.
-        with open(file_name, "rb") as fp:
-            fitted_model = pickle.load(fp)
-        fitted_model.fit(X_train, y_train)
-    else:
-        # We will run the experiment and select the best model.
-        X_train[target_column_name] = y_train
-        automl_config = AutoMLConfig(training_data=X_train, **automl_settings)
-        automl_run = current_step_run.submit_child(automl_config, show_output=True)
-        best_run, fitted_model = automl_run.get_output()
-        # As we have generated models, we need to register them for the future use.
-        description = "Backtest model example"
-        tags = {"last_training_date": last_training_date, "experiment": experiment.name}
-        if model_uid:
-            tags["model_uid"] = model_uid
-        automl_run.register_model(
-            model_name=best_run.properties["model_name"],
-            description=description,
-            tags=tags,
-        )
-        print(f"The model {best_run.properties['model_name']} was registered.")
-
-    # By default we will have forecast quantiles of 0.5, which is our target
-    if forecast_quantiles:
-        if 0.5 not in forecast_quantiles:
-            forecast_quantiles.append(0.5)
-        fitted_model.quantiles = forecast_quantiles
-
-    x_pred = fitted_model.forecast_quantiles(X_test)
-    x_pred["actual_level"] = y_test
-    x_pred["backtest_iteration"] = f"iteration_{last_training_date}"
-    x_pred.rename({0.5: "predicted_level"}, axis=1, inplace=True)
-    date_safe = RE_INVALID_SYMBOLS.sub("_", last_training_date)
-
-    x_pred.to_csv(os.path.join(output_dir, f"iteration_{date_safe}.csv"), index=False)
-    return x_pred
-
-
-def run(input_files):
-    """Run the script"""
-    logger.info("Running mini batch.")
-    ws = get_run().experiment.workspace
-    file_name = None
-    if model_name:
-        models = Model.list(ws, name=model_name)
-        cloud_model = None
-        if models:
-            for one_mod in models:
-                if cloud_model is None or one_mod.version > cloud_model.version:
-                    logger.info(
-                        "Using existing model from the workspace. Model version: {}".format(
-                            one_mod.version
-                        )
-                    )
-                    cloud_model = one_mod
-        file_name = cloud_model.download(exist_ok=True)
-
-    forecasts = []
-    logger.info("Running backtest.")
-    for input_file in input_files:
-        forecasts.append(run_backtest(input_file, file_name, get_run().experiment))
-    return pd.concat(forecasts)

how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/assets/score.py

@@ -1,171 +0,0 @@
-from typing import Any, Dict, Optional, List
-
-import argparse
-import json
-import os
-import re
-
-import numpy as np
-import pandas as pd
-
-from matplotlib import pyplot as plt
-from matplotlib.backends.backend_pdf import PdfPages
-
-from azureml.automl.core.shared import constants
-from azureml.automl.core.shared.types import GrainType
-from azureml.automl.runtime.shared.score import scoring
-
-GRAIN = "time_series_id"
-BACKTEST_ITER = "backtest_iteration"
-ACTUALS = "actual_level"
-PREDICTIONS = "predicted_level"
-ALL_GRAINS = "all_sets"
-
-FORECASTS_FILE = "forecast.csv"
-SCORES_FILE = "scores.csv"
-PLOTS_FILE = "plots_fcst_vs_actual.pdf"
-RE_INVALID_SYMBOLS = re.compile("[: ]")
-
-
-def _compute_metrics(df: pd.DataFrame, metrics: List[str]):
-    """
-    Compute metrics for one data frame.
-
-    :param df: The data frame which contains actual_level and predicted_level columns.
-    :return: The data frame with two columns - metric_name and metric.
-    """
-    scores = scoring.score_regression(
-        y_test=df[ACTUALS], y_pred=df[PREDICTIONS], metrics=metrics
-    )
-    metrics_df = pd.DataFrame(list(scores.items()), columns=["metric_name", "metric"])
-    metrics_df.sort_values(["metric_name"], inplace=True)
-    metrics_df.reset_index(drop=True, inplace=True)
-    return metrics_df
-
-
-def _format_grain_name(grain: GrainType) -> str:
-    """
-    Convert grain name to string.
-
-    :param grain: the grain name.
-    :return: the string representation of the given grain.
-    """
-    if not isinstance(grain, tuple) and not isinstance(grain, list):
-        return str(grain)
-    grain = list(map(str, grain))
-    return "|".join(grain)
-
-
-def compute_all_metrics(
-    fcst_df: pd.DataFrame,
-    ts_id_colnames: List[str],
-    metric_names: Optional[List[set]] = None,
-):
-    """
-    Calculate metrics per grain.
-
-    :param fcst_df: forecast data frame. Must contain 2 columns: 'actual_level' and 'predicted_level'
-    :param metric_names: (optional) the list of metric names to return
-    :param ts_id_colnames: (optional) list of grain column names
-    :return: dictionary of summary table for all tests and final decision on stationary vs nonstaionary
-    """
-    if not metric_names:
-        metric_names = list(constants.Metric.SCALAR_REGRESSION_SET)
-
-    if ts_id_colnames is None:
-        ts_id_colnames = []
-
-    metrics_list = []
-    if ts_id_colnames:
-        for grain, df in fcst_df.groupby(ts_id_colnames):
-            one_grain_metrics_df = _compute_metrics(df, metric_names)
-            one_grain_metrics_df[GRAIN] = _format_grain_name(grain)
-            metrics_list.append(one_grain_metrics_df)
-
-    # overall metrics
-    one_grain_metrics_df = _compute_metrics(fcst_df, metric_names)
-    one_grain_metrics_df[GRAIN] = ALL_GRAINS
-    metrics_list.append(one_grain_metrics_df)
-
-    # collect into a data frame
-    return pd.concat(metrics_list)
-
-
-def _draw_one_plot(
-    df: pd.DataFrame,
-    time_column_name: str,
-    grain_column_names: List[str],
-    pdf: PdfPages,
-) -> None:
-    """
-    Draw the single plot.
-
-    :param df: The data frame with the data to build plot.
-    :param time_column_name: The name of a time column.
-    :param grain_column_names: The name of grain columns.
-    :param pdf: The pdf backend used to render the plot.
-    """
-    fig, _ = plt.subplots(figsize=(20, 10))
-    df = df.set_index(time_column_name)
-    plt.plot(df[[ACTUALS, PREDICTIONS]])
-    plt.xticks(rotation=45)
-    iteration = df[BACKTEST_ITER].iloc[0]
-    if grain_column_names:
-        grain_name = [df[grain].iloc[0] for grain in grain_column_names]
-        plt.title(f"Time series ID: {_format_grain_name(grain_name)} {iteration}")
-    plt.legend(["actual", "forecast"])
-    plt.close(fig)
-    pdf.savefig(fig)
-
-
-def calculate_scores_and_build_plots(
-    input_dir: str, output_dir: str, automl_settings: Dict[str, Any]
-):
-    os.makedirs(output_dir, exist_ok=True)
-    grains = automl_settings.get(constants.TimeSeries.GRAIN_COLUMN_NAMES)
-    time_column_name = automl_settings.get(constants.TimeSeries.TIME_COLUMN_NAME)
-    if grains is None:
-        grains = []
-    if isinstance(grains, str):
-        grains = [grains]
-    while BACKTEST_ITER in grains:
-        grains.remove(BACKTEST_ITER)
-
-    dfs = []
-    for fle in os.listdir(input_dir):
-        file_path = os.path.join(input_dir, fle)
-        if os.path.isfile(file_path) and file_path.endswith(".csv"):
-            df_iter = pd.read_csv(file_path, parse_dates=[time_column_name])
-            for _, iteration in df_iter.groupby(BACKTEST_ITER):
-                dfs.append(iteration)
-    forecast_df = pd.concat(dfs, sort=False, ignore_index=True)
-    # To make sure plots are in order, sort the predictions by grain and iteration.
-    ts_index = grains + [BACKTEST_ITER]
-    forecast_df.sort_values(by=ts_index, inplace=True)
-    pdf = PdfPages(os.path.join(output_dir, PLOTS_FILE))
-    for _, one_forecast in forecast_df.groupby(ts_index):
-        _draw_one_plot(one_forecast, time_column_name, grains, pdf)
-    pdf.close()
-    forecast_df.to_csv(os.path.join(output_dir, FORECASTS_FILE), index=False)
-    # Remove np.NaN and np.inf from the prediction and actuals data.
-    forecast_df.replace([np.inf, -np.inf], np.nan, inplace=True)
-    forecast_df.dropna(subset=[ACTUALS, PREDICTIONS], inplace=True)
-    metrics = compute_all_metrics(forecast_df, grains + [BACKTEST_ITER])
-    metrics.to_csv(os.path.join(output_dir, SCORES_FILE), index=False)
-
-
-if __name__ == "__main__":
-    args = {"forecasts": "--forecasts", "scores_out": "--output-dir"}
-    parser = argparse.ArgumentParser("Parsing input arguments.")
-    for argname, arg in args.items():
-        parser.add_argument(arg, dest=argname, required=True)
-    parsed_args, _ = parser.parse_known_args()
-    input_dir = parsed_args.forecasts
-    output_dir = parsed_args.scores_out
-    with open(
-        os.path.join(
-            os.path.dirname(os.path.realpath(__file__)), "automl_settings.json"
-        )
-    ) as json_file:
-        automl_settings = json.load(json_file)
-    calculate_scores_and_build_plots(input_dir, output_dir, automl_settings)

how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/auto-ml-forecasting-backtest-single-model.ipynb

@@ -1,729 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License.\n",
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/auto-ml-forecasting-backtest-single-model.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Automated MachineLearning\n",
-        "_**The model backtesting**_\n",
-        "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "2. [Setup](#Setup)\n",
-        "3. [Data](#Data)\n",
-        "4. [Prepare remote compute and data.](#prepare_remote)\n",
-        "5. [Create the configuration for AutoML backtesting](#train)\n",
-        "6. [Backtest AutoML](#backtest_automl)\n",
-        "7. [View metrics](#Metrics)\n",
-        "8. [Backtest the best model](#backtest_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
-        "Model backtesting is used to evaluate its performance on historical data. To do that we step back on the backtesting period by the data set several times and split the data to train and test sets. Then these data sets are used for training and evaluation of model.<br>\n",
-        "This notebook is intended to demonstrate backtesting on a single model, this is the best solution for small data sets with a few or one time series in it. For scenarios where we would like to choose the best AutoML model for every backtest iteration, please see [AutoML Forecasting Backtest Many Models Example](../forecasting-backtest-many-models/auto-ml-forecasting-backtest-many-models.ipynb) notebook.\n",
-        "![Backtesting](Backtesting.png)\n",
-        "This notebook demonstrates two ways of backtesting:\n",
-        "- AutoML backtesting: we will train separate AutoML models for historical data\n",
-        "- Model backtesting: from the first run we will select the best model trained on the most recent data, retrain it on the past data and evaluate."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Setup"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "import numpy as np\n",
-        "import pandas as pd\n",
-        "import shutil\n",
-        "\n",
-        "import azureml.core\n",
-        "from azureml.core import Experiment, Model, Workspace"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "This notebook is compatible with Azure ML SDK version 1.35.1 or later."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "As part of the setup you have already created a <b>Workspace</b>."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ws = Workspace.from_config()\n",
-        "\n",
-        "output = {}\n",
-        "output[\"Subscription ID\"] = ws.subscription_id\n",
-        "output[\"Workspace\"] = ws.name\n",
-        "output[\"SKU\"] = ws.sku\n",
-        "output[\"Resource Group\"] = ws.resource_group\n",
-        "output[\"Location\"] = ws.location\n",
-        "output[\"SDK Version\"] = azureml.core.VERSION\n",
-        "pd.set_option(\"display.max_colwidth\", None)\n",
-        "outputDf = pd.DataFrame(data=output, index=[\"\"])\n",
-        "outputDf.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Data\n",
-        "For the demonstration purposes we will simulate one year of daily data. To do this we need to specify the following parameters: time column name, time series ID column names and label column name. Our intention is to forecast for two weeks ahead."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "TIME_COLUMN_NAME = \"date\"\n",
-        "TIME_SERIES_ID_COLUMN_NAMES = \"time_series_id\"\n",
-        "LABEL_COLUMN_NAME = \"y\"\n",
-        "FORECAST_HORIZON = 14\n",
-        "FREQUENCY = \"D\"\n",
-        "\n",
-        "\n",
-        "def simulate_timeseries_data(\n",
-        "    train_len: int,\n",
-        "    test_len: int,\n",
-        "    time_column_name: str,\n",
-        "    target_column_name: str,\n",
-        "    time_series_id_column_name: str,\n",
-        "    time_series_number: int = 1,\n",
-        "    freq: str = \"H\",\n",
-        "):\n",
-        "    \"\"\"\n",
-        "    Return the time series of designed length.\n",
-        "\n",
-        "    :param train_len: The length of training data (one series).\n",
-        "    :type train_len: int\n",
-        "    :param test_len: The length of testing data (one series).\n",
-        "    :type test_len: int\n",
-        "    :param time_column_name: The desired name of a time column.\n",
-        "    :type time_column_name: str\n",
-        "    :param time_series_number: The number of time series in the data set.\n",
-        "    :type time_series_number: int\n",
-        "    :param freq: The frequency string representing pandas offset.\n",
-        "                 see https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html\n",
-        "    :type freq: str\n",
-        "    :returns: the tuple of train and test data sets.\n",
-        "    :rtype: tuple\n",
-        "\n",
-        "    \"\"\"\n",
-        "    data_train = []  # type: List[pd.DataFrame]\n",
-        "    data_test = []  # type: List[pd.DataFrame]\n",
-        "    data_length = train_len + test_len\n",
-        "    for i in range(time_series_number):\n",
-        "        X = pd.DataFrame(\n",
-        "            {\n",
-        "                time_column_name: pd.date_range(\n",
-        "                    start=\"2000-01-01\", periods=data_length, freq=freq\n",
-        "                ),\n",
-        "                target_column_name: np.arange(data_length).astype(float)\n",
-        "                + np.random.rand(data_length)\n",
-        "                + i * 5,\n",
-        "                \"ext_predictor\": np.asarray(range(42, 42 + data_length)),\n",
-        "                time_series_id_column_name: np.repeat(\"ts{}\".format(i), data_length),\n",
-        "            }\n",
-        "        )\n",
-        "        data_train.append(X[:train_len])\n",
-        "        data_test.append(X[train_len:])\n",
-        "    train = pd.concat(data_train)\n",
-        "    label_train = train.pop(target_column_name).values\n",
-        "    test = pd.concat(data_test)\n",
-        "    label_test = test.pop(target_column_name).values\n",
-        "    return train, label_train, test, label_test\n",
-        "\n",
-        "\n",
-        "n_test_periods = FORECAST_HORIZON\n",
-        "n_train_periods = 365\n",
-        "X_train, y_train, X_test, y_test = simulate_timeseries_data(\n",
-        "    train_len=n_train_periods,\n",
-        "    test_len=n_test_periods,\n",
-        "    time_column_name=TIME_COLUMN_NAME,\n",
-        "    target_column_name=LABEL_COLUMN_NAME,\n",
-        "    time_series_id_column_name=TIME_SERIES_ID_COLUMN_NAMES,\n",
-        "    time_series_number=2,\n",
-        "    freq=FREQUENCY,\n",
-        ")\n",
-        "X_train[LABEL_COLUMN_NAME] = y_train"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Let's see what the training data looks like."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "X_train.tail()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Prepare remote compute and data. <a id=\"prepare_remote\"></a>\n",
-        "The [Machine Learning service workspace](https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-workspace), is paired with the storage account, which contains the default data store. We will use it to upload the artificial data and create [tabular dataset](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.tabulardataset?view=azure-ml-py) for training. A tabular dataset defines a series of lazily-evaluated, immutable operations to load data from the data source into tabular representation."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.data.dataset_factory import TabularDatasetFactory\n",
-        "\n",
-        "ds = ws.get_default_datastore()\n",
-        "# Upload saved data to the default data store.\n",
-        "train_data = TabularDatasetFactory.register_pandas_dataframe(\n",
-        "    X_train, target=(ds, \"data\"), name=\"data_backtest\"\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "You will need to create a compute target for backtesting. In this [tutorial](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-set-up-training-targets#amlcompute), you create AmlCompute as your training compute resource.\n",
-        "\n",
-        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
-        "from azureml.core.compute_target import ComputeTargetException\n",
-        "\n",
-        "# Choose a name for your CPU cluster\n",
-        "amlcompute_cluster_name = \"backtest-cluster\"\n",
-        "\n",
-        "# Verify that cluster does not exist already\n",
-        "try:\n",
-        "    compute_target = ComputeTarget(workspace=ws, name=amlcompute_cluster_name)\n",
-        "    print(\"Found existing cluster, use it.\")\n",
-        "except ComputeTargetException:\n",
-        "    compute_config = AmlCompute.provisioning_configuration(\n",
-        "        vm_size=\"STANDARD_DS12_V2\", max_nodes=6\n",
-        "    )\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, compute_config)\n",
-        "\n",
-        "compute_target.wait_for_completion(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Create the configuration for AutoML backtesting <a id=\"train\"></a>\n",
-        "\n",
-        "This dictionary defines the AutoML and many models settings. For this forecasting task we need to define several settings including the name of the time column, the maximum forecast horizon, and the partition column name definition.\n",
-        "\n",
-        "| Property                           | Description|\n",
-        "| :---------------                   | :------------------- |\n",
-        "| **task**                           | forecasting |\n",
-        "| **primary_metric**                 | This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>normalized_root_mean_squared_error</i><br><i>normalized_mean_absolute_error</i> |\n",
-        "| **iteration_timeout_minutes**      | Maximum amount of time in minutes that the model can train. This is optional but provides customers with greater control on exit criteria. |\n",
-        "| **iterations**                     | Number of models to train. This is optional but provides customers with greater control on exit criteria. |\n",
-        "| **experiment_timeout_hours**       | Maximum amount of time in hours that the experiment can take before it terminates. This is optional but provides customers with greater control on exit criteria. |\n",
-        "| **label_column_name**              | The name of the label column. |\n",
-        "| **max_horizon**               | The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly). Periods are inferred from your data. |\n",
-        "| **n_cross_validations**            | Number of cross validation splits. The default value is \"auto\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
-        "|**cv_step_size**|Number of periods between two consecutive cross-validation folds. The default value is \"auto\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value.\n",
-        "| **time_column_name**               | The name of your time column. |\n",
-        "| **grain_column_names**     | The column names used to uniquely identify timeseries in data that has multiple rows with the same timestamp. |"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "automl_settings = {\n",
-        "    \"task\": \"forecasting\",\n",
-        "    \"primary_metric\": \"normalized_root_mean_squared_error\",\n",
-        "    \"iteration_timeout_minutes\": 10,  # This needs to be changed based on the dataset. We ask customer to explore how long training is taking before settings this value\n",
-        "    \"iterations\": 15,\n",
-        "    \"experiment_timeout_hours\": 1,  # This also needs to be changed based on the dataset. For larger data set this number needs to be bigger.\n",
-        "    \"label_column_name\": LABEL_COLUMN_NAME,\n",
-        "    \"n_cross_validations\": \"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
-        "    \"cv_step_size\": \"auto\",\n",
-        "    \"time_column_name\": TIME_COLUMN_NAME,\n",
-        "    \"max_horizon\": FORECAST_HORIZON,\n",
-        "    \"track_child_runs\": False,\n",
-        "    \"grain_column_names\": TIME_SERIES_ID_COLUMN_NAMES,\n",
-        "}"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Backtest AutoML <a id=\"backtest_automl\"></a>\n",
-        "First we set backtesting parameters: we will step back by 30 days and will make 5 such steps; for each step we will forecast for next two weeks."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# The number of periods to step back on each backtest iteration.\n",
-        "BACKTESTING_PERIOD = 30\n",
-        "# The number of times we will back test the model.\n",
-        "NUMBER_OF_BACKTESTS = 5"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "To train AutoML on backtesting folds we will use the [Azure Machine Learning pipeline](https://docs.microsoft.com/en-us/azure/machine-learning/concept-ml-pipelines). It will generate backtest folds, then train model for each of them and calculate the accuracy metrics. To run pipeline, you also need to create an <b>Experiment</b>. An Experiment corresponds to a prediction problem you are trying to solve (here, it is a forecasting), while a Run corresponds to a specific approach to the problem."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from uuid import uuid1\n",
-        "\n",
-        "from pipeline_helper import get_backtest_pipeline\n",
-        "\n",
-        "pipeline_exp = Experiment(ws, \"automl-backtesting\")\n",
-        "\n",
-        "# We will create the unique identifier to mark our models.\n",
-        "model_uid = str(uuid1())\n",
-        "\n",
-        "pipeline = get_backtest_pipeline(\n",
-        "    experiment=pipeline_exp,\n",
-        "    dataset=train_data,\n",
-        "    # The STANDARD_DS12_V2 has 4 vCPU per node, we will set 2 process per node to be safe.\n",
-        "    process_per_node=2,\n",
-        "    # The maximum number of nodes for our compute is 6.\n",
-        "    node_count=6,\n",
-        "    compute_target=compute_target,\n",
-        "    automl_settings=automl_settings,\n",
-        "    step_size=BACKTESTING_PERIOD,\n",
-        "    step_number=NUMBER_OF_BACKTESTS,\n",
-        "    model_uid=model_uid,\n",
-        "    forecast_quantiles=[0.025, 0.975],  # Optional\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Run the pipeline and wait for results."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "pipeline_run = pipeline_exp.submit(pipeline)\n",
-        "pipeline_run.wait_for_completion(show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "After the run is complete, we can download the results. "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "metrics_output = pipeline_run.get_pipeline_output(\"results\")\n",
-        "metrics_output.download(\"backtest_metrics\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## View metrics<a id=\"Metrics\"></a>\n",
-        "To distinguish these metrics from the model backtest, which we will obtain in the next section, we will move the directory with metrics out of the backtest_metrics and will remove the parent folder. We will create the utility function for that."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "def copy_scoring_directory(new_name):\n",
-        "    scores_path = os.path.join(\"backtest_metrics\", \"azureml\")\n",
-        "    directory_list = [os.path.join(scores_path, d) for d in os.listdir(scores_path)]\n",
-        "    latest_file = max(directory_list, key=os.path.getctime)\n",
-        "    print(\n",
-        "        f\"The output directory {latest_file} was created on {pd.Timestamp(os.path.getctime(latest_file), unit='s')} GMT.\"\n",
-        "    )\n",
-        "    shutil.move(os.path.join(latest_file, \"results\"), new_name)\n",
-        "    shutil.rmtree(\"backtest_metrics\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Move the directory and list its contents."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "copy_scoring_directory(\"automl_backtest\")\n",
-        "pd.DataFrame({\"File\": os.listdir(\"automl_backtest\")})"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "The directory contains a set of files with results:\n",
-        "- forecast.csv contains forecasts for all backtest iterations. The backtest_iteration column contains iteration identifier with the last training date as a suffix\n",
-        "- scores.csv contains all metrics. If data set contains several time series, the metrics are given for all combinations of time series id and iterations, as well as scores for all iterations and time series id are marked as \"all_sets\"\n",
-        "- plots_fcst_vs_actual.pdf contains the predictions vs forecast plots for each iteration and time series.\n",
-        "\n",
-        "For demonstration purposes we will display the table of metrics for one of the time series with ID \"ts0\". Again, we will create the utility function, which will be re used in model backtesting."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "def get_metrics_for_ts(all_metrics, ts):\n",
-        "    \"\"\"\n",
-        "    Get the metrics for the time series with ID ts and return it as pandas data frame.\n",
-        "\n",
-        "    :param all_metrics: The table with all the metrics.\n",
-        "    :param ts: The ID of a time series of interest.\n",
-        "    :return: The pandas DataFrame with metrics for one time series.\n",
-        "    \"\"\"\n",
-        "    results_df = None\n",
-        "    for ts_id, one_series in all_metrics.groupby(\"time_series_id\"):\n",
-        "        if not ts_id.startswith(ts):\n",
-        "            continue\n",
-        "        iteration = ts_id.split(\"|\")[-1]\n",
-        "        df = one_series[[\"metric_name\", \"metric\"]]\n",
-        "        df.rename({\"metric\": iteration}, axis=1, inplace=True)\n",
-        "        df.set_index(\"metric_name\", inplace=True)\n",
-        "        if results_df is None:\n",
-        "            results_df = df\n",
-        "        else:\n",
-        "            results_df = results_df.merge(\n",
-        "                df, how=\"inner\", left_index=True, right_index=True\n",
-        "            )\n",
-        "    results_df.sort_index(axis=1, inplace=True)\n",
-        "    return results_df\n",
-        "\n",
-        "\n",
-        "metrics_df = pd.read_csv(os.path.join(\"automl_backtest\", \"scores.csv\"))\n",
-        "ts_id = \"ts0\"\n",
-        "get_metrics_for_ts(metrics_df, ts_id)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Forecast vs actuals plots."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from IPython.display import IFrame\n",
-        "\n",
-        "IFrame(\"./automl_backtest/plots_fcst_vs_actual.pdf\", width=800, height=300)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# <font color='blue'>Backtest the best model</font> <a id=\"backtest_model\"></a>\n",
-        "\n",
-        "For model backtesting we will use the same parameters we used to backtest AutoML. All the models, we have obtained in the previous run were registered in our workspace. To identify the model, each was assigned a tag with the last trainig date."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "model_list = Model.list(ws, tags=[[\"experiment\", \"automl-backtesting\"]])\n",
-        "model_data = {\"name\": [], \"last_training_date\": []}\n",
-        "for model in model_list:\n",
-        "    if (\n",
-        "        \"last_training_date\" not in model.tags\n",
-        "        or \"model_uid\" not in model.tags\n",
-        "        or model.tags[\"model_uid\"] != model_uid\n",
-        "    ):\n",
-        "        continue\n",
-        "    model_data[\"name\"].append(model.name)\n",
-        "    model_data[\"last_training_date\"].append(\n",
-        "        pd.Timestamp(model.tags[\"last_training_date\"])\n",
-        "    )\n",
-        "df_models = pd.DataFrame(model_data)\n",
-        "df_models.sort_values([\"last_training_date\"], inplace=True)\n",
-        "df_models.reset_index(inplace=True, drop=True)\n",
-        "df_models"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "We will backtest the model trained on the most recet data."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "model_name = df_models[\"name\"].iloc[-1]\n",
-        "model_name"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Retrain the models.\n",
-        "Assemble the pipeline, which will retrain the best model from AutoML run on historical data."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "pipeline_exp = Experiment(ws, \"model-backtesting\")\n",
-        "\n",
-        "pipeline = get_backtest_pipeline(\n",
-        "    experiment=pipeline_exp,\n",
-        "    dataset=train_data,\n",
-        "    # The STANDARD_DS12_V2 has 4 vCPU per node, we will set 2 process per node to be safe.\n",
-        "    process_per_node=2,\n",
-        "    # The maximum number of nodes for our compute is 6.\n",
-        "    node_count=6,\n",
-        "    compute_target=compute_target,\n",
-        "    automl_settings=automl_settings,\n",
-        "    step_size=BACKTESTING_PERIOD,\n",
-        "    step_number=NUMBER_OF_BACKTESTS,\n",
-        "    model_name=model_name,\n",
-        "    forecast_quantiles=[0.025, 0.975],\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Launch the backtesting pipeline."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "pipeline_run = pipeline_exp.submit(pipeline)\n",
-        "pipeline_run.wait_for_completion(show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "The metrics are stored in the pipeline output named \"score\". The next code will download the table with metrics."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "metrics_output = pipeline_run.get_pipeline_output(\"results\")\n",
-        "metrics_output.download(\"backtest_metrics\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Again, we will copy the data files from the downloaded directory, but in this case we will call the folder \"model_backtest\"; it will contain the same files as the one for AutoML backtesting."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "copy_scoring_directory(\"model_backtest\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Finally, we will display the metrics."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "model_metrics_df = pd.read_csv(os.path.join(\"model_backtest\", \"scores.csv\"))\n",
-        "get_metrics_for_ts(model_metrics_df, ts_id)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Forecast vs actuals plots."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from IPython.display import IFrame\n",
-        "\n",
-        "IFrame(\"./model_backtest/plots_fcst_vs_actual.pdf\", width=800, height=300)"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "jialiu"
-      }
-    ],
-    "category": "tutorial",
-    "compute": [
-      "Remote"
-    ],
-    "datasets": [
-      "None"
-    ],
-    "deployment": [
-      "None"
-    ],
-    "exclude_from_index": false,
-    "framework": [
-      "Azure ML AutoML"
-    ],
-    "kernelspec": {
-      "display_name": "Python 3.8 - AzureML",
-      "language": "python",
-      "name": "python38-azureml"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.8.5"
-    },
-    "vscode": {
-      "interpreter": {
-        "hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
-      }
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 4
-}

how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/pipeline_helper.py

@@ -1,169 +0,0 @@
-from typing import Any, Dict, Optional
-
-import os
-
-import azureml.train.automl.runtime._hts.hts_runtime_utilities as hru
-
-from azureml._restclient.jasmine_client import JasmineClient
-from azureml.contrib.automl.pipeline.steps import utilities
-from azureml.core import RunConfiguration
-from azureml.core.compute import ComputeTarget
-from azureml.core.experiment import Experiment
-from azureml.data import LinkTabularOutputDatasetConfig, TabularDataset
-from azureml.pipeline.core import Pipeline, PipelineData, PipelineParameter
-from azureml.pipeline.steps import ParallelRunConfig, ParallelRunStep, PythonScriptStep
-from azureml.train.automl.constants import Scenarios
-from azureml.data.dataset_consumption_config import DatasetConsumptionConfig
-
-
-PROJECT_FOLDER = "assets"
-SETTINGS_FILE = "automl_settings.json"
-
-
-def get_backtest_pipeline(
-    experiment: Experiment,
-    dataset: TabularDataset,
-    process_per_node: int,
-    node_count: int,
-    compute_target: ComputeTarget,
-    automl_settings: Dict[str, Any],
-    step_size: int,
-    step_number: int,
-    model_name: Optional[str] = None,
-    model_uid: Optional[str] = None,
-    forecast_quantiles: Optional[list] = None,
-) -> Pipeline:
-    """
-    :param experiment: The experiment used to run the pipeline.
-    :param dataset: Tabular data set to be used for model training.
-    :param process_per_node: The number of processes per node. Generally it should be the number of cores
-                             on the node divided by two.
-    :param node_count: The number of nodes to be used.
-    :param compute_target: The compute target to be used to run the pipeline.
-    :param model_name: The name of a model to be back tested.
-    :param automl_settings: The dictionary with automl settings.
-    :param step_size: The number of periods to step back in backtesting.
-    :param step_number: The number of backtesting iterations.
-    :param model_uid: The uid to mark models from this run of the experiment.
-    :param forecast_quantiles: The forecast quantiles that are required in the inference.
-    :return: The pipeline to be used for model retraining.
-             **Note:** The output will be uploaded in the pipeline output
-             called 'score'.
-    """
-    jasmine_client = JasmineClient(
-        service_context=experiment.workspace.service_context,
-        experiment_name=experiment.name,
-        experiment_id=experiment.id,
-    )
-    env = jasmine_client.get_curated_environment(
-        scenario=Scenarios.AUTOML,
-        enable_dnn=False,
-        enable_gpu=False,
-        compute=compute_target,
-        compute_sku=experiment.workspace.compute_targets.get(
-            compute_target.name
-        ).vm_size,
-    )
-    data_results = PipelineData(
-        name="results", datastore=None, pipeline_output_name="results"
-    )
-    ############################################################
-    # Split the data set using python script.
-    ############################################################
-    run_config = RunConfiguration()
-    run_config.docker.use_docker = True
-    run_config.environment = env
-
-    utilities.set_environment_variables_for_run(run_config)
-
-    split_data = PipelineData(name="split_data_output", datastore=None).as_dataset()
-    split_step = PythonScriptStep(
-        name="split_data_for_backtest",
-        script_name="data_split.py",
-        inputs=[dataset.as_named_input("training_data")],
-        outputs=[split_data],
-        source_directory=PROJECT_FOLDER,
-        arguments=[
-            "--step-size",
-            step_size,
-            "--step-number",
-            step_number,
-            "--time-column-name",
-            automl_settings.get("time_column_name"),
-            "--time-series-id-column-names",
-            automl_settings.get("grain_column_names"),
-            "--output-dir",
-            split_data,
-        ],
-        runconfig=run_config,
-        compute_target=compute_target,
-        allow_reuse=False,
-    )
-    ############################################################
-    # We will do the backtest the parallel run step.
-    ############################################################
-    settings_path = os.path.join(PROJECT_FOLDER, SETTINGS_FILE)
-    hru.dump_object_to_json(automl_settings, settings_path)
-    mini_batch_size = PipelineParameter(name="batch_size_param", default_value=str(1))
-    back_test_config = ParallelRunConfig(
-        source_directory=PROJECT_FOLDER,
-        entry_script="retrain_models.py",
-        mini_batch_size=mini_batch_size,
-        error_threshold=-1,
-        output_action="append_row",
-        append_row_file_name="outputs.txt",
-        compute_target=compute_target,
-        environment=env,
-        process_count_per_node=process_per_node,
-        run_invocation_timeout=3600,
-        node_count=node_count,
-    )
-    utilities.set_environment_variables_for_run(back_test_config)
-    forecasts = PipelineData(name="forecasts", datastore=None)
-    if model_name:
-        parallel_step_name = "{}-backtest".format(model_name.replace("_", "-"))
-    else:
-        parallel_step_name = "AutoML-backtest"
-
-    prs_args = [
-        "--target_column_name",
-        automl_settings.get("label_column_name"),
-        "--output-dir",
-        forecasts,
-    ]
-    if model_name is not None:
-        prs_args.append("--model-name")
-        prs_args.append(model_name)
-    if model_uid is not None:
-        prs_args.append("--model-uid")
-        prs_args.append(model_uid)
-    if forecast_quantiles:
-        prs_args.append("--forecast_quantiles")
-        prs_args.extend(forecast_quantiles)
-    backtest_prs = ParallelRunStep(
-        name=parallel_step_name,
-        parallel_run_config=back_test_config,
-        arguments=prs_args,
-        inputs=[split_data],
-        output=forecasts,
-        allow_reuse=False,
-    )
-    ############################################################
-    # Then we collect the output and return it as scores output.
-    ############################################################
-    collection_step = PythonScriptStep(
-        name="score",
-        script_name="score.py",
-        inputs=[forecasts.as_mount()],
-        outputs=[data_results],
-        source_directory=PROJECT_FOLDER,
-        arguments=["--forecasts", forecasts, "--output-dir", data_results],
-        runconfig=run_config,
-        compute_target=compute_target,
-        allow_reuse=False,
-    )
-    # Build and return the pipeline.
-    return Pipeline(
-        workspace=experiment.workspace,
-        steps=[split_step, backtest_prs, collection_step],
-    )

how-to-use-azureml/automated-machine-learning/forecasting-bike-share/auto-ml-forecasting-bike-share.ipynb

@@ -1,828 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/forecasting-bike-share/auto-ml-forecasting-bike-share.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<font color=\"red\" size=\"5\"><strong>!Important!</strong> </br>This notebook is outdated and is not supported by the AutoML Team. Please use the supported version ([link](https://github.com/Azure/azureml-examples/tree/main/sdk/python/jobs/automl-standalone-jobs/automl-forecasting-task-bike-share)).</font>"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Automated Machine Learning\n",
-        "**BikeShare Demand Forecasting**\n",
-        "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Compute](#Compute)\n",
-        "1. [Data](#Data)\n",
-        "1. [Train](#Train)\n",
-        "1. [Featurization](#Featurization)\n",
-        "1. [Evaluate](#Evaluate)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
-        "This notebook demonstrates demand forecasting for a bike-sharing service using AutoML.\n",
-        "\n",
-        "AutoML highlights here include built-in holiday featurization, accessing engineered feature names, and working with the `forecast` function. Please also look at the additional forecasting notebooks, which document lagging, rolling windows, forecast quantiles, other ways to use the forecast function, and forecaster deployment.\n",
-        "\n",
-        "Make sure you have executed the [configuration notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/configuration.ipynb) before running this notebook.\n",
-        "\n",
-        "Notebook synopsis:\n",
-        "1. Creating an Experiment in an existing Workspace\n",
-        "2. Configuration and local run of AutoML for a time-series model with lag and holiday features \n",
-        "3. Viewing the engineered names for featurized data and featurization summary for all raw features\n",
-        "4. Evaluating the fitted model using a rolling test "
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Setup\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "gather": {
-          "logged": 1680248038565
-        }
-      },
-      "outputs": [],
-      "source": [
-        "import json\n",
-        "import logging\n",
-        "from datetime import datetime\n",
-        "\n",
-        "import azureml.core\n",
-        "import numpy as np\n",
-        "import pandas as pd\n",
-        "from azureml.automl.core.featurization import FeaturizationConfig\n",
-        "from azureml.core import Dataset, Experiment, Workspace\n",
-        "from azureml.train.automl import AutoMLConfig"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "This notebook is compatible with Azure ML SDK version 1.35.0 or later."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "As part of the setup you have already created a <b>Workspace</b>. To run AutoML, you also need to create an <b>Experiment</b>. An Experiment corresponds to a prediction problem you are trying to solve, while a Run corresponds to a specific approach to the problem."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ws = Workspace.from_config()\n",
-        "\n",
-        "# choose a name for the run history container in the workspace\n",
-        "experiment_name = \"automl-bikeshareforecasting\"\n",
-        "\n",
-        "experiment = Experiment(ws, experiment_name)\n",
-        "\n",
-        "output = {}\n",
-        "output[\"Subscription ID\"] = ws.subscription_id\n",
-        "output[\"Workspace\"] = ws.name\n",
-        "output[\"SKU\"] = ws.sku\n",
-        "output[\"Resource Group\"] = ws.resource_group\n",
-        "output[\"Location\"] = ws.location\n",
-        "output[\"Run History Name\"] = experiment_name\n",
-        "output[\"SDK Version\"] = azureml.core.VERSION\n",
-        "pd.set_option(\"display.max_colwidth\", None)\n",
-        "outputDf = pd.DataFrame(data=output, index=[\"\"])\n",
-        "outputDf.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Compute\n",
-        "You will need to create a [compute target](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-set-up-training-targets#amlcompute) for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
-        "\n",
-        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
-        "\n",
-        "#### Creation of AmlCompute takes approximately 5 minutes. \n",
-        "If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
-        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
-        "from azureml.core.compute_target import ComputeTargetException\n",
-        "\n",
-        "# Choose a name for your cluster.\n",
-        "amlcompute_cluster_name = \"bike-cluster\"\n",
-        "\n",
-        "# Verify that cluster does not exist already\n",
-        "try:\n",
-        "    compute_target = ComputeTarget(workspace=ws, name=amlcompute_cluster_name)\n",
-        "    print(\"Found existing cluster, use it.\")\n",
-        "except ComputeTargetException:\n",
-        "    compute_config = AmlCompute.provisioning_configuration(\n",
-        "        vm_size=\"STANDARD_DS12_V2\", max_nodes=4\n",
-        "    )\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, compute_config)\n",
-        "\n",
-        "compute_target.wait_for_completion(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Data\n",
-        "\n",
-        "Let's set up what we know about the dataset. \n",
-        "\n",
-        "**Target column** is what we want to forecast.\n",
-        "\n",
-        "**Time column** is the time axis along which to predict."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "target_column_name = \"cnt\"\n",
-        "time_column_name = \"date\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "nteract": {
-          "transient": {
-            "deleting": false
-          }
-        }
-      },
-      "source": [
-        "You are now ready to load the historical bike share data. We will load the CSV file into a plain pandas DataFrame."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "jupyter": {
-          "outputs_hidden": false,
-          "source_hidden": false
-        },
-        "nteract": {
-          "transient": {
-            "deleting": false
-          }
-        }
-      },
-      "outputs": [],
-      "source": [
-        "all_data = pd.read_csv(\"bike-no.csv\", parse_dates=[time_column_name])\n",
-        "\n",
-        "# Drop the columns 'casual' and 'registered' as these columns are a breakdown of the total and therefore a leak.\n",
-        "all_data.drop([\"casual\", \"registered\"], axis=1, inplace=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "nteract": {
-          "transient": {
-            "deleting": false
-          }
-        }
-      },
-      "source": [
-        "### Split the data\n",
-        "\n",
-        "The first split we make is into train and test sets. Note we are splitting on time. Data before 9/1 will be used for training, and data after and including 9/1 will be used for testing."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "gather": {
-          "logged": 1680247376789
-        },
-        "jupyter": {
-          "outputs_hidden": false,
-          "source_hidden": false
-        },
-        "nteract": {
-          "transient": {
-            "deleting": false
-          }
-        }
-      },
-      "outputs": [],
-      "source": [
-        "# select data that occurs before a specified date\n",
-        "train = all_data[all_data[time_column_name] <= pd.Timestamp(\"2012-08-31\")].copy()\n",
-        "test = all_data[all_data[time_column_name] >= pd.Timestamp(\"2012-09-01\")].copy()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Upload data to datastore\n",
-        "\n",
-        "The [Machine Learning service workspace](https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-workspace) is paired with the storage account, which contains the default data store. We will use it to upload the bike share data and create [tabular dataset](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.tabulardataset?view=azure-ml-py) for training. A tabular dataset defines a series of lazily-evaluated, immutable operations to load data from the data source into tabular representation."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "jupyter": {
-          "outputs_hidden": false,
-          "source_hidden": false
-        },
-        "nteract": {
-          "transient": {
-            "deleting": false
-          }
-        }
-      },
-      "outputs": [],
-      "source": [
-        "from azureml.data.dataset_factory import TabularDatasetFactory\n",
-        "\n",
-        "datastore = ws.get_default_datastore()\n",
-        "\n",
-        "train_dataset = TabularDatasetFactory.register_pandas_dataframe(\n",
-        "    train, target=(datastore, \"dataset/\"), name=\"bike_no_train\"\n",
-        ")\n",
-        "\n",
-        "test_dataset = TabularDatasetFactory.register_pandas_dataframe(\n",
-        "    test, target=(datastore, \"dataset/\"), name=\"bike_no_test\"\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Forecasting Parameters\n",
-        "To define forecasting parameters for your experiment training, you can leverage the ForecastingParameters class. The table below details the forecasting parameter we will be passing into our experiment.\n",
-        "\n",
-        "|Property|Description|\n",
-        "|-|-|\n",
-        "|**time_column_name**|The name of your time column.|\n",
-        "|**forecast_horizon**|The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly).|\n",
-        "|**country_or_region_for_holidays**|The country/region used to generate holiday features. These should be ISO 3166 two-letter country/region codes (i.e. 'US', 'GB').|\n",
-        "|**target_lags**|The target_lags specifies how far back we will construct the lags of the target variable.|\n",
-        "|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information.\n",
-        "|**cv_step_size**|Number of periods between two consecutive cross-validation folds. The default value is \"auto\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Train\n",
-        "\n",
-        "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
-        "\n",
-        "|Property|Description|\n",
-        "|-|-|\n",
-        "|**task**|forecasting|\n",
-        "|**primary_metric**|This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>\n",
-        "|**blocked_models**|Models in blocked_models won't be used by AutoML. All supported models can be found at [here](https://docs.microsoft.com/en-us/python/api/azureml-train-automl-client/azureml.train.automl.constants.supportedmodels.forecasting?view=azure-ml-py).|\n",
-        "|**experiment_timeout_hours**|Experimentation timeout in hours.|\n",
-        "|**training_data**|Input dataset, containing both features and label column.|\n",
-        "|**label_column_name**|The name of the label column.|\n",
-        "|**compute_target**|The remote compute for training.|\n",
-        "|**n_cross_validations**|Number of cross-validation folds to use for model/pipeline selection. The default value is \"auto\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value.\n",
-        "|**enable_early_stopping**|If early stopping is on, training will stop when the primary metric is no longer improving.|\n",
-        "|**forecasting_parameters**|A class that holds all the forecasting related parameters.|\n",
-        "\n",
-        "This notebook uses the blocked_models parameter to exclude some models that take a longer time to train on this dataset. You can choose to remove models from the blocked_models list but you may need to increase the experiment_timeout_hours parameter value to get results."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Setting forecaster maximum horizon \n",
-        "\n",
-        "The forecast horizon is the number of periods into the future that the model should predict. Here, we set the horizon to 14 periods (i.e. 14 days). Notice that this is much shorter than the number of days in the test set; we will need to use a rolling test to evaluate the performance on the whole test set. For more discussion of forecast horizons and guiding principles for setting them, please see the [energy demand notebook](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand).  "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "forecast_horizon = 14"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Convert prediction type to integer\n",
-        "The featurization configuration can be used to change the default prediction type from decimal numbers to integer. This customization can be used in the scenario when the target column is expected to contain whole values as the number of rented bikes per day."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "featurization_config = FeaturizationConfig()\n",
-        "# Force the target column, to be integer type.\n",
-        "featurization_config.add_prediction_transform_type(\"Integer\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Config AutoML"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.automl.core.forecasting_parameters import ForecastingParameters\n",
-        "\n",
-        "forecasting_parameters = ForecastingParameters(\n",
-        "    time_column_name=time_column_name,\n",
-        "    forecast_horizon=forecast_horizon,\n",
-        "    country_or_region_for_holidays=\"US\",  # set country_or_region will trigger holiday featurizer\n",
-        "    target_lags=\"auto\",  # use heuristic based lag setting\n",
-        "    freq=\"D\",  # Set the forecast frequency to be daily\n",
-        "    cv_step_size=\"auto\",\n",
-        ")\n",
-        "\n",
-        "automl_config = AutoMLConfig(\n",
-        "    task=\"forecasting\",\n",
-        "    primary_metric=\"normalized_root_mean_squared_error\",\n",
-        "    featurization=featurization_config,\n",
-        "    blocked_models=[\"ExtremeRandomTrees\"],\n",
-        "    experiment_timeout_hours=0.3,\n",
-        "    training_data=train_dataset,\n",
-        "    label_column_name=target_column_name,\n",
-        "    compute_target=compute_target,\n",
-        "    enable_early_stopping=True,\n",
-        "    n_cross_validations=\"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
-        "    max_concurrent_iterations=4,\n",
-        "    max_cores_per_iteration=-1,\n",
-        "    verbosity=logging.INFO,\n",
-        "    forecasting_parameters=forecasting_parameters,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "We will now run the experiment, you can go to Azure ML portal to view the run details. "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run = experiment.submit(automl_config, show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run.wait_for_completion()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Retrieve the Best Run details\n",
-        "Below we retrieve the best Run object from among all the runs in the experiment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "best_run = remote_run.get_best_child()\n",
-        "best_run"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Featurization\n",
-        "\n",
-        "We can look at the engineered feature names generated in time-series featurization via. the JSON file named 'engineered_feature_names.json' under the run outputs. Note that a number of named holiday periods are represented. We recommend that you have at least one year of data when using this feature to ensure that all yearly holidays are captured in the training featurization."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Download the JSON file locally\n",
-        "best_run.download_file(\n",
-        "    \"outputs/engineered_feature_names.json\", \"engineered_feature_names.json\"\n",
-        ")\n",
-        "with open(\"engineered_feature_names.json\", \"r\") as f:\n",
-        "    records = json.load(f)\n",
-        "\n",
-        "records"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### View the featurization summary\n",
-        "\n",
-        "You can also see what featurization steps were performed on different raw features in the user data. For each raw feature in the user data, the following information is displayed:\n",
-        "\n",
-        "- Raw feature name\n",
-        "- Number of engineered features formed out of this raw feature\n",
-        "- Type detected\n",
-        "- If feature was dropped\n",
-        "- List of feature transformations for the raw feature"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Download the featurization summary JSON file locally\n",
-        "best_run.download_file(\n",
-        "    \"outputs/featurization_summary.json\", \"featurization_summary.json\"\n",
-        ")\n",
-        "\n",
-        "# Render the JSON as a pandas DataFrame\n",
-        "with open(\"featurization_summary.json\", \"r\") as f:\n",
-        "    records = json.load(f)\n",
-        "fs = pd.DataFrame.from_records(records)\n",
-        "\n",
-        "# View a summary of the featurization\n",
-        "fs[\n",
-        "    [\n",
-        "        \"RawFeatureName\",\n",
-        "        \"TypeDetected\",\n",
-        "        \"Dropped\",\n",
-        "        \"EngineeredFeatureCount\",\n",
-        "        \"Transformations\",\n",
-        "    ]\n",
-        "]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Evaluate"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "We now use the best fitted model from the AutoML Run to make forecasts for the test set. We will do batch scoring on the test dataset which should have the same schema as training dataset.\n",
-        "\n",
-        "The scoring will run on a remote compute. In this example, it will reuse the training compute."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "test_experiment = Experiment(ws, experiment_name + \"_test\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Retrieving forecasts from the model\n",
-        "To run the forecast on the remote compute we will use a helper script: forecasting_script. This script contains the utility methods which will be used by the remote estimator. We copy the script to the project folder to upload it to remote compute."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "import shutil\n",
-        "\n",
-        "script_folder = os.path.join(os.getcwd(), \"forecast\")\n",
-        "os.makedirs(script_folder, exist_ok=True)\n",
-        "shutil.copy(\"forecasting_script.py\", script_folder)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "For brevity, we have created a function called run_forecast that submits the test data to the best model determined during the training run and retrieves forecasts. The test set is longer than the forecast horizon specified at train time, so the forecasting script uses a so-called rolling evaluation to generate predictions over the whole test set. A rolling evaluation iterates the forecaster over the test set, using the actuals in the test set to make lag features as needed. "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from run_forecast import run_rolling_forecast\n",
-        "\n",
-        "remote_run = run_rolling_forecast(\n",
-        "    test_experiment, compute_target, best_run, test_dataset, target_column_name\n",
-        ")\n",
-        "remote_run"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run.wait_for_completion(show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Download the prediction result for metrics calculation\n",
-        "The test data with predictions are saved in artifact outputs/predictions.csv. You can download it and calculation some error metrics for the forecasts and vizualize the predictions vs. the actuals."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run.download_file(\"outputs/predictions.csv\", \"predictions.csv\")\n",
-        "fcst_df = pd.read_csv(\"predictions.csv\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Note that the rolling forecast can contain multiple predictions for each date, each from a different forecast origin. For example, consider 2012-09-05:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "fcst_df[fcst_df.date == \"2012-09-05\"]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Here, the forecast origin refers to the latest date of actuals available for a given forecast. The earliest origin in the rolling forecast, 2012-08-31, is the last day in the training data. For origin date 2012-09-01, the forecasts use actual recorded counts from the training data *and* the actual count recorded on 2012-09-01. Note that the model is not retrained for origin dates later than 2012-08-31, but the values for model features, such as lagged values of daily count, are updated.\n",
-        "\n",
-        "Let's calculate the metrics over all rolling forecasts:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.automl.core.shared import constants\n",
-        "from azureml.automl.runtime.shared.score import scoring\n",
-        "from sklearn.metrics import mean_absolute_error, mean_squared_error\n",
-        "\n",
-        "# use automl metrics module\n",
-        "scores = scoring.score_regression(\n",
-        "    y_test=fcst_df[target_column_name],\n",
-        "    y_pred=fcst_df[\"predicted\"],\n",
-        "    metrics=list(constants.Metric.SCALAR_REGRESSION_SET),\n",
-        ")\n",
-        "\n",
-        "print(\"[Test data scores]\\n\")\n",
-        "for key, value in scores.items():\n",
-        "    print(\"{}:   {:.3f}\".format(key, value))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "For more details on what metrics are included and how they are calculated, please refer to [supported metrics](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#regressionforecasting-metrics). You could also calculate residuals, like described [here](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#residuals).\n",
-        "\n",
-        "The rolling forecast metric values are very high in comparison to the validation metrics reported by the AutoML job. What's going on here? We will investigate in the following cells!"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Forecast versus actuals plot\n",
-        "We will plot predictions and actuals on a time series plot. Since there are many forecasts for each date, we select the 14-day-ahead forecast from each forecast origin for our comparison."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from matplotlib import pyplot as plt\n",
-        "\n",
-        "%matplotlib inline\n",
-        "\n",
-        "fcst_df_h14 = (\n",
-        "    fcst_df.groupby(\"forecast_origin\", as_index=False)\n",
-        "    .last()\n",
-        "    .drop(columns=[\"forecast_origin\"])\n",
-        ")\n",
-        "fcst_df_h14.set_index(time_column_name, inplace=True)\n",
-        "plt.plot(fcst_df_h14[[target_column_name, \"predicted\"]])\n",
-        "plt.xticks(rotation=45)\n",
-        "plt.title(f\"Predicted vs. Actuals\")\n",
-        "plt.legend([\"actual\", \"14-day-ahead forecast\"])\n",
-        "plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Looking at the plot, there are two clear issues:\n",
-        "1. An anomalously low count value on October 29th, 2012.\n",
-        "2. End-of-year holidays (Thanksgiving and Christmas) in late November and late December.\n",
-        "\n",
-        "What happened on Oct. 29th, 2012? That day, Hurricane Sandy brought severe storm surge flooding to the east coast of the United States, particularly around New York City. This is certainly an anomalous event that the model did not account for!\n",
-        "\n",
-        "As for the late year holidays, the model apparently did not learn to account for the full reduction of bike share rentals on these major holidays. The training data covers 2011 and early 2012, so the model fit only had access to a single occurrence of these holidays. This makes it challenging to resolve holiday effects; however, a larger AutoML model search may result in a better model that is more holiday-aware.\n",
-        "\n",
-        "If we filter the predictions prior to the Thanksgiving holiday and remove the anomalous day of 2012-10-29, the metrics are closer to validation levels:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "date_filter = (fcst_df.date != \"2012-10-29\") & (fcst_df.date < \"2012-11-22\")\n",
-        "scores = scoring.score_regression(\n",
-        "    y_test=fcst_df[date_filter][target_column_name],\n",
-        "    y_pred=fcst_df[date_filter][\"predicted\"],\n",
-        "    metrics=list(constants.Metric.SCALAR_REGRESSION_SET),\n",
-        ")\n",
-        "\n",
-        "print(\"[Test data scores (filtered)]\\n\")\n",
-        "for key, value in scores.items():\n",
-        "    print(\"{}:   {:.3f}\".format(key, value))"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "jialiu"
-      }
-    ],
-    "category": "tutorial",
-    "compute": [
-      "Remote"
-    ],
-    "datasets": [
-      "BikeShare"
-    ],
-    "deployment": [
-      "None"
-    ],
-    "exclude_from_index": false,
-    "file_extension": ".py",
-    "framework": [
-      "Azure ML AutoML"
-    ],
-    "friendly_name": "Forecasting BikeShare Demand",
-    "index_order": 1,
-    "kernel_info": {
-      "name": "python38-azureml"
-    },
-    "kernelspec": {
-      "display_name": "Python 3.8 - AzureML",
-      "language": "python",
-      "name": "python38-azureml"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.8.10"
-    },
-    "microsoft": {
-      "ms_spell_check": {
-        "ms_spell_check_language": "en"
-      }
-    },
-    "mimetype": "text/x-python",
-    "name": "python",
-    "npconvert_exporter": "python",
-    "nteract": {
-      "version": "nteract-front-end@1.0.0"
-    },
-    "pygments_lexer": "ipython3",
-    "tags": [
-      "Forecasting"
-    ],
-    "task": "Forecasting",
-    "version": 3,
-    "vscode": {
-      "interpreter": {
-        "hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
-      }
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 4
-}

how-to-use-azureml/automated-machine-learning/forecasting-bike-share/bike-no.csv

@@ -1,732 +0,0 @@
-instant,date,season,yr,mnth,weekday,weathersit,temp,atemp,hum,windspeed,casual,registered,cnt
-1,1/1/2011,1,0,1,6,2,0.344167,0.363625,0.805833,0.160446,331,654,985
-2,1/2/2011,1,0,1,0,2,0.363478,0.353739,0.696087,0.248539,131,670,801
-3,1/3/2011,1,0,1,1,1,0.196364,0.189405,0.437273,0.248309,120,1229,1349
-4,1/4/2011,1,0,1,2,1,0.2,0.212122,0.590435,0.160296,108,1454,1562
-5,1/5/2011,1,0,1,3,1,0.226957,0.22927,0.436957,0.1869,82,1518,1600
-6,1/6/2011,1,0,1,4,1,0.204348,0.233209,0.518261,0.0895652,88,1518,1606
-7,1/7/2011,1,0,1,5,2,0.196522,0.208839,0.498696,0.168726,148,1362,1510
-8,1/8/2011,1,0,1,6,2,0.165,0.162254,0.535833,0.266804,68,891,959
-9,1/9/2011,1,0,1,0,1,0.138333,0.116175,0.434167,0.36195,54,768,822
-10,1/10/2011,1,0,1,1,1,0.150833,0.150888,0.482917,0.223267,41,1280,1321
-11,1/11/2011,1,0,1,2,2,0.169091,0.191464,0.686364,0.122132,43,1220,1263
-12,1/12/2011,1,0,1,3,1,0.172727,0.160473,0.599545,0.304627,25,1137,1162
-13,1/13/2011,1,0,1,4,1,0.165,0.150883,0.470417,0.301,38,1368,1406
-14,1/14/2011,1,0,1,5,1,0.16087,0.188413,0.537826,0.126548,54,1367,1421
-15,1/15/2011,1,0,1,6,2,0.233333,0.248112,0.49875,0.157963,222,1026,1248
-16,1/16/2011,1,0,1,0,1,0.231667,0.234217,0.48375,0.188433,251,953,1204
-17,1/17/2011,1,0,1,1,2,0.175833,0.176771,0.5375,0.194017,117,883,1000
-18,1/18/2011,1,0,1,2,2,0.216667,0.232333,0.861667,0.146775,9,674,683
-19,1/19/2011,1,0,1,3,2,0.292174,0.298422,0.741739,0.208317,78,1572,1650
-20,1/20/2011,1,0,1,4,2,0.261667,0.25505,0.538333,0.195904,83,1844,1927
-21,1/21/2011,1,0,1,5,1,0.1775,0.157833,0.457083,0.353242,75,1468,1543
-22,1/22/2011,1,0,1,6,1,0.0591304,0.0790696,0.4,0.17197,93,888,981
-23,1/23/2011,1,0,1,0,1,0.0965217,0.0988391,0.436522,0.2466,150,836,986
-24,1/24/2011,1,0,1,1,1,0.0973913,0.11793,0.491739,0.15833,86,1330,1416
-25,1/25/2011,1,0,1,2,2,0.223478,0.234526,0.616957,0.129796,186,1799,1985
-26,1/26/2011,1,0,1,3,3,0.2175,0.2036,0.8625,0.29385,34,472,506
-27,1/27/2011,1,0,1,4,1,0.195,0.2197,0.6875,0.113837,15,416,431
-28,1/28/2011,1,0,1,5,2,0.203478,0.223317,0.793043,0.1233,38,1129,1167
-29,1/29/2011,1,0,1,6,1,0.196522,0.212126,0.651739,0.145365,123,975,1098
-30,1/30/2011,1,0,1,0,1,0.216522,0.250322,0.722174,0.0739826,140,956,1096
-31,1/31/2011,1,0,1,1,2,0.180833,0.18625,0.60375,0.187192,42,1459,1501
-32,2/1/2011,1,0,2,2,2,0.192174,0.23453,0.829565,0.053213,47,1313,1360
-33,2/2/2011,1,0,2,3,2,0.26,0.254417,0.775417,0.264308,72,1454,1526
-34,2/3/2011,1,0,2,4,1,0.186957,0.177878,0.437826,0.277752,61,1489,1550
-35,2/4/2011,1,0,2,5,2,0.211304,0.228587,0.585217,0.127839,88,1620,1708
-36,2/5/2011,1,0,2,6,2,0.233333,0.243058,0.929167,0.161079,100,905,1005
-37,2/6/2011,1,0,2,0,1,0.285833,0.291671,0.568333,0.1418,354,1269,1623
-38,2/7/2011,1,0,2,1,1,0.271667,0.303658,0.738333,0.0454083,120,1592,1712
-39,2/8/2011,1,0,2,2,1,0.220833,0.198246,0.537917,0.36195,64,1466,1530
-40,2/9/2011,1,0,2,3,2,0.134783,0.144283,0.494783,0.188839,53,1552,1605
-41,2/10/2011,1,0,2,4,1,0.144348,0.149548,0.437391,0.221935,47,1491,1538
-42,2/11/2011,1,0,2,5,1,0.189091,0.213509,0.506364,0.10855,149,1597,1746
-43,2/12/2011,1,0,2,6,1,0.2225,0.232954,0.544167,0.203367,288,1184,1472
-44,2/13/2011,1,0,2,0,1,0.316522,0.324113,0.457391,0.260883,397,1192,1589
-45,2/14/2011,1,0,2,1,1,0.415,0.39835,0.375833,0.417908,208,1705,1913
-46,2/15/2011,1,0,2,2,1,0.266087,0.254274,0.314348,0.291374,140,1675,1815
-47,2/16/2011,1,0,2,3,1,0.318261,0.3162,0.423478,0.251791,218,1897,2115
-48,2/17/2011,1,0,2,4,1,0.435833,0.428658,0.505,0.230104,259,2216,2475
-49,2/18/2011,1,0,2,5,1,0.521667,0.511983,0.516667,0.264925,579,2348,2927
-50,2/19/2011,1,0,2,6,1,0.399167,0.391404,0.187917,0.507463,532,1103,1635
-51,2/20/2011,1,0,2,0,1,0.285217,0.27733,0.407826,0.223235,639,1173,1812
-52,2/21/2011,1,0,2,1,2,0.303333,0.284075,0.605,0.307846,195,912,1107
-53,2/22/2011,1,0,2,2,1,0.182222,0.186033,0.577778,0.195683,74,1376,1450
-54,2/23/2011,1,0,2,3,1,0.221739,0.245717,0.423043,0.094113,139,1778,1917
-55,2/24/2011,1,0,2,4,2,0.295652,0.289191,0.697391,0.250496,100,1707,1807
-56,2/25/2011,1,0,2,5,2,0.364348,0.350461,0.712174,0.346539,120,1341,1461
-57,2/26/2011,1,0,2,6,1,0.2825,0.282192,0.537917,0.186571,424,1545,1969
-58,2/27/2011,1,0,2,0,1,0.343478,0.351109,0.68,0.125248,694,1708,2402
-59,2/28/2011,1,0,2,1,2,0.407273,0.400118,0.876364,0.289686,81,1365,1446
-60,3/1/2011,1,0,3,2,1,0.266667,0.263879,0.535,0.216425,137,1714,1851
-61,3/2/2011,1,0,3,3,1,0.335,0.320071,0.449583,0.307833,231,1903,2134
-62,3/3/2011,1,0,3,4,1,0.198333,0.200133,0.318333,0.225754,123,1562,1685
-63,3/4/2011,1,0,3,5,2,0.261667,0.255679,0.610417,0.203346,214,1730,1944
-64,3/5/2011,1,0,3,6,2,0.384167,0.378779,0.789167,0.251871,640,1437,2077
-65,3/6/2011,1,0,3,0,2,0.376522,0.366252,0.948261,0.343287,114,491,605
-66,3/7/2011,1,0,3,1,1,0.261739,0.238461,0.551304,0.341352,244,1628,1872
-67,3/8/2011,1,0,3,2,1,0.2925,0.3024,0.420833,0.12065,316,1817,2133
-68,3/9/2011,1,0,3,3,2,0.295833,0.286608,0.775417,0.22015,191,1700,1891
-69,3/10/2011,1,0,3,4,3,0.389091,0.385668,0,0.261877,46,577,623
-70,3/11/2011,1,0,3,5,2,0.316522,0.305,0.649565,0.23297,247,1730,1977
-71,3/12/2011,1,0,3,6,1,0.329167,0.32575,0.594583,0.220775,724,1408,2132
-72,3/13/2011,1,0,3,0,1,0.384348,0.380091,0.527391,0.270604,982,1435,2417
-73,3/14/2011,1,0,3,1,1,0.325217,0.332,0.496957,0.136926,359,1687,2046
-74,3/15/2011,1,0,3,2,2,0.317391,0.318178,0.655652,0.184309,289,1767,2056
-75,3/16/2011,1,0,3,3,2,0.365217,0.36693,0.776522,0.203117,321,1871,2192
-76,3/17/2011,1,0,3,4,1,0.415,0.410333,0.602917,0.209579,424,2320,2744
-77,3/18/2011,1,0,3,5,1,0.54,0.527009,0.525217,0.231017,884,2355,3239
-78,3/19/2011,1,0,3,6,1,0.4725,0.466525,0.379167,0.368167,1424,1693,3117
-79,3/20/2011,1,0,3,0,1,0.3325,0.32575,0.47375,0.207721,1047,1424,2471
-80,3/21/2011,2,0,3,1,2,0.430435,0.409735,0.737391,0.288783,401,1676,2077
-81,3/22/2011,2,0,3,2,1,0.441667,0.440642,0.624583,0.22575,460,2243,2703
-82,3/23/2011,2,0,3,3,2,0.346957,0.337939,0.839565,0.234261,203,1918,2121
-83,3/24/2011,2,0,3,4,2,0.285,0.270833,0.805833,0.243787,166,1699,1865
-84,3/25/2011,2,0,3,5,1,0.264167,0.256312,0.495,0.230725,300,1910,2210
-85,3/26/2011,2,0,3,6,1,0.265833,0.257571,0.394167,0.209571,981,1515,2496
-86,3/27/2011,2,0,3,0,2,0.253043,0.250339,0.493913,0.1843,472,1221,1693
-87,3/28/2011,2,0,3,1,1,0.264348,0.257574,0.302174,0.212204,222,1806,2028
-88,3/29/2011,2,0,3,2,1,0.3025,0.292908,0.314167,0.226996,317,2108,2425
-89,3/30/2011,2,0,3,3,2,0.3,0.29735,0.646667,0.172888,168,1368,1536
-90,3/31/2011,2,0,3,4,3,0.268333,0.257575,0.918333,0.217646,179,1506,1685
-91,4/1/2011,2,0,4,5,2,0.3,0.283454,0.68625,0.258708,307,1920,2227
-92,4/2/2011,2,0,4,6,2,0.315,0.315637,0.65375,0.197146,898,1354,2252
-93,4/3/2011,2,0,4,0,1,0.378333,0.378767,0.48,0.182213,1651,1598,3249
-94,4/4/2011,2,0,4,1,1,0.573333,0.542929,0.42625,0.385571,734,2381,3115
-95,4/5/2011,2,0,4,2,2,0.414167,0.39835,0.642083,0.388067,167,1628,1795
-96,4/6/2011,2,0,4,3,1,0.390833,0.387608,0.470833,0.263063,413,2395,2808
-97,4/7/2011,2,0,4,4,1,0.4375,0.433696,0.602917,0.162312,571,2570,3141
-98,4/8/2011,2,0,4,5,2,0.335833,0.324479,0.83625,0.226992,172,1299,1471
-99,4/9/2011,2,0,4,6,2,0.3425,0.341529,0.8775,0.133083,879,1576,2455
-100,4/10/2011,2,0,4,0,2,0.426667,0.426737,0.8575,0.146767,1188,1707,2895
-101,4/11/2011,2,0,4,1,2,0.595652,0.565217,0.716956,0.324474,855,2493,3348
-102,4/12/2011,2,0,4,2,2,0.5025,0.493054,0.739167,0.274879,257,1777,2034
-103,4/13/2011,2,0,4,3,2,0.4125,0.417283,0.819167,0.250617,209,1953,2162
-104,4/14/2011,2,0,4,4,1,0.4675,0.462742,0.540417,0.1107,529,2738,3267
-105,4/15/2011,2,0,4,5,1,0.446667,0.441913,0.67125,0.226375,642,2484,3126
-106,4/16/2011,2,0,4,6,3,0.430833,0.425492,0.888333,0.340808,121,674,795
-107,4/17/2011,2,0,4,0,1,0.456667,0.445696,0.479583,0.303496,1558,2186,3744
-108,4/18/2011,2,0,4,1,1,0.5125,0.503146,0.5425,0.163567,669,2760,3429
-109,4/19/2011,2,0,4,2,2,0.505833,0.489258,0.665833,0.157971,409,2795,3204
-110,4/20/2011,2,0,4,3,1,0.595,0.564392,0.614167,0.241925,613,3331,3944
-111,4/21/2011,2,0,4,4,1,0.459167,0.453892,0.407083,0.325258,745,3444,4189
-112,4/22/2011,2,0,4,5,2,0.336667,0.321954,0.729583,0.219521,177,1506,1683
-113,4/23/2011,2,0,4,6,2,0.46,0.450121,0.887917,0.230725,1462,2574,4036
-114,4/24/2011,2,0,4,0,2,0.581667,0.551763,0.810833,0.192175,1710,2481,4191
-115,4/25/2011,2,0,4,1,1,0.606667,0.5745,0.776667,0.185333,773,3300,4073
-116,4/26/2011,2,0,4,2,1,0.631667,0.594083,0.729167,0.3265,678,3722,4400
-117,4/27/2011,2,0,4,3,2,0.62,0.575142,0.835417,0.3122,547,3325,3872
-118,4/28/2011,2,0,4,4,2,0.6175,0.578929,0.700833,0.320908,569,3489,4058
-119,4/29/2011,2,0,4,5,1,0.51,0.497463,0.457083,0.240063,878,3717,4595
-120,4/30/2011,2,0,4,6,1,0.4725,0.464021,0.503333,0.235075,1965,3347,5312
-121,5/1/2011,2,0,5,0,2,0.451667,0.448204,0.762083,0.106354,1138,2213,3351
-122,5/2/2011,2,0,5,1,2,0.549167,0.532833,0.73,0.183454,847,3554,4401
-123,5/3/2011,2,0,5,2,2,0.616667,0.582079,0.697083,0.342667,603,3848,4451
-124,5/4/2011,2,0,5,3,2,0.414167,0.40465,0.737083,0.328996,255,2378,2633
-125,5/5/2011,2,0,5,4,1,0.459167,0.441917,0.444167,0.295392,614,3819,4433
-126,5/6/2011,2,0,5,5,1,0.479167,0.474117,0.59,0.228246,894,3714,4608
-127,5/7/2011,2,0,5,6,1,0.52,0.512621,0.54125,0.16045,1612,3102,4714
-128,5/8/2011,2,0,5,0,1,0.528333,0.518933,0.631667,0.0746375,1401,2932,4333
-129,5/9/2011,2,0,5,1,1,0.5325,0.525246,0.58875,0.176,664,3698,4362
-130,5/10/2011,2,0,5,2,1,0.5325,0.522721,0.489167,0.115671,694,4109,4803
-131,5/11/2011,2,0,5,3,1,0.5425,0.5284,0.632917,0.120642,550,3632,4182
-132,5/12/2011,2,0,5,4,1,0.535,0.523363,0.7475,0.189667,695,4169,4864
-133,5/13/2011,2,0,5,5,2,0.5125,0.4943,0.863333,0.179725,692,3413,4105
-134,5/14/2011,2,0,5,6,2,0.520833,0.500629,0.9225,0.13495,902,2507,3409
-135,5/15/2011,2,0,5,0,2,0.5625,0.536,0.867083,0.152979,1582,2971,4553
-136,5/16/2011,2,0,5,1,1,0.5775,0.550512,0.787917,0.126871,773,3185,3958
-137,5/17/2011,2,0,5,2,2,0.561667,0.538529,0.837917,0.277354,678,3445,4123
-138,5/18/2011,2,0,5,3,2,0.55,0.527158,0.87,0.201492,536,3319,3855
-139,5/19/2011,2,0,5,4,2,0.530833,0.510742,0.829583,0.108213,735,3840,4575
-140,5/20/2011,2,0,5,5,1,0.536667,0.529042,0.719583,0.125013,909,4008,4917
-141,5/21/2011,2,0,5,6,1,0.6025,0.571975,0.626667,0.12065,2258,3547,5805
-142,5/22/2011,2,0,5,0,1,0.604167,0.5745,0.749583,0.148008,1576,3084,4660
-143,5/23/2011,2,0,5,1,2,0.631667,0.590296,0.81,0.233842,836,3438,4274
-144,5/24/2011,2,0,5,2,2,0.66,0.604813,0.740833,0.207092,659,3833,4492
-145,5/25/2011,2,0,5,3,1,0.660833,0.615542,0.69625,0.154233,740,4238,4978
-146,5/26/2011,2,0,5,4,1,0.708333,0.654688,0.6775,0.199642,758,3919,4677
-147,5/27/2011,2,0,5,5,1,0.681667,0.637008,0.65375,0.240679,871,3808,4679
-148,5/28/2011,2,0,5,6,1,0.655833,0.612379,0.729583,0.230092,2001,2757,4758
-149,5/29/2011,2,0,5,0,1,0.6675,0.61555,0.81875,0.213938,2355,2433,4788
-150,5/30/2011,2,0,5,1,1,0.733333,0.671092,0.685,0.131225,1549,2549,4098
-151,5/31/2011,2,0,5,2,1,0.775,0.725383,0.636667,0.111329,673,3309,3982
-152,6/1/2011,2,0,6,3,2,0.764167,0.720967,0.677083,0.207092,513,3461,3974
-153,6/2/2011,2,0,6,4,1,0.715,0.643942,0.305,0.292287,736,4232,4968
-154,6/3/2011,2,0,6,5,1,0.62,0.587133,0.354167,0.253121,898,4414,5312
-155,6/4/2011,2,0,6,6,1,0.635,0.594696,0.45625,0.123142,1869,3473,5342
-156,6/5/2011,2,0,6,0,2,0.648333,0.616804,0.6525,0.138692,1685,3221,4906
-157,6/6/2011,2,0,6,1,1,0.678333,0.621858,0.6,0.121896,673,3875,4548
-158,6/7/2011,2,0,6,2,1,0.7075,0.65595,0.597917,0.187808,763,4070,4833
-159,6/8/2011,2,0,6,3,1,0.775833,0.727279,0.622083,0.136817,676,3725,4401
-160,6/9/2011,2,0,6,4,2,0.808333,0.757579,0.568333,0.149883,563,3352,3915
-161,6/10/2011,2,0,6,5,1,0.755,0.703292,0.605,0.140554,815,3771,4586
-162,6/11/2011,2,0,6,6,1,0.725,0.678038,0.654583,0.15485,1729,3237,4966
-163,6/12/2011,2,0,6,0,1,0.6925,0.643325,0.747917,0.163567,1467,2993,4460
-164,6/13/2011,2,0,6,1,1,0.635,0.601654,0.494583,0.30535,863,4157,5020
-165,6/14/2011,2,0,6,2,1,0.604167,0.591546,0.507083,0.269283,727,4164,4891
-166,6/15/2011,2,0,6,3,1,0.626667,0.587754,0.471667,0.167912,769,4411,5180
-167,6/16/2011,2,0,6,4,2,0.628333,0.595346,0.688333,0.206471,545,3222,3767
-168,6/17/2011,2,0,6,5,1,0.649167,0.600383,0.735833,0.143029,863,3981,4844
-169,6/18/2011,2,0,6,6,1,0.696667,0.643954,0.670417,0.119408,1807,3312,5119
-170,6/19/2011,2,0,6,0,2,0.699167,0.645846,0.666667,0.102,1639,3105,4744
-171,6/20/2011,2,0,6,1,2,0.635,0.595346,0.74625,0.155475,699,3311,4010
-172,6/21/2011,3,0,6,2,2,0.680833,0.637646,0.770417,0.171025,774,4061,4835
-173,6/22/2011,3,0,6,3,1,0.733333,0.693829,0.7075,0.172262,661,3846,4507
-174,6/23/2011,3,0,6,4,2,0.728333,0.693833,0.703333,0.238804,746,4044,4790
-175,6/24/2011,3,0,6,5,1,0.724167,0.656583,0.573333,0.222025,969,4022,4991
-176,6/25/2011,3,0,6,6,1,0.695,0.643313,0.483333,0.209571,1782,3420,5202
-177,6/26/2011,3,0,6,0,1,0.68,0.637629,0.513333,0.0945333,1920,3385,5305
-178,6/27/2011,3,0,6,1,2,0.6825,0.637004,0.658333,0.107588,854,3854,4708
-179,6/28/2011,3,0,6,2,1,0.744167,0.692558,0.634167,0.144283,732,3916,4648
-180,6/29/2011,3,0,6,3,1,0.728333,0.654688,0.497917,0.261821,848,4377,5225
-181,6/30/2011,3,0,6,4,1,0.696667,0.637008,0.434167,0.185312,1027,4488,5515
-182,7/1/2011,3,0,7,5,1,0.7225,0.652162,0.39625,0.102608,1246,4116,5362
-183,7/2/2011,3,0,7,6,1,0.738333,0.667308,0.444583,0.115062,2204,2915,5119
-184,7/3/2011,3,0,7,0,2,0.716667,0.668575,0.6825,0.228858,2282,2367,4649
-185,7/4/2011,3,0,7,1,2,0.726667,0.665417,0.637917,0.0814792,3065,2978,6043
-186,7/5/2011,3,0,7,2,1,0.746667,0.696338,0.590417,0.126258,1031,3634,4665
-187,7/6/2011,3,0,7,3,1,0.72,0.685633,0.743333,0.149883,784,3845,4629
-188,7/7/2011,3,0,7,4,1,0.75,0.686871,0.65125,0.1592,754,3838,4592
-189,7/8/2011,3,0,7,5,2,0.709167,0.670483,0.757917,0.225129,692,3348,4040
-190,7/9/2011,3,0,7,6,1,0.733333,0.664158,0.609167,0.167912,1988,3348,5336
-191,7/10/2011,3,0,7,0,1,0.7475,0.690025,0.578333,0.183471,1743,3138,4881
-192,7/11/2011,3,0,7,1,1,0.7625,0.729804,0.635833,0.282337,723,3363,4086
-193,7/12/2011,3,0,7,2,1,0.794167,0.739275,0.559167,0.200254,662,3596,4258
-194,7/13/2011,3,0,7,3,1,0.746667,0.689404,0.631667,0.146133,748,3594,4342
-195,7/14/2011,3,0,7,4,1,0.680833,0.635104,0.47625,0.240667,888,4196,5084
-196,7/15/2011,3,0,7,5,1,0.663333,0.624371,0.59125,0.182833,1318,4220,5538
-197,7/16/2011,3,0,7,6,1,0.686667,0.638263,0.585,0.208342,2418,3505,5923
-198,7/17/2011,3,0,7,0,1,0.719167,0.669833,0.604167,0.245033,2006,3296,5302
-199,7/18/2011,3,0,7,1,1,0.746667,0.703925,0.65125,0.215804,841,3617,4458
-200,7/19/2011,3,0,7,2,1,0.776667,0.747479,0.650417,0.1306,752,3789,4541
-201,7/20/2011,3,0,7,3,1,0.768333,0.74685,0.707083,0.113817,644,3688,4332
-202,7/21/2011,3,0,7,4,2,0.815,0.826371,0.69125,0.222021,632,3152,3784
-203,7/22/2011,3,0,7,5,1,0.848333,0.840896,0.580417,0.1331,562,2825,3387
-204,7/23/2011,3,0,7,6,1,0.849167,0.804287,0.5,0.131221,987,2298,3285
-205,7/24/2011,3,0,7,0,1,0.83,0.794829,0.550833,0.169171,1050,2556,3606
-206,7/25/2011,3,0,7,1,1,0.743333,0.720958,0.757083,0.0908083,568,3272,3840
-207,7/26/2011,3,0,7,2,1,0.771667,0.696979,0.540833,0.200258,750,3840,4590
-208,7/27/2011,3,0,7,3,1,0.775,0.690667,0.402917,0.183463,755,3901,4656
-209,7/28/2011,3,0,7,4,1,0.779167,0.7399,0.583333,0.178479,606,3784,4390
-210,7/29/2011,3,0,7,5,1,0.838333,0.785967,0.5425,0.174138,670,3176,3846
-211,7/30/2011,3,0,7,6,1,0.804167,0.728537,0.465833,0.168537,1559,2916,4475
-212,7/31/2011,3,0,7,0,1,0.805833,0.729796,0.480833,0.164813,1524,2778,4302
-213,8/1/2011,3,0,8,1,1,0.771667,0.703292,0.550833,0.156717,729,3537,4266
-214,8/2/2011,3,0,8,2,1,0.783333,0.707071,0.49125,0.20585,801,4044,4845
-215,8/3/2011,3,0,8,3,2,0.731667,0.679937,0.6575,0.135583,467,3107,3574
-216,8/4/2011,3,0,8,4,2,0.71,0.664788,0.7575,0.19715,799,3777,4576
-217,8/5/2011,3,0,8,5,1,0.710833,0.656567,0.630833,0.184696,1023,3843,4866
-218,8/6/2011,3,0,8,6,2,0.716667,0.676154,0.755,0.22825,1521,2773,4294
-219,8/7/2011,3,0,8,0,1,0.7425,0.715292,0.752917,0.201487,1298,2487,3785
-220,8/8/2011,3,0,8,1,1,0.765,0.703283,0.592083,0.192175,846,3480,4326
-221,8/9/2011,3,0,8,2,1,0.775,0.724121,0.570417,0.151121,907,3695,4602
-222,8/10/2011,3,0,8,3,1,0.766667,0.684983,0.424167,0.200258,884,3896,4780
-223,8/11/2011,3,0,8,4,1,0.7175,0.651521,0.42375,0.164796,812,3980,4792
-224,8/12/2011,3,0,8,5,1,0.708333,0.654042,0.415,0.125621,1051,3854,4905
-225,8/13/2011,3,0,8,6,2,0.685833,0.645858,0.729583,0.211454,1504,2646,4150
-226,8/14/2011,3,0,8,0,2,0.676667,0.624388,0.8175,0.222633,1338,2482,3820
-227,8/15/2011,3,0,8,1,1,0.665833,0.616167,0.712083,0.208954,775,3563,4338
-228,8/16/2011,3,0,8,2,1,0.700833,0.645837,0.578333,0.236329,721,4004,4725
-229,8/17/2011,3,0,8,3,1,0.723333,0.666671,0.575417,0.143667,668,4026,4694
-230,8/18/2011,3,0,8,4,1,0.711667,0.662258,0.654583,0.233208,639,3166,3805
-231,8/19/2011,3,0,8,5,2,0.685,0.633221,0.722917,0.139308,797,3356,4153
-232,8/20/2011,3,0,8,6,1,0.6975,0.648996,0.674167,0.104467,1914,3277,5191
-233,8/21/2011,3,0,8,0,1,0.710833,0.675525,0.77,0.248754,1249,2624,3873
-234,8/22/2011,3,0,8,1,1,0.691667,0.638254,0.47,0.27675,833,3925,4758
-235,8/23/2011,3,0,8,2,1,0.640833,0.606067,0.455417,0.146763,1281,4614,5895
-236,8/24/2011,3,0,8,3,1,0.673333,0.630692,0.605,0.253108,949,4181,5130
-237,8/25/2011,3,0,8,4,2,0.684167,0.645854,0.771667,0.210833,435,3107,3542
-238,8/26/2011,3,0,8,5,1,0.7,0.659733,0.76125,0.0839625,768,3893,4661
-239,8/27/2011,3,0,8,6,2,0.68,0.635556,0.85,0.375617,226,889,1115
-240,8/28/2011,3,0,8,0,1,0.707059,0.647959,0.561765,0.304659,1415,2919,4334
-241,8/29/2011,3,0,8,1,1,0.636667,0.607958,0.554583,0.159825,729,3905,4634
-242,8/30/2011,3,0,8,2,1,0.639167,0.594704,0.548333,0.125008,775,4429,5204
-243,8/31/2011,3,0,8,3,1,0.656667,0.611121,0.597917,0.0833333,688,4370,5058
-244,9/1/2011,3,0,9,4,1,0.655,0.614921,0.639167,0.141796,783,4332,5115
-245,9/2/2011,3,0,9,5,2,0.643333,0.604808,0.727083,0.139929,875,3852,4727
-246,9/3/2011,3,0,9,6,1,0.669167,0.633213,0.716667,0.185325,1935,2549,4484
-247,9/4/2011,3,0,9,0,1,0.709167,0.665429,0.742083,0.206467,2521,2419,4940
-248,9/5/2011,3,0,9,1,2,0.673333,0.625646,0.790417,0.212696,1236,2115,3351
-249,9/6/2011,3,0,9,2,3,0.54,0.5152,0.886957,0.343943,204,2506,2710
-250,9/7/2011,3,0,9,3,3,0.599167,0.544229,0.917083,0.0970208,118,1878,1996
-251,9/8/2011,3,0,9,4,3,0.633913,0.555361,0.939565,0.192748,153,1689,1842
-252,9/9/2011,3,0,9,5,2,0.65,0.578946,0.897917,0.124379,417,3127,3544
-253,9/10/2011,3,0,9,6,1,0.66,0.607962,0.75375,0.153608,1750,3595,5345
-254,9/11/2011,3,0,9,0,1,0.653333,0.609229,0.71375,0.115054,1633,3413,5046
-255,9/12/2011,3,0,9,1,1,0.644348,0.60213,0.692174,0.088913,690,4023,4713
-256,9/13/2011,3,0,9,2,1,0.650833,0.603554,0.7125,0.141804,701,4062,4763
-257,9/14/2011,3,0,9,3,1,0.673333,0.6269,0.697083,0.1673,647,4138,4785
-258,9/15/2011,3,0,9,4,2,0.5775,0.553671,0.709167,0.271146,428,3231,3659
-259,9/16/2011,3,0,9,5,2,0.469167,0.461475,0.590417,0.164183,742,4018,4760
-260,9/17/2011,3,0,9,6,2,0.491667,0.478512,0.718333,0.189675,1434,3077,4511
-261,9/18/2011,3,0,9,0,1,0.5075,0.490537,0.695,0.178483,1353,2921,4274
-262,9/19/2011,3,0,9,1,2,0.549167,0.529675,0.69,0.151742,691,3848,4539
-263,9/20/2011,3,0,9,2,2,0.561667,0.532217,0.88125,0.134954,438,3203,3641
-264,9/21/2011,3,0,9,3,2,0.595,0.550533,0.9,0.0964042,539,3813,4352
-265,9/22/2011,3,0,9,4,2,0.628333,0.554963,0.902083,0.128125,555,4240,4795
-266,9/23/2011,4,0,9,5,2,0.609167,0.522125,0.9725,0.0783667,258,2137,2395
-267,9/24/2011,4,0,9,6,2,0.606667,0.564412,0.8625,0.0783833,1776,3647,5423
-268,9/25/2011,4,0,9,0,2,0.634167,0.572637,0.845,0.0503792,1544,3466,5010
-269,9/26/2011,4,0,9,1,2,0.649167,0.589042,0.848333,0.1107,684,3946,4630
-270,9/27/2011,4,0,9,2,2,0.636667,0.574525,0.885417,0.118171,477,3643,4120
-271,9/28/2011,4,0,9,3,2,0.635,0.575158,0.84875,0.148629,480,3427,3907
-272,9/29/2011,4,0,9,4,1,0.616667,0.574512,0.699167,0.172883,653,4186,4839
-273,9/30/2011,4,0,9,5,1,0.564167,0.544829,0.6475,0.206475,830,4372,5202
-274,10/1/2011,4,0,10,6,2,0.41,0.412863,0.75375,0.292296,480,1949,2429
-275,10/2/2011,4,0,10,0,2,0.356667,0.345317,0.791667,0.222013,616,2302,2918
-276,10/3/2011,4,0,10,1,2,0.384167,0.392046,0.760833,0.0833458,330,3240,3570
-277,10/4/2011,4,0,10,2,1,0.484167,0.472858,0.71,0.205854,486,3970,4456
-278,10/5/2011,4,0,10,3,1,0.538333,0.527138,0.647917,0.17725,559,4267,4826
-279,10/6/2011,4,0,10,4,1,0.494167,0.480425,0.620833,0.134954,639,4126,4765
-280,10/7/2011,4,0,10,5,1,0.510833,0.504404,0.684167,0.0223917,949,4036,4985
-281,10/8/2011,4,0,10,6,1,0.521667,0.513242,0.70125,0.0454042,2235,3174,5409
-282,10/9/2011,4,0,10,0,1,0.540833,0.523983,0.7275,0.06345,2397,3114,5511
-283,10/10/2011,4,0,10,1,1,0.570833,0.542925,0.73375,0.0423042,1514,3603,5117
-284,10/11/2011,4,0,10,2,2,0.566667,0.546096,0.80875,0.143042,667,3896,4563
-285,10/12/2011,4,0,10,3,3,0.543333,0.517717,0.90625,0.24815,217,2199,2416
-286,10/13/2011,4,0,10,4,2,0.589167,0.551804,0.896667,0.141787,290,2623,2913
-287,10/14/2011,4,0,10,5,2,0.550833,0.529675,0.71625,0.223883,529,3115,3644
-288,10/15/2011,4,0,10,6,1,0.506667,0.498725,0.483333,0.258083,1899,3318,5217
-289,10/16/2011,4,0,10,0,1,0.511667,0.503154,0.486667,0.281717,1748,3293,5041
-290,10/17/2011,4,0,10,1,1,0.534167,0.510725,0.579583,0.175379,713,3857,4570
-291,10/18/2011,4,0,10,2,2,0.5325,0.522721,0.701667,0.110087,637,4111,4748
-292,10/19/2011,4,0,10,3,3,0.541739,0.513848,0.895217,0.243339,254,2170,2424
-293,10/20/2011,4,0,10,4,1,0.475833,0.466525,0.63625,0.422275,471,3724,4195
-294,10/21/2011,4,0,10,5,1,0.4275,0.423596,0.574167,0.221396,676,3628,4304
-295,10/22/2011,4,0,10,6,1,0.4225,0.425492,0.629167,0.0926667,1499,2809,4308
-296,10/23/2011,4,0,10,0,1,0.421667,0.422333,0.74125,0.0995125,1619,2762,4381
-297,10/24/2011,4,0,10,1,1,0.463333,0.457067,0.772083,0.118792,699,3488,4187
-298,10/25/2011,4,0,10,2,1,0.471667,0.463375,0.622917,0.166658,695,3992,4687
-299,10/26/2011,4,0,10,3,2,0.484167,0.472846,0.720417,0.148642,404,3490,3894
-300,10/27/2011,4,0,10,4,2,0.47,0.457046,0.812917,0.197763,240,2419,2659
-301,10/28/2011,4,0,10,5,2,0.330833,0.318812,0.585833,0.229479,456,3291,3747
-302,10/29/2011,4,0,10,6,3,0.254167,0.227913,0.8825,0.351371,57,570,627
-303,10/30/2011,4,0,10,0,1,0.319167,0.321329,0.62375,0.176617,885,2446,3331
-304,10/31/2011,4,0,10,1,1,0.34,0.356063,0.703333,0.10635,362,3307,3669
-305,11/1/2011,4,0,11,2,1,0.400833,0.397088,0.68375,0.135571,410,3658,4068
-306,11/2/2011,4,0,11,3,1,0.3775,0.390133,0.71875,0.0820917,370,3816,4186
-307,11/3/2011,4,0,11,4,1,0.408333,0.405921,0.702083,0.136817,318,3656,3974
-308,11/4/2011,4,0,11,5,2,0.403333,0.403392,0.6225,0.271779,470,3576,4046
-309,11/5/2011,4,0,11,6,1,0.326667,0.323854,0.519167,0.189062,1156,2770,3926
-310,11/6/2011,4,0,11,0,1,0.348333,0.362358,0.734583,0.0920542,952,2697,3649
-311,11/7/2011,4,0,11,1,1,0.395,0.400871,0.75875,0.057225,373,3662,4035
-312,11/8/2011,4,0,11,2,1,0.408333,0.412246,0.721667,0.0690375,376,3829,4205
-313,11/9/2011,4,0,11,3,1,0.4,0.409079,0.758333,0.0621958,305,3804,4109
-314,11/10/2011,4,0,11,4,2,0.38,0.373721,0.813333,0.189067,190,2743,2933
-315,11/11/2011,4,0,11,5,1,0.324167,0.306817,0.44625,0.314675,440,2928,3368
-316,11/12/2011,4,0,11,6,1,0.356667,0.357942,0.552917,0.212062,1275,2792,4067
-317,11/13/2011,4,0,11,0,1,0.440833,0.43055,0.458333,0.281721,1004,2713,3717
-318,11/14/2011,4,0,11,1,1,0.53,0.524612,0.587083,0.306596,595,3891,4486
-319,11/15/2011,4,0,11,2,2,0.53,0.507579,0.68875,0.199633,449,3746,4195
-320,11/16/2011,4,0,11,3,3,0.456667,0.451988,0.93,0.136829,145,1672,1817
-321,11/17/2011,4,0,11,4,2,0.341667,0.323221,0.575833,0.305362,139,2914,3053
-322,11/18/2011,4,0,11,5,1,0.274167,0.272721,0.41,0.168533,245,3147,3392
-323,11/19/2011,4,0,11,6,1,0.329167,0.324483,0.502083,0.224496,943,2720,3663
-324,11/20/2011,4,0,11,0,2,0.463333,0.457058,0.684583,0.18595,787,2733,3520
-325,11/21/2011,4,0,11,1,3,0.4475,0.445062,0.91,0.138054,220,2545,2765
-326,11/22/2011,4,0,11,2,3,0.416667,0.421696,0.9625,0.118792,69,1538,1607
-327,11/23/2011,4,0,11,3,2,0.440833,0.430537,0.757917,0.335825,112,2454,2566
-328,11/24/2011,4,0,11,4,1,0.373333,0.372471,0.549167,0.167304,560,935,1495
-329,11/25/2011,4,0,11,5,1,0.375,0.380671,0.64375,0.0988958,1095,1697,2792
-330,11/26/2011,4,0,11,6,1,0.375833,0.385087,0.681667,0.0684208,1249,1819,3068
-331,11/27/2011,4,0,11,0,1,0.459167,0.4558,0.698333,0.208954,810,2261,3071
-332,11/28/2011,4,0,11,1,1,0.503478,0.490122,0.743043,0.142122,253,3614,3867
-333,11/29/2011,4,0,11,2,2,0.458333,0.451375,0.830833,0.258092,96,2818,2914
-334,11/30/2011,4,0,11,3,1,0.325,0.311221,0.613333,0.271158,188,3425,3613
-335,12/1/2011,4,0,12,4,1,0.3125,0.305554,0.524583,0.220158,182,3545,3727
-336,12/2/2011,4,0,12,5,1,0.314167,0.331433,0.625833,0.100754,268,3672,3940
-337,12/3/2011,4,0,12,6,1,0.299167,0.310604,0.612917,0.0957833,706,2908,3614
-338,12/4/2011,4,0,12,0,1,0.330833,0.3491,0.775833,0.0839583,634,2851,3485
-339,12/5/2011,4,0,12,1,2,0.385833,0.393925,0.827083,0.0622083,233,3578,3811
-340,12/6/2011,4,0,12,2,3,0.4625,0.4564,0.949583,0.232583,126,2468,2594
-341,12/7/2011,4,0,12,3,3,0.41,0.400246,0.970417,0.266175,50,655,705
-342,12/8/2011,4,0,12,4,1,0.265833,0.256938,0.58,0.240058,150,3172,3322
-343,12/9/2011,4,0,12,5,1,0.290833,0.317542,0.695833,0.0827167,261,3359,3620
-344,12/10/2011,4,0,12,6,1,0.275,0.266412,0.5075,0.233221,502,2688,3190
-345,12/11/2011,4,0,12,0,1,0.220833,0.253154,0.49,0.0665417,377,2366,2743
-346,12/12/2011,4,0,12,1,1,0.238333,0.270196,0.670833,0.06345,143,3167,3310
-347,12/13/2011,4,0,12,2,1,0.2825,0.301138,0.59,0.14055,155,3368,3523
-348,12/14/2011,4,0,12,3,2,0.3175,0.338362,0.66375,0.0609583,178,3562,3740
-349,12/15/2011,4,0,12,4,2,0.4225,0.412237,0.634167,0.268042,181,3528,3709
-350,12/16/2011,4,0,12,5,2,0.375,0.359825,0.500417,0.260575,178,3399,3577
-351,12/17/2011,4,0,12,6,2,0.258333,0.249371,0.560833,0.243167,275,2464,2739
-352,12/18/2011,4,0,12,0,1,0.238333,0.245579,0.58625,0.169779,220,2211,2431
-353,12/19/2011,4,0,12,1,1,0.276667,0.280933,0.6375,0.172896,260,3143,3403
-354,12/20/2011,4,0,12,2,2,0.385833,0.396454,0.595417,0.0615708,216,3534,3750
-355,12/21/2011,1,0,12,3,2,0.428333,0.428017,0.858333,0.2214,107,2553,2660
-356,12/22/2011,1,0,12,4,2,0.423333,0.426121,0.7575,0.047275,227,2841,3068
-357,12/23/2011,1,0,12,5,1,0.373333,0.377513,0.68625,0.274246,163,2046,2209
-358,12/24/2011,1,0,12,6,1,0.3025,0.299242,0.5425,0.190304,155,856,1011
-359,12/25/2011,1,0,12,0,1,0.274783,0.279961,0.681304,0.155091,303,451,754
-360,12/26/2011,1,0,12,1,1,0.321739,0.315535,0.506957,0.239465,430,887,1317
-361,12/27/2011,1,0,12,2,2,0.325,0.327633,0.7625,0.18845,103,1059,1162
-362,12/28/2011,1,0,12,3,1,0.29913,0.279974,0.503913,0.293961,255,2047,2302
-363,12/29/2011,1,0,12,4,1,0.248333,0.263892,0.574167,0.119412,254,2169,2423
-364,12/30/2011,1,0,12,5,1,0.311667,0.318812,0.636667,0.134337,491,2508,2999
-365,12/31/2011,1,0,12,6,1,0.41,0.414121,0.615833,0.220154,665,1820,2485
-366,1/1/2012,1,1,1,0,1,0.37,0.375621,0.6925,0.192167,686,1608,2294
-367,1/2/2012,1,1,1,1,1,0.273043,0.252304,0.381304,0.329665,244,1707,1951
-368,1/3/2012,1,1,1,2,1,0.15,0.126275,0.44125,0.365671,89,2147,2236
-369,1/4/2012,1,1,1,3,2,0.1075,0.119337,0.414583,0.1847,95,2273,2368
-370,1/5/2012,1,1,1,4,1,0.265833,0.278412,0.524167,0.129987,140,3132,3272
-371,1/6/2012,1,1,1,5,1,0.334167,0.340267,0.542083,0.167908,307,3791,4098
-372,1/7/2012,1,1,1,6,1,0.393333,0.390779,0.531667,0.174758,1070,3451,4521
-373,1/8/2012,1,1,1,0,1,0.3375,0.340258,0.465,0.191542,599,2826,3425
-374,1/9/2012,1,1,1,1,2,0.224167,0.247479,0.701667,0.0989,106,2270,2376
-375,1/10/2012,1,1,1,2,1,0.308696,0.318826,0.646522,0.187552,173,3425,3598
-376,1/11/2012,1,1,1,3,2,0.274167,0.282821,0.8475,0.131221,92,2085,2177
-377,1/12/2012,1,1,1,4,2,0.3825,0.381938,0.802917,0.180967,269,3828,4097
-378,1/13/2012,1,1,1,5,1,0.274167,0.249362,0.5075,0.378108,174,3040,3214
-379,1/14/2012,1,1,1,6,1,0.18,0.183087,0.4575,0.187183,333,2160,2493
-380,1/15/2012,1,1,1,0,1,0.166667,0.161625,0.419167,0.251258,284,2027,2311
-381,1/16/2012,1,1,1,1,1,0.19,0.190663,0.5225,0.231358,217,2081,2298
-382,1/17/2012,1,1,1,2,2,0.373043,0.364278,0.716087,0.34913,127,2808,2935
-383,1/18/2012,1,1,1,3,1,0.303333,0.275254,0.443333,0.415429,109,3267,3376
-384,1/19/2012,1,1,1,4,1,0.19,0.190038,0.4975,0.220158,130,3162,3292
-385,1/20/2012,1,1,1,5,2,0.2175,0.220958,0.45,0.20275,115,3048,3163
-386,1/21/2012,1,1,1,6,2,0.173333,0.174875,0.83125,0.222642,67,1234,1301
-387,1/22/2012,1,1,1,0,2,0.1625,0.16225,0.79625,0.199638,196,1781,1977
-388,1/23/2012,1,1,1,1,2,0.218333,0.243058,0.91125,0.110708,145,2287,2432
-389,1/24/2012,1,1,1,2,1,0.3425,0.349108,0.835833,0.123767,439,3900,4339
-390,1/25/2012,1,1,1,3,1,0.294167,0.294821,0.64375,0.161071,467,3803,4270
-391,1/26/2012,1,1,1,4,2,0.341667,0.35605,0.769583,0.0733958,244,3831,4075
-392,1/27/2012,1,1,1,5,2,0.425,0.415383,0.74125,0.342667,269,3187,3456
-393,1/28/2012,1,1,1,6,1,0.315833,0.326379,0.543333,0.210829,775,3248,4023
-394,1/29/2012,1,1,1,0,1,0.2825,0.272721,0.31125,0.24005,558,2685,3243
-395,1/30/2012,1,1,1,1,1,0.269167,0.262625,0.400833,0.215792,126,3498,3624
-396,1/31/2012,1,1,1,2,1,0.39,0.381317,0.416667,0.261817,324,4185,4509
-397,2/1/2012,1,1,2,3,1,0.469167,0.466538,0.507917,0.189067,304,4275,4579
-398,2/2/2012,1,1,2,4,2,0.399167,0.398971,0.672917,0.187187,190,3571,3761
-399,2/3/2012,1,1,2,5,1,0.313333,0.309346,0.526667,0.178496,310,3841,4151
-400,2/4/2012,1,1,2,6,2,0.264167,0.272725,0.779583,0.121896,384,2448,2832
-401,2/5/2012,1,1,2,0,2,0.265833,0.264521,0.687917,0.175996,318,2629,2947
-402,2/6/2012,1,1,2,1,1,0.282609,0.296426,0.622174,0.1538,206,3578,3784
-403,2/7/2012,1,1,2,2,1,0.354167,0.361104,0.49625,0.147379,199,4176,4375
-404,2/8/2012,1,1,2,3,2,0.256667,0.266421,0.722917,0.133721,109,2693,2802
-405,2/9/2012,1,1,2,4,1,0.265,0.261988,0.562083,0.194037,163,3667,3830
-406,2/10/2012,1,1,2,5,2,0.280833,0.293558,0.54,0.116929,227,3604,3831
-407,2/11/2012,1,1,2,6,3,0.224167,0.210867,0.73125,0.289796,192,1977,2169
-408,2/12/2012,1,1,2,0,1,0.1275,0.101658,0.464583,0.409212,73,1456,1529
-409,2/13/2012,1,1,2,1,1,0.2225,0.227913,0.41125,0.167283,94,3328,3422
-410,2/14/2012,1,1,2,2,2,0.319167,0.333946,0.50875,0.141179,135,3787,3922
-411,2/15/2012,1,1,2,3,1,0.348333,0.351629,0.53125,0.1816,141,4028,4169
-412,2/16/2012,1,1,2,4,2,0.316667,0.330162,0.752917,0.091425,74,2931,3005
-413,2/17/2012,1,1,2,5,1,0.343333,0.351629,0.634583,0.205846,349,3805,4154
-414,2/18/2012,1,1,2,6,1,0.346667,0.355425,0.534583,0.190929,1435,2883,4318
-415,2/19/2012,1,1,2,0,2,0.28,0.265788,0.515833,0.253112,618,2071,2689
-416,2/20/2012,1,1,2,1,1,0.28,0.273391,0.507826,0.229083,502,2627,3129
-417,2/21/2012,1,1,2,2,1,0.287826,0.295113,0.594348,0.205717,163,3614,3777
-418,2/22/2012,1,1,2,3,1,0.395833,0.392667,0.567917,0.234471,394,4379,4773
-419,2/23/2012,1,1,2,4,1,0.454167,0.444446,0.554583,0.190913,516,4546,5062
-420,2/24/2012,1,1,2,5,2,0.4075,0.410971,0.7375,0.237567,246,3241,3487
-421,2/25/2012,1,1,2,6,1,0.290833,0.255675,0.395833,0.421642,317,2415,2732
-422,2/26/2012,1,1,2,0,1,0.279167,0.268308,0.41,0.205229,515,2874,3389
-423,2/27/2012,1,1,2,1,1,0.366667,0.357954,0.490833,0.268033,253,4069,4322
-424,2/28/2012,1,1,2,2,1,0.359167,0.353525,0.395833,0.193417,229,4134,4363
-425,2/29/2012,1,1,2,3,2,0.344348,0.34847,0.804783,0.179117,65,1769,1834
-426,3/1/2012,1,1,3,4,1,0.485833,0.475371,0.615417,0.226987,325,4665,4990
-427,3/2/2012,1,1,3,5,2,0.353333,0.359842,0.657083,0.144904,246,2948,3194
-428,3/3/2012,1,1,3,6,2,0.414167,0.413492,0.62125,0.161079,956,3110,4066
-429,3/4/2012,1,1,3,0,1,0.325833,0.303021,0.403333,0.334571,710,2713,3423
-430,3/5/2012,1,1,3,1,1,0.243333,0.241171,0.50625,0.228858,203,3130,3333
-431,3/6/2012,1,1,3,2,1,0.258333,0.255042,0.456667,0.200875,221,3735,3956
-432,3/7/2012,1,1,3,3,1,0.404167,0.3851,0.513333,0.345779,432,4484,4916
-433,3/8/2012,1,1,3,4,1,0.5275,0.524604,0.5675,0.441563,486,4896,5382
-434,3/9/2012,1,1,3,5,2,0.410833,0.397083,0.407083,0.4148,447,4122,4569
-435,3/10/2012,1,1,3,6,1,0.2875,0.277767,0.350417,0.22575,968,3150,4118
-436,3/11/2012,1,1,3,0,1,0.361739,0.35967,0.476957,0.222587,1658,3253,4911
-437,3/12/2012,1,1,3,1,1,0.466667,0.459592,0.489167,0.207713,838,4460,5298
-438,3/13/2012,1,1,3,2,1,0.565,0.542929,0.6175,0.23695,762,5085,5847
-439,3/14/2012,1,1,3,3,1,0.5725,0.548617,0.507083,0.115062,997,5315,6312
-440,3/15/2012,1,1,3,4,1,0.5575,0.532825,0.579583,0.149883,1005,5187,6192
-441,3/16/2012,1,1,3,5,2,0.435833,0.436229,0.842083,0.113192,548,3830,4378
-442,3/17/2012,1,1,3,6,2,0.514167,0.505046,0.755833,0.110704,3155,4681,7836
-443,3/18/2012,1,1,3,0,2,0.4725,0.464,0.81,0.126883,2207,3685,5892
-444,3/19/2012,1,1,3,1,1,0.545,0.532821,0.72875,0.162317,982,5171,6153
-445,3/20/2012,1,1,3,2,1,0.560833,0.538533,0.807917,0.121271,1051,5042,6093
-446,3/21/2012,2,1,3,3,2,0.531667,0.513258,0.82125,0.0895583,1122,5108,6230
-447,3/22/2012,2,1,3,4,1,0.554167,0.531567,0.83125,0.117562,1334,5537,6871
-448,3/23/2012,2,1,3,5,2,0.601667,0.570067,0.694167,0.1163,2469,5893,8362
-449,3/24/2012,2,1,3,6,2,0.5025,0.486733,0.885417,0.192783,1033,2339,3372
-450,3/25/2012,2,1,3,0,2,0.4375,0.437488,0.880833,0.220775,1532,3464,4996
-451,3/26/2012,2,1,3,1,1,0.445833,0.43875,0.477917,0.386821,795,4763,5558
-452,3/27/2012,2,1,3,2,1,0.323333,0.315654,0.29,0.187192,531,4571,5102
-453,3/28/2012,2,1,3,3,1,0.484167,0.47095,0.48125,0.291671,674,5024,5698
-454,3/29/2012,2,1,3,4,1,0.494167,0.482304,0.439167,0.31965,834,5299,6133
-455,3/30/2012,2,1,3,5,2,0.37,0.375621,0.580833,0.138067,796,4663,5459
-456,3/31/2012,2,1,3,6,2,0.424167,0.421708,0.738333,0.250617,2301,3934,6235
-457,4/1/2012,2,1,4,0,2,0.425833,0.417287,0.67625,0.172267,2347,3694,6041
-458,4/2/2012,2,1,4,1,1,0.433913,0.427513,0.504348,0.312139,1208,4728,5936
-459,4/3/2012,2,1,4,2,1,0.466667,0.461483,0.396667,0.100133,1348,5424,6772
-460,4/4/2012,2,1,4,3,1,0.541667,0.53345,0.469583,0.180975,1058,5378,6436
-461,4/5/2012,2,1,4,4,1,0.435,0.431163,0.374167,0.219529,1192,5265,6457
-462,4/6/2012,2,1,4,5,1,0.403333,0.390767,0.377083,0.300388,1807,4653,6460
-463,4/7/2012,2,1,4,6,1,0.4375,0.426129,0.254167,0.274871,3252,3605,6857
-464,4/8/2012,2,1,4,0,1,0.5,0.492425,0.275833,0.232596,2230,2939,5169
-465,4/9/2012,2,1,4,1,1,0.489167,0.476638,0.3175,0.358196,905,4680,5585
-466,4/10/2012,2,1,4,2,1,0.446667,0.436233,0.435,0.249375,819,5099,5918
-467,4/11/2012,2,1,4,3,1,0.348696,0.337274,0.469565,0.295274,482,4380,4862
-468,4/12/2012,2,1,4,4,1,0.3975,0.387604,0.46625,0.290429,663,4746,5409
-469,4/13/2012,2,1,4,5,1,0.4425,0.431808,0.408333,0.155471,1252,5146,6398
-470,4/14/2012,2,1,4,6,1,0.495,0.487996,0.502917,0.190917,2795,4665,7460
-471,4/15/2012,2,1,4,0,1,0.606667,0.573875,0.507917,0.225129,2846,4286,7132
-472,4/16/2012,2,1,4,1,1,0.664167,0.614925,0.561667,0.284829,1198,5172,6370
-473,4/17/2012,2,1,4,2,1,0.608333,0.598487,0.390417,0.273629,989,5702,6691
-474,4/18/2012,2,1,4,3,2,0.463333,0.457038,0.569167,0.167912,347,4020,4367
-475,4/19/2012,2,1,4,4,1,0.498333,0.493046,0.6125,0.0659292,846,5719,6565
-476,4/20/2012,2,1,4,5,1,0.526667,0.515775,0.694583,0.149871,1340,5950,7290
-477,4/21/2012,2,1,4,6,1,0.57,0.542921,0.682917,0.283587,2541,4083,6624
-478,4/22/2012,2,1,4,0,3,0.396667,0.389504,0.835417,0.344546,120,907,1027
-479,4/23/2012,2,1,4,1,2,0.321667,0.301125,0.766667,0.303496,195,3019,3214
-480,4/24/2012,2,1,4,2,1,0.413333,0.405283,0.454167,0.249383,518,5115,5633
-481,4/25/2012,2,1,4,3,1,0.476667,0.470317,0.427917,0.118792,655,5541,6196
-482,4/26/2012,2,1,4,4,2,0.498333,0.483583,0.756667,0.176625,475,4551,5026
-483,4/27/2012,2,1,4,5,1,0.4575,0.452637,0.400833,0.347633,1014,5219,6233
-484,4/28/2012,2,1,4,6,2,0.376667,0.377504,0.489583,0.129975,1120,3100,4220
-485,4/29/2012,2,1,4,0,1,0.458333,0.450121,0.587083,0.116908,2229,4075,6304
-486,4/30/2012,2,1,4,1,2,0.464167,0.457696,0.57,0.171638,665,4907,5572
-487,5/1/2012,2,1,5,2,2,0.613333,0.577021,0.659583,0.156096,653,5087,5740
-488,5/2/2012,2,1,5,3,1,0.564167,0.537896,0.797083,0.138058,667,5502,6169
-489,5/3/2012,2,1,5,4,2,0.56,0.537242,0.768333,0.133696,764,5657,6421
-490,5/4/2012,2,1,5,5,1,0.6275,0.590917,0.735417,0.162938,1069,5227,6296
-491,5/5/2012,2,1,5,6,2,0.621667,0.584608,0.756667,0.152992,2496,4387,6883
-492,5/6/2012,2,1,5,0,2,0.5625,0.546737,0.74,0.149879,2135,4224,6359
-493,5/7/2012,2,1,5,1,2,0.5375,0.527142,0.664167,0.230721,1008,5265,6273
-494,5/8/2012,2,1,5,2,2,0.581667,0.557471,0.685833,0.296029,738,4990,5728
-495,5/9/2012,2,1,5,3,2,0.575,0.553025,0.744167,0.216412,620,4097,4717
-496,5/10/2012,2,1,5,4,1,0.505833,0.491783,0.552083,0.314063,1026,5546,6572
-497,5/11/2012,2,1,5,5,1,0.533333,0.520833,0.360417,0.236937,1319,5711,7030
-498,5/12/2012,2,1,5,6,1,0.564167,0.544817,0.480417,0.123133,2622,4807,7429
-499,5/13/2012,2,1,5,0,1,0.6125,0.585238,0.57625,0.225117,2172,3946,6118
-500,5/14/2012,2,1,5,1,2,0.573333,0.5499,0.789583,0.212692,342,2501,2843
-501,5/15/2012,2,1,5,2,2,0.611667,0.576404,0.794583,0.147392,625,4490,5115
-502,5/16/2012,2,1,5,3,1,0.636667,0.595975,0.697917,0.122512,991,6433,7424
-503,5/17/2012,2,1,5,4,1,0.593333,0.572613,0.52,0.229475,1242,6142,7384
-504,5/18/2012,2,1,5,5,1,0.564167,0.551121,0.523333,0.136817,1521,6118,7639
-505,5/19/2012,2,1,5,6,1,0.6,0.566908,0.45625,0.083975,3410,4884,8294
-506,5/20/2012,2,1,5,0,1,0.620833,0.583967,0.530417,0.254367,2704,4425,7129
-507,5/21/2012,2,1,5,1,2,0.598333,0.565667,0.81125,0.233204,630,3729,4359
-508,5/22/2012,2,1,5,2,2,0.615,0.580825,0.765833,0.118167,819,5254,6073
-509,5/23/2012,2,1,5,3,2,0.621667,0.584612,0.774583,0.102,766,4494,5260
-510,5/24/2012,2,1,5,4,1,0.655,0.6067,0.716667,0.172896,1059,5711,6770
-511,5/25/2012,2,1,5,5,1,0.68,0.627529,0.747083,0.14055,1417,5317,6734
-512,5/26/2012,2,1,5,6,1,0.6925,0.642696,0.7325,0.198992,2855,3681,6536
-513,5/27/2012,2,1,5,0,1,0.69,0.641425,0.697083,0.215171,3283,3308,6591
-514,5/28/2012,2,1,5,1,1,0.7125,0.6793,0.67625,0.196521,2557,3486,6043
-515,5/29/2012,2,1,5,2,1,0.7225,0.672992,0.684583,0.2954,880,4863,5743
-516,5/30/2012,2,1,5,3,2,0.656667,0.611129,0.67,0.134329,745,6110,6855
-517,5/31/2012,2,1,5,4,1,0.68,0.631329,0.492917,0.195279,1100,6238,7338
-518,6/1/2012,2,1,6,5,2,0.654167,0.607962,0.755417,0.237563,533,3594,4127
-519,6/2/2012,2,1,6,6,1,0.583333,0.566288,0.549167,0.186562,2795,5325,8120
-520,6/3/2012,2,1,6,0,1,0.6025,0.575133,0.493333,0.184087,2494,5147,7641
-521,6/4/2012,2,1,6,1,1,0.5975,0.578283,0.487083,0.284833,1071,5927,6998
-522,6/5/2012,2,1,6,2,2,0.540833,0.525892,0.613333,0.209575,968,6033,7001
-523,6/6/2012,2,1,6,3,1,0.554167,0.542292,0.61125,0.077125,1027,6028,7055
-524,6/7/2012,2,1,6,4,1,0.6025,0.569442,0.567083,0.15735,1038,6456,7494
-525,6/8/2012,2,1,6,5,1,0.649167,0.597862,0.467917,0.175383,1488,6248,7736
-526,6/9/2012,2,1,6,6,1,0.710833,0.648367,0.437083,0.144287,2708,4790,7498
-527,6/10/2012,2,1,6,0,1,0.726667,0.663517,0.538333,0.133721,2224,4374,6598
-528,6/11/2012,2,1,6,1,2,0.720833,0.659721,0.587917,0.207713,1017,5647,6664
-529,6/12/2012,2,1,6,2,2,0.653333,0.597875,0.833333,0.214546,477,4495,4972
-530,6/13/2012,2,1,6,3,1,0.655833,0.611117,0.582083,0.343279,1173,6248,7421
-531,6/14/2012,2,1,6,4,1,0.648333,0.624383,0.569583,0.253733,1180,6183,7363
-532,6/15/2012,2,1,6,5,1,0.639167,0.599754,0.589583,0.176617,1563,6102,7665
-533,6/16/2012,2,1,6,6,1,0.631667,0.594708,0.504167,0.166667,2963,4739,7702
-534,6/17/2012,2,1,6,0,1,0.5925,0.571975,0.59875,0.144904,2634,4344,6978
-535,6/18/2012,2,1,6,1,2,0.568333,0.544842,0.777917,0.174746,653,4446,5099
-536,6/19/2012,2,1,6,2,1,0.688333,0.654692,0.69,0.148017,968,5857,6825
-537,6/20/2012,2,1,6,3,1,0.7825,0.720975,0.592083,0.113812,872,5339,6211
-538,6/21/2012,3,1,6,4,1,0.805833,0.752542,0.567917,0.118787,778,5127,5905
-539,6/22/2012,3,1,6,5,1,0.7775,0.724121,0.57375,0.182842,964,4859,5823
-540,6/23/2012,3,1,6,6,1,0.731667,0.652792,0.534583,0.179721,2657,4801,7458
-541,6/24/2012,3,1,6,0,1,0.743333,0.674254,0.479167,0.145525,2551,4340,6891
-542,6/25/2012,3,1,6,1,1,0.715833,0.654042,0.504167,0.300383,1139,5640,6779
-543,6/26/2012,3,1,6,2,1,0.630833,0.594704,0.373333,0.347642,1077,6365,7442
-544,6/27/2012,3,1,6,3,1,0.6975,0.640792,0.36,0.271775,1077,6258,7335
-545,6/28/2012,3,1,6,4,1,0.749167,0.675512,0.4225,0.17165,921,5958,6879
-546,6/29/2012,3,1,6,5,1,0.834167,0.786613,0.48875,0.165417,829,4634,5463
-547,6/30/2012,3,1,6,6,1,0.765,0.687508,0.60125,0.161071,1455,4232,5687
-548,7/1/2012,3,1,7,0,1,0.815833,0.750629,0.51875,0.168529,1421,4110,5531
-549,7/2/2012,3,1,7,1,1,0.781667,0.702038,0.447083,0.195267,904,5323,6227
-550,7/3/2012,3,1,7,2,1,0.780833,0.70265,0.492083,0.126237,1052,5608,6660
-551,7/4/2012,3,1,7,3,1,0.789167,0.732337,0.53875,0.13495,2562,4841,7403
-552,7/5/2012,3,1,7,4,1,0.8275,0.761367,0.457917,0.194029,1405,4836,6241
-553,7/6/2012,3,1,7,5,1,0.828333,0.752533,0.450833,0.146142,1366,4841,6207
-554,7/7/2012,3,1,7,6,1,0.861667,0.804913,0.492083,0.163554,1448,3392,4840
-555,7/8/2012,3,1,7,0,1,0.8225,0.790396,0.57375,0.125629,1203,3469,4672
-556,7/9/2012,3,1,7,1,2,0.710833,0.654054,0.683333,0.180975,998,5571,6569
-557,7/10/2012,3,1,7,2,2,0.720833,0.664796,0.6675,0.151737,954,5336,6290
-558,7/11/2012,3,1,7,3,1,0.716667,0.650271,0.633333,0.151733,975,6289,7264
-559,7/12/2012,3,1,7,4,1,0.715833,0.654683,0.529583,0.146775,1032,6414,7446
-560,7/13/2012,3,1,7,5,2,0.731667,0.667933,0.485833,0.08085,1511,5988,7499
-561,7/14/2012,3,1,7,6,2,0.703333,0.666042,0.699167,0.143679,2355,4614,6969
-562,7/15/2012,3,1,7,0,1,0.745833,0.705196,0.717917,0.166667,1920,4111,6031
-563,7/16/2012,3,1,7,1,1,0.763333,0.724125,0.645,0.164187,1088,5742,6830
-564,7/17/2012,3,1,7,2,1,0.818333,0.755683,0.505833,0.114429,921,5865,6786
-565,7/18/2012,3,1,7,3,1,0.793333,0.745583,0.577083,0.137442,799,4914,5713
-566,7/19/2012,3,1,7,4,1,0.77,0.714642,0.600417,0.165429,888,5703,6591
-567,7/20/2012,3,1,7,5,2,0.665833,0.613025,0.844167,0.208967,747,5123,5870
-568,7/21/2012,3,1,7,6,3,0.595833,0.549912,0.865417,0.2133,1264,3195,4459
-569,7/22/2012,3,1,7,0,2,0.6675,0.623125,0.7625,0.0939208,2544,4866,7410
-570,7/23/2012,3,1,7,1,1,0.741667,0.690017,0.694167,0.138683,1135,5831,6966
-571,7/24/2012,3,1,7,2,1,0.750833,0.70645,0.655,0.211454,1140,6452,7592
-572,7/25/2012,3,1,7,3,1,0.724167,0.654054,0.45,0.1648,1383,6790,8173
-573,7/26/2012,3,1,7,4,1,0.776667,0.739263,0.596667,0.284813,1036,5825,6861
-574,7/27/2012,3,1,7,5,1,0.781667,0.734217,0.594583,0.152992,1259,5645,6904
-575,7/28/2012,3,1,7,6,1,0.755833,0.697604,0.613333,0.15735,2234,4451,6685
-576,7/29/2012,3,1,7,0,1,0.721667,0.667933,0.62375,0.170396,2153,4444,6597
-577,7/30/2012,3,1,7,1,1,0.730833,0.684987,0.66875,0.153617,1040,6065,7105
-578,7/31/2012,3,1,7,2,1,0.713333,0.662896,0.704167,0.165425,968,6248,7216
-579,8/1/2012,3,1,8,3,1,0.7175,0.667308,0.6775,0.141179,1074,6506,7580
-580,8/2/2012,3,1,8,4,1,0.7525,0.707088,0.659583,0.129354,983,6278,7261
-581,8/3/2012,3,1,8,5,2,0.765833,0.722867,0.6425,0.215792,1328,5847,7175
-582,8/4/2012,3,1,8,6,1,0.793333,0.751267,0.613333,0.257458,2345,4479,6824
-583,8/5/2012,3,1,8,0,1,0.769167,0.731079,0.6525,0.290421,1707,3757,5464
-584,8/6/2012,3,1,8,1,2,0.7525,0.710246,0.654167,0.129354,1233,5780,7013
-585,8/7/2012,3,1,8,2,2,0.735833,0.697621,0.70375,0.116908,1278,5995,7273
-586,8/8/2012,3,1,8,3,2,0.75,0.707717,0.672917,0.1107,1263,6271,7534
-587,8/9/2012,3,1,8,4,1,0.755833,0.699508,0.620417,0.1561,1196,6090,7286
-588,8/10/2012,3,1,8,5,2,0.715833,0.667942,0.715833,0.238813,1065,4721,5786
-589,8/11/2012,3,1,8,6,2,0.6925,0.638267,0.732917,0.206479,2247,4052,6299
-590,8/12/2012,3,1,8,0,1,0.700833,0.644579,0.530417,0.122512,2182,4362,6544
-591,8/13/2012,3,1,8,1,1,0.720833,0.662254,0.545417,0.136212,1207,5676,6883
-592,8/14/2012,3,1,8,2,1,0.726667,0.676779,0.686667,0.169158,1128,5656,6784
-593,8/15/2012,3,1,8,3,1,0.706667,0.654037,0.619583,0.169771,1198,6149,7347
-594,8/16/2012,3,1,8,4,1,0.719167,0.654688,0.519167,0.141796,1338,6267,7605
-595,8/17/2012,3,1,8,5,1,0.723333,0.2424,0.570833,0.231354,1483,5665,7148
-596,8/18/2012,3,1,8,6,1,0.678333,0.618071,0.603333,0.177867,2827,5038,7865
-597,8/19/2012,3,1,8,0,2,0.635833,0.603554,0.711667,0.08645,1208,3341,4549
-598,8/20/2012,3,1,8,1,2,0.635833,0.595967,0.734167,0.129979,1026,5504,6530
-599,8/21/2012,3,1,8,2,1,0.649167,0.601025,0.67375,0.0727708,1081,5925,7006
-600,8/22/2012,3,1,8,3,1,0.6675,0.621854,0.677083,0.0702833,1094,6281,7375
-601,8/23/2012,3,1,8,4,1,0.695833,0.637008,0.635833,0.0845958,1363,6402,7765
-602,8/24/2012,3,1,8,5,2,0.7025,0.6471,0.615,0.0721458,1325,6257,7582
-603,8/25/2012,3,1,8,6,2,0.661667,0.618696,0.712917,0.244408,1829,4224,6053
-604,8/26/2012,3,1,8,0,2,0.653333,0.595996,0.845833,0.228858,1483,3772,5255
-605,8/27/2012,3,1,8,1,1,0.703333,0.654688,0.730417,0.128733,989,5928,6917
-606,8/28/2012,3,1,8,2,1,0.728333,0.66605,0.62,0.190925,935,6105,7040
-607,8/29/2012,3,1,8,3,1,0.685,0.635733,0.552083,0.112562,1177,6520,7697
-608,8/30/2012,3,1,8,4,1,0.706667,0.652779,0.590417,0.0771167,1172,6541,7713
-609,8/31/2012,3,1,8,5,1,0.764167,0.6894,0.5875,0.168533,1433,5917,7350
-610,9/1/2012,3,1,9,6,2,0.753333,0.702654,0.638333,0.113187,2352,3788,6140
-611,9/2/2012,3,1,9,0,2,0.696667,0.649,0.815,0.0640708,2613,3197,5810
-612,9/3/2012,3,1,9,1,1,0.7075,0.661629,0.790833,0.151121,1965,4069,6034
-613,9/4/2012,3,1,9,2,1,0.725833,0.686888,0.755,0.236321,867,5997,6864
-614,9/5/2012,3,1,9,3,1,0.736667,0.708983,0.74125,0.187808,832,6280,7112
-615,9/6/2012,3,1,9,4,2,0.696667,0.655329,0.810417,0.142421,611,5592,6203
-616,9/7/2012,3,1,9,5,1,0.703333,0.657204,0.73625,0.171646,1045,6459,7504
-617,9/8/2012,3,1,9,6,2,0.659167,0.611121,0.799167,0.281104,1557,4419,5976
-618,9/9/2012,3,1,9,0,1,0.61,0.578925,0.5475,0.224496,2570,5657,8227
-619,9/10/2012,3,1,9,1,1,0.583333,0.565654,0.50375,0.258713,1118,6407,7525
-620,9/11/2012,3,1,9,2,1,0.5775,0.554292,0.52,0.0920542,1070,6697,7767
-621,9/12/2012,3,1,9,3,1,0.599167,0.570075,0.577083,0.131846,1050,6820,7870
-622,9/13/2012,3,1,9,4,1,0.6125,0.579558,0.637083,0.0827208,1054,6750,7804
-623,9/14/2012,3,1,9,5,1,0.633333,0.594083,0.6725,0.103863,1379,6630,8009
-624,9/15/2012,3,1,9,6,1,0.608333,0.585867,0.501667,0.247521,3160,5554,8714
-625,9/16/2012,3,1,9,0,1,0.58,0.563125,0.57,0.0901833,2166,5167,7333
-626,9/17/2012,3,1,9,1,2,0.580833,0.55305,0.734583,0.151742,1022,5847,6869
-627,9/18/2012,3,1,9,2,2,0.623333,0.565067,0.8725,0.357587,371,3702,4073
-628,9/19/2012,3,1,9,3,1,0.5525,0.540404,0.536667,0.215175,788,6803,7591
-629,9/20/2012,3,1,9,4,1,0.546667,0.532192,0.618333,0.118167,939,6781,7720
-630,9/21/2012,3,1,9,5,1,0.599167,0.571971,0.66875,0.154229,1250,6917,8167
-631,9/22/2012,3,1,9,6,1,0.65,0.610488,0.646667,0.283583,2512,5883,8395
-632,9/23/2012,4,1,9,0,1,0.529167,0.518933,0.467083,0.223258,2454,5453,7907
-633,9/24/2012,4,1,9,1,1,0.514167,0.502513,0.492917,0.142404,1001,6435,7436
-634,9/25/2012,4,1,9,2,1,0.55,0.544179,0.57,0.236321,845,6693,7538
-635,9/26/2012,4,1,9,3,1,0.635,0.596613,0.630833,0.2444,787,6946,7733
-636,9/27/2012,4,1,9,4,2,0.65,0.607975,0.690833,0.134342,751,6642,7393
-637,9/28/2012,4,1,9,5,2,0.619167,0.585863,0.69,0.164179,1045,6370,7415
-638,9/29/2012,4,1,9,6,1,0.5425,0.530296,0.542917,0.227604,2589,5966,8555
-639,9/30/2012,4,1,9,0,1,0.526667,0.517663,0.583333,0.134958,2015,4874,6889
-640,10/1/2012,4,1,10,1,2,0.520833,0.512,0.649167,0.0908042,763,6015,6778
-641,10/2/2012,4,1,10,2,3,0.590833,0.542333,0.871667,0.104475,315,4324,4639
-642,10/3/2012,4,1,10,3,2,0.6575,0.599133,0.79375,0.0665458,728,6844,7572
-643,10/4/2012,4,1,10,4,2,0.6575,0.607975,0.722917,0.117546,891,6437,7328
-644,10/5/2012,4,1,10,5,1,0.615,0.580187,0.6275,0.10635,1516,6640,8156
-645,10/6/2012,4,1,10,6,1,0.554167,0.538521,0.664167,0.268025,3031,4934,7965
-646,10/7/2012,4,1,10,0,2,0.415833,0.419813,0.708333,0.141162,781,2729,3510
-647,10/8/2012,4,1,10,1,2,0.383333,0.387608,0.709583,0.189679,874,4604,5478
-648,10/9/2012,4,1,10,2,2,0.446667,0.438112,0.761667,0.1903,601,5791,6392
-649,10/10/2012,4,1,10,3,1,0.514167,0.503142,0.630833,0.187821,780,6911,7691
-650,10/11/2012,4,1,10,4,1,0.435,0.431167,0.463333,0.181596,834,6736,7570
-651,10/12/2012,4,1,10,5,1,0.4375,0.433071,0.539167,0.235092,1060,6222,7282
-652,10/13/2012,4,1,10,6,1,0.393333,0.391396,0.494583,0.146142,2252,4857,7109
-653,10/14/2012,4,1,10,0,1,0.521667,0.508204,0.640417,0.278612,2080,4559,6639
-654,10/15/2012,4,1,10,1,2,0.561667,0.53915,0.7075,0.296037,760,5115,5875
-655,10/16/2012,4,1,10,2,1,0.468333,0.460846,0.558333,0.182221,922,6612,7534
-656,10/17/2012,4,1,10,3,1,0.455833,0.450108,0.692917,0.101371,979,6482,7461
-657,10/18/2012,4,1,10,4,2,0.5225,0.512625,0.728333,0.236937,1008,6501,7509
-658,10/19/2012,4,1,10,5,2,0.563333,0.537896,0.815,0.134954,753,4671,5424
-659,10/20/2012,4,1,10,6,1,0.484167,0.472842,0.572917,0.117537,2806,5284,8090
-660,10/21/2012,4,1,10,0,1,0.464167,0.456429,0.51,0.166054,2132,4692,6824
-661,10/22/2012,4,1,10,1,1,0.4875,0.482942,0.568333,0.0814833,830,6228,7058
-662,10/23/2012,4,1,10,2,1,0.544167,0.530304,0.641667,0.0945458,841,6625,7466
-663,10/24/2012,4,1,10,3,1,0.5875,0.558721,0.63625,0.0727792,795,6898,7693
-664,10/25/2012,4,1,10,4,2,0.55,0.529688,0.800417,0.124375,875,6484,7359
-665,10/26/2012,4,1,10,5,2,0.545833,0.52275,0.807083,0.132467,1182,6262,7444
-666,10/27/2012,4,1,10,6,2,0.53,0.515133,0.72,0.235692,2643,5209,7852
-667,10/28/2012,4,1,10,0,2,0.4775,0.467771,0.694583,0.398008,998,3461,4459
-668,10/29/2012,4,1,10,1,3,0.44,0.4394,0.88,0.3582,2,20,22
-669,10/30/2012,4,1,10,2,2,0.318182,0.309909,0.825455,0.213009,87,1009,1096
-670,10/31/2012,4,1,10,3,2,0.3575,0.3611,0.666667,0.166667,419,5147,5566
-671,11/1/2012,4,1,11,4,2,0.365833,0.369942,0.581667,0.157346,466,5520,5986
-672,11/2/2012,4,1,11,5,1,0.355,0.356042,0.522083,0.266175,618,5229,5847
-673,11/3/2012,4,1,11,6,2,0.343333,0.323846,0.49125,0.270529,1029,4109,5138
-674,11/4/2012,4,1,11,0,1,0.325833,0.329538,0.532917,0.179108,1201,3906,5107
-675,11/5/2012,4,1,11,1,1,0.319167,0.308075,0.494167,0.236325,378,4881,5259
-676,11/6/2012,4,1,11,2,1,0.280833,0.281567,0.567083,0.173513,466,5220,5686
-677,11/7/2012,4,1,11,3,2,0.295833,0.274621,0.5475,0.304108,326,4709,5035
-678,11/8/2012,4,1,11,4,1,0.352174,0.341891,0.333478,0.347835,340,4975,5315
-679,11/9/2012,4,1,11,5,1,0.361667,0.355413,0.540833,0.214558,709,5283,5992
-680,11/10/2012,4,1,11,6,1,0.389167,0.393937,0.645417,0.0578458,2090,4446,6536
-681,11/11/2012,4,1,11,0,1,0.420833,0.421713,0.659167,0.1275,2290,4562,6852
-682,11/12/2012,4,1,11,1,1,0.485,0.475383,0.741667,0.173517,1097,5172,6269
-683,11/13/2012,4,1,11,2,2,0.343333,0.323225,0.662917,0.342046,327,3767,4094
-684,11/14/2012,4,1,11,3,1,0.289167,0.281563,0.552083,0.199625,373,5122,5495
-685,11/15/2012,4,1,11,4,2,0.321667,0.324492,0.620417,0.152987,320,5125,5445
-686,11/16/2012,4,1,11,5,1,0.345,0.347204,0.524583,0.171025,484,5214,5698
-687,11/17/2012,4,1,11,6,1,0.325,0.326383,0.545417,0.179729,1313,4316,5629
-688,11/18/2012,4,1,11,0,1,0.3425,0.337746,0.692917,0.227612,922,3747,4669
-689,11/19/2012,4,1,11,1,2,0.380833,0.375621,0.623333,0.235067,449,5050,5499
-690,11/20/2012,4,1,11,2,2,0.374167,0.380667,0.685,0.082725,534,5100,5634
-691,11/21/2012,4,1,11,3,1,0.353333,0.364892,0.61375,0.103246,615,4531,5146
-692,11/22/2012,4,1,11,4,1,0.34,0.350371,0.580417,0.0528708,955,1470,2425
-693,11/23/2012,4,1,11,5,1,0.368333,0.378779,0.56875,0.148021,1603,2307,3910
-694,11/24/2012,4,1,11,6,1,0.278333,0.248742,0.404583,0.376871,532,1745,2277
-695,11/25/2012,4,1,11,0,1,0.245833,0.257583,0.468333,0.1505,309,2115,2424
-696,11/26/2012,4,1,11,1,1,0.313333,0.339004,0.535417,0.04665,337,4750,5087
-697,11/27/2012,4,1,11,2,2,0.291667,0.281558,0.786667,0.237562,123,3836,3959
-698,11/28/2012,4,1,11,3,1,0.296667,0.289762,0.50625,0.210821,198,5062,5260
-699,11/29/2012,4,1,11,4,1,0.28087,0.298422,0.555652,0.115522,243,5080,5323
-700,11/30/2012,4,1,11,5,1,0.298333,0.323867,0.649583,0.0584708,362,5306,5668
-701,12/1/2012,4,1,12,6,2,0.298333,0.316904,0.806667,0.0597042,951,4240,5191
-702,12/2/2012,4,1,12,0,2,0.3475,0.359208,0.823333,0.124379,892,3757,4649
-703,12/3/2012,4,1,12,1,1,0.4525,0.455796,0.7675,0.0827208,555,5679,6234
-704,12/4/2012,4,1,12,2,1,0.475833,0.469054,0.73375,0.174129,551,6055,6606
-705,12/5/2012,4,1,12,3,1,0.438333,0.428012,0.485,0.324021,331,5398,5729
-706,12/6/2012,4,1,12,4,1,0.255833,0.258204,0.50875,0.174754,340,5035,5375
-707,12/7/2012,4,1,12,5,2,0.320833,0.321958,0.764167,0.1306,349,4659,5008
-708,12/8/2012,4,1,12,6,2,0.381667,0.389508,0.91125,0.101379,1153,4429,5582
-709,12/9/2012,4,1,12,0,2,0.384167,0.390146,0.905417,0.157975,441,2787,3228
-710,12/10/2012,4,1,12,1,2,0.435833,0.435575,0.925,0.190308,329,4841,5170
-711,12/11/2012,4,1,12,2,2,0.353333,0.338363,0.596667,0.296037,282,5219,5501
-712,12/12/2012,4,1,12,3,2,0.2975,0.297338,0.538333,0.162937,310,5009,5319
-713,12/13/2012,4,1,12,4,1,0.295833,0.294188,0.485833,0.174129,425,5107,5532
-714,12/14/2012,4,1,12,5,1,0.281667,0.294192,0.642917,0.131229,429,5182,5611
-715,12/15/2012,4,1,12,6,1,0.324167,0.338383,0.650417,0.10635,767,4280,5047
-716,12/16/2012,4,1,12,0,2,0.3625,0.369938,0.83875,0.100742,538,3248,3786
-717,12/17/2012,4,1,12,1,2,0.393333,0.4015,0.907083,0.0982583,212,4373,4585
-718,12/18/2012,4,1,12,2,1,0.410833,0.409708,0.66625,0.221404,433,5124,5557
-719,12/19/2012,4,1,12,3,1,0.3325,0.342162,0.625417,0.184092,333,4934,5267
-720,12/20/2012,4,1,12,4,2,0.33,0.335217,0.667917,0.132463,314,3814,4128
-721,12/21/2012,1,1,12,5,2,0.326667,0.301767,0.556667,0.374383,221,3402,3623
-722,12/22/2012,1,1,12,6,1,0.265833,0.236113,0.44125,0.407346,205,1544,1749
-723,12/23/2012,1,1,12,0,1,0.245833,0.259471,0.515417,0.133083,408,1379,1787
-724,12/24/2012,1,1,12,1,2,0.231304,0.2589,0.791304,0.0772304,174,746,920
-725,12/25/2012,1,1,12,2,2,0.291304,0.294465,0.734783,0.168726,440,573,1013
-726,12/26/2012,1,1,12,3,3,0.243333,0.220333,0.823333,0.316546,9,432,441
-727,12/27/2012,1,1,12,4,2,0.254167,0.226642,0.652917,0.350133,247,1867,2114
-728,12/28/2012,1,1,12,5,2,0.253333,0.255046,0.59,0.155471,644,2451,3095
-729,12/29/2012,1,1,12,6,2,0.253333,0.2424,0.752917,0.124383,159,1182,1341
-730,12/30/2012,1,1,12,0,1,0.255833,0.2317,0.483333,0.350754,364,1432,1796
-731,12/31/2012,1,1,12,1,2,0.215833,0.223487,0.5775,0.154846,439,2290,2729

how-to-use-azureml/automated-machine-learning/forecasting-bike-share/forecasting_script.py

@@ -1,53 +0,0 @@
-import argparse
-from azureml.core import Dataset, Run
-import joblib
-
-parser = argparse.ArgumentParser()
-parser.add_argument(
-    "--target_column_name",
-    type=str,
-    dest="target_column_name",
-    help="Target Column Name",
-)
-parser.add_argument(
-    "--test_dataset", type=str, dest="test_dataset", help="Test Dataset"
-)
-
-args = parser.parse_args()
-target_column_name = args.target_column_name
-test_dataset_id = args.test_dataset
-
-run = Run.get_context()
-ws = run.experiment.workspace
-
-# get the input dataset by id
-test_dataset = Dataset.get_by_id(ws, id=test_dataset_id)
-
-X_test_df = (
-    test_dataset.drop_columns(columns=[target_column_name])
-    .to_pandas_dataframe()
-    .reset_index(drop=True)
-)
-y_test_df = (
-    test_dataset.with_timestamp_columns(None)
-    .keep_columns(columns=[target_column_name])
-    .to_pandas_dataframe()
-)
-
-fitted_model = joblib.load("model.pkl")
-
-X_rf = fitted_model.rolling_forecast(X_test_df, y_test_df.values, step=1)
-
-# Add predictions, actuals, and horizon relative to rolling origin to the test feature data
-assign_dict = {
-    fitted_model.forecast_origin_column_name: "forecast_origin",
-    fitted_model.forecast_column_name: "predicted",
-    fitted_model.actual_column_name: target_column_name,
-}
-X_rf.rename(columns=assign_dict, inplace=True)
-
-file_name = "outputs/predictions.csv"
-export_csv = X_rf.to_csv(file_name, header=True)
-
-# Upload the predictions into artifacts
-run.upload_file(name=file_name, path_or_stream=file_name)

how-to-use-azureml/automated-machine-learning/forecasting-bike-share/metrics_helper.py

@@ -1,22 +0,0 @@
-import pandas as pd
-import numpy as np
-
-
-def APE(actual, pred):
-    """
-    Calculate absolute percentage error.
-    Returns a vector of APE values with same length as actual/pred.
-    """
-    return 100 * np.abs((actual - pred) / actual)
-
-
-def MAPE(actual, pred):
-    """
-    Calculate mean absolute percentage error.
-    Remove NA and values where actual is close to zero
-    """
-    not_na = ~(np.isnan(actual) | np.isnan(pred))
-    not_zero = ~np.isclose(actual, 0.0)
-    actual_safe = actual[not_na & not_zero]
-    pred_safe = pred[not_na & not_zero]
-    return np.mean(APE(actual_safe, pred_safe))

how-to-use-azureml/automated-machine-learning/forecasting-bike-share/run_forecast.py

@@ -1,40 +0,0 @@
-from azureml.core import ScriptRunConfig
-
-
-def run_rolling_forecast(
-    test_experiment,
-    compute_target,
-    train_run,
-    test_dataset,
-    target_column_name,
-    inference_folder="./forecast",
-):
-    train_run.download_file("outputs/model.pkl", inference_folder + "/model.pkl")
-
-    inference_env = train_run.get_environment()
-
-    config = ScriptRunConfig(
-        source_directory=inference_folder,
-        script="forecasting_script.py",
-        arguments=[
-            "--target_column_name",
-            target_column_name,
-            "--test_dataset",
-            test_dataset.as_named_input(test_dataset.name),
-        ],
-        compute_target=compute_target,
-        environment=inference_env,
-    )
-
-    run = test_experiment.submit(
-        config,
-        tags={
-            "training_run_id": train_run.id,
-            "run_algorithm": train_run.properties["run_algorithm"],
-            "valid_score": train_run.properties["score"],
-            "primary_metric": train_run.properties["primary_metric"],
-        },
-    )
-
-    run.log("run_algorithm", run.tags["run_algorithm"])
-    return run

how-to-use-azureml/automated-machine-learning/forecasting-energy-demand/auto-ml-forecasting-energy-demand.ipynb

@@ -9,64 +9,42 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand/auto-ml-forecasting-energy-demand.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<font color=\"red\" size=\"5\"><strong>!Important!</strong> </br>This notebook is outdated and is not supported by the AutoML Team. Please use the supported version ([link](https://github.com/Azure/azureml-examples/blob/main/sdk/python/jobs/automl-standalone-jobs/automl-forecasting-task-energy-demand/automl-forecasting-task-energy-demand-advanced-mlflow.ipynb)).</font>"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
         "# Automated Machine Learning\n",
-        "_**Forecasting using the Energy Demand Dataset**_\n",
+        "_**Energy Demand Forecasting**_\n",
         "\n",
         "## Contents\n",
-        "1. [Introduction](#introduction)\n",
-        "1. [Setup](#setup)\n",
-        "1. [Data and Forecasting Configurations](#data)\n",
-        "1. [Train](#train)\n",
-        "1. [Generate and Evaluate the Forecast](#forecast)\n",
-        "\n",
-        "Advanced Forecasting\n",
-        "1. [Advanced Training](#advanced_training)\n",
-        "1. [Advanced Results](#advanced_results)"
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Data](#Data)\n",
+        "1. [Train](#Train)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "# Introduction<a id=\"introduction\"></a>\n",
+        "## Introduction\n",
+        "In this example, we show how AutoML can be used for energy demand forecasting.\n",
         "\n",
-        "In this example we use the associated New York City energy demand dataset to showcase how you can use AutoML for a simple forecasting problem and explore the results. The goal is predict the energy demand for the next 48 hours based on historic time-series data.\n",
+        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
         "\n",
-        "If you are using an Azure Machine Learning Compute Instance, you are all set. Otherwise, go through the [configuration notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/configuration.ipynb) first, if you haven't already, to establish your connection to the AzureML Workspace.\n",
-        "\n",
-        "In this notebook you will learn how to:\n",
-        "1. Creating an Experiment using an existing Workspace\n",
-        "1. Configure AutoML using 'AutoMLConfig'\n",
-        "1. Train the model using AmlCompute\n",
-        "1. Explore the engineered features and results\n",
-        "1. Generate the forecast and compute the out-of-sample accuracy metrics\n",
-        "1. Configuration and remote run of AutoML for a time-series model with lag and rolling window features\n",
-        "1. Run and explore the forecast with lagging features"
+        "In this notebook you would see\n",
+        "1. Creating an Experiment in an existing Workspace\n",
+        "2. Instantiating AutoMLConfig with new task type \"forecasting\" for timeseries data training, and other timeseries related settings: for this dataset we use the basic one: \"time_column_name\" \n",
+        "3. Training the Model using local compute\n",
+        "4. Exploring the results\n",
+        "5. Testing the fitted model"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "# Setup<a id=\"setup\"></a>"
+        "## Setup\n"
       ]
     },
     {
@@ -75,46 +53,27 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "import json\n",
-        "import logging\n",
-        "\n",
-        "from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score\n",
-        "from matplotlib import pyplot as plt\n",
+        "import azureml.core\n",
         "import pandas as pd\n",
         "import numpy as np\n",
+        "import logging\n",
         "import warnings\n",
-        "import os\n",
-        "\n",
         "# Squash warning messages for cleaner output in the notebook\n",
         "warnings.showwarning = lambda *args, **kwargs: None\n",
         "\n",
-        "import azureml.core\n",
-        "from azureml.core import Experiment, Workspace, Dataset\n",
+        "\n",
+        "from azureml.core.workspace import Workspace\n",
+        "from azureml.core.experiment import Experiment\n",
         "from azureml.train.automl import AutoMLConfig\n",
-        "from datetime import datetime"
+        "from matplotlib import pyplot as plt\n",
+        "from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "This notebook is compatible with Azure ML SDK version 1.35.0 or later."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "As part of the setup you have already created an Azure ML `Workspace` object. For Automated ML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
+        "As part of the setup you have already created a <b>Workspace</b>. For AutoML you would need to create an <b>Experiment</b>. An <b>Experiment</b> is a named object in a <b>Workspace</b>, which is used to run experiments."
       ]
     },
     {
@@ -126,22 +85,22 @@
         "ws = Workspace.from_config()\n",
         "\n",
         "# choose a name for the run history container in the workspace\n",
-        "experiment_name = \"automl-forecasting-energydemand\"\n",
-        "\n",
-        "# # project folder\n",
-        "# project_folder = './sample_projects/automl-forecasting-energy-demand'\n",
+        "experiment_name = 'automl-energydemandforecasting'\n",
+        "# project folder\n",
+        "project_folder = './sample_projects/automl-local-energydemandforecasting'\n",
         "\n",
         "experiment = Experiment(ws, experiment_name)\n",
         "\n",
         "output = {}\n",
-        "output[\"Subscription ID\"] = ws.subscription_id\n",
-        "output[\"Workspace\"] = ws.name\n",
-        "output[\"Resource Group\"] = ws.resource_group\n",
-        "output[\"Location\"] = ws.location\n",
-        "output[\"Run History Name\"] = experiment_name\n",
-        "output[\"SDK Version\"] = azureml.core.VERSION\n",
-        "pd.set_option(\"display.max_colwidth\", None)\n",
-        "outputDf = pd.DataFrame(data=output, index=[\"\"])\n",
+        "output['SDK version'] = azureml.core.VERSION\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace'] = ws.name\n",
+        "output['Resource Group'] = ws.resource_group\n",
+        "output['Location'] = ws.location\n",
+        "output['Project Directory'] = project_folder\n",
+        "output['Run History Name'] = experiment_name\n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
         "outputDf.T"
       ]
     },
@@ -149,14 +108,8 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Create or Attach existing AmlCompute\n",
-        "A compute target is required to execute a remote Automated ML run. \n",
-        "\n",
-        "[Azure Machine Learning Compute](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-set-up-training-targets#amlcompute) is a managed-compute infrastructure that allows the user to easily create a single or multi-node compute. In this tutorial, you create AmlCompute as your training compute resource.\n",
-        "\n",
-        "#### Creation of AmlCompute takes approximately 5 minutes. \n",
-        "If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
-        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
+        "## Data\n",
+        "Read energy demanding data from file, and preview data."
       ]
     },
     {
@@ -165,46 +118,16 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
-        "from azureml.core.compute_target import ComputeTargetException\n",
-        "\n",
-        "# Choose a name for your cluster.\n",
-        "amlcompute_cluster_name = \"energy-cluster\"\n",
-        "\n",
-        "# Verify that cluster does not exist already\n",
-        "try:\n",
-        "    compute_target = ComputeTarget(workspace=ws, name=amlcompute_cluster_name)\n",
-        "    print(\"Found existing cluster, use it.\")\n",
-        "except ComputeTargetException:\n",
-        "    compute_config = AmlCompute.provisioning_configuration(\n",
-        "        vm_size=\"STANDARD_DS12_V2\", max_nodes=6\n",
-        "    )\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, compute_config)\n",
-        "\n",
-        "compute_target.wait_for_completion(show_output=True)"
+        "data = pd.read_csv(\"nyc_energy.csv\", parse_dates=['timeStamp'])\n",
+        "data.head()"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "# Data<a id=\"data\"></a>\n",
-        "\n",
-        "We will use energy consumption [data from New York City](http://mis.nyiso.com/public/P-58Blist.htm) for model training. The data is stored in a tabular format and includes energy demand and basic weather data at an hourly frequency. \n",
-        "\n",
-        "With Azure Machine Learning datasets you can keep a single copy of data in your storage, easily access data during model training, share data and collaborate with other users. Below, we will upload the datatset and create a [tabular dataset](https://docs.microsoft.com/bs-latn-ba/azure/machine-learning/service/how-to-create-register-datasets#dataset-types) to be used training and prediction."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Let's set up what we know about the dataset.\n",
-        "\n",
-        "<b>Target column</b> is what we want to forecast.<br></br>\n",
-        "<b>Time column</b> is the time axis along which to predict.\n",
-        "\n",
-        "The other columns, \"temp\" and \"precip\", are implicitly designated as features."
+        "### Split the data to train and test\n",
+        "\n"
       ]
     },
     {
@@ -213,8 +136,15 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "target_column_name = \"demand\"\n",
-        "time_column_name = \"timeStamp\""
+        "train = data[data['timeStamp'] < '2017-02-01']\n",
+        "test = data[data['timeStamp'] >= '2017-02-01']\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Prepare the test data, we will feed X_test to the fitted model and get prediction"
       ]
     },
     {
@@ -223,17 +153,17 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "dataset = Dataset.Tabular.from_delimited_files(\n",
-        "    path=\"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/nyc_energy.csv\"\n",
-        ").with_timestamp_columns(fine_grain_timestamp=time_column_name)\n",
-        "dataset.take(5).to_pandas_dataframe().reset_index(drop=True)"
+        "y_test = test.pop('demand').values\n",
+        "X_test = test"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "The NYC Energy dataset is missing energy demand values for all datetimes later than August 10th, 2017 5AM. Below, we trim the rows containing these missing values from the end of the dataset."
+        "### Split the train data to train and valid\n",
+        "\n",
+        "Use one month's data as valid data\n"
       ]
     },
     {
@@ -242,145 +172,69 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "# Cut off the end of the dataset due to large number of nan values\n",
-        "dataset = dataset.time_before(datetime(2017, 10, 10, 5))"
+        "X_train = train[train['timeStamp'] < '2017-01-01']\n",
+        "X_valid = train[train['timeStamp'] >= '2017-01-01']\n",
+        "y_train = X_train.pop('demand').values\n",
+        "y_valid = X_valid.pop('demand').values\n",
+        "print(X_train.shape)\n",
+        "print(y_train.shape)\n",
+        "print(X_valid.shape)\n",
+        "print(y_valid.shape)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Split the data into train and test sets"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "The first split we make is into train and test sets. Note that we are splitting on time. Data before and including August 8th, 2017 5AM will be used for training, and data after will be used for testing."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# split into train based on time\n",
-        "train = (\n",
-        "    dataset.time_before(datetime(2017, 8, 8, 5), include_boundary=True)\n",
-        "    .to_pandas_dataframe()\n",
-        "    .reset_index(drop=True)\n",
-        ")\n",
-        "train.sort_values(time_column_name).tail(5)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# split into test based on time\n",
-        "test = (\n",
-        "    dataset.time_between(datetime(2017, 8, 8, 6), datetime(2017, 8, 10, 5))\n",
-        "    .to_pandas_dataframe()\n",
-        "    .reset_index(drop=True)\n",
-        ")\n",
-        "test.head(5)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "jupyter": {
-          "outputs_hidden": false
-        },
-        "nteract": {
-          "transient": {
-            "deleting": false
-          }
-        }
-      },
-      "outputs": [],
-      "source": [
-        "# register the splitted train and test data in workspace storage\n",
-        "from azureml.data.dataset_factory import TabularDatasetFactory\n",
+        "## Train\n",
         "\n",
-        "datastore = ws.get_default_datastore()\n",
-        "train_dataset = TabularDatasetFactory.register_pandas_dataframe(\n",
-        "    train, target=(datastore, \"dataset/\"), name=\"nyc_energy_train\"\n",
-        ")\n",
-        "test_dataset = TabularDatasetFactory.register_pandas_dataframe(\n",
-        "    test, target=(datastore, \"dataset/\"), name=\"nyc_energy_test\"\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Setting the maximum forecast horizon\n",
-        "\n",
-        "The forecast horizon is the number of periods into the future that the model should predict. It is generally recommend that users set forecast horizons to less than 100 time periods (i.e. less than 100 hours in the NYC energy example). Furthermore, **AutoML's memory use and computation time increase in proportion to the length of the horizon**, so consider carefully how this value is set. If a long horizon forecast really is necessary, consider aggregating the series to a coarser time scale. \n",
-        "\n",
-        "Learn more about forecast horizons in our [Auto-train a time-series forecast model](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-auto-train-forecast#configure-and-run-experiment) guide.\n",
-        "\n",
-        "In this example, we set the horizon to 48 hours."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "forecast_horizon = 48"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Forecasting Parameters\n",
-        "To define forecasting parameters for your experiment training, you can leverage the ForecastingParameters class. The table below details the forecasting parameter we will be passing into our experiment.\n",
-        "\n",
-        "|Property|Description|\n",
-        "|-|-|\n",
-        "|**time_column_name**|The name of your time column.|\n",
-        "|**forecast_horizon**|The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly).|\n",
-        "|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information.\n",
-        "|**cv_step_size**|Number of periods between two consecutive cross-validation folds. The default value is \"auto\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Train<a id=\"train\"></a>\n",
-        "\n",
-        "Instantiate an AutoMLConfig object. This config defines the settings and data used to run the experiment. We can provide extra configurations within 'automl_settings', for this forecasting task we add the forecasting parameters to hold all the additional forecasting parameters.\n",
+        "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
         "\n",
         "|Property|Description|\n",
         "|-|-|\n",
         "|**task**|forecasting|\n",
-        "|**primary_metric**|This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>|\n",
-        "|**blocked_models**|Models in blocked_models won't be used by AutoML. All supported models can be found at [here](https://docs.microsoft.com/en-us/python/api/azureml-train-automl-client/azureml.train.automl.constants.supportedmodels.forecasting?view=azure-ml-py).|\n",
-        "|**experiment_timeout_hours**|Maximum amount of time in hours that the experiment take before it terminates.|\n",
-        "|**training_data**|The training data to be used within the experiment.|\n",
-        "|**label_column_name**|The name of the label column.|\n",
-        "|**compute_target**|The remote compute for training.|\n",
-        "|**n_cross_validations**|Number of cross-validation folds to use for model/pipeline selection. The default value is \"auto\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value.\n",
-        "|**enable_early_stopping**|Flag to enble early termination if the score is not improving in the short term.|\n",
-        "|**forecasting_parameters**|A class holds all the forecasting related parameters.|\n"
+        "|**primary_metric**|This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>\n",
+        "|**iterations**|Number of iterations. In each iteration, Auto ML trains a specific pipeline on the given data|\n",
+        "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+        "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+        "|**y**|(sparse) array-like, shape = [n_samples, ], targets values.|\n",
+        "|**X_valid**|Data used to evaluate a model in a iteration. (sparse) array-like, shape = [n_samples, n_features]|\n",
+        "|**y_valid**|Data used to evaluate a model in a iteration. (sparse) array-like, shape = [n_samples, ], targets values.|\n",
+        "|**path**|Relative path to the project folder.  AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "time_column_name = 'timeStamp'\n",
+        "automl_settings = {\n",
+        "    \"time_column_name\": time_column_name,\n",
+        "}\n",
+        "\n",
+        "\n",
+        "automl_config = AutoMLConfig(task = 'forecasting',\n",
+        "                             debug_log = 'automl_nyc_energy_errors.log',\n",
+        "                             primary_metric='normalized_root_mean_squared_error',\n",
+        "                             iterations = 10,\n",
+        "                             iteration_timeout_minutes = 5,\n",
+        "                             X = X_train,\n",
+        "                             y = y_train,\n",
+        "                             X_valid = X_valid,\n",
+        "                             y_valid = y_valid,\n",
+        "                             path=project_folder,\n",
+        "                             verbosity = logging.INFO,\n",
+        "                            **automl_settings)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "This notebook uses the blocked_models parameter to exclude some models that take a longer time to train on this dataset. You can choose to remove models from the blocked_models list but you may need to increase the experiment_timeout_hours parameter value to get results."
+        "You can call the submit method on the experiment object and pass the run configuration. For Local runs the execution is synchronous. Depending on the data and number of iterations this can run for while.\n",
+        "You will see the currently running iterations printing to the console."
       ]
     },
     {
@@ -389,36 +243,24 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.automl.core.forecasting_parameters import ForecastingParameters\n",
-        "\n",
-        "forecasting_parameters = ForecastingParameters(\n",
-        "    time_column_name=time_column_name,\n",
-        "    forecast_horizon=forecast_horizon,\n",
-        "    freq=\"H\",  # Set the forecast frequency to be hourly\n",
-        "    cv_step_size=\"auto\",\n",
-        ")\n",
-        "\n",
-        "automl_config = AutoMLConfig(\n",
-        "    task=\"forecasting\",\n",
-        "    primary_metric=\"normalized_root_mean_squared_error\",\n",
-        "    blocked_models=[\"ExtremeRandomTrees\", \"AutoArima\", \"Prophet\"],\n",
-        "    experiment_timeout_hours=0.3,\n",
-        "    training_data=train_dataset,\n",
-        "    label_column_name=target_column_name,\n",
-        "    compute_target=compute_target,\n",
-        "    enable_early_stopping=True,\n",
-        "    n_cross_validations=\"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
-        "    verbosity=logging.INFO,\n",
-        "    forecasting_parameters=forecasting_parameters,\n",
-        ")"
+        "local_run = experiment.submit(automl_config, show_output=True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Call the `submit` method on the experiment object and pass the run configuration. Depending on the data and the number of iterations this can run for a while.\n",
-        "One may specify `show_output = True` to print currently running iterations to the console."
+        "### Retrieve the Best Model\n",
+        "Below we select the best pipeline from our iterations. The get_output method on automl_classifier returns the best run and the fitted model for the last fit invocation. There are overloads on get_output that allow you to retrieve the best run and fitted model for any logged metric or a particular iteration."
       ]
     },
     {
@@ -427,24 +269,17 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "remote_run = experiment.submit(automl_config, show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run.wait_for_completion()"
+        "best_run, fitted_model = local_run.get_output()\n",
+        "fitted_model.steps"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Retrieve the Best Run details\n",
-        "Below we retrieve the best Run object from among all the runs in the experiment."
+        "### Test the Best Fitted Model\n",
+        "\n",
+        "Predict on training and test set, and calculate residual values."
       ]
     },
     {
@@ -453,16 +288,15 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "best_run = remote_run.get_best_child()\n",
-        "best_run"
+        "y_pred = fitted_model.predict(X_test)\n",
+        "y_pred"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Featurization\n",
-        "We can look at the engineered feature names generated in time-series featurization via. the JSON file named 'engineered_feature_names.json' under the run outputs."
+        "### Use the Check Data Function to remove the nan values from y_test to avoid error when calculate metrics "
       ]
     },
     {
@@ -471,28 +305,29 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "# Download the JSON file locally\n",
-        "best_run.download_file(\n",
-        "    \"outputs/engineered_feature_names.json\", \"engineered_feature_names.json\"\n",
-        ")\n",
-        "with open(\"engineered_feature_names.json\", \"r\") as f:\n",
-        "    records = json.load(f)\n",
+        "if len(y_test) != len(y_pred):\n",
+        "    raise ValueError(\n",
+        "        'the true values and prediction values do not have equal length.')\n",
+        "elif len(y_test) == 0:\n",
+        "    raise ValueError(\n",
+        "        'y_true and y_pred are empty.')\n",
         "\n",
-        "records"
+        "# if there is any non-numeric element in the y_true or y_pred,\n",
+        "# the ValueError exception will be thrown.\n",
+        "y_test_f = np.array(y_test).astype(float)\n",
+        "y_pred_f = np.array(y_pred).astype(float)\n",
+        "\n",
+        "# remove entries both in y_true and y_pred where at least\n",
+        "# one element in y_true or y_pred is missing\n",
+        "y_test = y_test_f[~(np.isnan(y_test_f) | np.isnan(y_pred_f))]\n",
+        "y_pred = y_pred_f[~(np.isnan(y_test_f) | np.isnan(y_pred_f))]"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### View featurization summary\n",
-        "You can also see what featurization steps were performed on different raw features in the user data. For each raw feature in the user data, the following information is displayed:\n",
-        "\n",
-        "+ Raw feature name\n",
-        "+ Number of engineered features formed out of this raw feature\n",
-        "+ Type detected\n",
-        "+ If feature was dropped\n",
-        "+ List of feature transformations for the raw feature"
+        "### Calculate metrics for the prediction\n"
       ]
     },
     {
@@ -501,299 +336,18 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "# Download the featurization summary JSON file locally\n",
-        "best_run.download_file(\n",
-        "    \"outputs/featurization_summary.json\", \"featurization_summary.json\"\n",
-        ")\n",
+        "print(\"[Test Data] \\nRoot Mean squared error: %.2f\" % np.sqrt(mean_squared_error(y_test, y_pred)))\n",
+        "# Explained variance score: 1 is perfect prediction\n",
+        "print('mean_absolute_error score: %.2f' % mean_absolute_error(y_test, y_pred))\n",
+        "print('R2 score: %.2f' % r2_score(y_test, y_pred))\n",
         "\n",
-        "# Render the JSON as a pandas DataFrame\n",
-        "with open(\"featurization_summary.json\", \"r\") as f:\n",
-        "    records = json.load(f)\n",
-        "fs = pd.DataFrame.from_records(records)\n",
         "\n",
-        "# View a summary of the featurization\n",
-        "fs[\n",
-        "    [\n",
-        "        \"RawFeatureName\",\n",
-        "        \"TypeDetected\",\n",
-        "        \"Dropped\",\n",
-        "        \"EngineeredFeatureCount\",\n",
-        "        \"Transformations\",\n",
-        "    ]\n",
-        "]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Forecasting<a id=\"forecast\"></a>\n",
-        "\n",
-        "Now that we have retrieved the best pipeline/model, it can be used to make predictions on test data. We will do batch scoring on the test dataset which should have the same schema as training dataset.\n",
-        "\n",
-        "The inference will run on a remote compute. In this example, it will re-use the training compute."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "test_experiment = Experiment(ws, experiment_name + \"_inference\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Retrieving forecasts from the model\n",
-        "We have created a function called `run_forecast` that submits the test data to the best model determined during the training run and retrieves forecasts. This function uses a helper script `forecasting_script` which is uploaded and expecuted on the remote compute."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from run_forecast import run_remote_inference\n",
-        "\n",
-        "remote_run_infer = run_remote_inference(\n",
-        "    test_experiment=test_experiment,\n",
-        "    compute_target=compute_target,\n",
-        "    train_run=best_run,\n",
-        "    test_dataset=test_dataset,\n",
-        "    target_column_name=target_column_name,\n",
-        ")\n",
-        "remote_run_infer.wait_for_completion(show_output=False)\n",
-        "\n",
-        "# download the inference output file to the local machine\n",
-        "remote_run_infer.download_file(\"outputs/predictions.csv\", \"predictions.csv\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Evaluate\n",
-        "To evaluate the accuracy of the forecast, we'll compare against the actual sales quantities for some select metrics, included the mean absolute percentage error (MAPE). For more metrics that can be used for evaluation after training, please see [supported metrics](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#regressionforecasting-metrics), and [how to calculate residuals](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#residuals)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# load forecast data frame\n",
-        "fcst_df = pd.read_csv(\"predictions.csv\", parse_dates=[time_column_name])\n",
-        "fcst_df.head()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.automl.core.shared import constants\n",
-        "from azureml.automl.runtime.shared.score import scoring\n",
-        "from matplotlib import pyplot as plt\n",
-        "\n",
-        "# use automl metrics module\n",
-        "scores = scoring.score_regression(\n",
-        "    y_test=fcst_df[target_column_name],\n",
-        "    y_pred=fcst_df[\"predicted\"],\n",
-        "    metrics=list(constants.Metric.SCALAR_REGRESSION_SET),\n",
-        ")\n",
-        "\n",
-        "print(\"[Test data scores]\\n\")\n",
-        "for key, value in scores.items():\n",
-        "    print(\"{}:   {:.3f}\".format(key, value))\n",
         "\n",
         "# Plot outputs\n",
-        "%matplotlib inline\n",
-        "test_pred = plt.scatter(fcst_df[target_column_name], fcst_df[\"predicted\"], color=\"b\")\n",
-        "test_test = plt.scatter(\n",
-        "    fcst_df[target_column_name], fcst_df[target_column_name], color=\"g\"\n",
-        ")\n",
-        "plt.legend(\n",
-        "    (test_pred, test_test), (\"prediction\", \"truth\"), loc=\"upper left\", fontsize=8\n",
-        ")\n",
-        "plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Advanced Training <a id=\"advanced_training\"></a>\n",
-        "We did not use lags in the previous model specification. In effect, the prediction was the result of a simple regression on date, time series identifier columns and any additional features. This is often a very good prediction as common time series patterns like seasonality and trends can be captured in this manner. Such simple regression is horizon-less: it doesn't matter how far into the future we are predicting, because we are not using past data. In the previous example, the horizon was only used to split the data for cross-validation."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Using lags and rolling window features\n",
-        "Now we will configure the target lags, that is the previous values of the target variables, meaning the prediction is no longer horizon-less. We therefore must still specify the `forecast_horizon` that the model will learn to forecast. The `target_lags` keyword specifies how far back we will construct the lags of the target variable, and the `target_rolling_window_size` specifies the size of the rolling window over which we will generate the `max`, `min` and `sum` features.\n",
-        "\n",
-        "This notebook uses the blocked_models parameter to exclude some models that take a longer time to train on this dataset.  You can choose to remove models from the blocked_models list but you may need to increase the iteration_timeout_minutes parameter value to get results."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "advanced_forecasting_parameters = ForecastingParameters(\n",
-        "    time_column_name=time_column_name,\n",
-        "    forecast_horizon=forecast_horizon,\n",
-        "    target_lags=12,\n",
-        "    target_rolling_window_size=4,\n",
-        "    cv_step_size=\"auto\",\n",
-        ")\n",
-        "\n",
-        "automl_config = AutoMLConfig(\n",
-        "    task=\"forecasting\",\n",
-        "    primary_metric=\"normalized_root_mean_squared_error\",\n",
-        "    blocked_models=[\n",
-        "        \"ElasticNet\",\n",
-        "        \"ExtremeRandomTrees\",\n",
-        "        \"GradientBoosting\",\n",
-        "        \"XGBoostRegressor\",\n",
-        "        \"ExtremeRandomTrees\",\n",
-        "        \"AutoArima\",\n",
-        "        \"Prophet\",\n",
-        "    ],  # These models are blocked for tutorial purposes, remove this for real use cases.\n",
-        "    experiment_timeout_hours=0.3,\n",
-        "    training_data=train_dataset,\n",
-        "    label_column_name=target_column_name,\n",
-        "    compute_target=compute_target,\n",
-        "    enable_early_stopping=True,\n",
-        "    n_cross_validations=\"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
-        "    verbosity=logging.INFO,\n",
-        "    forecasting_parameters=advanced_forecasting_parameters,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "We now start a new remote run, this time with lag and rolling window featurization. AutoML applies featurizations in the setup stage, prior to iterating over ML models. The full training set is featurized first, followed by featurization of each of the CV splits. Lag and rolling window features introduce additional complexity, so the run will take longer than in the previous example that lacked these featurizations."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "advanced_remote_run = experiment.submit(automl_config, show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "advanced_remote_run.wait_for_completion()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Retrieve the Best Run details"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "best_run_lags = remote_run.get_best_child()\n",
-        "best_run_lags"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Advanced Results<a id=\"advanced_results\"></a>\n",
-        "We did not use lags in the previous model specification. In effect, the prediction was the result of a simple regression on date, time series identifier columns and any additional features. This is often a very good prediction as common time series patterns like seasonality and trends can be captured in this manner. Such simple regression is horizon-less: it doesn't matter how far into the future we are predicting, because we are not using past data. In the previous example, the horizon was only used to split the data for cross-validation."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "test_experiment_advanced = Experiment(ws, experiment_name + \"_inference_advanced\")\n",
-        "advanced_remote_run_infer = run_remote_inference(\n",
-        "    test_experiment=test_experiment_advanced,\n",
-        "    compute_target=compute_target,\n",
-        "    train_run=best_run_lags,\n",
-        "    test_dataset=test_dataset,\n",
-        "    target_column_name=target_column_name,\n",
-        "    inference_folder=\"./forecast_advanced\",\n",
-        ")\n",
-        "advanced_remote_run_infer.wait_for_completion(show_output=False)\n",
-        "\n",
-        "# download the inference output file to the local machine\n",
-        "advanced_remote_run_infer.download_file(\n",
-        "    \"outputs/predictions.csv\", \"predictions_advanced.csv\"\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "fcst_adv_df = pd.read_csv(\"predictions_advanced.csv\", parse_dates=[time_column_name])\n",
-        "fcst_adv_df.head()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.automl.core.shared import constants\n",
-        "from azureml.automl.runtime.shared.score import scoring\n",
-        "from matplotlib import pyplot as plt\n",
-        "\n",
-        "# use automl metrics module\n",
-        "scores = scoring.score_regression(\n",
-        "    y_test=fcst_adv_df[target_column_name],\n",
-        "    y_pred=fcst_adv_df[\"predicted\"],\n",
-        "    metrics=list(constants.Metric.SCALAR_REGRESSION_SET),\n",
-        ")\n",
-        "\n",
-        "print(\"[Test data scores]\\n\")\n",
-        "for key, value in scores.items():\n",
-        "    print(\"{}:   {:.3f}\".format(key, value))\n",
-        "\n",
-        "# Plot outputs\n",
-        "%matplotlib inline\n",
-        "test_pred = plt.scatter(\n",
-        "    fcst_adv_df[target_column_name], fcst_adv_df[\"predicted\"], color=\"b\"\n",
-        ")\n",
-        "test_test = plt.scatter(\n",
-        "    fcst_adv_df[target_column_name], fcst_adv_df[target_column_name], color=\"g\"\n",
-        ")\n",
-        "plt.legend(\n",
-        "    (test_pred, test_test), (\"prediction\", \"truth\"), loc=\"upper left\", fontsize=8\n",
-        ")\n",
+        "%matplotlib notebook\n",
+        "test_pred = plt.scatter(y_test, y_pred, color='b')\n",
+        "test_test = plt.scatter(y_test, y_test, color='g')\n",
+        "plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
         "plt.show()"
       ]
     }
@@ -801,20 +355,13 @@
   "metadata": {
     "authors": [
       {
-        "name": "jialiu"
+        "name": "xiaga"
       }
     ],
-    "categories": [
-      "how-to-use-azureml",
-      "automated-machine-learning"
-    ],
-    "kernel_info": {
-      "name": "python3"
-    },
     "kernelspec": {
-      "display_name": "Python 3.8 - AzureML",
+      "display_name": "Python 3.6",
       "language": "python",
-      "name": "python38-azureml"
+      "name": "python36"
     },
     "language_info": {
       "codemirror_mode": {
@@ -826,22 +373,9 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.8.10"
-    },
-    "microsoft": {
-      "ms_spell_check": {
-        "ms_spell_check_language": "en"
-      }
-    },
-    "nteract": {
-      "version": "nteract-front-end@1.0.0"
-    },
-    "vscode": {
-      "interpreter": {
-        "hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
-      }
+      "version": "3.6.8"
     }
   },
   "nbformat": 4,
-  "nbformat_minor": 4
+  "nbformat_minor": 2
 }

how-to-use-azureml/automated-machine-learning/forecasting-energy-demand/forecasting_script.py

@@ -1,61 +0,0 @@
-"""
-This is the script that is executed on the compute instance. It relies
-on the model.pkl file which is uploaded along with this script to the
-compute instance.
-"""
-
-import argparse
-from azureml.core import Dataset, Run
-import joblib
-from pandas.tseries.frequencies import to_offset
-
-parser = argparse.ArgumentParser()
-parser.add_argument(
-    "--target_column_name",
-    type=str,
-    dest="target_column_name",
-    help="Target Column Name",
-)
-parser.add_argument(
-    "--test_dataset", type=str, dest="test_dataset", help="Test Dataset"
-)
-
-args = parser.parse_args()
-target_column_name = args.target_column_name
-test_dataset_id = args.test_dataset
-
-run = Run.get_context()
-ws = run.experiment.workspace
-
-# get the input dataset by id
-test_dataset = Dataset.get_by_id(ws, id=test_dataset_id)
-
-X_test = test_dataset.to_pandas_dataframe().reset_index(drop=True)
-y_test = X_test.pop(target_column_name).values
-
-# generate forecast
-fitted_model = joblib.load("model.pkl")
-# We have default quantiles values set as below(95th percentile)
-quantiles = [0.025, 0.5, 0.975]
-predicted_column_name = "predicted"
-PI = "prediction_interval"
-fitted_model.quantiles = quantiles
-pred_quantiles = fitted_model.forecast_quantiles(X_test)
-pred_quantiles[PI] = pred_quantiles[[min(quantiles), max(quantiles)]].apply(
-    lambda x: "[{}, {}]".format(x[0], x[1]), axis=1
-)
-X_test[target_column_name] = y_test
-X_test[PI] = pred_quantiles[PI]
-X_test[predicted_column_name] = pred_quantiles[0.5]
-# drop rows where prediction or actuals are nan
-# happens because of missing actuals
-# or at edges of time due to lags/rolling windows
-clean = X_test[
-    X_test[[target_column_name, predicted_column_name]].notnull().all(axis=1)
-]
-
-file_name = "outputs/predictions.csv"
-export_csv = clean.to_csv(file_name, header=True, index=False)  # added Index
-
-# Upload the predictions into artifacts
-run.upload_file(name=file_name, path_or_stream=file_name)

how-to-use-azureml/automated-machine-learning/forecasting-energy-demand/run_forecast.py

@@ -1,49 +0,0 @@
-import os
-import shutil
-from azureml.core import ScriptRunConfig
-
-
-def run_remote_inference(
-    test_experiment,
-    compute_target,
-    train_run,
-    test_dataset,
-    target_column_name,
-    inference_folder="./forecast",
-):
-    # Create local directory to copy the model.pkl and forecsting_script.py files into.
-    # These files will be uploaded to and executed on the compute instance.
-    os.makedirs(inference_folder, exist_ok=True)
-    shutil.copy("forecasting_script.py", inference_folder)
-
-    train_run.download_file(
-        "outputs/model.pkl", os.path.join(inference_folder, "model.pkl")
-    )
-
-    inference_env = train_run.get_environment()
-
-    config = ScriptRunConfig(
-        source_directory=inference_folder,
-        script="forecasting_script.py",
-        arguments=[
-            "--target_column_name",
-            target_column_name,
-            "--test_dataset",
-            test_dataset.as_named_input(test_dataset.name),
-        ],
-        compute_target=compute_target,
-        environment=inference_env,
-    )
-
-    run = test_experiment.submit(
-        config,
-        tags={
-            "training_run_id": train_run.id,
-            "run_algorithm": train_run.properties["run_algorithm"],
-            "valid_score": train_run.properties["score"],
-            "primary_metric": train_run.properties["primary_metric"],
-        },
-    )
-
-    run.log("run_algorithm", run.tags["run_algorithm"])
-    return run

how-to-use-azureml/automated-machine-learning/forecasting-forecast-function/auto-ml-forecasting-function.ipynb

@@ -1,935 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Automated Machine Learning\n",
-        "\n",
-        "#### Forecasting away from training data\n",
-        "\n",
-        "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "2. [Setup](#Setup)\n",
-        "3. [Data](#Data)\n",
-        "4. [Prepare remote compute and data.](#prepare_remote)\n",
-        "4. [Create the configuration and train a forecaster](#train)\n",
-        "5. [Forecasting from the trained model](#forecasting)\n",
-        "6. [Forecasting away from training data](#forecasting_away)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
-        "This notebook demonstrates the full interface of the `forecast()` function. \n",
-        "\n",
-        "The best known and most frequent usage of `forecast` enables forecasting on test sets that immediately follows training data. \n",
-        "\n",
-        "However, in many use cases it is necessary to continue using the model for some time before retraining it. This happens especially in **high frequency forecasting** when forecasts need to be made more frequently than the model can be retrained. Examples are in Internet of Things and predictive cloud resource scaling.\n",
-        "\n",
-        "Here we show how to use the `forecast()` function when a time gap exists between training data and prediction period.\n",
-        "\n",
-        "Terminology:\n",
-        "* forecast origin: the last period when the target value is known\n",
-        "* forecast periods(s): the period(s) for which the value of the target is desired.\n",
-        "* lookback: how many past periods (before forecast origin) the model function depends on. The larger of number of lags and length of rolling window.\n",
-        "* prediction context: `lookback` periods immediately preceding the forecast origin\n",
-        "\n",
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/automl-forecasting-function.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Setup"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Please make sure you have followed the [configuration notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/configuration.ipynb) so that your ML workspace information is saved in the config file."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "import pandas as pd\n",
-        "import numpy as np\n",
-        "import logging\n",
-        "import warnings\n",
-        "\n",
-        "import azureml.core\n",
-        "from azureml.core.dataset import Dataset\n",
-        "from pandas.tseries.frequencies import to_offset\n",
-        "from azureml.core.compute import AmlCompute\n",
-        "from azureml.core.compute import ComputeTarget\n",
-        "from azureml.core.runconfig import RunConfiguration\n",
-        "from azureml.core.conda_dependencies import CondaDependencies\n",
-        "\n",
-        "# Squash warning messages for cleaner output in the notebook\n",
-        "warnings.showwarning = lambda *args, **kwargs: None\n",
-        "\n",
-        "np.set_printoptions(precision=4, suppress=True, linewidth=120)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "This notebook is compatible with Azure ML SDK version 1.35.0 or later."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.workspace import Workspace\n",
-        "from azureml.core.experiment import Experiment\n",
-        "from azureml.train.automl import AutoMLConfig\n",
-        "\n",
-        "ws = Workspace.from_config()\n",
-        "\n",
-        "# choose a name for the run history container in the workspace\n",
-        "experiment_name = \"automl-forecast-function-demo\"\n",
-        "\n",
-        "experiment = Experiment(ws, experiment_name)\n",
-        "\n",
-        "output = {}\n",
-        "output[\"Subscription ID\"] = ws.subscription_id\n",
-        "output[\"Workspace\"] = ws.name\n",
-        "output[\"SKU\"] = ws.sku\n",
-        "output[\"Resource Group\"] = ws.resource_group\n",
-        "output[\"Location\"] = ws.location\n",
-        "output[\"Run History Name\"] = experiment_name\n",
-        "output[\"SDK Version\"] = azureml.core.VERSION\n",
-        "pd.set_option(\"display.max_colwidth\", None)\n",
-        "outputDf = pd.DataFrame(data=output, index=[\"\"])\n",
-        "outputDf.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Data\n",
-        "For the demonstration purposes we will generate the data artificially and use them for the forecasting."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "TIME_COLUMN_NAME = \"date\"\n",
-        "TIME_SERIES_ID_COLUMN_NAME = \"time_series_id\"\n",
-        "TARGET_COLUMN_NAME = \"y\"\n",
-        "\n",
-        "\n",
-        "def get_timeseries(\n",
-        "    train_len: int,\n",
-        "    test_len: int,\n",
-        "    time_column_name: str,\n",
-        "    target_column_name: str,\n",
-        "    time_series_id_column_name: str,\n",
-        "    time_series_number: int = 1,\n",
-        "    freq: str = \"H\",\n",
-        "):\n",
-        "    \"\"\"\n",
-        "    Return the time series of designed length.\n",
-        "\n",
-        "    :param train_len: The length of training data (one series).\n",
-        "    :type train_len: int\n",
-        "    :param test_len: The length of testing data (one series).\n",
-        "    :type test_len: int\n",
-        "    :param time_column_name: The desired name of a time column.\n",
-        "    :type time_column_name: str\n",
-        "    :param time_series_number: The number of time series in the data set.\n",
-        "    :type time_series_number: int\n",
-        "    :param freq: The frequency string representing pandas offset.\n",
-        "                 see https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html\n",
-        "    :type freq: str\n",
-        "    :returns: the tuple of train and test data sets.\n",
-        "    :rtype: tuple\n",
-        "\n",
-        "    \"\"\"\n",
-        "    data_train = []  # type: List[pd.DataFrame]\n",
-        "    data_test = []  # type: List[pd.DataFrame]\n",
-        "    data_length = train_len + test_len\n",
-        "    for i in range(time_series_number):\n",
-        "        X = pd.DataFrame(\n",
-        "            {\n",
-        "                time_column_name: pd.date_range(\n",
-        "                    start=\"2000-01-01\", periods=data_length, freq=freq\n",
-        "                ),\n",
-        "                target_column_name: np.arange(data_length).astype(float)\n",
-        "                + np.random.rand(data_length)\n",
-        "                + i * 5,\n",
-        "                \"ext_predictor\": np.asarray(range(42, 42 + data_length)),\n",
-        "                time_series_id_column_name: np.repeat(\"ts{}\".format(i), data_length),\n",
-        "            }\n",
-        "        )\n",
-        "        data_train.append(X[:train_len])\n",
-        "        data_test.append(X[train_len:])\n",
-        "    X_train = pd.concat(data_train)\n",
-        "    y_train = X_train.pop(target_column_name).values\n",
-        "    X_test = pd.concat(data_test)\n",
-        "    y_test = X_test.pop(target_column_name).values\n",
-        "    return X_train, y_train, X_test, y_test\n",
-        "\n",
-        "\n",
-        "n_test_periods = 6\n",
-        "n_train_periods = 30\n",
-        "X_train, y_train, X_test, y_test = get_timeseries(\n",
-        "    train_len=n_train_periods,\n",
-        "    test_len=n_test_periods,\n",
-        "    time_column_name=TIME_COLUMN_NAME,\n",
-        "    target_column_name=TARGET_COLUMN_NAME,\n",
-        "    time_series_id_column_name=TIME_SERIES_ID_COLUMN_NAME,\n",
-        "    time_series_number=2,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Let's see what the training data looks like."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "X_train.tail()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# plot the example time series\n",
-        "import matplotlib.pyplot as plt\n",
-        "\n",
-        "whole_data = X_train.copy()\n",
-        "target_label = \"y\"\n",
-        "whole_data[target_label] = y_train\n",
-        "for g in whole_data.groupby(\"time_series_id\"):\n",
-        "    plt.plot(g[1][\"date\"].values, g[1][\"y\"].values, label=g[0])\n",
-        "plt.legend()\n",
-        "plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Prepare remote compute and data. <a id=\"prepare_remote\"></a>\n",
-        "The [Machine Learning service workspace](https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-workspace), is paired with the storage account, which contains the default data store. We will use it to upload the artificial data and create [tabular dataset](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.tabulardataset?view=azure-ml-py) for training. A tabular dataset defines a series of lazily-evaluated, immutable operations to load data from the data source into tabular representation."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# We need to save thw artificial data and then upload them to default workspace datastore.\n",
-        "DATA_PATH = \"fc_fn_data\"\n",
-        "DATA_PATH_X = \"{}/data_train.csv\".format(DATA_PATH)\n",
-        "if not os.path.isdir(\"data\"):\n",
-        "    os.mkdir(\"data\")\n",
-        "pd.DataFrame(whole_data).to_csv(\"data/data_train.csv\", index=False)\n",
-        "# Upload saved data to the default data store.\n",
-        "ds = ws.get_default_datastore()\n",
-        "ds.upload(src_dir=\"./data\", target_path=DATA_PATH, overwrite=True, show_progress=True)\n",
-        "train_data = Dataset.Tabular.from_delimited_files(path=ds.path(DATA_PATH_X))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "You will need to create a [compute target](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-set-up-training-targets#amlcompute) for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
-        "\n",
-        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
-        "from azureml.core.compute_target import ComputeTargetException\n",
-        "\n",
-        "# Choose a name for your CPU cluster\n",
-        "amlcompute_cluster_name = \"fcfn-cluster\"\n",
-        "\n",
-        "# Verify that cluster does not exist already\n",
-        "try:\n",
-        "    compute_target = ComputeTarget(workspace=ws, name=amlcompute_cluster_name)\n",
-        "    print(\"Found existing cluster, use it.\")\n",
-        "except ComputeTargetException:\n",
-        "    compute_config = AmlCompute.provisioning_configuration(\n",
-        "        vm_size=\"STANDARD_DS12_V2\", max_nodes=6\n",
-        "    )\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, compute_config)\n",
-        "\n",
-        "compute_target.wait_for_completion(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Create the configuration and train a forecaster <a id=\"train\"></a>\n",
-        "First generate the configuration, in which we:\n",
-        "* Set metadata columns: target, time column and time-series id column names.\n",
-        "* Validate our data using cross validation with rolling window method.\n",
-        "* Set normalized root mean squared error as a metric to select the best model.\n",
-        "* Set early termination to True, so the iterations through the models will stop when no improvements in accuracy score will be made.\n",
-        "* Set limitations on the length of experiment run to 15 minutes.\n",
-        "* Finally, we set the task to be forecasting.\n",
-        "* We apply the lag lead operator to the target value i.e. we use the previous values as a predictor for the future ones.\n",
-        "* [Optional] Forecast frequency parameter (freq) represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.automl.core.forecasting_parameters import ForecastingParameters\n",
-        "\n",
-        "lags = [1, 2, 3]\n",
-        "forecast_horizon = n_test_periods\n",
-        "forecasting_parameters = ForecastingParameters(\n",
-        "    time_column_name=TIME_COLUMN_NAME,\n",
-        "    forecast_horizon=forecast_horizon,\n",
-        "    time_series_id_column_names=[TIME_SERIES_ID_COLUMN_NAME],\n",
-        "    target_lags=lags,\n",
-        "    freq=\"H\",  # Set the forecast frequency to be hourly,\n",
-        "    cv_step_size=\"auto\",\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Run the model selection and training process.  Validation errors and current status will be shown when setting `show_output=True` and the execution will be synchronous."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.workspace import Workspace\n",
-        "from azureml.core.experiment import Experiment\n",
-        "from azureml.train.automl import AutoMLConfig\n",
-        "\n",
-        "\n",
-        "automl_config = AutoMLConfig(\n",
-        "    task=\"forecasting\",\n",
-        "    debug_log=\"automl_forecasting_function.log\",\n",
-        "    primary_metric=\"normalized_root_mean_squared_error\",\n",
-        "    experiment_timeout_hours=0.25,\n",
-        "    enable_early_stopping=True,\n",
-        "    training_data=train_data,\n",
-        "    compute_target=compute_target,\n",
-        "    n_cross_validations=\"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
-        "    verbosity=logging.INFO,\n",
-        "    max_concurrent_iterations=4,\n",
-        "    max_cores_per_iteration=-1,\n",
-        "    label_column_name=target_label,\n",
-        "    forecasting_parameters=forecasting_parameters,\n",
-        ")\n",
-        "\n",
-        "remote_run = experiment.submit(automl_config, show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run.wait_for_completion()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Retrieve the best model to use it further.\n",
-        "_, fitted_model = remote_run.get_output()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Forecasting from the trained model <a id=\"forecasting\"></a>"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "In this section we will review the `forecast` interface for two main scenarios: forecasting right after the training data, and the more complex interface for forecasting when there is a gap (in the time sense) between training and testing data."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### X_train is directly followed by the X_test\n",
-        "\n",
-        "Let's first consider the case when the prediction period immediately follows the training data. This is typical in scenarios where we have the time to retrain the model every time we wish to forecast. Forecasts that are made on daily and slower cadence typically fall into this category. Retraining the model every time benefits the accuracy because the most recent data is often the most informative.\n",
-        "\n",
-        "![Forecasting after training](forecast_function_at_train.png)\n",
-        "\n",
-        "We use `X_test` as a **forecast request** to generate the predictions."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Typical path: X_test is known, forecast all upcoming periods"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# The data set contains hourly data, the training set ends at 01/02/2000 at 05:00\n",
-        "\n",
-        "# These are predictions we are asking the model to make (does not contain thet target column y),\n",
-        "# for 6 periods beginning with 2000-01-02 06:00, which immediately follows the training data\n",
-        "X_test"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "y_pred_no_gap, xy_nogap = fitted_model.forecast(X_test)\n",
-        "\n",
-        "# xy_nogap contains the predictions in the _automl_target_col column.\n",
-        "# Those same numbers are output in y_pred_no_gap\n",
-        "xy_nogap"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Confidence intervals"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Forecasting model may be used for the prediction of forecasting intervals by running ```forecast_quantiles()```. \n",
-        "This method accepts the same parameters as forecast()."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "quantiles = fitted_model.forecast_quantiles(X_test)\n",
-        "quantiles"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Distribution forecasts\n",
-        "\n",
-        "Often the figure of interest is not just the point prediction, but the prediction at some quantile of the distribution. \n",
-        "This arises when the forecast is used to control some kind of inventory, for example of grocery items or virtual machines for a cloud service. In such case, the control point is usually something like \"we want the item to be in stock and not run out 99% of the time\". This is called a \"service level\". Here is how you get quantile forecasts."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# specify which quantiles you would like\n",
-        "fitted_model.quantiles = [0.01, 0.5, 0.95]\n",
-        "# use forecast_quantiles function, not the forecast() one\n",
-        "y_pred_quantiles = fitted_model.forecast_quantiles(X_test)\n",
-        "\n",
-        "# quantile forecasts returned in a Dataframe along with the time and time series id columns\n",
-        "y_pred_quantiles"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Destination-date forecast: \"just do something\"\n",
-        "\n",
-        "In some scenarios, the X_test is not known. The forecast is likely to be weak, because it is missing contemporaneous predictors, which we will need to impute. If you still wish to predict forward under the assumption that the last known values will be carried forward, you can forecast out to \"destination date\". The destination date still needs to fit within the forecast horizon from training."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# We will take the destination date as a last date in the test set.\n",
-        "dest = max(X_test[TIME_COLUMN_NAME])\n",
-        "y_pred_dest, xy_dest = fitted_model.forecast(forecast_destination=dest)\n",
-        "\n",
-        "# This form also shows how we imputed the predictors which were not given. (Not so well! Use with caution!)\n",
-        "xy_dest"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Forecasting away from training data <a id=\"forecasting_away\"></a>\n",
-        "\n",
-        "Suppose we trained a model, some time passed, and now we want to apply the model without re-training. If the model \"looks back\" -- uses previous values of the target -- then we somehow need to provide those values to the model.\n",
-        "\n",
-        "![Forecasting after training](forecast_function_away_from_train.png)\n",
-        "\n",
-        "The notion of forecast origin comes into play: the forecast origin is **the last period for which we have seen the target value**. This applies per time-series, so each time-series can have a different forecast origin. \n",
-        "\n",
-        "The part of data before the forecast origin is the **prediction context**. To provide the context values the model needs when it looks back, we pass definite values in `y_test` (aligned with corresponding times in `X_test`)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# generate the same kind of test data we trained on,\n",
-        "# but now make the train set much longer, so that the test set will be in the future\n",
-        "X_context, y_context, X_away, y_away = get_timeseries(\n",
-        "    train_len=42,  # train data was 30 steps long\n",
-        "    test_len=4,\n",
-        "    time_column_name=TIME_COLUMN_NAME,\n",
-        "    target_column_name=TARGET_COLUMN_NAME,\n",
-        "    time_series_id_column_name=TIME_SERIES_ID_COLUMN_NAME,\n",
-        "    time_series_number=2,\n",
-        ")\n",
-        "\n",
-        "# end of the data we trained on\n",
-        "print(X_train.groupby(TIME_SERIES_ID_COLUMN_NAME)[TIME_COLUMN_NAME].max())\n",
-        "# start of the data we want to predict on\n",
-        "print(X_away.groupby(TIME_SERIES_ID_COLUMN_NAME)[TIME_COLUMN_NAME].min())"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "There is a gap of 12 hours between end of training and beginning of `X_away`. (It looks like 13 because all timestamps point to the start of the one hour periods.) Using only `X_away` will fail without adding context data for the model to consume."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "try:\n",
-        "    y_pred_away, xy_away = fitted_model.forecast(X_away)\n",
-        "    xy_away\n",
-        "except Exception as e:\n",
-        "    print(e)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "How should we read that eror message? The forecast origin is at the last time the model saw an actual value of `y` (the target). That was at the end of the training data! The model is attempting to forecast from the end of training data. But the requested forecast periods are past the forecast horizon. We need to provide a define `y` value to establish the forecast origin.\n",
-        "\n",
-        "We will use this helper function to take the required amount of context from the data preceding the testing data. It's definition is intentionally simplified to keep the idea in the clear."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "def make_forecasting_query(\n",
-        "    fulldata, time_column_name, target_column_name, forecast_origin, horizon, lookback\n",
-        "):\n",
-        "\n",
-        "    \"\"\"\n",
-        "    This function will take the full dataset, and create the query\n",
-        "    to predict all values of the time series from the `forecast_origin`\n",
-        "    forward for the next `horizon` horizons. Context from previous\n",
-        "    `lookback` periods will be included.\n",
-        "\n",
-        "\n",
-        "\n",
-        "    fulldata: pandas.DataFrame           a time series dataset. Needs to contain X and y.\n",
-        "    time_column_name: string             which column (must be in fulldata) is the time axis\n",
-        "    target_column_name: string           which column (must be in fulldata) is to be forecast\n",
-        "    forecast_origin: datetime type       the last time we (pretend to) have target values\n",
-        "    horizon: timedelta                   how far forward, in time units (not periods)\n",
-        "    lookback: timedelta                  how far back does the model look\n",
-        "\n",
-        "    Example:\n",
-        "\n",
-        "\n",
-        "    ```\n",
-        "\n",
-        "    forecast_origin = pd.to_datetime(\"2012-09-01\") + pd.DateOffset(days=5) # forecast 5 days after end of training\n",
-        "    print(forecast_origin)\n",
-        "\n",
-        "    X_query, y_query = make_forecasting_query(data,\n",
-        "                       forecast_origin = forecast_origin,\n",
-        "                       horizon = pd.DateOffset(days=7), # 7 days into the future\n",
-        "                       lookback = pd.DateOffset(days=1), # model has lag 1 period (day)\n",
-        "                      )\n",
-        "\n",
-        "    ```\n",
-        "    \"\"\"\n",
-        "\n",
-        "    X_past = fulldata[\n",
-        "        (fulldata[time_column_name] > forecast_origin - lookback)\n",
-        "        & (fulldata[time_column_name] <= forecast_origin)\n",
-        "    ]\n",
-        "\n",
-        "    X_future = fulldata[\n",
-        "        (fulldata[time_column_name] > forecast_origin)\n",
-        "        & (fulldata[time_column_name] <= forecast_origin + horizon)\n",
-        "    ]\n",
-        "\n",
-        "    y_past = X_past.pop(target_column_name).values.astype(float)\n",
-        "    y_future = X_future.pop(target_column_name).values.astype(float)\n",
-        "\n",
-        "    # Now take y_future and turn it into question marks\n",
-        "    y_query = y_future.copy().astype(float)  # because sometimes life hands you an int\n",
-        "    y_query.fill(np.NaN)\n",
-        "\n",
-        "    print(\"X_past is \" + str(X_past.shape) + \" - shaped\")\n",
-        "    print(\"X_future is \" + str(X_future.shape) + \" - shaped\")\n",
-        "    print(\"y_past is \" + str(y_past.shape) + \" - shaped\")\n",
-        "    print(\"y_query is \" + str(y_query.shape) + \" - shaped\")\n",
-        "\n",
-        "    X_pred = pd.concat([X_past, X_future])\n",
-        "    y_pred = np.concatenate([y_past, y_query])\n",
-        "    return X_pred, y_pred"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Let's see where the context data ends - it ends, by construction, just before the testing data starts."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "print(\n",
-        "    X_context.groupby(TIME_SERIES_ID_COLUMN_NAME)[TIME_COLUMN_NAME].agg(\n",
-        "        [\"min\", \"max\", \"count\"]\n",
-        "    )\n",
-        ")\n",
-        "print(\n",
-        "    X_away.groupby(TIME_SERIES_ID_COLUMN_NAME)[TIME_COLUMN_NAME].agg(\n",
-        "        [\"min\", \"max\", \"count\"]\n",
-        "    )\n",
-        ")\n",
-        "X_context.tail(5)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Since the length of the lookback is 3,\n",
-        "# we need to add 3 periods from the context to the request\n",
-        "# so that the model has the data it needs\n",
-        "\n",
-        "# Put the X and y back together for a while.\n",
-        "# They like each other and it makes them happy.\n",
-        "X_context[TARGET_COLUMN_NAME] = y_context\n",
-        "X_away[TARGET_COLUMN_NAME] = y_away\n",
-        "fulldata = pd.concat([X_context, X_away])\n",
-        "\n",
-        "# forecast origin is the last point of data, which is one 1-hr period before test\n",
-        "forecast_origin = X_away[TIME_COLUMN_NAME].min() - pd.DateOffset(hours=1)\n",
-        "# it is indeed the last point of the context\n",
-        "assert forecast_origin == X_context[TIME_COLUMN_NAME].max()\n",
-        "print(\"Forecast origin: \" + str(forecast_origin))\n",
-        "\n",
-        "# the model uses lags and rolling windows to look back in time\n",
-        "n_lookback_periods = max(lags)\n",
-        "lookback = pd.DateOffset(hours=n_lookback_periods)\n",
-        "\n",
-        "horizon = pd.DateOffset(hours=forecast_horizon)\n",
-        "\n",
-        "# now make the forecast query from context (refer to figure)\n",
-        "X_pred, y_pred = make_forecasting_query(\n",
-        "    fulldata, TIME_COLUMN_NAME, TARGET_COLUMN_NAME, forecast_origin, horizon, lookback\n",
-        ")\n",
-        "\n",
-        "# show the forecast request aligned\n",
-        "X_show = X_pred.copy()\n",
-        "X_show[TARGET_COLUMN_NAME] = y_pred\n",
-        "X_show"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Note that the forecast origin is at 17:00 for both time-series, and periods from 18:00 are to be forecast."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Now everything works\n",
-        "y_pred_away, xy_away = fitted_model.forecast(X_pred, y_pred)\n",
-        "\n",
-        "# show the forecast aligned\n",
-        "X_show = xy_away.reset_index()\n",
-        "# without the generated features\n",
-        "X_show[[\"date\", \"time_series_id\", \"ext_predictor\", \"_automl_target_col\"]]\n",
-        "# prediction is in _automl_target_col"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Forecasting farther than the forecast horizon <a id=\"recursive forecasting\"></a>\n",
-        "When the forecast destination, or the latest date in the prediction data frame, is farther into the future than the specified forecast horizon, the forecaster must be iteratively applied. Here, we advance the forecast origin on each iteration over the prediction window, predicting `max_horizon` periods ahead on each iteration. There are two choices for the context data to use as the forecaster advances into the prediction window:\n",
-        "\n",
-        "1. We can use forecasted values from previous iterations (recursive forecast),\n",
-        "2. We can use known, actual values of the target if they are available (rolling forecast).\n",
-        "\n",
-        "The first method is useful in a true forecasting scenario when we do not yet know the actual target values while the second is useful in an evaluation scenario where we want to compute accuracy metrics for the `max_horizon`-period-ahead forecaster over a long test set. We refer to the first as a **recursive forecast** since we apply the forecaster recursively over the prediction window and the second as a **rolling forecast** since we roll forward over known actuals.\n",
-        "\n",
-        "### Recursive forecasting\n",
-        "By default, the `forecast()` function will make point predictions out to the later date using a recursive operation mode. Internally, the method recursively applies the regular forecaster to generate context so that we can forecast further into the future. \n",
-        "\n",
-        "To illustrate the use-case and operation of recursive forecasting, we'll consider an example with a single time-series where the forecasting period directly follows the training period and is twice as long as the forecasting horizon given at training time.\n",
-        "\n",
-        "![Recursive_forecast_overview](recursive_forecast_overview_small.png)\n",
-        "\n",
-        "Internally, we apply the forecaster in an iterative manner and finish the forecast task in two interations. In the first iteration, we apply the forecaster and get the prediction for the first forecast-horizon periods (y_pred1). In the second iteraction, y_pred1 is used as the context to produce the prediction for the next forecast-horizon periods (y_pred2). The combination of (y_pred1 and y_pred2) gives the results for the total forecast periods. \n",
-        "\n",
-        "A caveat: forecast accuracy will likely be worse the farther we predict into the future since errors are compounded with recursive application of the forecaster.\n",
-        "\n",
-        "![Recursive_forecast_iter1](recursive_forecast_iter1.png)\n",
-        "![Recursive_forecast_iter2](recursive_forecast_iter2.png)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# generate the same kind of test data we trained on, but with a single time-series and test period twice as long\n",
-        "# as the forecast_horizon.\n",
-        "_, _, X_test_long, y_test_long = get_timeseries(\n",
-        "    train_len=n_train_periods,\n",
-        "    test_len=forecast_horizon * 2,\n",
-        "    time_column_name=TIME_COLUMN_NAME,\n",
-        "    target_column_name=TARGET_COLUMN_NAME,\n",
-        "    time_series_id_column_name=TIME_SERIES_ID_COLUMN_NAME,\n",
-        "    time_series_number=1,\n",
-        ")\n",
-        "\n",
-        "print(X_test_long.groupby(TIME_SERIES_ID_COLUMN_NAME)[TIME_COLUMN_NAME].min())\n",
-        "print(X_test_long.groupby(TIME_SERIES_ID_COLUMN_NAME)[TIME_COLUMN_NAME].max())"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# forecast() function will invoke the recursive forecast method internally.\n",
-        "y_pred_long, X_trans_long = fitted_model.forecast(X_test_long)\n",
-        "y_pred_long"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# What forecast() function does in this case is equivalent to iterating it twice over the test set as the following.\n",
-        "y_pred1, _ = fitted_model.forecast(X_test_long[:forecast_horizon])\n",
-        "y_pred_all, _ = fitted_model.forecast(\n",
-        "    X_test_long, np.concatenate((y_pred1, np.full(forecast_horizon, np.nan)))\n",
-        ")\n",
-        "np.array_equal(y_pred_all, y_pred_long)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Rolling forecasts\n",
-        "A rolling forecast is a similar concept to the recursive forecasts described above except that we use known actual values of the target for our context data. We have provided a different, public method for this called `rolling_forecast`. In addition to test data and actuals (`X_test` and `y_test`), `rolling_forecast` also accepts an optional `step` parameter that controls how far the origin advances on each iteration. The recursive forecast mode uses a fixed step of `max_horizon` while `rolling_forecast` defaults to a step size of 1, but can be set to any integer from 1 to `max_horizon`, inclusive.\n",
-        "\n",
-        "Let's see what the rolling forecast looks like on the long test set with the step set to 1:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "X_rf = fitted_model.rolling_forecast(X_test_long, y_test_long, step=1)\n",
-        "X_rf.head(n=12)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Notice that `rolling_forecast` has returned a single DataFrame containing all results and has generated some new columns: `_automl_forecast_origin`, `_automl_forecast_y`, and `_automl_actual_y`. These are the origin date for each forecast, the forecasted value and the actual value, respectively. Note that \"y\" in the forecast and actual column names will generally be replaced by the target column name supplied to AutoML.\n",
-        "\n",
-        "The output above shows forecasts for two prediction windows, the first with origin at the end of the training set and the second including the first observation in the test set (2000-01-01 06:00:00). Since the forecast windows overlap, there are multiple forecasts for most dates which are associated with different origin dates."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Confidence interval and distributional forecasts\n",
-        "AutoML cannot currently estimate forecast errors beyond the forecast horizon set during training, so the `forecast_quantiles()` function will return missing values for quantiles not equal to 0.5 beyond the forecast horizon. "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "fitted_model.forecast_quantiles(X_test_long)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Similarly with the simple senarios illustrated above, forecasting farther than the forecast horizon in other senarios like 'multiple time-series', 'Destination-date forecast', and 'forecast away from the training data' are also automatically handled by the `forecast()` function. "
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "jialiu"
-      }
-    ],
-    "category": "tutorial",
-    "compute": [
-      "Remote"
-    ],
-    "datasets": [
-      "None"
-    ],
-    "deployment": [
-      "None"
-    ],
-    "exclude_from_index": false,
-    "framework": [
-      "Azure ML AutoML"
-    ],
-    "friendly_name": "Forecasting away from training data",
-    "index_order": 3,
-    "kernelspec": {
-      "display_name": "Python 3.8 - AzureML",
-      "language": "python",
-      "name": "python38-azureml"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.7.13"
-    },
-    "tags": [
-      "Forecasting",
-      "Confidence Intervals"
-    ],
-    "task": "Forecasting",
-    "vscode": {
-      "interpreter": {
-        "hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
-      }
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 4
-}

how-to-use-azureml/automated-machine-learning/forecasting-github-dau/auto-ml-forecasting-github-dau.ipynb

@@ -1,710 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/forecasting-github-dau/auto-ml-forecasting-github-dau.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<font color=\"red\" size=\"5\"><strong>!Important!</strong> </br>This notebook is outdated and is not supported by the AutoML Team. Please use the supported version ([link](https://github.com/Azure/azureml-examples/tree/main/sdk/python/jobs/automl-standalone-jobs/automl-forecasting-github-dau)).</font>"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "source": [
-        "# Automated Machine Learning\n",
-        "**Github DAU Forecasting**\n",
-        "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Data](#Data)\n",
-        "1. [Train](#Train)\n",
-        "1. [Evaluate](#Evaluate)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "source": [
-        "## Introduction\n",
-        "This notebook demonstrates demand forecasting for Github Daily Active Users Dataset using AutoML.\n",
-        "\n",
-        "AutoML highlights here include using Deep Learning forecasts, Arima, Prophet,  Remote Execution and Remote Inferencing, and working with the `forecast` function. Please also look at the additional forecasting notebooks, which document lagging, rolling windows, forecast quantiles, other ways to use the forecast function, and forecaster deployment.\n",
-        "\n",
-        "Make sure you have executed the [configuration](https://github.com/Azure/MachineLearningNotebooks/blob/master/configuration.ipynb) before running this notebook.\n",
-        "\n",
-        "Notebook synopsis:\n",
-        "\n",
-        "1. Creating an Experiment in an existing Workspace\n",
-        "2. Configuration and remote run of AutoML for a time-series model exploring DNNs\n",
-        "4. Evaluating the fitted model using a rolling test "
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "source": [
-        "## Setup\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "import azureml.core\n",
-        "import pandas as pd\n",
-        "import numpy as np\n",
-        "import logging\n",
-        "import warnings\n",
-        "\n",
-        "from pandas.tseries.frequencies import to_offset\n",
-        "\n",
-        "# Squash warning messages for cleaner output in the notebook\n",
-        "warnings.showwarning = lambda *args, **kwargs: None\n",
-        "\n",
-        "from azureml.core import Workspace, Experiment, Dataset\n",
-        "from azureml.train.automl import AutoMLConfig\n",
-        "from matplotlib import pyplot as plt\n",
-        "from sklearn.metrics import mean_absolute_error, mean_squared_error\n",
-        "from azureml.train.estimator import Estimator"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "This notebook is compatible with Azure ML SDK version 1.35.0 or later."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "source": [
-        "As part of the setup you have already created a <b>Workspace</b>. To run AutoML, you also need to create an <b>Experiment</b>. An Experiment corresponds to a prediction problem you are trying to solve, while a Run corresponds to a specific approach to the problem."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "outputs": [],
-      "source": [
-        "ws = Workspace.from_config()\n",
-        "\n",
-        "# choose a name for the run history container in the workspace\n",
-        "experiment_name = \"github-remote-cpu\"\n",
-        "\n",
-        "experiment = Experiment(ws, experiment_name)\n",
-        "\n",
-        "output = {}\n",
-        "output[\"Subscription ID\"] = ws.subscription_id\n",
-        "output[\"Workspace\"] = ws.name\n",
-        "output[\"Resource Group\"] = ws.resource_group\n",
-        "output[\"Location\"] = ws.location\n",
-        "output[\"Run History Name\"] = experiment_name\n",
-        "output[\"SDK Version\"] = azureml.core.VERSION\n",
-        "pd.set_option(\"display.max_colwidth\", None)\n",
-        "outputDf = pd.DataFrame(data=output, index=[\"\"])\n",
-        "outputDf.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "source": [
-        "### Using AmlCompute\n",
-        "You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) for your AutoML run. In this tutorial, you use `AmlCompute` as your training compute resource.\n",
-        "\n",
-        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "outputs": [],
-      "source": [
-        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
-        "from azureml.core.compute_target import ComputeTargetException\n",
-        "\n",
-        "# Choose a name for your CPU cluster\n",
-        "cpu_cluster_name = \"github-cluster\"\n",
-        "\n",
-        "# Verify that cluster does not exist already\n",
-        "try:\n",
-        "    compute_target = ComputeTarget(workspace=ws, name=cpu_cluster_name)\n",
-        "    print(\"Found existing cluster, use it.\")\n",
-        "except ComputeTargetException:\n",
-        "    compute_config = AmlCompute.provisioning_configuration(\n",
-        "        vm_size=\"STANDARD_DS12_V2\", max_nodes=4\n",
-        "    )\n",
-        "    compute_target = ComputeTarget.create(ws, cpu_cluster_name, compute_config)\n",
-        "\n",
-        "compute_target.wait_for_completion(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "source": [
-        "## Data\n",
-        "Read Github DAU data from file, and preview data."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "source": [
-        "Let's set up what we know about the dataset. \n",
-        "\n",
-        "**Target column** is what we want to forecast.\n",
-        "\n",
-        "**Time column** is the time axis along which to predict.\n",
-        "\n",
-        "**Time series identifier columns** are identified by values of the columns listed `time_series_id_column_names`, for example \"store\" and \"item\" if your data has multiple time series of sales, one series for each combination of store and item sold.\n",
-        "\n",
-        "**Forecast frequency (freq)** This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information.\n",
-        "\n",
-        "This dataset has only one time series. Please see the [orange juice notebook](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales) for an example of a multi-time series dataset."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "outputs": [],
-      "source": [
-        "import pandas as pd\n",
-        "from pandas import DataFrame\n",
-        "from pandas import Grouper\n",
-        "from pandas import concat\n",
-        "from pandas.plotting import register_matplotlib_converters\n",
-        "\n",
-        "register_matplotlib_converters()\n",
-        "plt.figure(figsize=(20, 10))\n",
-        "plt.tight_layout()\n",
-        "\n",
-        "plt.subplot(2, 1, 1)\n",
-        "plt.title(\"Github Daily Active User By Year\")\n",
-        "df = pd.read_csv(\"github_dau_2011-2018_train.csv\", parse_dates=True, index_col=\"date\")\n",
-        "test_df = pd.read_csv(\n",
-        "    \"github_dau_2011-2018_test.csv\", parse_dates=True, index_col=\"date\"\n",
-        ")\n",
-        "plt.plot(df)\n",
-        "\n",
-        "plt.subplot(2, 1, 2)\n",
-        "plt.title(\"Github Daily Active User By Month\")\n",
-        "groups = df.groupby(df.index.month)\n",
-        "months = concat([DataFrame(x[1].values) for x in groups], axis=1)\n",
-        "months = DataFrame(months)\n",
-        "months.columns = range(1, 49)\n",
-        "months.boxplot()\n",
-        "\n",
-        "plt.show()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "outputs": [],
-      "source": [
-        "target_column_name = \"count\"\n",
-        "time_column_name = \"date\"\n",
-        "time_series_id_column_names = []\n",
-        "freq = \"D\"  # Daily data"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Split Training data into Train and Validation set and Upload to Datastores"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "outputs": [],
-      "source": [
-        "from helper import split_fraction_by_grain\n",
-        "from helper import split_full_for_forecasting\n",
-        "\n",
-        "train, valid = split_full_for_forecasting(df, time_column_name)\n",
-        "\n",
-        "# Reset index to create a Tabualr Dataset.\n",
-        "train.reset_index(inplace=True)\n",
-        "valid.reset_index(inplace=True)\n",
-        "test_df.reset_index(inplace=True)\n",
-        "\n",
-        "datastore = ws.get_default_datastore()\n",
-        "train_dataset = Dataset.Tabular.register_pandas_dataframe(\n",
-        "    train, target=(datastore, \"dataset/\"), name=\"Github_DAU_train\"\n",
-        ")\n",
-        "valid_dataset = Dataset.Tabular.register_pandas_dataframe(\n",
-        "    valid, target=(datastore, \"dataset/\"), name=\"Github_DAU_valid\"\n",
-        ")\n",
-        "test_dataset = Dataset.Tabular.register_pandas_dataframe(\n",
-        "    test_df, target=(datastore, \"dataset/\"), name=\"Github_DAU_test\"\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "source": [
-        "### Setting forecaster maximum horizon \n",
-        "\n",
-        "The forecast horizon is the number of periods into the future that the model should predict. Here, we set the horizon to 14 periods (i.e. 14 days). Notice that this is much shorter than the number of months in the test set; we will need to use a rolling test to evaluate the performance on the whole test set. For more discussion of forecast horizons and guiding principles for setting them, please see the [energy demand notebook](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand).  "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "outputs": [],
-      "source": [
-        "forecast_horizon = 14"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "source": [
-        "## Train\n",
-        "\n",
-        "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
-        "\n",
-        "|Property|Description|\n",
-        "|-|-|\n",
-        "|**task**|forecasting|\n",
-        "|**primary_metric**|This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>\n",
-        "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
-        "|**training_data**|Input dataset, containing both features and label column.|\n",
-        "|**label_column_name**|The name of the label column.|\n",
-        "|**enable_dnn**|Enable Forecasting DNNs|\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "outputs": [],
-      "source": [
-        "from azureml.automl.core.forecasting_parameters import ForecastingParameters\n",
-        "\n",
-        "forecasting_parameters = ForecastingParameters(\n",
-        "    time_column_name=time_column_name,\n",
-        "    forecast_horizon=forecast_horizon,\n",
-        "    freq=\"D\",  # Set the forecast frequency to be daily\n",
-        ")\n",
-        "\n",
-        "# To only allow the TCNForecaster we set the allowed_models parameter to reflect this.\n",
-        "automl_config = AutoMLConfig(\n",
-        "    task=\"forecasting\",\n",
-        "    primary_metric=\"normalized_root_mean_squared_error\",\n",
-        "    experiment_timeout_hours=1.5,\n",
-        "    training_data=train_dataset,\n",
-        "    label_column_name=target_column_name,\n",
-        "    validation_data=valid_dataset,\n",
-        "    verbosity=logging.INFO,\n",
-        "    compute_target=compute_target,\n",
-        "    max_concurrent_iterations=4,\n",
-        "    max_cores_per_iteration=-1,\n",
-        "    enable_dnn=True,\n",
-        "    allowed_models=[\"TCNForecaster\"],\n",
-        "    forecasting_parameters=forecasting_parameters,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "source": [
-        "We will now run the experiment, starting with 10 iterations of model search. The experiment can be continued for more iterations if more accurate results are required. Validation errors and current status will be shown when setting `show_output=True` and the execution will be synchronous."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "outputs": [],
-      "source": [
-        "remote_run = experiment.submit(automl_config, show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "outputs": [],
-      "source": [
-        "# If you need to retrieve a run that already started, use the following code\n",
-        "# from azureml.train.automl.run import AutoMLRun\n",
-        "# remote_run = AutoMLRun(experiment = experiment, run_id = '<replace with your run id>')"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "source": [
-        "Displaying the run objects gives you links to the visual tools in the Azure Portal. Go try them!"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "source": [
-        "### Retrieve the Best Model for Each Algorithm\n",
-        "Below we select the best pipeline from our iterations. The get_output method on automl_classifier returns the best run and the fitted model for the last fit invocation. There are overloads on get_output that allow you to retrieve the best run and fitted model for any logged metric or a particular iteration."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "outputs": [],
-      "source": [
-        "from helper import get_result_df\n",
-        "\n",
-        "summary_df = get_result_df(remote_run)\n",
-        "summary_df"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "outputs": [],
-      "source": [
-        "from azureml.core.run import Run\n",
-        "from azureml.widgets import RunDetails\n",
-        "\n",
-        "forecast_model = \"TCNForecaster\"\n",
-        "if not forecast_model in summary_df[\"run_id\"]:\n",
-        "    forecast_model = \"ForecastTCN\"\n",
-        "\n",
-        "best_dnn_run_id = summary_df[summary_df[\"Score\"] == summary_df[\"Score\"].min()][\n",
-        "    \"run_id\"\n",
-        "][forecast_model]\n",
-        "best_dnn_run = Run(experiment, best_dnn_run_id)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "outputs": [],
-      "source": [
-        "best_dnn_run.parent\n",
-        "RunDetails(best_dnn_run.parent).show()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "outputs": [],
-      "source": [
-        "best_dnn_run\n",
-        "RunDetails(best_dnn_run).show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "source": [
-        "## Evaluate on Test Data"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "source": [
-        "We now use the best fitted model from the AutoML Run to make forecasts for the test set.  \n",
-        "\n",
-        "We always score on the original dataset whose schema matches the training set schema."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "outputs": [],
-      "source": [
-        "# preview the first 3 rows of the dataset\n",
-        "test_dataset.take(5).to_pandas_dataframe()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "compute_target = ws.compute_targets[\"github-cluster\"]\n",
-        "test_experiment = Experiment(ws, experiment_name + \"_test\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "import shutil\n",
-        "\n",
-        "script_folder = os.path.join(os.getcwd(), \"inference\")\n",
-        "os.makedirs(script_folder, exist_ok=True)\n",
-        "shutil.copy(\"infer.py\", script_folder)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from helper import run_inference\n",
-        "\n",
-        "test_run = run_inference(\n",
-        "    test_experiment,\n",
-        "    compute_target,\n",
-        "    script_folder,\n",
-        "    best_dnn_run,\n",
-        "    test_dataset,\n",
-        "    valid_dataset,\n",
-        "    forecast_horizon,\n",
-        "    target_column_name,\n",
-        "    time_column_name,\n",
-        "    freq,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "RunDetails(test_run).show()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from helper import run_multiple_inferences\n",
-        "\n",
-        "summary_df = run_multiple_inferences(\n",
-        "    summary_df,\n",
-        "    experiment,\n",
-        "    test_experiment,\n",
-        "    compute_target,\n",
-        "    script_folder,\n",
-        "    test_dataset,\n",
-        "    valid_dataset,\n",
-        "    forecast_horizon,\n",
-        "    target_column_name,\n",
-        "    time_column_name,\n",
-        "    freq,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "outputs": [],
-      "source": [
-        "for run_name, run_summary in summary_df.iterrows():\n",
-        "    print(run_name)\n",
-        "    print(run_summary)\n",
-        "    run_id = run_summary.run_id\n",
-        "    test_run_id = run_summary.test_run_id\n",
-        "    test_run = Run(test_experiment, test_run_id)\n",
-        "    test_run.wait_for_completion()\n",
-        "    test_score = test_run.get_metrics()[run_summary.primary_metric]\n",
-        "    summary_df.loc[summary_df.run_id == run_id, \"Test Score\"] = test_score\n",
-        "    print(\"Test Score: \", test_score)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "hideCode": false,
-        "hidePrompt": false
-      },
-      "outputs": [],
-      "source": [
-        "summary_df"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": []
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "jialiu"
-      }
-    ],
-    "hide_code_all_hidden": false,
-    "kernelspec": {
-      "display_name": "Python 3.8 - AzureML",
-      "language": "python",
-      "name": "python38-azureml"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.8.10"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 4
-}

how-to-use-azureml/automated-machine-learning/forecasting-github-dau/github_dau_2011-2018_test.csv

@@ -1,455 +0,0 @@
-date,count,day_of_week,month_of_year,holiday
-2017-06-04,104663,6.0,5.0,0.0
-2017-06-05,155824,0.0,5.0,0.0
-2017-06-06,164908,1.0,5.0,0.0
-2017-06-07,170309,2.0,5.0,0.0
-2017-06-08,164256,3.0,5.0,0.0
-2017-06-09,153406,4.0,5.0,0.0
-2017-06-10,97024,5.0,5.0,0.0
-2017-06-11,103442,6.0,5.0,0.0
-2017-06-12,160768,0.0,5.0,0.0
-2017-06-13,166288,1.0,5.0,0.0
-2017-06-14,163819,2.0,5.0,0.0
-2017-06-15,157593,3.0,5.0,0.0
-2017-06-16,149259,4.0,5.0,0.0
-2017-06-17,95579,5.0,5.0,0.0
-2017-06-18,98723,6.0,5.0,0.0
-2017-06-19,159076,0.0,5.0,0.0
-2017-06-20,163340,1.0,5.0,0.0
-2017-06-21,163344,2.0,5.0,0.0
-2017-06-22,159528,3.0,5.0,0.0
-2017-06-23,146563,4.0,5.0,0.0
-2017-06-24,92631,5.0,5.0,0.0
-2017-06-25,96549,6.0,5.0,0.0
-2017-06-26,153249,0.0,5.0,0.0
-2017-06-27,160357,1.0,5.0,0.0
-2017-06-28,159941,2.0,5.0,0.0
-2017-06-29,156781,3.0,5.0,0.0
-2017-06-30,144709,4.0,5.0,0.0
-2017-07-01,89101,5.0,6.0,0.0
-2017-07-02,93046,6.0,6.0,0.0
-2017-07-03,144113,0.0,6.0,0.0
-2017-07-04,143061,1.0,6.0,1.0
-2017-07-05,154603,2.0,6.0,0.0
-2017-07-06,157200,3.0,6.0,0.0
-2017-07-07,147213,4.0,6.0,0.0
-2017-07-08,92348,5.0,6.0,0.0
-2017-07-09,97018,6.0,6.0,0.0
-2017-07-10,157192,0.0,6.0,0.0
-2017-07-11,161819,1.0,6.0,0.0
-2017-07-12,161998,2.0,6.0,0.0
-2017-07-13,160280,3.0,6.0,0.0
-2017-07-14,146818,4.0,6.0,0.0
-2017-07-15,93041,5.0,6.0,0.0
-2017-07-16,97505,6.0,6.0,0.0
-2017-07-17,156167,0.0,6.0,0.0
-2017-07-18,162855,1.0,6.0,0.0
-2017-07-19,162519,2.0,6.0,0.0
-2017-07-20,159941,3.0,6.0,0.0
-2017-07-21,148460,4.0,6.0,0.0
-2017-07-22,93431,5.0,6.0,0.0
-2017-07-23,98553,6.0,6.0,0.0
-2017-07-24,156202,0.0,6.0,0.0
-2017-07-25,162503,1.0,6.0,0.0
-2017-07-26,158479,2.0,6.0,0.0
-2017-07-27,158192,3.0,6.0,0.0
-2017-07-28,147108,4.0,6.0,0.0
-2017-07-29,93799,5.0,6.0,0.0
-2017-07-30,97920,6.0,6.0,0.0
-2017-07-31,152197,0.0,6.0,0.0
-2017-08-01,158477,1.0,7.0,0.0
-2017-08-02,159089,2.0,7.0,0.0
-2017-08-03,157182,3.0,7.0,0.0
-2017-08-04,146345,4.0,7.0,0.0
-2017-08-05,92534,5.0,7.0,0.0
-2017-08-06,97128,6.0,7.0,0.0
-2017-08-07,151359,0.0,7.0,0.0
-2017-08-08,159895,1.0,7.0,0.0
-2017-08-09,158329,2.0,7.0,0.0
-2017-08-10,155468,3.0,7.0,0.0
-2017-08-11,144914,4.0,7.0,0.0
-2017-08-12,92258,5.0,7.0,0.0
-2017-08-13,95933,6.0,7.0,0.0
-2017-08-14,147706,0.0,7.0,0.0
-2017-08-15,151115,1.0,7.0,0.0
-2017-08-16,157640,2.0,7.0,0.0
-2017-08-17,156600,3.0,7.0,0.0
-2017-08-18,146980,4.0,7.0,0.0
-2017-08-19,94592,5.0,7.0,0.0
-2017-08-20,99320,6.0,7.0,0.0
-2017-08-21,145727,0.0,7.0,0.0
-2017-08-22,160260,1.0,7.0,0.0
-2017-08-23,160440,2.0,7.0,0.0
-2017-08-24,157830,3.0,7.0,0.0
-2017-08-25,145822,4.0,7.0,0.0
-2017-08-26,94706,5.0,7.0,0.0
-2017-08-27,99047,6.0,7.0,0.0
-2017-08-28,152112,0.0,7.0,0.0
-2017-08-29,162440,1.0,7.0,0.0
-2017-08-30,162902,2.0,7.0,0.0
-2017-08-31,159498,3.0,7.0,0.0
-2017-09-01,145689,4.0,8.0,0.0
-2017-09-02,93589,5.0,8.0,0.0
-2017-09-03,100058,6.0,8.0,0.0
-2017-09-04,140865,0.0,8.0,1.0
-2017-09-05,165715,1.0,8.0,0.0
-2017-09-06,167463,2.0,8.0,0.0
-2017-09-07,164811,3.0,8.0,0.0
-2017-09-08,156157,4.0,8.0,0.0
-2017-09-09,101358,5.0,8.0,0.0
-2017-09-10,107915,6.0,8.0,0.0
-2017-09-11,167845,0.0,8.0,0.0
-2017-09-12,172756,1.0,8.0,0.0
-2017-09-13,172851,2.0,8.0,0.0
-2017-09-14,171675,3.0,8.0,0.0
-2017-09-15,159266,4.0,8.0,0.0
-2017-09-16,103547,5.0,8.0,0.0
-2017-09-17,110964,6.0,8.0,0.0
-2017-09-18,170976,0.0,8.0,0.0
-2017-09-19,177864,1.0,8.0,0.0
-2017-09-20,173567,2.0,8.0,0.0
-2017-09-21,172017,3.0,8.0,0.0
-2017-09-22,161357,4.0,8.0,0.0
-2017-09-23,104681,5.0,8.0,0.0
-2017-09-24,111711,6.0,8.0,0.0
-2017-09-25,173517,0.0,8.0,0.0
-2017-09-26,180049,1.0,8.0,0.0
-2017-09-27,178307,2.0,8.0,0.0
-2017-09-28,174157,3.0,8.0,0.0
-2017-09-29,161707,4.0,8.0,0.0
-2017-09-30,110536,5.0,8.0,0.0
-2017-10-01,106505,6.0,9.0,0.0
-2017-10-02,157565,0.0,9.0,0.0
-2017-10-03,164764,1.0,9.0,0.0
-2017-10-04,163383,2.0,9.0,0.0
-2017-10-05,162847,3.0,9.0,0.0
-2017-10-06,153575,4.0,9.0,0.0
-2017-10-07,107472,5.0,9.0,0.0
-2017-10-08,116127,6.0,9.0,0.0
-2017-10-09,174457,0.0,9.0,1.0
-2017-10-10,185217,1.0,9.0,0.0
-2017-10-11,185120,2.0,9.0,0.0
-2017-10-12,180844,3.0,9.0,0.0
-2017-10-13,170178,4.0,9.0,0.0
-2017-10-14,112754,5.0,9.0,0.0
-2017-10-15,121251,6.0,9.0,0.0
-2017-10-16,183906,0.0,9.0,0.0
-2017-10-17,188945,1.0,9.0,0.0
-2017-10-18,187297,2.0,9.0,0.0
-2017-10-19,183867,3.0,9.0,0.0
-2017-10-20,173021,4.0,9.0,0.0
-2017-10-21,115851,5.0,9.0,0.0
-2017-10-22,126088,6.0,9.0,0.0
-2017-10-23,189452,0.0,9.0,0.0
-2017-10-24,194412,1.0,9.0,0.0
-2017-10-25,192293,2.0,9.0,0.0
-2017-10-26,190163,3.0,9.0,0.0
-2017-10-27,177053,4.0,9.0,0.0
-2017-10-28,114934,5.0,9.0,0.0
-2017-10-29,125289,6.0,9.0,0.0
-2017-10-30,189245,0.0,9.0,0.0
-2017-10-31,191480,1.0,9.0,0.0
-2017-11-01,182281,2.0,10.0,0.0
-2017-11-02,186351,3.0,10.0,0.0
-2017-11-03,175422,4.0,10.0,0.0
-2017-11-04,118160,5.0,10.0,0.0
-2017-11-05,127602,6.0,10.0,0.0
-2017-11-06,191067,0.0,10.0,0.0
-2017-11-07,197083,1.0,10.0,0.0
-2017-11-08,194333,2.0,10.0,0.0
-2017-11-09,193914,3.0,10.0,0.0
-2017-11-10,179933,4.0,10.0,1.0
-2017-11-11,121346,5.0,10.0,0.0
-2017-11-12,131900,6.0,10.0,0.0
-2017-11-13,196969,0.0,10.0,0.0
-2017-11-14,201949,1.0,10.0,0.0
-2017-11-15,198424,2.0,10.0,0.0
-2017-11-16,196902,3.0,10.0,0.0
-2017-11-17,183893,4.0,10.0,0.0
-2017-11-18,122767,5.0,10.0,0.0
-2017-11-19,130890,6.0,10.0,0.0
-2017-11-20,194515,0.0,10.0,0.0
-2017-11-21,198601,1.0,10.0,0.0
-2017-11-22,191041,2.0,10.0,0.0
-2017-11-23,170321,3.0,10.0,1.0
-2017-11-24,155623,4.0,10.0,0.0
-2017-11-25,115759,5.0,10.0,0.0
-2017-11-26,128771,6.0,10.0,0.0
-2017-11-27,199419,0.0,10.0,0.0
-2017-11-28,207253,1.0,10.0,0.0
-2017-11-29,205406,2.0,10.0,0.0
-2017-11-30,200674,3.0,10.0,0.0
-2017-12-01,187017,4.0,11.0,0.0
-2017-12-02,129735,5.0,11.0,0.0
-2017-12-03,139120,6.0,11.0,0.0
-2017-12-04,205505,0.0,11.0,0.0
-2017-12-05,208218,1.0,11.0,0.0
-2017-12-06,202480,2.0,11.0,0.0
-2017-12-07,197822,3.0,11.0,0.0
-2017-12-08,180686,4.0,11.0,0.0
-2017-12-09,123667,5.0,11.0,0.0
-2017-12-10,130987,6.0,11.0,0.0
-2017-12-11,193901,0.0,11.0,0.0
-2017-12-12,194997,1.0,11.0,0.0
-2017-12-13,192063,2.0,11.0,0.0
-2017-12-14,186496,3.0,11.0,0.0
-2017-12-15,170812,4.0,11.0,0.0
-2017-12-16,110474,5.0,11.0,0.0
-2017-12-17,118165,6.0,11.0,0.0
-2017-12-18,176843,0.0,11.0,0.0
-2017-12-19,179550,1.0,11.0,0.0
-2017-12-20,173506,2.0,11.0,0.0
-2017-12-21,165910,3.0,11.0,0.0
-2017-12-22,145886,4.0,11.0,0.0
-2017-12-23,95246,5.0,11.0,0.0
-2017-12-24,88781,6.0,11.0,0.0
-2017-12-25,98189,0.0,11.0,1.0
-2017-12-26,121383,1.0,11.0,0.0
-2017-12-27,135300,2.0,11.0,0.0
-2017-12-28,136827,3.0,11.0,0.0
-2017-12-29,127700,4.0,11.0,0.0
-2017-12-30,93014,5.0,11.0,0.0
-2017-12-31,82878,6.0,11.0,0.0
-2018-01-01,86419,0.0,0.0,1.0
-2018-01-02,147428,1.0,0.0,0.0
-2018-01-03,162193,2.0,0.0,0.0
-2018-01-04,163784,3.0,0.0,0.0
-2018-01-05,158606,4.0,0.0,0.0
-2018-01-06,113467,5.0,0.0,0.0
-2018-01-07,118313,6.0,0.0,0.0
-2018-01-08,175623,0.0,0.0,0.0
-2018-01-09,183880,1.0,0.0,0.0
-2018-01-10,183945,2.0,0.0,0.0
-2018-01-11,181769,3.0,0.0,0.0
-2018-01-12,170552,4.0,0.0,0.0
-2018-01-13,115707,5.0,0.0,0.0
-2018-01-14,121191,6.0,0.0,0.0
-2018-01-15,176127,0.0,0.0,1.0
-2018-01-16,188032,1.0,0.0,0.0
-2018-01-17,189871,2.0,0.0,0.0
-2018-01-18,189348,3.0,0.0,0.0
-2018-01-19,177456,4.0,0.0,0.0
-2018-01-20,123321,5.0,0.0,0.0
-2018-01-21,128306,6.0,0.0,0.0
-2018-01-22,186132,0.0,0.0,0.0
-2018-01-23,197618,1.0,0.0,0.0
-2018-01-24,196402,2.0,0.0,0.0
-2018-01-25,192722,3.0,0.0,0.0
-2018-01-26,179415,4.0,0.0,0.0
-2018-01-27,125769,5.0,0.0,0.0
-2018-01-28,133306,6.0,0.0,0.0
-2018-01-29,194151,0.0,0.0,0.0
-2018-01-30,198680,1.0,0.0,0.0
-2018-01-31,198652,2.0,0.0,0.0
-2018-02-01,195472,3.0,1.0,0.0
-2018-02-02,183173,4.0,1.0,0.0
-2018-02-03,124276,5.0,1.0,0.0
-2018-02-04,129054,6.0,1.0,0.0
-2018-02-05,190024,0.0,1.0,0.0
-2018-02-06,198658,1.0,1.0,0.0
-2018-02-07,198272,2.0,1.0,0.0
-2018-02-08,195339,3.0,1.0,0.0
-2018-02-09,183086,4.0,1.0,0.0
-2018-02-10,122536,5.0,1.0,0.0
-2018-02-11,133033,6.0,1.0,0.0
-2018-02-12,185386,0.0,1.0,0.0
-2018-02-13,184789,1.0,1.0,0.0
-2018-02-14,176089,2.0,1.0,0.0
-2018-02-15,171317,3.0,1.0,0.0
-2018-02-16,162693,4.0,1.0,0.0
-2018-02-17,116342,5.0,1.0,0.0
-2018-02-18,122466,6.0,1.0,0.0
-2018-02-19,172364,0.0,1.0,1.0
-2018-02-20,185896,1.0,1.0,0.0
-2018-02-21,188166,2.0,1.0,0.0
-2018-02-22,189427,3.0,1.0,0.0
-2018-02-23,178732,4.0,1.0,0.0
-2018-02-24,132664,5.0,1.0,0.0
-2018-02-25,134008,6.0,1.0,0.0
-2018-02-26,200075,0.0,1.0,0.0
-2018-02-27,207996,1.0,1.0,0.0
-2018-02-28,204416,2.0,1.0,0.0
-2018-03-01,201320,3.0,2.0,0.0
-2018-03-02,188205,4.0,2.0,0.0
-2018-03-03,131162,5.0,2.0,0.0
-2018-03-04,138320,6.0,2.0,0.0
-2018-03-05,207326,0.0,2.0,0.0
-2018-03-06,212462,1.0,2.0,0.0
-2018-03-07,209357,2.0,2.0,0.0
-2018-03-08,194876,3.0,2.0,0.0
-2018-03-09,193761,4.0,2.0,0.0
-2018-03-10,133449,5.0,2.0,0.0
-2018-03-11,142258,6.0,2.0,0.0
-2018-03-12,208753,0.0,2.0,0.0
-2018-03-13,210602,1.0,2.0,0.0
-2018-03-14,214236,2.0,2.0,0.0
-2018-03-15,210761,3.0,2.0,0.0
-2018-03-16,196619,4.0,2.0,0.0
-2018-03-17,133056,5.0,2.0,0.0
-2018-03-18,141335,6.0,2.0,0.0
-2018-03-19,211580,0.0,2.0,0.0
-2018-03-20,219051,1.0,2.0,0.0
-2018-03-21,215435,2.0,2.0,0.0
-2018-03-22,211961,3.0,2.0,0.0
-2018-03-23,196009,4.0,2.0,0.0
-2018-03-24,132390,5.0,2.0,0.0
-2018-03-25,140021,6.0,2.0,0.0
-2018-03-26,205273,0.0,2.0,0.0
-2018-03-27,212686,1.0,2.0,0.0
-2018-03-28,210683,2.0,2.0,0.0
-2018-03-29,189044,3.0,2.0,0.0
-2018-03-30,170256,4.0,2.0,0.0
-2018-03-31,125999,5.0,2.0,0.0
-2018-04-01,126749,6.0,3.0,0.0
-2018-04-02,186546,0.0,3.0,0.0
-2018-04-03,207905,1.0,3.0,0.0
-2018-04-04,201528,2.0,3.0,0.0
-2018-04-05,188580,3.0,3.0,0.0
-2018-04-06,173714,4.0,3.0,0.0
-2018-04-07,125723,5.0,3.0,0.0
-2018-04-08,142545,6.0,3.0,0.0
-2018-04-09,204767,0.0,3.0,0.0
-2018-04-10,212048,1.0,3.0,0.0
-2018-04-11,210517,2.0,3.0,0.0
-2018-04-12,206924,3.0,3.0,0.0
-2018-04-13,191679,4.0,3.0,0.0
-2018-04-14,126394,5.0,3.0,0.0
-2018-04-15,137279,6.0,3.0,0.0
-2018-04-16,208085,0.0,3.0,0.0
-2018-04-17,213273,1.0,3.0,0.0
-2018-04-18,211580,2.0,3.0,0.0
-2018-04-19,206037,3.0,3.0,0.0
-2018-04-20,191211,4.0,3.0,0.0
-2018-04-21,125564,5.0,3.0,0.0
-2018-04-22,136469,6.0,3.0,0.0
-2018-04-23,206288,0.0,3.0,0.0
-2018-04-24,212115,1.0,3.0,0.0
-2018-04-25,207948,2.0,3.0,0.0
-2018-04-26,205759,3.0,3.0,0.0
-2018-04-27,181330,4.0,3.0,0.0
-2018-04-28,130046,5.0,3.0,0.0
-2018-04-29,120802,6.0,3.0,0.0
-2018-04-30,170390,0.0,3.0,0.0
-2018-05-01,169054,1.0,4.0,0.0
-2018-05-02,197891,2.0,4.0,0.0
-2018-05-03,199820,3.0,4.0,0.0
-2018-05-04,186783,4.0,4.0,0.0
-2018-05-05,124420,5.0,4.0,0.0
-2018-05-06,130666,6.0,4.0,0.0
-2018-05-07,196014,0.0,4.0,0.0
-2018-05-08,203058,1.0,4.0,0.0
-2018-05-09,198582,2.0,4.0,0.0
-2018-05-10,191321,3.0,4.0,0.0
-2018-05-11,183639,4.0,4.0,0.0
-2018-05-12,122023,5.0,4.0,0.0
-2018-05-13,128775,6.0,4.0,0.0
-2018-05-14,199104,0.0,4.0,0.0
-2018-05-15,200658,1.0,4.0,0.0
-2018-05-16,201541,2.0,4.0,0.0
-2018-05-17,196886,3.0,4.0,0.0
-2018-05-18,188597,4.0,4.0,0.0
-2018-05-19,121392,5.0,4.0,0.0
-2018-05-20,126981,6.0,4.0,0.0
-2018-05-21,189291,0.0,4.0,0.0
-2018-05-22,203038,1.0,4.0,0.0
-2018-05-23,205330,2.0,4.0,0.0
-2018-05-24,199208,3.0,4.0,0.0
-2018-05-25,187768,4.0,4.0,0.0
-2018-05-26,117635,5.0,4.0,0.0
-2018-05-27,124352,6.0,4.0,0.0
-2018-05-28,180398,0.0,4.0,1.0
-2018-05-29,194170,1.0,4.0,0.0
-2018-05-30,200281,2.0,4.0,0.0
-2018-05-31,197244,3.0,4.0,0.0
-2018-06-01,184037,4.0,5.0,0.0
-2018-06-02,121135,5.0,5.0,0.0
-2018-06-03,129389,6.0,5.0,0.0
-2018-06-04,200331,0.0,5.0,0.0
-2018-06-05,207735,1.0,5.0,0.0
-2018-06-06,203354,2.0,5.0,0.0
-2018-06-07,200520,3.0,5.0,0.0
-2018-06-08,182038,4.0,5.0,0.0
-2018-06-09,120164,5.0,5.0,0.0
-2018-06-10,125256,6.0,5.0,0.0
-2018-06-11,194786,0.0,5.0,0.0
-2018-06-12,200815,1.0,5.0,0.0
-2018-06-13,197740,2.0,5.0,0.0
-2018-06-14,192294,3.0,5.0,0.0
-2018-06-15,173587,4.0,5.0,0.0
-2018-06-16,105955,5.0,5.0,0.0
-2018-06-17,110780,6.0,5.0,0.0
-2018-06-18,174582,0.0,5.0,0.0
-2018-06-19,193310,1.0,5.0,0.0
-2018-06-20,193062,2.0,5.0,0.0
-2018-06-21,187986,3.0,5.0,0.0
-2018-06-22,173606,4.0,5.0,0.0
-2018-06-23,111795,5.0,5.0,0.0
-2018-06-24,116134,6.0,5.0,0.0
-2018-06-25,185919,0.0,5.0,0.0
-2018-06-26,193142,1.0,5.0,0.0
-2018-06-27,188114,2.0,5.0,0.0
-2018-06-28,183737,3.0,5.0,0.0
-2018-06-29,171496,4.0,5.0,0.0
-2018-06-30,107210,5.0,5.0,0.0
-2018-07-01,111053,6.0,6.0,0.0
-2018-07-02,176198,0.0,6.0,0.0
-2018-07-03,184040,1.0,6.0,0.0
-2018-07-04,169783,2.0,6.0,1.0
-2018-07-05,177996,3.0,6.0,0.0
-2018-07-06,167378,4.0,6.0,0.0
-2018-07-07,106401,5.0,6.0,0.0
-2018-07-08,112327,6.0,6.0,0.0
-2018-07-09,182835,0.0,6.0,0.0
-2018-07-10,187694,1.0,6.0,0.0
-2018-07-11,185762,2.0,6.0,0.0
-2018-07-12,184099,3.0,6.0,0.0
-2018-07-13,170860,4.0,6.0,0.0
-2018-07-14,106799,5.0,6.0,0.0
-2018-07-15,108475,6.0,6.0,0.0
-2018-07-16,175704,0.0,6.0,0.0
-2018-07-17,183596,1.0,6.0,0.0
-2018-07-18,179897,2.0,6.0,0.0
-2018-07-19,183373,3.0,6.0,0.0
-2018-07-20,169626,4.0,6.0,0.0
-2018-07-21,106785,5.0,6.0,0.0
-2018-07-22,112387,6.0,6.0,0.0
-2018-07-23,180572,0.0,6.0,0.0
-2018-07-24,186943,1.0,6.0,0.0
-2018-07-25,185744,2.0,6.0,0.0
-2018-07-26,183117,3.0,6.0,0.0
-2018-07-27,168526,4.0,6.0,0.0
-2018-07-28,105936,5.0,6.0,0.0
-2018-07-29,111708,6.0,6.0,0.0
-2018-07-30,179950,0.0,6.0,0.0
-2018-07-31,185930,1.0,6.0,0.0
-2018-08-01,183366,2.0,7.0,0.0
-2018-08-02,182412,3.0,7.0,0.0
-2018-08-03,173429,4.0,7.0,0.0
-2018-08-04,106108,5.0,7.0,0.0
-2018-08-05,110059,6.0,7.0,0.0
-2018-08-06,178355,0.0,7.0,0.0
-2018-08-07,185518,1.0,7.0,0.0
-2018-08-08,183204,2.0,7.0,0.0
-2018-08-09,181276,3.0,7.0,0.0
-2018-08-10,168297,4.0,7.0,0.0
-2018-08-11,106488,5.0,7.0,0.0
-2018-08-12,111786,6.0,7.0,0.0
-2018-08-13,178620,0.0,7.0,0.0
-2018-08-14,181922,1.0,7.0,0.0
-2018-08-15,172198,2.0,7.0,0.0
-2018-08-16,177367,3.0,7.0,0.0
-2018-08-17,166550,4.0,7.0,0.0
-2018-08-18,107011,5.0,7.0,0.0
-2018-08-19,112299,6.0,7.0,0.0
-2018-08-20,176718,0.0,7.0,0.0
-2018-08-21,182562,1.0,7.0,0.0
-2018-08-22,181484,2.0,7.0,0.0
-2018-08-23,180317,3.0,7.0,0.0
-2018-08-24,170197,4.0,7.0,0.0
-2018-08-25,109383,5.0,7.0,0.0
-2018-08-26,113373,6.0,7.0,0.0
-2018-08-27,180142,0.0,7.0,0.0
-2018-08-28,191628,1.0,7.0,0.0
-2018-08-29,191149,2.0,7.0,0.0
-2018-08-30,187503,3.0,7.0,0.0
-2018-08-31,172280,4.0,7.0,0.0

how-to-use-azureml/automated-machine-learning/forecasting-github-dau/helper.py

@@ -1,176 +0,0 @@
-import pandas as pd
-from azureml.core import Environment
-from azureml.core.conda_dependencies import CondaDependencies
-from azureml.train.estimator import Estimator
-from azureml.core.run import Run
-from azureml.automl.core.shared import constants
-
-
-def split_fraction_by_grain(df, fraction, time_column_name, grain_column_names=None):
-    if not grain_column_names:
-        df["tmp_grain_column"] = "grain"
-        grain_column_names = ["tmp_grain_column"]
-
-    """Group df by grain and split on last n rows for each group."""
-    df_grouped = df.sort_values(time_column_name).groupby(
-        grain_column_names, group_keys=False
-    )
-
-    df_head = df_grouped.apply(
-        lambda dfg: dfg.iloc[: -int(len(dfg) * fraction)] if fraction > 0 else dfg
-    )
-
-    df_tail = df_grouped.apply(
-        lambda dfg: dfg.iloc[-int(len(dfg) * fraction) :] if fraction > 0 else dfg[:0]
-    )
-
-    if "tmp_grain_column" in grain_column_names:
-        for df2 in (df, df_head, df_tail):
-            df2.drop("tmp_grain_column", axis=1, inplace=True)
-
-        grain_column_names.remove("tmp_grain_column")
-
-    return df_head, df_tail
-
-
-def split_full_for_forecasting(
-    df, time_column_name, grain_column_names=None, test_split=0.2
-):
-    index_name = df.index.name
-
-    # Assumes that there isn't already a column called tmpindex
-
-    df["tmpindex"] = df.index
-
-    train_df, test_df = split_fraction_by_grain(
-        df, test_split, time_column_name, grain_column_names
-    )
-
-    train_df = train_df.set_index("tmpindex")
-    train_df.index.name = index_name
-
-    test_df = test_df.set_index("tmpindex")
-    test_df.index.name = index_name
-
-    df.drop("tmpindex", axis=1, inplace=True)
-
-    return train_df, test_df
-
-
-def get_result_df(remote_run):
-    children = list(remote_run.get_children(recursive=True))
-    summary_df = pd.DataFrame(
-        index=["run_id", "run_algorithm", "primary_metric", "Score"]
-    )
-    goal_minimize = False
-    for run in children:
-        if (
-            run.get_status().lower() == constants.RunState.COMPLETE_RUN
-            and "run_algorithm" in run.properties
-            and "score" in run.properties
-        ):
-            # We only count in the completed child runs.
-            summary_df[run.id] = [
-                run.id,
-                run.properties["run_algorithm"],
-                run.properties["primary_metric"],
-                float(run.properties["score"]),
-            ]
-            if "goal" in run.properties:
-                goal_minimize = run.properties["goal"].split("_")[-1] == "min"
-
-    summary_df = summary_df.T.sort_values("Score", ascending=goal_minimize)
-    summary_df = summary_df.set_index("run_algorithm")
-    return summary_df
-
-
-def run_inference(
-    test_experiment,
-    compute_target,
-    script_folder,
-    train_run,
-    test_dataset,
-    lookback_dataset,
-    max_horizon,
-    target_column_name,
-    time_column_name,
-    freq,
-):
-    model_base_name = "model.pkl"
-    if "model_data_location" in train_run.properties:
-        model_location = train_run.properties["model_data_location"]
-        _, model_base_name = model_location.rsplit("/", 1)
-    train_run.download_file(
-        "outputs/{}".format(model_base_name), "inference/{}".format(model_base_name)
-    )
-
-    inference_env = train_run.get_environment()
-
-    est = Estimator(
-        source_directory=script_folder,
-        entry_script="infer.py",
-        script_params={
-            "--max_horizon": max_horizon,
-            "--target_column_name": target_column_name,
-            "--time_column_name": time_column_name,
-            "--frequency": freq,
-            "--model_path": model_base_name,
-        },
-        inputs=[
-            test_dataset.as_named_input("test_data"),
-            lookback_dataset.as_named_input("lookback_data"),
-        ],
-        compute_target=compute_target,
-        environment_definition=inference_env,
-    )
-
-    run = test_experiment.submit(
-        est,
-        tags={
-            "training_run_id": train_run.id,
-            "run_algorithm": train_run.properties["run_algorithm"],
-            "valid_score": train_run.properties["score"],
-            "primary_metric": train_run.properties["primary_metric"],
-        },
-    )
-
-    run.log("run_algorithm", run.tags["run_algorithm"])
-    return run
-
-
-def run_multiple_inferences(
-    summary_df,
-    train_experiment,
-    test_experiment,
-    compute_target,
-    script_folder,
-    test_dataset,
-    lookback_dataset,
-    max_horizon,
-    target_column_name,
-    time_column_name,
-    freq,
-):
-    for run_name, run_summary in summary_df.iterrows():
-        print(run_name)
-        print(run_summary)
-        run_id = run_summary.run_id
-        train_run = Run(train_experiment, run_id)
-
-        test_run = run_inference(
-            test_experiment,
-            compute_target,
-            script_folder,
-            train_run,
-            test_dataset,
-            lookback_dataset,
-            max_horizon,
-            target_column_name,
-            time_column_name,
-            freq,
-        )
-
-        print(test_run)
-        summary_df.loc[summary_df.run_id == run_id, "test_run_id"] = test_run.id
-
-    return summary_df

how-to-use-azureml/automated-machine-learning/forecasting-github-dau/infer.py

@@ -1,145 +0,0 @@
-import argparse
-import os
-
-import numpy as np
-import pandas as pd
-
-import joblib
-from sklearn.metrics import mean_absolute_error, mean_squared_error
-
-from azureml.automl.runtime.shared.score import scoring, constants
-from azureml.core import Run
-
-try:
-    import torch
-
-    _torch_present = True
-except ImportError:
-    _torch_present = False
-
-
-def map_location_cuda(storage, loc):
-    return storage.cuda()
-
-
-def APE(actual, pred):
-    """
-    Calculate absolute percentage error.
-    Returns a vector of APE values with same length as actual/pred.
-    """
-    return 100 * np.abs((actual - pred) / actual)
-
-
-def MAPE(actual, pred):
-    """
-    Calculate mean absolute percentage error.
-    Remove NA and values where actual is close to zero
-    """
-    not_na = ~(np.isnan(actual) | np.isnan(pred))
-    not_zero = ~np.isclose(actual, 0.0)
-    actual_safe = actual[not_na & not_zero]
-    pred_safe = pred[not_na & not_zero]
-    return np.mean(APE(actual_safe, pred_safe))
-
-
-parser = argparse.ArgumentParser()
-parser.add_argument(
-    "--max_horizon",
-    type=int,
-    dest="max_horizon",
-    default=10,
-    help="Max Horizon for forecasting",
-)
-parser.add_argument(
-    "--target_column_name",
-    type=str,
-    dest="target_column_name",
-    help="Target Column Name",
-)
-parser.add_argument(
-    "--time_column_name", type=str, dest="time_column_name", help="Time Column Name"
-)
-parser.add_argument(
-    "--frequency", type=str, dest="freq", help="Frequency of prediction"
-)
-parser.add_argument(
-    "--model_path",
-    type=str,
-    dest="model_path",
-    default="model.pkl",
-    help="Filename of model to be loaded",
-)
-
-args = parser.parse_args()
-max_horizon = args.max_horizon
-target_column_name = args.target_column_name
-time_column_name = args.time_column_name
-freq = args.freq
-model_path = args.model_path
-
-print("args passed are: ")
-print(max_horizon)
-print(target_column_name)
-print(time_column_name)
-print(freq)
-print(model_path)
-
-run = Run.get_context()
-# get input dataset by name
-test_dataset = run.input_datasets["test_data"]
-
-grain_column_names = []
-
-df = test_dataset.to_pandas_dataframe()
-
-print("Read df")
-print(df)
-
-X_test_df = df
-y_test = df.pop(target_column_name).to_numpy()
-
-_, ext = os.path.splitext(model_path)
-if ext == ".pt":
-    # Load the fc-tcn torch model.
-    assert _torch_present
-    if torch.cuda.is_available():
-        map_location = map_location_cuda
-    else:
-        map_location = "cpu"
-    with open(model_path, "rb") as fh:
-        fitted_model = torch.load(fh, map_location=map_location)
-else:
-    # Load the sklearn pipeline.
-    fitted_model = joblib.load(model_path)
-
-X_rf = fitted_model.rolling_forecast(X_test_df, y_test, step=1)
-assign_dict = {
-    fitted_model.forecast_origin_column_name: "forecast_origin",
-    fitted_model.forecast_column_name: "predicted",
-    fitted_model.actual_column_name: target_column_name,
-}
-X_rf.rename(columns=assign_dict, inplace=True)
-
-print(X_rf.head())
-
-# Use the AutoML scoring module
-regression_metrics = list(constants.REGRESSION_SCALAR_SET)
-y_test = np.array(X_rf[target_column_name])
-y_pred = np.array(X_rf["predicted"])
-scores = scoring.score_regression(y_test, y_pred, regression_metrics)
-
-print("scores:")
-print(scores)
-
-for key, value in scores.items():
-    run.log(key, value)
-
-print("Simple forecasting model")
-rmse = np.sqrt(mean_squared_error(X_rf[target_column_name], X_rf["predicted"]))
-print("[Test Data] \nRoot Mean squared error: %.2f" % rmse)
-mae = mean_absolute_error(X_rf[target_column_name], X_rf["predicted"])
-print("mean_absolute_error score: %.2f" % mae)
-print("MAPE: %.2f" % MAPE(X_rf[target_column_name], X_rf["predicted"]))
-
-run.log("rmse", rmse)
-run.log("mae", mae)

how-to-use-azureml/automated-machine-learning/forecasting-hierarchical-timeseries/auto-ml-forecasting-hierarchical-timeseries.ipynb

@@ -1,681 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/forecasting-hierarchical-timeseries/auto-ml-forecasting-hierarchical-timeseries.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<font color=\"red\" size=\"5\"><strong>!Important!</strong> </br>This notebook is outdated and is not supported by the AutoML Team. Please use the supported version ([link](https://github.com/Azure/azureml-examples/tree/main/sdk/python/jobs/pipelines/1k_demand_forecasting_with_pipeline_components/automl-forecasting-demand-hierarchical-timeseries-in-pipeline)).</font>"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Hierarchical Time Series - Automated ML\n",
-        "**_Generate hierarchical time series forecasts with Automated Machine Learning_**\n",
-        "\n",
-        "---"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "For this notebook we are using a synthetic dataset portraying sales data to predict the the quantity of a vartiety of product skus across several states, stores, and product categories.\n",
-        "\n",
-        "**NOTE: There are limits on how many runs we can do in parallel per workspace, and we currently recommend to set the parallelism to maximum of 320 runs per experiment per workspace. If users want to have more parallelism and increase this limit they might encounter Too Many Requests errors (HTTP 429).**"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Prerequisites\n",
-        "You'll need to create a compute Instance by following [these](https://learn.microsoft.com/en-us/azure/machine-learning/v1/how-to-create-manage-compute-instance?tabs=python) instructions."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## 1.0 Set up workspace, datastore, experiment"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "gather": {
-          "logged": 1613003526897
-        }
-      },
-      "outputs": [],
-      "source": [
-        "import azureml.core\n",
-        "from azureml.core import Workspace, Datastore\n",
-        "import pandas as pd\n",
-        "\n",
-        "# Set up your workspace\n",
-        "ws = Workspace.from_config()\n",
-        "ws.get_details()\n",
-        "\n",
-        "# Set up your datastores\n",
-        "dstore = ws.get_default_datastore()\n",
-        "\n",
-        "output = {}\n",
-        "output[\"SDK version\"] = azureml.core.VERSION\n",
-        "output[\"Subscription ID\"] = ws.subscription_id\n",
-        "output[\"Workspace\"] = ws.name\n",
-        "output[\"Resource Group\"] = ws.resource_group\n",
-        "output[\"Location\"] = ws.location\n",
-        "output[\"Default datastore name\"] = dstore.name\n",
-        "output[\"SDK Version\"] = azureml.core.VERSION\n",
-        "pd.set_option(\"display.max_colwidth\", None)\n",
-        "outputDf = pd.DataFrame(data=output, index=[\"\"])\n",
-        "outputDf.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Choose an experiment"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "gather": {
-          "logged": 1613003540729
-        }
-      },
-      "outputs": [],
-      "source": [
-        "from azureml.core import Experiment\n",
-        "\n",
-        "experiment = Experiment(ws, \"automl-hts\")\n",
-        "\n",
-        "print(\"Experiment name: \" + experiment.name)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## 2.0 Data\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "nteract": {
-          "transient": {
-            "deleting": false
-          }
-        }
-      },
-      "source": [
-        "### Upload local csv files to datastore\n",
-        "You can upload your train and inference csv files to the default datastore in your workspace. \n",
-        "\n",
-        "A Datastore is a place where data can be stored that is then made accessible to a compute either by means of mounting or copying the data to the compute target.\n",
-        "Please refer to [Datastore](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.datastore.datastore?view=azure-ml-py) documentation on how to access data from Datastore."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "datastore_path = \"hts-sample\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "datastore = ws.get_default_datastore()\n",
-        "datastore"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Create the TabularDatasets \n",
-        "\n",
-        "Datasets in Azure Machine Learning are references to specific data in a Datastore. The data can be retrieved as a [TabularDatasets](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.tabulardataset?view=azure-ml-py). We will read in the data as a pandas DataFrame, upload to the data store and register them to your Workspace using ```register_pandas_dataframe``` so they can be called as an input into the training pipeline. We will use the inference dataset as part of the forecasting pipeline. The step need only be completed once."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "gather": {
-          "logged": 1613007017296
-        }
-      },
-      "outputs": [],
-      "source": [
-        "from azureml.data.dataset_factory import TabularDatasetFactory\n",
-        "\n",
-        "registered_train = TabularDatasetFactory.register_pandas_dataframe(\n",
-        "    pd.read_csv(\"Data/hts-sample-train.csv\"),\n",
-        "    target=(datastore, \"hts-sample\"),\n",
-        "    name=\"hts-sales-train\",\n",
-        ")\n",
-        "registered_inference = TabularDatasetFactory.register_pandas_dataframe(\n",
-        "    pd.read_csv(\"Data/hts-sample-test.csv\"),\n",
-        "    target=(datastore, \"hts-sample\"),\n",
-        "    name=\"hts-sales-test\",\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## 3.0 Build the training pipeline\n",
-        "Now that the dataset, WorkSpace, and datastore are set up, we can put together a pipeline for training.\n",
-        "\n",
-        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Choose a compute target\n",
-        "\n",
-        "You will need to create a [compute target](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-set-up-training-targets#amlcompute) for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
-        "\n",
-        "\\*\\*Creation of AmlCompute takes approximately 5 minutes.**\n",
-        "\n",
-        "If the AmlCompute with that name is already in your workspace this code will skip the creation process. As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read this [article](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-manage-quotas) on the default limits and how to request more quota."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "gather": {
-          "logged": 1613007037308
-        }
-      },
-      "outputs": [],
-      "source": [
-        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
-        "\n",
-        "# Name your cluster\n",
-        "compute_name = \"hts-compute\"\n",
-        "\n",
-        "\n",
-        "if compute_name in ws.compute_targets:\n",
-        "    compute_target = ws.compute_targets[compute_name]\n",
-        "    if compute_target and type(compute_target) is AmlCompute:\n",
-        "        print(\"Found compute target: \" + compute_name)\n",
-        "else:\n",
-        "    print(\"Creating a new compute target...\")\n",
-        "    provisioning_config = AmlCompute.provisioning_configuration(\n",
-        "        vm_size=\"STANDARD_D16S_V3\", max_nodes=20\n",
-        "    )\n",
-        "    # Create the compute target\n",
-        "    compute_target = ComputeTarget.create(ws, compute_name, provisioning_config)\n",
-        "\n",
-        "    # Can poll for a minimum number of nodes and for a specific timeout.\n",
-        "    # If no min node count is provided it will use the scale settings for the cluster\n",
-        "    compute_target.wait_for_completion(\n",
-        "        show_output=True, min_node_count=None, timeout_in_minutes=20\n",
-        "    )\n",
-        "\n",
-        "    # For a more detailed view of current cluster status, use the 'status' property\n",
-        "    print(compute_target.status.serialize())"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Set up training parameters\n",
-        "\n",
-        "We need to provide ``ForecastingParameters``, ``AutoMLConfig`` and ``HTSTrainParameters`` objects. For the forecasting task we need to define several settings including the name of the time column, the maximum forecast horizon, the hierarchy definition, and the level of the hierarchy at which to train.\n",
-        "\n",
-        "#### ``ForecastingParameters`` arguments\n",
-        "| Property                           | Description|\n",
-        "| :---------------                   | :------------------- |\n",
-        "| **forecast_horizon**               | The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly). Periods are inferred from your data. |\n",
-        "| **time_column_name**               | The name of your time column. |\n",
-        "| **time_series_id_column_names**    | The column names used to uniquely identify timeseries in data that has multiple rows with the same timestamp. |\n",
-        "| **cv_step_size**                   | Number of periods between two consecutive cross-validation folds. The default value is \\\"auto\\\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value. |\n",
-        "\n",
-        "#### ``AutoMLConfig`` arguments\n",
-        "| Property                           | Description|\n",
-        "| :---------------                   | :------------------- |\n",
-        "| **task**                           | forecasting |\n",
-        "| **primary_metric**                 | This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i> |\n",
-        "| **blocked_models**                 | Blocked models won't be used by AutoML. |\n",
-        "| **iteration_timeout_minutes**      | Maximum amount of time in minutes that the model can train. This is optional but provides customers with greater control on exit criteria. |\n",
-        "| **iterations**                     | Number of models to train. This is optional but provides customers with greater control on exit criteria. |\n",
-        "| **experiment_timeout_hours**       | Maximum amount of time in hours that each experiment can take before it terminates. This is optional but provides customers with greater control on exit criteria. **It does not control the overall timeout for the pipeline run, instead controls the timeout for each training run per partitioned time series.** |\n",
-        "| **label_column_name**              | The name of the label column. |\n",
-        "| **n_cross_validations**            | Number of cross validation splits. The default value is \\\"auto\\\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
-        "| **enable_early_stopping**          | Flag to enable early termination if the primary metric is no longer improving. |\n",
-        "| **enable_engineered_explanations** | Engineered feature explanations will be downloaded if enable_engineered_explanations flag is set to True. By default it is set to False to save storage space. |\n",
-        "| **track_child_runs**               | Flag to disable tracking of child runs. Only best run is tracked if the flag is set to False (this includes the model and metrics of the run). |\n",
-        "| **pipeline_fetch_max_batch_size**  | Determines how many pipelines (training algorithms) to fetch at a time for training, this helps reduce throttling when training at large scale. |\n",
-        "| **model_explainability**           | Flag to disable explaining the best automated ML model at the end of all training iterations. The default is True and will block non-explainable models which may impact the forecast accuracy. For more information, see [Interpretability: model explanations in automated machine learning](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-machine-learning-interpretability-automl). |\n",
-        "\n",
-        "#### ``HTSTrainParameters`` arguments\n",
-        "| Property                           | Description|\n",
-        "| :---------------                   | :------------------- |\n",
-        "| **automl_settings**                | The ``AutoMLConfig`` object defined above. |\n",
-        "| **hierarchy_column_names**         | The names of columns that define the hierarchical structure of the data from highest level to most granular. |\n",
-        "| **training_level**                 | The level of the hierarchy to be used for training models. |\n",
-        "| **enable_engineered_explanations** | The switch controls engineered explanations. |"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "gather": {
-          "logged": 1613007061544
-        }
-      },
-      "outputs": [],
-      "source": [
-        "from azureml.train.automl.runtime._hts.hts_parameters import HTSTrainParameters\n",
-        "from azureml.automl.core.forecasting_parameters import ForecastingParameters\n",
-        "from azureml.train.automl.automlconfig import AutoMLConfig\n",
-        "\n",
-        "\n",
-        "model_explainability = True\n",
-        "\n",
-        "engineered_explanations = False\n",
-        "# Define your hierarchy. Adjust the settings below based on your dataset.\n",
-        "hierarchy = [\"state\", \"store_id\", \"product_category\", \"SKU\"]\n",
-        "training_level = \"SKU\"\n",
-        "\n",
-        "# Set your forecast parameters. Adjust the settings below based on your dataset.\n",
-        "time_column_name = \"date\"\n",
-        "label_column_name = \"quantity\"\n",
-        "forecast_horizon = 7\n",
-        "\n",
-        "forecasting_parameters = ForecastingParameters(\n",
-        "    time_column_name=time_column_name,\n",
-        "    forecast_horizon=forecast_horizon,\n",
-        ")\n",
-        "\n",
-        "automl_settings = AutoMLConfig(\n",
-        "    task=\"forecasting\",\n",
-        "    primary_metric=\"normalized_root_mean_squared_error\",\n",
-        "    experiment_timeout_hours=1,\n",
-        "    label_column_name=label_column_name,\n",
-        "    track_child_runs=False,\n",
-        "    forecasting_parameters=forecasting_parameters,\n",
-        "    pipeline_fetch_max_batch_size=15,\n",
-        "    model_explainability=model_explainability,\n",
-        "    n_cross_validations=\"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
-        "    cv_step_size=\"auto\",\n",
-        "    # The following settings are specific to this sample and should be adjusted according to your own needs.\n",
-        "    iteration_timeout_minutes=10,\n",
-        "    iterations=15,\n",
-        ")\n",
-        "\n",
-        "hts_parameters = HTSTrainParameters(\n",
-        "    automl_settings=automl_settings,\n",
-        "    hierarchy_column_names=hierarchy,\n",
-        "    training_level=training_level,\n",
-        "    enable_engineered_explanations=engineered_explanations,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Set up hierarchy training pipeline"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Parallel run step is leveraged to train multiple models at once. To configure the ParallelRunConfig you will need to determine the appropriate number of workers and nodes for your use case. The ``process_count_per_node`` is based off the number of cores of the compute VM. The node_count will determine the number of master nodes to use, increasing the node count will speed up the training process.\n",
-        "\n",
-        "| Property                           | Description|\n",
-        "| :---------------                   | :------------------- |\n",
-        "| **experiment**                     | The experiment used for training. |\n",
-        "| **train_data**                     | The file dataset to be used as input to the training run. |\n",
-        "| **node_count**                     | The number of compute nodes to be used for running the user script. We recommend to start with 3 and increase the node_count if the training time is taking too long. |\n",
-        "| **process_count_per_node**         | Process count per node, we recommend 2:1 ratio for number of cores: number of processes per node. eg. If node has 16 cores then configure 8 or less process count per node for optimal performance. |\n",
-        "| **train_pipeline_parameters**      | The set of configuration parameters defined in the previous section. |\n",
-        "| **run_invocation_timeout**         | Maximum amount of time in seconds that the ``ParallelRunStep`` class is allowed. This is optional but provides customers with greater control on exit criteria. This must be greater than ``experiment_timeout_hours`` by at least 300 seconds. |\n",
-        "\n",
-        "Calling this method will create a new aggregated dataset which is generated dynamically on pipeline execution.\n",
-        "\n",
-        "**Note**: Total time taken for the **training step** in the pipeline to complete = $ \\frac{t}{ p \\times n } \\times ts $\n",
-        "where,\n",
-        "- $ t $ is time taken for training one partition (can be viewed in the training logs)\n",
-        "- $ p $ is ``process_count_per_node``\n",
-        "- $ n $ is ``node_count``\n",
-        "- $ ts $ is total number of partitions in time series based on ``partition_column_names``"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.contrib.automl.pipeline.steps import AutoMLPipelineBuilder\n",
-        "\n",
-        "\n",
-        "training_pipeline_steps = AutoMLPipelineBuilder.get_many_models_train_steps(\n",
-        "    experiment=experiment,\n",
-        "    train_data=registered_train,\n",
-        "    compute_target=compute_target,\n",
-        "    node_count=2,\n",
-        "    process_count_per_node=8,\n",
-        "    train_pipeline_parameters=hts_parameters,\n",
-        "    run_invocation_timeout=3900,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.pipeline.core import Pipeline\n",
-        "\n",
-        "training_pipeline = Pipeline(ws, steps=training_pipeline_steps)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Submit the pipeline to run\n",
-        "Next we submit our pipeline to run. The whole training pipeline takes about 1h using a Standard_D16_V3 VM with our current ParallelRunConfig setting."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "training_run = experiment.submit(training_pipeline)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "training_run.wait_for_completion(show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Check the run status, if training_run is in completed state, continue to forecasting. If training_run is in another state, check the portal for failures."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### [Optional] Get the explanations\n",
-        "First we need to download the explanations to the local disk."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "if model_explainability:\n",
-        "    expl_output = training_run.get_pipeline_output(\"explanations\")\n",
-        "    expl_output.download(\"training_explanations\")\n",
-        "else:\n",
-        "    print(\n",
-        "        \"Model explanations are available only if model_explainability is set to True.\"\n",
-        "    )"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "The explanations are downloaded to the \"training_explanations/azureml\" directory."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "\n",
-        "if model_explainability:\n",
-        "    explanations_dirrectory = os.listdir(\n",
-        "        os.path.join(\"training_explanations\", \"azureml\")\n",
-        "    )\n",
-        "    if len(explanations_dirrectory) > 1:\n",
-        "        print(\n",
-        "            \"Warning! The directory contains multiple explanations, only the first one will be displayed.\"\n",
-        "        )\n",
-        "    print(\"The explanations are located at {}.\".format(explanations_dirrectory[0]))\n",
-        "    # Now we will list all the explanations.\n",
-        "    explanation_path = os.path.join(\n",
-        "        \"training_explanations\",\n",
-        "        \"azureml\",\n",
-        "        explanations_dirrectory[0],\n",
-        "        \"training_explanations\",\n",
-        "    )\n",
-        "    print(\"Available explanations\")\n",
-        "    print(\"==============================\")\n",
-        "    print(\"\\n\".join(os.listdir(explanation_path)))\n",
-        "else:\n",
-        "    print(\n",
-        "        \"Model explanations are available only if model_explainability is set to True.\"\n",
-        "    )"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "View the explanations on \"state\" level."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from IPython.display import display\n",
-        "\n",
-        "explanation_type = \"raw\"\n",
-        "level = \"state\"\n",
-        "\n",
-        "if model_explainability:\n",
-        "    display(\n",
-        "        pd.read_csv(\n",
-        "            os.path.join(explanation_path, \"{}_explanations_{}.csv\").format(\n",
-        "                explanation_type, level\n",
-        "            )\n",
-        "        )\n",
-        "    )"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## 5.0 Forecasting\n",
-        "For hierarchical forecasting we need to provide the HTSInferenceParameters object.\n",
-        "#### ``HTSInferenceParameters`` arguments\n",
-        "| Property                           | Description|\n",
-        "| :---------------                   | :------------------- |\n",
-        "| **hierarchy_forecast_level:**      | The default level of the hierarchy to produce prediction/forecast on. |\n",
-        "| **allocation_method:**             | \\[Optional] The disaggregation method to use if the hierarchy forecast level specified is below the define hierarchy training level. <br><i>(average historical proportions) 'average_historical_proportions'</i><br><i>(proportions of the historical averages) 'proportions_of_historical_average'</i> |\n",
-        "\n",
-        "#### ``get_many_models_batch_inference_steps`` arguments\n",
-        "| Property                           | Description|\n",
-        "| :---------------                   | :------------------- |\n",
-        "| **experiment**                     | The experiment used for inference run. |\n",
-        "| **inference_data**                 | The data to use for inferencing. It should be the same schema as used for training.\n",
-        "| **compute_target**                 | The compute target that runs the inference pipeline. |\n",
-        "| **node_count**                     | The number of compute nodes to be used for running the user script. We recommend to start with the number of cores per node (varies by compute sku). |\n",
-        "| **process_count_per_node**         | \\[Optional] The number of processes per node. By default it's 2 (should be at most half of the number of cores in a single node of the compute cluster that will be used for the experiment).\n",
-        "| **inference_pipeline_parameters**  | \\[Optional] The ``HTSInferenceParameters`` object defined above. |\n",
-        "| **train_run_id**                   | \\[Optional] The run id of the **training pipeline**. By default it is the latest successful training pipeline run in the experiment. |\n",
-        "| **train_experiment_name**          | \\[Optional] The train experiment that contains the train pipeline. This one is only needed when the train pipeline is not in the same experiement as the inference pipeline. |\n",
-        "| **run_invocation_timeout**         | \\[Optional] Maximum amount of time in seconds that the ``ParallelRunStep`` class is allowed. This is optional but provides customers with greater control on exit criteria. |"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.train.automl.runtime._hts.hts_parameters import HTSInferenceParameters\n",
-        "\n",
-        "inference_parameters = HTSInferenceParameters(\n",
-        "    hierarchy_forecast_level=\"store_id\",  # The setting is specific to this dataset and should be changed based on your dataset.\n",
-        "    allocation_method=\"proportions_of_historical_average\",\n",
-        ")\n",
-        "\n",
-        "steps = AutoMLPipelineBuilder.get_many_models_batch_inference_steps(\n",
-        "    experiment=experiment,\n",
-        "    inference_data=registered_inference,\n",
-        "    compute_target=compute_target,\n",
-        "    inference_pipeline_parameters=inference_parameters,\n",
-        "    node_count=2,\n",
-        "    process_count_per_node=8,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.pipeline.core import Pipeline\n",
-        "\n",
-        "inference_pipeline = Pipeline(ws, steps=steps)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "inference_run = experiment.submit(inference_pipeline)\n",
-        "inference_run.wait_for_completion(show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Retrieve results\n",
-        "\n",
-        "Forecast results can be retrieved through the following code. The prediction results summary and the actual predictions are downloaded in forecast_results folder"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "forecasts = inference_run.get_pipeline_output(\"forecasts\")\n",
-        "forecasts.download(\"forecast_results\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Resbumit the Pipeline\n",
-        "\n",
-        "The inference pipeline can be submitted with different configurations."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "inference_run = experiment.submit(\n",
-        "    inference_pipeline, pipeline_parameters={\"hierarchy_forecast_level\": \"state\"}\n",
-        ")\n",
-        "inference_run.wait_for_completion(show_output=False)"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "jialiu"
-      }
-    ],
-    "categories": [
-      "how-to-use-azureml",
-      "automated-machine-learning"
-    ],
-    "kernelspec": {
-      "display_name": "Python 3.8 - AzureML",
-      "language": "python",
-      "name": "python38-azureml"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.8.10"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 4
-}

how-to-use-azureml/automated-machine-learning/forecasting-many-models/README.md

@@ -1,122 +0,0 @@
----
-page_type: sample
-languages:
-- python
-products:
-- azure-machine-learning
-description: Tutorial showing how to solve a complex machine learning time series forecasting problems at scale by using Azure Automated ML and Many Models solution accelerator.
----
-
-![Many Models Solution Accelerator Banner](images/mmsa.png)
-# Many Models Solution Accelerator
-
-<!-- 
-Guidelines on README format: https://review.docs.microsoft.com/help/onboard/admin/samples/concepts/readme-template?branch=master
-
-Guidance on onboarding samples to docs.microsoft.com/samples: https://review.docs.microsoft.com/help/onboard/admin/samples/process/onboarding?branch=master
-
-Taxonomies for products and languages: https://review.docs.microsoft.com/new-hope/information-architecture/metadata/taxonomies?branch=master
--->
-
-In the real world, many problems can be too complex to be solved by a single machine learning model. Whether that be predicting sales for each individual store, building a predictive maintanence model for hundreds of oil wells, or tailoring an experience to individual users, building a model for each instance can lead to improved results on many machine learning problems.
-
-This Pattern is very common across a wide variety of industries and applicable to many real world use cases. Below are some examples we have seen where this pattern is being used.
-
-- Energy and utility companies building predictive maintenance models for thousands of oil wells, hundreds of wind turbines or hundreds of smart meters
-
-- Retail organizations building workforce optimization models for thousands of stores, campaign promotion propensity models, Price optimization models for hundreds of thousands of products they sell
-
-- Restaurant chains building demand forecasting models across thousands of restaurants  
-
-- Banks and financial institutes building models for cash replenishment for ATM Machine and for several ATMs or building personalized models for individuals
-
-- Enterprises building revenue forecasting models at each division level
-
-- Document management companies building text analytics and legal document search models per each state
-
-Azure Machine Learning (AML) makes it easy to train, operate, and manage hundreds or even thousands of models. This repo will walk you through the end to end process of creating a many models solution from training to scoring to monitoring.
-
-## Prerequisites
-
-To use this solution accelerator, all you need is access to an [Azure subscription](https://azure.microsoft.com/free/) and an [Azure Machine Learning Workspace](https://docs.microsoft.com/azure/machine-learning/how-to-manage-workspace) that you'll create below.
-
-While it's not required, a basic understanding of Azure Machine Learning will be helpful for understanding the solution. The following resources can help introduce you to AML:
-
-1. [Azure Machine Learning Overview](https://azure.microsoft.com/services/machine-learning/)
-2. [Azure Machine Learning Tutorials](https://docs.microsoft.com/azure/machine-learning/tutorial-1st-experiment-sdk-setup)
-3. [Azure Machine Learning Sample Notebooks on Github](https://github.com/Azure/azureml-examples)
-
-## Getting started
-
-### 1. Deploy Resources
-
-Start by deploying the resources to Azure. The button below will deploy Azure Machine Learning and its related resources:
-
-<a href="https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.githubusercontent.com%2Fmicrosoft%2Fsolution-accelerator-many-models%2Fmaster%2Fazuredeploy.json" target="_blank">
-    <img src="http://azuredeploy.net/deploybutton.png"/>
-</a>
-
-### 2. Configure Development Environment
-
-Next you'll need to configure your [development environment](https://docs.microsoft.com/azure/machine-learning/how-to-configure-environment) for Azure Machine Learning. We recommend using a [Compute Instance](https://docs.microsoft.com/azure/machine-learning/how-to-configure-environment#compute-instance) as it's the fastest way to get up and running.
-
-### 3. Run Notebooks
-
-Once your development environment is set up, run through the Jupyter Notebooks sequentially following the steps outlined. By the end, you'll know how to train, score, and make predictions using the many models pattern on Azure Machine Learning.
-
-![Sequence of Notebooks](./images/mmsa-overview.png)
-
-
-## Contents
-
-In this repo, you'll train and score a forecasting model for each orange juice brand and for each store at a (simulated) grocery chain. By the end, you'll have forecasted sales by using up to 11,973 models to predict sales for the next few weeks.
-
-The data used in this sample is simulated based on the [Dominick's Orange Juice Dataset](http://www.cs.unitn.it/~taufer/QMMA/L10-OJ-Data.html#(1)), sales data from a Chicago area grocery store.
-
-<img src="images/Flow_map.png" width="1000">
-
-### Using Automated ML to train the models:
-
-The [`auto-ml-forecasting-many-models.ipynb`](./auto-ml-forecasting-many-models.ipynb) noteboook is a guided solution accelerator that demonstrates steps from data preparation, to model training, and forecasting on train models as well as operationalizing the solution.
-
-## How-to-videos
-
-Watch these how-to-videos for a step by step walk-through of the many model solution accelerator to learn how to setup your models using Automated ML.
-
-### Automated ML
-
-[![Watch the video](https://media.giphy.com/media/dWUKfameudyNGRnp1t/giphy.gif)](https://channel9.msdn.com/Shows/Docs-AI/Building-Large-Scale-Machine-Learning-Forecasting-Models-using-Azure-Machine-Learnings-Automated-ML)
-
-## Key concepts
-
-### ParallelRunStep
-
-[ParallelRunStep](https://docs.microsoft.com/en-us/python/api/azureml-pipeline-steps/azureml.pipeline.steps.parallel_run_step.parallelrunstep?view=azure-ml-py) enables the parallel training of models and is commonly used for batch inferencing. This [document](https://docs.microsoft.com/azure/machine-learning/how-to-use-parallel-run-step) walks through some of the key concepts around ParallelRunStep.
-
-### Pipelines
-
-[Pipelines](https://docs.microsoft.com/azure/machine-learning/concept-ml-pipelines) allow you to create workflows in your machine learning projects. These workflows have a number of benefits including speed, simplicity, repeatability, and modularity.
-
-### Automated Machine Learning
-
-[Automated Machine Learning](https://docs.microsoft.com/azure/machine-learning/concept-automated-ml) also referred to as automated ML or AutoML, is the process of automating the time consuming, iterative tasks of machine learning model development. It allows data scientists, analysts, and developers to build ML models with high scale, efficiency, and productivity all while sustaining model quality.
-
-### Other Concepts
-
-In additional to ParallelRunStep, Pipelines and Automated Machine Learning, you'll also be working with the following concepts including [workspace](https://docs.microsoft.com/azure/machine-learning/concept-workspace), [datasets](https://docs.microsoft.com/azure/machine-learning/concept-data#datasets), [compute targets](https://docs.microsoft.com/azure/machine-learning/concept-compute-target#train), [python script steps](https://docs.microsoft.com/python/api/azureml-pipeline-steps/azureml.pipeline.steps.python_script_step.pythonscriptstep?view=azure-ml-py), and [Azure Open Datasets](https://azure.microsoft.com/services/open-datasets/).
-
-## Contributing
-
-This project welcomes contributions and suggestions. To learn more visit the [contributing](../../../CONTRIBUTING.md) section.
-
-Most contributions require you to agree to a Contributor License Agreement (CLA)
-declaring that you have the right to, and actually do, grant us
-the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.
-
-When you submit a pull request, a CLA bot will automatically determine whether you need to provide
-a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions
-provided by the bot. You will only need to do this once across all repos using our CLA.
-
-This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
-For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or
-contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.

how-to-use-azureml/automated-machine-learning/forecasting-many-models/auto-ml-forecasting-many-models.ipynb

@@ -1,898 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/forecasting-hierarchical-timeseries/auto-ml-forecasting-hierarchical-timeseries.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<font color=\"red\" size=\"5\"><strong>!Important!</strong> </br>This notebook is outdated and is not supported by the AutoML Team. Please use the supported version ([link](https://github.com/Azure/azureml-examples/tree/main/sdk/python/jobs/pipelines/1k_demand_forecasting_with_pipeline_components/automl-forecasting-demand-many-models-in-pipeline)).</font>"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Many Models - Automated ML\n",
-        "**_Generate many models time series forecasts with Automated Machine Learning_**\n",
-        "\n",
-        "---"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "For this notebook we are using a synthetic dataset portraying sales data to predict the the quantity of a vartiety of product skus across several states, stores, and product categories.\n",
-        "\n",
-        "**NOTE: There are limits on how many runs we can do in parallel per workspace, and we currently recommend to set the parallelism to maximum of 320 runs per experiment per workspace. If users want to have more parallelism and increase this limit they might encounter Too Many Requests errors (HTTP 429).**"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Prerequisites\n",
-        "You'll need to create a compute Instance by following [these](https://learn.microsoft.com/en-us/azure/machine-learning/v1/how-to-create-manage-compute-instance?tabs=python) instructions."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## 1.0 Set up workspace, datastore, experiment"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "gather": {
-          "logged": 1613003526897
-        }
-      },
-      "outputs": [],
-      "source": [
-        "import azureml.core\n",
-        "from azureml.core import Workspace, Datastore\n",
-        "import pandas as pd\n",
-        "\n",
-        "# Set up your workspace\n",
-        "ws = Workspace.from_config()\n",
-        "ws.get_details()\n",
-        "\n",
-        "# Set up your datastores\n",
-        "dstore = ws.get_default_datastore()\n",
-        "\n",
-        "output = {}\n",
-        "output[\"SDK version\"] = azureml.core.VERSION\n",
-        "output[\"Subscription ID\"] = ws.subscription_id\n",
-        "output[\"Workspace\"] = ws.name\n",
-        "output[\"Resource Group\"] = ws.resource_group\n",
-        "output[\"Location\"] = ws.location\n",
-        "output[\"Default datastore name\"] = dstore.name\n",
-        "output[\"SDK Version\"] = azureml.core.VERSION\n",
-        "pd.set_option(\"display.max_colwidth\", None)\n",
-        "outputDf = pd.DataFrame(data=output, index=[\"\"])\n",
-        "outputDf.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Choose an experiment"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "gather": {
-          "logged": 1613003540729
-        }
-      },
-      "outputs": [],
-      "source": [
-        "from azureml.core import Experiment\n",
-        "\n",
-        "experiment = Experiment(ws, \"automl-many-models\")\n",
-        "\n",
-        "print(\"Experiment name: \" + experiment.name)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## 2.0 Data\n",
-        "\n",
-        "This notebook uses simulated orange juice sales data to walk you through the process of training many models on Azure Machine Learning using Automated ML. \n",
-        "\n",
-        "The time series data used in this example was simulated based on the University of Chicago's Dominick's Finer Foods dataset which featured two years of sales of 3 different orange juice brands for individual stores. The full simulated dataset includes 3,991 stores with 3 orange juice brands each thus allowing 11,973 models to be trained to showcase the power of the many models pattern.\n",
-        "\n",
-        "  \n",
-        "In this notebook, two datasets will be created: one with all 11,973 files and one with only 10 files that can be used to quickly test and debug. For each dataset, you'll be walked through the process of:\n",
-        "\n",
-        "1. Registering the blob container as a Datastore to the Workspace\n",
-        "2. Registering a tabular dataset to the Workspace"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "nteract": {
-          "transient": {
-            "deleting": false
-          }
-        }
-      },
-      "source": [
-        "### 2.1 Data Preparation\n",
-        "The OJ data is available in the public blob container. The data is split to be used for training and for inferencing. For the current dataset, the data was split on time column ('WeekStarting') before and after '1992-5-28' .\n",
-        "\n",
-        "The container has\n",
-        "<ol>\n",
-        "    <li><b>'oj-data-tabular'</b> and <b>'oj-inference-tabular'</b> folders that contains training and inference data respectively for the 11,973 models. </li>\n",
-        "    <li>It also has <b>'oj-data-small-tabular'</b> and <b>'oj-inference-small-tabular'</b> folders that has training and inference data for 10 models.</li>\n",
-        "</ol>\n",
-        "\n",
-        "To create the [TabularDataset](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.tabular_dataset.tabulardataset?view=azure-ml-py) needed for the ParallelRunStep, you first need to register the blob container to the workspace."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "nteract": {
-          "transient": {
-            "deleting": false
-          }
-        }
-      },
-      "source": [
-        "<b> To use your own data, put your own data in a blobstore folder. As shown it can be one file or multiple files. We can then register datastore using that blob as shown below.\n",
-        "    \n",
-        "<h3> How sample data in blob store looks like</h3>\n",
-        "\n",
-        "['oj-data-tabular'](https://ms.portal.azure.com/#blade/Microsoft_Azure_Storage/ContainerMenuBlade/overview/storageAccountId/%2Fsubscriptions%2F102a16c3-37d3-48a8-9237-4c9b1e8e80e0%2FresourceGroups%2FAutoMLSampleNotebooksData%2Fproviders%2FMicrosoft.Storage%2FstorageAccounts%2Fautomlsamplenotebookdata/path/automl-sample-notebook-data/etag/%220x8D84EAA65DE50B7%22/defaultEncryptionScope/%24account-encryption-key/denyEncryptionScopeOverride//defaultId//publicAccessVal/Container)</b>\n",
-        "![image-4.png](mm-1.png)\n",
-        "\n",
-        "['oj-inference-tabular'](https://ms.portal.azure.com/#blade/Microsoft_Azure_Storage/ContainerMenuBlade/overview/storageAccountId/%2Fsubscriptions%2F102a16c3-37d3-48a8-9237-4c9b1e8e80e0%2FresourceGroups%2FAutoMLSampleNotebooksData%2Fproviders%2FMicrosoft.Storage%2FstorageAccounts%2Fautomlsamplenotebookdata/path/automl-sample-notebook-data/etag/%220x8D84EAA65DE50B7%22/defaultEncryptionScope/%24account-encryption-key/denyEncryptionScopeOverride//defaultId//publicAccessVal/Container)\n",
-        "![image-3.png](mm-2.png)\n",
-        "\n",
-        "['oj-data-small-tabular'](https://ms.portal.azure.com/#blade/Microsoft_Azure_Storage/ContainerMenuBlade/overview/storageAccountId/%2Fsubscriptions%2F102a16c3-37d3-48a8-9237-4c9b1e8e80e0%2FresourceGroups%2FAutoMLSampleNotebooksData%2Fproviders%2FMicrosoft.Storage%2FstorageAccounts%2Fautomlsamplenotebookdata/path/automl-sample-notebook-data/etag/%220x8D84EAA65DE50B7%22/defaultEncryptionScope/%24account-encryption-key/denyEncryptionScopeOverride//defaultId//publicAccessVal/Container)\n",
-        "\n",
-        "![image-5.png](mm-3.png)\n",
-        "\n",
-        "['oj-inference-small-tabular'](https://ms.portal.azure.com/#blade/Microsoft_Azure_Storage/ContainerMenuBlade/overview/storageAccountId/%2Fsubscriptions%2F102a16c3-37d3-48a8-9237-4c9b1e8e80e0%2FresourceGroups%2FAutoMLSampleNotebooksData%2Fproviders%2FMicrosoft.Storage%2FstorageAccounts%2Fautomlsamplenotebookdata/path/automl-sample-notebook-data/etag/%220x8D84EAA65DE50B7%22/defaultEncryptionScope/%24account-encryption-key/denyEncryptionScopeOverride//defaultId//publicAccessVal/Container)\n",
-        "![image-6.png](mm-4.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### 2.2 Register the blob container as DataStore\n",
-        "\n",
-        "A Datastore is a place where data can be stored that is then made accessible to a compute either by means of mounting or copying the data to the compute target.\n",
-        "\n",
-        "Please refer to [Datastore](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.datastore(class)?view=azure-ml-py) documentation on how to access data from Datastore.\n",
-        "\n",
-        "In this next step, we will be registering blob storage as datastore to the Workspace."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core import Datastore\n",
-        "\n",
-        "# Please change the following to point to your own blob container and pass in account_key\n",
-        "blob_datastore_name = \"automl_many_models\"\n",
-        "container_name = \"automl-sample-notebook-data\"\n",
-        "account_name = \"automlsamplenotebookdata\"\n",
-        "\n",
-        "oj_datastore = Datastore.register_azure_blob_container(\n",
-        "    workspace=ws,\n",
-        "    datastore_name=blob_datastore_name,\n",
-        "    container_name=container_name,\n",
-        "    account_name=account_name,\n",
-        "    create_if_not_exists=True,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### 2.3 Using tabular datasets \n",
-        "\n",
-        "Now that the datastore is available from the Workspace, [TabularDataset](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.tabular_dataset.tabulardataset?view=azure-ml-py) can be created. Datasets in Azure Machine Learning are references to specific data in a Datastore.  We are using TabularDataset, so that users who have their data which can be in one or many files (*.parquet or *.csv) and have not split up data according to group columns needed for training, can do so using out of box support for 'partiion_by' feature of TabularDataset shown in section 5.0 below."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "gather": {
-          "logged": 1613007017296
-        }
-      },
-      "outputs": [],
-      "source": [
-        "from azureml.core import Dataset\n",
-        "\n",
-        "ds_name_small = \"oj-data-small-tabular\"\n",
-        "input_ds_small = Dataset.Tabular.from_delimited_files(\n",
-        "    path=oj_datastore.path(ds_name_small + \"/\"), validate=False\n",
-        ")\n",
-        "\n",
-        "inference_name_small = \"oj-inference-small-tabular\"\n",
-        "inference_ds_small = Dataset.Tabular.from_delimited_files(\n",
-        "    path=oj_datastore.path(inference_name_small + \"/\"), validate=False\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### 2.4 Configure data with ``OutputFileDatasetConfig`` objects\n",
-        "This step shows how to configure output data from a pipeline step. One of the use cases for this step is when you want to do some preprocessing before feeding the data to training step. Intermediate data (or output of a step) is represented by an ``OutputFileDatasetConfig`` object. ``output_data`` is produced as the output of a step. Optionally, this data can be registered as a dataset by calling the ``register_on_complete`` method. If you create an ``OutputFileDatasetConfig`` in one step and use it as an input to another step, that data dependency between steps creates an implicit execution order in the pipeline.\n",
-        "\n",
-        "``OutputFileDatasetConfig`` objects return a directory, and by default write output to the default datastore of the workspace.\n",
-        "\n",
-        "Since instance creation for class ``OutputTabularDatasetConfig`` is not allowed, we first create an instance of this class. Then we use the ``read_parquet_files`` method to read the parquet file into ``OutputTabularDatasetConfig``."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.data.output_dataset_config import OutputFileDatasetConfig\n",
-        "\n",
-        "output_data = OutputFileDatasetConfig(\n",
-        "    name=\"processed_data\", destination=(dstore, \"outputdataset/{run-id}/{output-name}\")\n",
-        ").as_upload()\n",
-        "# output_data_dataset = output_data.register_on_complete(\n",
-        "#     name='processed_data', description = 'files from prev step')\n",
-        "output_data = output_data.read_parquet_files()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## 3.0 Build the training pipeline\n",
-        "Now that the dataset, WorkSpace, and datastore are set up, we can put together a pipeline for training.\n",
-        "\n",
-        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Choose a compute target\n",
-        "\n",
-        "You will need to create a [compute target](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-set-up-training-targets#amlcompute) for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
-        "\n",
-        "\\*\\*Creation of AmlCompute takes approximately 5 minutes.**\n",
-        "\n",
-        "If the AmlCompute with that name is already in your workspace this code will skip the creation process. As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read this [article](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-manage-quotas) on the default limits and how to request more quota."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "gather": {
-          "logged": 1613007037308
-        }
-      },
-      "outputs": [],
-      "source": [
-        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
-        "\n",
-        "# Name your cluster\n",
-        "compute_name = \"mm-compute-v1\"\n",
-        "\n",
-        "\n",
-        "if compute_name in ws.compute_targets:\n",
-        "    compute_target = ws.compute_targets[compute_name]\n",
-        "    if compute_target and type(compute_target) is AmlCompute:\n",
-        "        print(\"Found compute target: \" + compute_name)\n",
-        "else:\n",
-        "    print(\"Creating a new compute target...\")\n",
-        "    provisioning_config = AmlCompute.provisioning_configuration(\n",
-        "        vm_size=\"STANDARD_D14_V2\", max_nodes=20\n",
-        "    )\n",
-        "    # Create the compute target\n",
-        "    compute_target = ComputeTarget.create(ws, compute_name, provisioning_config)\n",
-        "\n",
-        "    # Can poll for a minimum number of nodes and for a specific timeout.\n",
-        "    # If no min node count is provided it will use the scale settings for the cluster\n",
-        "    compute_target.wait_for_completion(\n",
-        "        show_output=True, min_node_count=None, timeout_in_minutes=20\n",
-        "    )\n",
-        "\n",
-        "    # For a more detailed view of current cluster status, use the 'status' property\n",
-        "    print(compute_target.status.serialize())"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Configure the training run's environment\n",
-        "The next step is making sure that the remote training run has all the dependencies needed by the training steps. Dependencies and the runtime context are set by creating and configuring a RunConfiguration object.\n",
-        "\n",
-        "The code below shows two options for handling dependencies. As presented, with ``USE_CURATED_ENV = True``, the configuration is based on a [curated environment](https://docs.microsoft.com/en-us/azure/machine-learning/resource-curated-environments). Curated environments have prebuilt Docker images in the [Microsoft Container Registry](https://hub.docker.com/publishers/microsoftowner). For more information, see [Azure Machine Learning curated environments](https://docs.microsoft.com/en-us/azure/machine-learning/resource-curated-environments).\n",
-        "\n",
-        "The path taken if you change ``USE_CURATED_ENV`` to False shows the pattern for explicitly setting your dependencies. In that scenario, a new custom Docker image will be created and registered in an Azure Container Registry within your resource group (see [Introduction to private Docker container registries in Azure](https://docs.microsoft.com/en-us/azure/container-registry/container-registry-intro)). Building and registering this image can take quite a few minutes."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.runconfig import RunConfiguration\n",
-        "from azureml.core.conda_dependencies import CondaDependencies\n",
-        "from azureml.core import Environment\n",
-        "\n",
-        "aml_run_config = RunConfiguration()\n",
-        "aml_run_config.target = compute_target\n",
-        "\n",
-        "USE_CURATED_ENV = True\n",
-        "if USE_CURATED_ENV:\n",
-        "    curated_environment = Environment.get(\n",
-        "        workspace=ws, name=\"AzureML-sklearn-1.5\"\n",
-        "    )\n",
-        "    aml_run_config.environment = curated_environment\n",
-        "else:\n",
-        "    aml_run_config.environment.python.user_managed_dependencies = False\n",
-        "\n",
-        "    # Add some packages relied on by data prep step\n",
-        "    aml_run_config.environment.python.conda_dependencies = CondaDependencies.create(\n",
-        "        conda_packages=[\"pandas\", \"scikit-learn\"],\n",
-        "        pip_packages=[\"azureml-sdk\", \"azureml-dataset-runtime[fuse,pandas]\"],\n",
-        "        pin_sdk_version=False,\n",
-        "    )"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Set up training parameters\n",
-        "\n",
-        "We need to provide ``ForecastingParameters``, ``AutoMLConfig`` and ``ManyModelsTrainParameters`` objects. For the forecasting task we also need to define several settings including the name of the time column, the maximum forecast horizon, and the partition column name(s) definition.\n",
-        "\n",
-        "#### ``ForecastingParameters`` arguments\n",
-        "| Property                           | Description|\n",
-        "| :---------------                   | :------------------- |\n",
-        "| **forecast_horizon**               | The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly). Periods are inferred from your data. |\n",
-        "| **time_column_name**               | The name of your time column. |\n",
-        "| **time_series_id_column_names**    | The column names used to uniquely identify timeseries in data that has multiple rows with the same timestamp. |\n",
-        "| **cv_step_size**                   | Number of periods between two consecutive cross-validation folds. The default value is \\\"auto\\\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value. |\n",
-        "\n",
-        "#### ``AutoMLConfig`` arguments\n",
-        "| Property                           | Description|\n",
-        "| :---------------                   | :------------------- |\n",
-        "| **task**                           | forecasting |\n",
-        "| **primary_metric**                 | This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i> |\n",
-        "| **blocked_models**                 | Blocked models won't be used by AutoML. |\n",
-        "| **iteration_timeout_minutes**      | Maximum amount of time in minutes that the model can train. This is optional but provides customers with greater control on exit criteria. |\n",
-        "| **iterations**                     | Number of models to train. This is optional but provides customers with greater control on exit criteria. |\n",
-        "| **experiment_timeout_hours**       | Maximum amount of time in hours that each experiment can take before it terminates. This is optional but provides customers with greater control on exit criteria. **It does not control the overall timeout for the pipeline run, instead controls the timeout for each training run per partitioned time series.** |\n",
-        "| **label_column_name**              | The name of the label column. |\n",
-        "| **n_cross_validations**            | Number of cross validation splits. The default value is \\\"auto\\\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
-        "| **enable_early_stopping**          | Flag to enable early termination if the primary metric is no longer improving. |\n",
-        "| **enable_engineered_explanations** | Engineered feature explanations will be downloaded if enable_engineered_explanations flag is set to True. By default it is set to False to save storage space. |\n",
-        "| **track_child_runs**               | Flag to disable tracking of child runs. Only best run is tracked if the flag is set to False (this includes the model and metrics of the run). |\n",
-        "| **pipeline_fetch_max_batch_size**  | Determines how many pipelines (training algorithms) to fetch at a time for training, this helps reduce throttling when training at large scale. |\n",
-        "\n",
-        "\n",
-        "#### ``ManyModelsTrainParameters`` arguments\n",
-        "| Property                           | Description|\n",
-        "| :---------------                   | :------------------- |\n",
-        "| **automl_settings**                | The ``AutoMLConfig`` object defined above. |\n",
-        "| **partition_column_names**         | The names of columns used to group your models. For timeseries, the groups must not split up individual time-series. That is, each group must contain one or more whole time-series. |"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "gather": {
-          "logged": 1613007061544
-        }
-      },
-      "outputs": [],
-      "source": [
-        "from azureml.train.automl.runtime._many_models.many_models_parameters import (\n",
-        "    ManyModelsTrainParameters,\n",
-        ")\n",
-        "from azureml.automl.core.forecasting_parameters import ForecastingParameters\n",
-        "from azureml.train.automl.automlconfig import AutoMLConfig\n",
-        "\n",
-        "partition_column_names = [\"Store\", \"Brand\"]\n",
-        "\n",
-        "forecasting_parameters = ForecastingParameters(\n",
-        "    time_column_name=\"WeekStarting\",\n",
-        "    forecast_horizon=6,\n",
-        "    time_series_id_column_names=partition_column_names,\n",
-        "    cv_step_size=\"auto\",\n",
-        ")\n",
-        "\n",
-        "automl_settings = AutoMLConfig(\n",
-        "    task=\"forecasting\",\n",
-        "    primary_metric=\"normalized_root_mean_squared_error\",\n",
-        "    iteration_timeout_minutes=10,\n",
-        "    iterations=15,\n",
-        "    experiment_timeout_hours=0.25,\n",
-        "    label_column_name=\"Quantity\",\n",
-        "    n_cross_validations=\"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
-        "    track_child_runs=False,\n",
-        "    forecasting_parameters=forecasting_parameters,\n",
-        ")\n",
-        "\n",
-        "mm_paramters = ManyModelsTrainParameters(\n",
-        "    automl_settings=automl_settings, partition_column_names=partition_column_names\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Construct your pipeline steps\n",
-        "Once you have the compute resource and environment created, you're ready to define your pipeline's steps. There are many built-in steps available via the Azure Machine Learning SDK, as you can see on the [reference documentation for the azureml.pipeline.steps package](https://docs.microsoft.com/en-us/python/api/azureml-pipeline-steps/azureml.pipeline.steps?view=azure-ml-py). The most flexible class is [PythonScriptStep](https://docs.microsoft.com/en-us/python/api/azureml-pipeline-steps/azureml.pipeline.steps.python_script_step.pythonscriptstep?view=azure-ml-py), which runs a Python script.\n",
-        "\n",
-        "Your data preparation code is in a subdirectory (in this example, \"data_preprocessing_tabular.py\" in the directory \"./scripts\"). As part of the pipeline creation process, this directory is zipped and uploaded to the compute_target and the step runs the script specified as the value for ``script_name``.\n",
-        "\n",
-        "The ``arguments`` values specify the inputs and outputs of the step. In the example below, the baseline data is the ``input_ds_small`` dataset. The script data_preprocessing_tabular.py does whatever data-transformation tasks are appropriate to the task at hand and outputs the data to ``output_data``, of type ``OutputFileDatasetConfig``. For more information, see [Moving data into and between ML pipeline steps (Python)](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-move-data-in-out-of-pipelines). The step will run on the machine defined by ``compute_target``, using the configuration ``aml_run_config``.\n",
-        "\n",
-        "Reuse of previous results (``allow_reuse``) is key when using pipelines in a collaborative environment since eliminating unnecessary reruns offers agility. Reuse is the default behavior when the ``script_name``, ``inputs``, and the parameters of a step remain the same. When reuse is allowed, results from the previous run are immediately sent to the next step. If ``allow_reuse`` is set to False, a new run will always be generated for this step during pipeline execution.\n",
-        "\n",
-        "> Note that we only support partitioned FileDataset and TabularDataset without partition when using such output as input.\n",
-        "\n",
-        "> Note that we **drop column** \"Revenue\" from the dataset in this step to avoid information leak as \"Quantity\" = \"Revenue\" / \"Price\". **Please modify the logic based on your data**."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.pipeline.steps import PythonScriptStep\n",
-        "\n",
-        "dataprep_source_dir = \"./scripts\"\n",
-        "entry_point = \"data_preprocessing_tabular.py\"\n",
-        "ds_input = input_ds_small.as_named_input(\"train_10_models\")\n",
-        "\n",
-        "data_prep_step = PythonScriptStep(\n",
-        "    script_name=entry_point,\n",
-        "    source_directory=dataprep_source_dir,\n",
-        "    arguments=[\"--input\", ds_input, \"--output\", output_data],\n",
-        "    compute_target=compute_target,\n",
-        "    runconfig=aml_run_config,\n",
-        "    allow_reuse=False,\n",
-        ")\n",
-        "\n",
-        "input_ds_small = output_data"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Set up many models pipeline"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Parallel run step is leveraged to train multiple models at once. To configure the ParallelRunConfig you will need to determine the appropriate number of workers and nodes for your use case. The ``process_count_per_node`` is based off the number of cores of the compute VM. The node_count will determine the number of master nodes to use, increasing the node count will speed up the training process.\n",
-        "\n",
-        "| Property                           | Description|\n",
-        "| :---------------                   | :------------------- |\n",
-        "| **experiment**                     | The experiment used for training. |\n",
-        "| **train_data**                     | The file dataset to be used as input to the training run. |\n",
-        "| **node_count**                     | The number of compute nodes to be used for running the user script. We recommend to start with 3 and increase the node_count if the training time is taking too long. |\n",
-        "| **process_count_per_node**         | Process count per node, we recommend 2:1 ratio for number of cores: number of processes per node. eg. If node has 16 cores then configure 8 or less process count per node for optimal performance. |\n",
-        "| **train_pipeline_parameters**      | The set of configuration parameters defined in the previous section. |\n",
-        "| **run_invocation_timeout**         | Maximum amount of time in seconds that the ``ParallelRunStep`` class is allowed. This is optional but provides customers with greater control on exit criteria. This must be greater than ``experiment_timeout_hours`` by at least 300 seconds. |\n",
-        "\n",
-        "Calling this method will create a new aggregated dataset which is generated dynamically on pipeline execution.\n",
-        "\n",
-        "**Note**: Total time taken for the **training step** in the pipeline to complete = $ \\frac{t}{ p \\times n } \\times ts $\n",
-        "where,\n",
-        "- $ t $ is time taken for training one partition (can be viewed in the training logs)\n",
-        "- $ p $ is ``process_count_per_node``\n",
-        "- $ n $ is ``node_count``\n",
-        "- $ ts $ is total number of partitions in time series based on ``partition_column_names``"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.contrib.automl.pipeline.steps import AutoMLPipelineBuilder\n",
-        "\n",
-        "\n",
-        "training_pipeline_steps = AutoMLPipelineBuilder.get_many_models_train_steps(\n",
-        "    experiment=experiment,\n",
-        "    train_data=input_ds_small,\n",
-        "    compute_target=compute_target,\n",
-        "    node_count=2,\n",
-        "    process_count_per_node=8,\n",
-        "    run_invocation_timeout=1200,\n",
-        "    train_pipeline_parameters=mm_paramters,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.pipeline.core import Pipeline\n",
-        "\n",
-        "training_pipeline = Pipeline(ws, steps=training_pipeline_steps)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Submit the pipeline to run\n",
-        "Next we submit our pipeline to run. The whole training pipeline takes about 40m using a STANDARD_D16S_V3 VM with our current ParallelRunConfig setting."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "training_run = experiment.submit(training_pipeline)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "training_run.wait_for_completion(show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Check the run status, if training_run is in completed state, continue to forecasting. If training_run is in another state, check the portal for failures."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## 5.0 Publish and schedule the train pipeline (Optional)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### 5.1 Publish the pipeline\n",
-        "\n",
-        "Once you have a pipeline you're happy with, you can publish a pipeline so you can call it programmatically later on. See this [tutorial](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-create-your-first-pipeline#publish-a-pipeline) for additional information on publishing and calling pipelines."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# published_pipeline = training_pipeline.publish(name = 'automl_train_many_models',\n",
-        "#                                                description = 'train many models',\n",
-        "#                                                version = '1',\n",
-        "#                                                continue_on_step_failure = False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### 5.2 Schedule the pipeline\n",
-        "You can also [schedule the pipeline](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-schedule-pipelines) to run on a time-based or change-based schedule. This could be used to automatically retrain models every month or based on another trigger such as data drift."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# from azureml.pipeline.core import Schedule, ScheduleRecurrence\n",
-        "\n",
-        "# training_pipeline_id = published_pipeline.id\n",
-        "\n",
-        "# recurrence = ScheduleRecurrence(frequency=\"Month\", interval=1, start_time=\"2020-01-01T09:00:00\")\n",
-        "# recurring_schedule = Schedule.create(ws, name=\"automl_training_recurring_schedule\",\n",
-        "#                                      description=\"Schedule Training Pipeline to run on the first day of every month\",\n",
-        "#                                      pipeline_id=training_pipeline_id,\n",
-        "#                                      experiment_name=experiment.name,\n",
-        "#                                      recurrence=recurrence)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## 6.0 Forecasting"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Set up output dataset for inference data\n",
-        "Output of inference can be represented as [OutputFileDatasetConfig](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.output_dataset_config.outputdatasetconfig?view=azure-ml-py) object and OutputFileDatasetConfig can be registered as a dataset. "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.data import OutputFileDatasetConfig\n",
-        "\n",
-        "output_inference_data_ds = OutputFileDatasetConfig(\n",
-        "    name=\"many_models_inference_output\", destination=(dstore, \"oj/inference_data/\")\n",
-        ").register_on_complete(name=\"oj_inference_data_ds\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "For many models we need to provide the ManyModelsInferenceParameters object.\n",
-        "\n",
-        "#### ``ManyModelsInferenceParameters`` arguments\n",
-        "| Property                           | Description|\n",
-        "| :---------------                   | :------------------- |\n",
-        "| **partition_column_names**         | List of column names that identifies groups. |\n",
-        "| **target_column_name**             | \\[Optional] Column name only if the inference dataset has the target. |\n",
-        "| **time_column_name**               | \\[Optional] Time column name only if it is timeseries. |\n",
-        "| **inference_type**                 | \\[Optional] Which inference method to use on the model. Possible values are 'forecast', 'predict_proba', and 'predict'. |\n",
-        "| **forecast_mode**                  | \\[Optional] The type of forecast to be used, either 'rolling' or 'recursive'; defaults to 'recursive'. |\n",
-        "| **step**                           | \\[Optional] Number of periods to advance the forecasting window in each iteration **(for rolling forecast only)**; defaults to 1. |\n",
-        "\n",
-        "#### ``get_many_models_batch_inference_steps`` arguments\n",
-        "| Property                           | Description|\n",
-        "| :---------------                   | :------------------- |\n",
-        "| **experiment**                     | The experiment used for inference run. |\n",
-        "| **inference_data**                 | The data to use for inferencing. It should be the same schema as used for training.\n",
-        "| **compute_target**                 | The compute target that runs the inference pipeline. |\n",
-        "| **node_count**                     | The number of compute nodes to be used for running the user script. We recommend to start with the number of cores per node (varies by compute sku). |\n",
-        "| **process_count_per_node**         | \\[Optional] The number of processes per node. By default it's 2 (should be at most half of the number of cores in a single node of the compute cluster that will be used for the experiment).\n",
-        "| **inference_pipeline_parameters**  | \\[Optional] The ``ManyModelsInferenceParameters`` object defined above. |\n",
-        "| **append_row_file_name**           | \\[Optional] The name of the output file (optional, default value is 'parallel_run_step.txt'). Supports 'txt' and 'csv' file extension. A 'txt' file extension generates the output in 'txt' format with space as separator without column names. A 'csv' file extension generates the output in 'csv' format with comma as separator and with column names. |\n",
-        "| **train_run_id**                   | \\[Optional] The run id of the **training pipeline**. By default it is the latest successful training pipeline run in the experiment. |\n",
-        "| **train_experiment_name**          | \\[Optional] The train experiment that contains the train pipeline. This one is only needed when the train pipeline is not in the same experiement as the inference pipeline. |\n",
-        "| **run_invocation_timeout**         | \\[Optional] Maximum amount of time in seconds that the ``ParallelRunStep`` class is allowed. This is optional but provides customers with greater control on exit criteria. |\n",
-        "| **output_datastore**               | \\[Optional] The ``Datastore`` or ``OutputDatasetConfig`` to be used for output. If specified any pipeline output will be written to that location. If unspecified the default datastore will be used. |\n",
-        "| **arguments**                      | \\[Optional] Arguments to be passed to inference script. Possible argument is '--forecast_quantiles' followed by quantile values. |"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.contrib.automl.pipeline.steps import AutoMLPipelineBuilder\n",
-        "from azureml.train.automl.runtime._many_models.many_models_parameters import (\n",
-        "    ManyModelsInferenceParameters,\n",
-        ")\n",
-        "\n",
-        "mm_parameters = ManyModelsInferenceParameters(\n",
-        "    partition_column_names=[\"Store\", \"Brand\"],\n",
-        "    time_column_name=\"WeekStarting\",\n",
-        "    target_column_name=\"Quantity\",\n",
-        ")\n",
-        "\n",
-        "output_file_name = \"parallel_run_step.csv\"\n",
-        "\n",
-        "inference_steps = AutoMLPipelineBuilder.get_many_models_batch_inference_steps(\n",
-        "    experiment=experiment,\n",
-        "    inference_data=inference_ds_small,\n",
-        "    node_count=2,\n",
-        "    process_count_per_node=8,\n",
-        "    compute_target=compute_target,\n",
-        "    run_invocation_timeout=300,\n",
-        "    output_datastore=output_inference_data_ds,\n",
-        "    train_run_id=training_run.id,\n",
-        "    train_experiment_name=training_run.experiment.name,\n",
-        "    inference_pipeline_parameters=mm_parameters,\n",
-        "    append_row_file_name=output_file_name,\n",
-        "    arguments=[\"--forecast_quantiles\", 0.1, 0.9],\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.pipeline.core import Pipeline\n",
-        "\n",
-        "inference_pipeline = Pipeline(ws, steps=inference_steps)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "inference_run = experiment.submit(inference_pipeline)\n",
-        "inference_run.wait_for_completion(show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Retrieve results\n",
-        "\n",
-        "The forecasting pipeline forecasts the orange juice quantity for a Store by Brand. The pipeline returns one file with the predictions for each store and outputs the result to the forecasting_output Blob container. The details of the blob container is listed in 'forecasting_output.txt' under Outputs+logs. \n",
-        "\n",
-        "The following code snippet:\n",
-        "1. Downloads the contents of the output folder that is passed in the parallel run step \n",
-        "2. Reads the output file that has the predictions as pandas dataframe and \n",
-        "3. Displays the top 10 rows of the predictions"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.contrib.automl.pipeline.steps.utilities import get_output_from_mm_pipeline\n",
-        "\n",
-        "forecasting_results_name = \"forecasting_results\"\n",
-        "forecasting_output_name = \"many_models_inference_output\"\n",
-        "forecast_file = get_output_from_mm_pipeline(\n",
-        "    inference_run, forecasting_results_name, forecasting_output_name, output_file_name\n",
-        ")\n",
-        "df = pd.read_csv(forecast_file)\n",
-        "print(\n",
-        "    \"Prediction has \", df.shape[0], \" rows. Here the first 10 rows are being displayed.\"\n",
-        ")\n",
-        "df.head(10)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## 7.0 Publish and schedule the inference pipeline (Optional)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### 7.1 Publish the pipeline\n",
-        "\n",
-        "Once you have a pipeline you're happy with, you can publish a pipeline so you can call it programmatically later on. See this [tutorial](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-create-your-first-pipeline#publish-a-pipeline) for additional information on publishing and calling pipelines."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# published_pipeline_inf = inference_pipeline.publish(name = 'automl_forecast_many_models',\n",
-        "#                                                     description = 'forecast many models',\n",
-        "#                                                     version = '1',\n",
-        "#                                                     continue_on_step_failure = False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### 7.2 Schedule the pipeline\n",
-        "You can also [schedule the pipeline](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-schedule-pipelines) to run on a time-based or change-based schedule. This could be used to automatically retrain or forecast models every month or based on another trigger such as data drift."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# from azureml.pipeline.core import Schedule, ScheduleRecurrence\n",
-        "\n",
-        "# forecasting_pipeline_id = published_pipeline.id\n",
-        "\n",
-        "# recurrence = ScheduleRecurrence(frequency=\"Month\", interval=1, start_time=\"2020-01-01T09:00:00\")\n",
-        "# recurring_schedule = Schedule.create(ws, name=\"automl_forecasting_recurring_schedule\",\n",
-        "#                             description=\"Schedule Forecasting Pipeline to run on the first day of every week\",\n",
-        "#                             pipeline_id=forecasting_pipeline_id,\n",
-        "#                             experiment_name=experiment.name,\n",
-        "#                             recurrence=recurrence)"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "jialiu"
-      }
-    ],
-    "categories": [
-      "how-to-use-azureml",
-      "automated-machine-learning"
-    ],
-    "kernelspec": {
-      "display_name": "Python 3.8 - AzureML",
-      "language": "python",
-      "name": "python38-azureml"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.8.10"
-    },
-    "vscode": {
-      "interpreter": {
-        "hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
-      }
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 4
-}

how-to-use-azureml/automated-machine-learning/forecasting-many-models/scripts/data_preprocessing_file.py

@@ -1,39 +0,0 @@
-from pathlib import Path
-from azureml.core import Run
-
-import argparse
-import os
-
-
-def main(args):
-    output = Path(args.output)
-    output.mkdir(parents=True, exist_ok=True)
-
-    run_context = Run.get_context()
-    input_path = run_context.input_datasets["train_10_models"]
-
-    for file_name in os.listdir(input_path):
-        input_file = os.path.join(input_path, file_name)
-        with open(input_file, "r") as f:
-            content = f.read()
-
-            # Apply any data pre-processing techniques here
-
-            output_file = os.path.join(output, file_name)
-            with open(output_file, "w") as f:
-                f.write(content)
-
-
-def my_parse_args():
-    parser = argparse.ArgumentParser("Test")
-
-    parser.add_argument("--input", type=str)
-    parser.add_argument("--output", type=str)
-
-    args = parser.parse_args()
-    return args
-
-
-if __name__ == "__main__":
-    args = my_parse_args()
-    main(args)

how-to-use-azureml/automated-machine-learning/forecasting-many-models/scripts/data_preprocessing_tabular.py

@@ -1,37 +0,0 @@
-from pathlib import Path
-from azureml.core import Run
-import argparse
-
-
-def main(args):
-    output = Path(args.output)
-    output.mkdir(parents=True, exist_ok=True)
-
-    run_context = Run.get_context()
-    dataset = run_context.input_datasets["train_10_models"]
-    df = dataset.to_pandas_dataframe()
-
-    # Drop the column "Revenue" from the dataset to avoid information leak as
-    # "Quantity" = "Revenue" / "Price". Please modify the logic based on your data.
-    drop_column_name = "Revenue"
-    if drop_column_name in df.columns:
-        df.drop(drop_column_name, axis=1, inplace=True)
-
-    # Apply any data pre-processing techniques here
-
-    df.to_parquet(output / "data_prepared_result.parquet", compression=None)
-
-
-def my_parse_args():
-    parser = argparse.ArgumentParser("Test")
-
-    parser.add_argument("--input", type=str)
-    parser.add_argument("--output", type=str)
-
-    args = parser.parse_args()
-    return args
-
-
-if __name__ == "__main__":
-    args = my_parse_args()
-    main(args)

how-to-use-azureml/automated-machine-learning/forecasting-many-models/update_env.yml

@@ -1,3 +0,0 @@
-dependencies:
-- pip:
-  - azureml-contrib-automl-pipeline-steps

how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales/auto-ml-forecasting-orange-juice-sales.ipynb

@@ -9,20 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales/auto-ml-forecasting-orange-juice-sales.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<font color=\"red\" size=\"5\"><strong>!Important!</strong> </br>This notebook is outdated and is not supported by the AutoML Team. Please use the supported version ([link](https://github.com/Azure/azureml-examples/tree/main/sdk/python/jobs/automl-standalone-jobs/automl-forecasting-orange-juice-sales)).</font>"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -31,23 +17,26 @@
         "_**Orange Juice Sales Forecasting**_\n",
         "\n",
         "## Contents\n",
-        "1. [Introduction](#introduction)\n",
-        "1. [Setup](#setup)\n",
-        "1. [Compute](#compute)\n",
-        "1. [Data](#data)\n",
-        "1. [Train](#train)\n",
-        "1. [Forecast](#forecast)\n",
-        "1. [Operationalize](#operationalize)"
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Data](#Data)\n",
+        "1. [Train](#Train)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Introduction<a id=\"introduction\"></a>\n",
-        "In this example, we use AutoML to train, select, and operationalize a time-series forecasting model for multiple time-series.\n",
+        "## Introduction\n",
+        "In this example, we use AutoML to find and tune a time-series forecasting model.\n",
         "\n",
-        "Make sure you have executed the [configuration notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/configuration.ipynb) before running this notebook.\n",
+        "Make sure you have executed the [configuration notebook](../../../configuration.ipynb) before running this notebook.\n",
+        "\n",
+        "In this notebook, you will:\n",
+        "1. Create an Experiment in an existing Workspace\n",
+        "2. Instantiate an AutoMLConfig \n",
+        "3. Find and train a forecasting model using local compute\n",
+        "4. Evaluate the performance of the model\n",
         "\n",
         "The examples in the follow code samples use the University of Chicago's Dominick's Finer Foods dataset to forecast orange juice sales. Dominick's was a grocery chain in the Chicago metropolitan area."
       ]
@@ -56,7 +45,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Setup<a id=\"setup\"></a>"
+        "## Setup"
       ]
     },
     {
@@ -65,38 +54,26 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "import json\n",
-        "import logging\n",
-        "\n",
         "import azureml.core\n",
         "import pandas as pd\n",
-        "from azureml.automl.core.featurization import FeaturizationConfig\n",
-        "from azureml.core.experiment import Experiment\n",
+        "import numpy as np\n",
+        "import logging\n",
+        "import warnings\n",
+        "# Squash warning messages for cleaner output in the notebook\n",
+        "warnings.showwarning = lambda *args, **kwargs: None\n",
+        "\n",
+        "\n",
         "from azureml.core.workspace import Workspace\n",
-        "from azureml.train.automl import AutoMLConfig"
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.train.automl import AutoMLConfig\n",
+        "from sklearn.metrics import mean_absolute_error, mean_squared_error"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "This notebook is compatible with Azure ML SDK version 1.35.0 or later."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "As part of the setup you have already created a <b>Workspace</b>. To run AutoML, you also need to create an <b>Experiment</b>. An Experiment corresponds to a prediction problem you are trying to solve, while a Run corresponds to a specific approach to the problem. "
+        "As part of the setup you have already created a <b>Workspace</b>. To run AutoML, you also need to create an <b>Experiment</b>. An Experiment is a named object in a Workspace which represents a predictive task, the output of which is a trained model and a set of evaluation metrics for the model. "
       ]
     },
     {
@@ -108,20 +85,22 @@
         "ws = Workspace.from_config()\n",
         "\n",
         "# choose a name for the run history container in the workspace\n",
-        "experiment_name = \"automl-ojforecasting\"\n",
+        "experiment_name = 'automl-ojsalesforecasting'\n",
+        "# project folder\n",
+        "project_folder = './sample_projects/automl-local-ojsalesforecasting'\n",
         "\n",
         "experiment = Experiment(ws, experiment_name)\n",
         "\n",
         "output = {}\n",
-        "output[\"Subscription ID\"] = ws.subscription_id\n",
-        "output[\"Workspace\"] = ws.name\n",
-        "output[\"SKU\"] = ws.sku\n",
-        "output[\"Resource Group\"] = ws.resource_group\n",
-        "output[\"Location\"] = ws.location\n",
-        "output[\"Run History Name\"] = experiment_name\n",
-        "output[\"SDK Version\"] = azureml.core.VERSION\n",
-        "pd.set_option(\"display.max_colwidth\", None)\n",
-        "outputDf = pd.DataFrame(data=output, index=[\"\"])\n",
+        "output['SDK version'] = azureml.core.VERSION\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace'] = ws.name\n",
+        "output['Resource Group'] = ws.resource_group\n",
+        "output['Location'] = ws.location\n",
+        "output['Project Directory'] = project_folder\n",
+        "output['Run History Name'] = experiment_name\n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
         "outputDf.T"
       ]
     },
@@ -129,46 +108,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Compute<a id=\"compute\"></a>\n",
-        "You will need to create a [compute target](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-set-up-training-targets#amlcompute) for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
-        "\n",
-        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
-        "\n",
-        "#### Creation of AmlCompute takes approximately 5 minutes. \n",
-        "If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
-        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
-        "from azureml.core.compute_target import ComputeTargetException\n",
-        "\n",
-        "# Choose a name for your CPU cluster\n",
-        "amlcompute_cluster_name = \"oj-cluster\"\n",
-        "\n",
-        "# Verify that cluster does not exist already\n",
-        "try:\n",
-        "    compute_target = ComputeTarget(workspace=ws, name=amlcompute_cluster_name)\n",
-        "    print(\"Found existing cluster, use it.\")\n",
-        "except ComputeTargetException:\n",
-        "    compute_config = AmlCompute.provisioning_configuration(\n",
-        "        vm_size=\"STANDARD_D12_V2\", max_nodes=6\n",
-        "    )\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, compute_config)\n",
-        "\n",
-        "compute_target.wait_for_completion(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Data<a id=\"data\"></a>\n",
+        "## Data\n",
         "You are now ready to load the historical orange juice sales data. We will load the CSV file into a plain pandas DataFrame; the time column in the CSV is called _WeekStarting_, so it will be specially parsed into the datetime type."
       ]
     },
@@ -178,12 +118,8 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "time_column_name = \"WeekStarting\"\n",
+        "time_column_name = 'WeekStarting'\n",
         "data = pd.read_csv(\"dominicks_OJ.csv\", parse_dates=[time_column_name])\n",
-        "\n",
-        "# Drop the columns 'logQuantity' as it is a leaky feature.\n",
-        "data.drop(\"logQuantity\", axis=1, inplace=True)\n",
-        "\n",
         "data.head()"
       ]
     },
@@ -193,7 +129,7 @@
       "source": [
         "Each row in the DataFrame holds a quantity of weekly sales for an OJ brand at a single store. The data also includes the sales price, a flag indicating if the OJ brand was advertised in the store that week, and some customer demographic information based on the store location. For historical reasons, the data also include the logarithm of the sales quantity. The Dominick's grocery data is commonly used to illustrate econometric modeling techniques where logarithms of quantities are generally preferred.    \n",
         "\n",
-        "The task is now to build a time-series model for the _Quantity_ column. It is important to note that this dataset is comprised of many individual time-series - one for each unique combination of _Store_ and _Brand_. To distinguish the individual time-series, we define the **time_series_id_column_names** - the columns whose values determine the boundaries between time-series: "
+        "The task is now to build a time-series model for the _Quantity_ column. It is important to note that this dataset is comprised of many individual time-series - one for each unique combination of _Store_ and _Brand_. To distinguish the individual time-series, we thus define the **grain** - the columns whose values determine the boundaries between time-series: "
       ]
     },
     {
@@ -202,9 +138,9 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "time_series_id_column_names = [\"Store\", \"Brand\"]\n",
-        "nseries = data.groupby(time_series_id_column_names).ngroups\n",
-        "print(\"Data contains {0} individual time-series.\".format(nseries))"
+        "grain_column_names = ['Store', 'Brand']\n",
+        "nseries = data.groupby(grain_column_names).ngroups\n",
+        "print('Data contains {0} individual time-series.'.format(nseries))"
       ]
     },
     {
@@ -222,8 +158,8 @@
       "source": [
         "use_stores = [2, 5, 8]\n",
         "data_subset = data[data.Store.isin(use_stores)]\n",
-        "nseries = data_subset.groupby(time_series_id_column_names).ngroups\n",
-        "print(\"Data subset contains {0} individual time-series.\".format(nseries))"
+        "nseries = data_subset.groupby(grain_column_names).ngroups\n",
+        "print('Data subset contains {0} individual time-series.'.format(nseries))"
       ]
     },
     {
@@ -231,7 +167,7 @@
       "metadata": {},
       "source": [
         "### Data Splitting\n",
-        "We now split the data into a training and a testing set for later forecast evaluation. The test set will contain the final 20 weeks of observed sales for each time-series. The splits should be stratified by series, so we use a group-by statement on the time series identifier columns."
+        "We now split the data into a training and a testing set for later forecast evaluation. The test set will contain the final 20 weeks of observed sales for each time-series. The splits should be stratified by series, so we use a group-by statement on the grain columns."
       ]
     },
     {
@@ -242,61 +178,15 @@
       "source": [
         "n_test_periods = 20\n",
         "\n",
-        "\n",
-        "def split_last_n_by_series_id(df, n):\n",
-        "    \"\"\"Group df by series identifiers and split on last n rows for each group.\"\"\"\n",
-        "    df_grouped = df.sort_values(time_column_name).groupby(  # Sort by ascending time\n",
-        "        time_series_id_column_names, group_keys=False\n",
-        "    )\n",
+        "def split_last_n_by_grain(df, n):\n",
+        "    \"\"\"Group df by grain and split on last n rows for each group.\"\"\"\n",
+        "    df_grouped = (df.sort_values(time_column_name) # Sort by ascending time\n",
+        "                  .groupby(grain_column_names, group_keys=False))\n",
         "    df_head = df_grouped.apply(lambda dfg: dfg.iloc[:-n])\n",
-        "    df_head.reset_index(inplace=True, drop=True)\n",
         "    df_tail = df_grouped.apply(lambda dfg: dfg.iloc[-n:])\n",
-        "    df_tail.reset_index(inplace=True, drop=True)\n",
         "    return df_head, df_tail\n",
         "\n",
-        "\n",
-        "train, test = split_last_n_by_series_id(data_subset, n_test_periods)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Upload data to datastore\n",
-        "The [Machine Learning service workspace](https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-workspace), is paired with the storage account, which contains the default data store. We will use it to upload the train and test data and create [tabular datasets](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.tabulardataset?view=azure-ml-py) for training and testing. A tabular dataset defines a series of lazily-evaluated, immutable operations to load data from the data source into tabular representation."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.data.dataset_factory import TabularDatasetFactory\n",
-        "\n",
-        "datastore = ws.get_default_datastore()\n",
-        "train_dataset = TabularDatasetFactory.register_pandas_dataframe(\n",
-        "    train, target=(datastore, \"dataset/\"), name=\"dominicks_OJ_train\"\n",
-        ")\n",
-        "test_dataset = TabularDatasetFactory.register_pandas_dataframe(\n",
-        "    test, target=(datastore, \"dataset/\"), name=\"dominicks_OJ_test\"\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Create dataset for training"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "train_dataset.to_pandas_dataframe().tail()"
+        "X_train, X_test = split_last_n_by_grain(data_subset, n_test_periods)"
       ]
     },
     {
@@ -308,11 +198,11 @@
         "For forecasting tasks, AutoML uses pre-processing and estimation steps that are specific to time-series. AutoML will undertake the following pre-processing steps:\n",
         "* Detect time-series sample frequency (e.g. hourly, daily, weekly) and create new records for absent time points to make the series regular. A regular time series has a well-defined frequency and has a value at every sample point in a contiguous time span \n",
         "* Impute missing values in the target (via forward-fill) and feature columns (using median column values) \n",
-        "* Create features based on time series identifiers to enable fixed effects across different series\n",
+        "* Create grain-based features to enable fixed effects across different series\n",
         "* Create time-based features to assist in learning seasonal patterns\n",
         "* Encode categorical variables to numeric quantities\n",
         "\n",
-        "In this notebook, AutoML will train a single, regression-type model across **all** time-series in a given training set. This allows the model to generalize across related series. If you're looking for training multiple models for different time-series, please see the many-models notebook.\n",
+        "AutoML will currently train a single, regression-type model across **all** time-series in a given training set. This allows the model to generalize across related series.\n",
         "\n",
         "You are almost ready to start an AutoML training job. First, we need to separate the target column from the rest of the DataFrame: "
       ]
@@ -323,84 +213,23 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "target_column_name = \"Quantity\""
+        "target_column_name = 'Quantity'\n",
+        "y_train = X_train.pop(target_column_name).values"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Customization\n",
+        "## Train\n",
         "\n",
-        "The featurization customization in forecasting is an advanced feature in AutoML which allows our customers to change the default forecasting featurization behaviors and column types through `FeaturizationConfig`. The supported scenarios include:\n",
+        "The AutoMLConfig object defines the settings and data for an AutoML training job. Here, we set necessary inputs like the task type, the number of AutoML iterations to try, the training data, and cross-validation parameters. \n",
         "\n",
-        "1. Column purposes update: Override feature type for the specified column. Currently supports DateTime, Categorical and Numeric. This customization can be used in the scenario that the type of the column cannot correctly reflect its purpose. Some numerical columns, for instance, can be treated as Categorical columns which need to be converted to categorical while some can be treated as epoch timestamp which need to be converted to datetime. To tell our SDK to correctly preprocess these columns, a configuration need to be add with the columns and their desired types.\n",
-        "2. Transformer parameters update: Currently supports parameter change for Imputer only. User can customize imputation methods. The supported imputing methods for target column are constant and ffill (forward fill). The supported imputing methods for feature columns are mean, median, most frequent, constant and ffill (forward fill). This customization can be used for the scenario that our customers know which imputation methods fit best to the input data. For instance, some datasets use NaN to represent 0 which the correct behavior should impute all the missing value with 0. To achieve this behavior, these columns need to be configured as constant imputation with `fill_value` 0.\n",
-        "3. Drop columns: Columns to drop from being featurized. These usually are the columns which are leaky or the columns contain no useful data."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "tags": [
-          "sample-featurizationconfig-remarks"
-        ]
-      },
-      "outputs": [],
-      "source": [
-        "featurization_config = FeaturizationConfig()\n",
-        "# Force the CPWVOL5 feature to be numeric type.\n",
-        "featurization_config.add_column_purpose(\"CPWVOL5\", \"Numeric\")\n",
-        "# Fill missing values in the target column, Quantity, with zeros.\n",
-        "featurization_config.add_transformer_params(\n",
-        "    \"Imputer\", [\"Quantity\"], {\"strategy\": \"constant\", \"fill_value\": 0}\n",
-        ")\n",
-        "# Fill missing values in the INCOME column with median value.\n",
-        "featurization_config.add_transformer_params(\n",
-        "    \"Imputer\", [\"INCOME\"], {\"strategy\": \"median\"}\n",
-        ")\n",
-        "# Fill missing values in the Price column with forward fill (last value carried forward).\n",
-        "featurization_config.add_transformer_params(\"Imputer\", [\"Price\"], {\"strategy\": \"ffill\"})"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Forecasting Parameters\n",
-        "To define forecasting parameters for your experiment training, you can leverage the ForecastingParameters class. The table below details the forecasting parameter we will be passing into our experiment.\n",
+        "For forecasting tasks, there are some additional parameters that can be set: the name of the column holding the date/time, the grain column names, and the maximum forecast horizon. A time column is required for forecasting, while the grain is optional. If a grain is not given, AutoML assumes that the whole dataset is a single time-series. We also pass a list of columns to drop prior to modeling. The _logQuantity_ column is completely correlated with the target quantity, so it must be removed to prevent a target leak.\n",
         "\n",
+        "The forecast horizon is given in units of the time-series frequency; for instance, the OJ series frequency is weekly, so a horizon of 20 means that a trained model will estimate sales up-to 20 weeks beyond the latest date in the training data for each series. In this example, we set the maximum horizon to the number of samples per series in the test set (n_test_periods). Generally, the value of this parameter will be dictated by business needs. For example, a demand planning organizaion that needs to estimate the next month of sales would set the horizon accordingly.   \n",
         "\n",
-        "|Property|Description|\n",
-        "|-|-|\n",
-        "|**time_column_name**|The name of your time column.|\n",
-        "|**forecast_horizon**|The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly).|\n",
-        "|**time_series_id_column_names**|The column names used to uniquely identify the time series in data that has multiple rows with the same timestamp. If the time series identifiers are not defined, the data set is assumed to be one time series.|\n",
-        "|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information.\n",
-        "|**cv_step_size**|Number of periods between two consecutive cross-validation folds. The default value is \"auto\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Train<a id=\"train\"></a>\n",
-        "\n",
-        "The [AutoMLConfig](https://docs.microsoft.com/en-us/python/api/azureml-train-automl-client/azureml.train.automl.automlconfig.automlconfig?view=azure-ml-py) object defines the settings and data for an AutoML training job. Here, we set necessary inputs like the task type, the number of AutoML iterations to try, the training data, and cross-validation parameters.\n",
-        "\n",
-        "For forecasting tasks, there are some additional parameters that can be set in the `ForecastingParameters` class: the name of the column holding the date/time, the timeseries id column names, and the maximum forecast horizon. A time column is required for forecasting, while the time_series_id is optional. If time_series_id columns are not given, AutoML assumes that the whole dataset is a single time-series. We also pass a list of columns to drop prior to modeling. The _logQuantity_ column is completely correlated with the target quantity, so it must be removed to prevent a target leak.\n",
-        "\n",
-        "The forecast horizon is given in units of the time-series frequency; for instance, the OJ series frequency is weekly, so a horizon of 20 means that a trained model will estimate sales up to 20 weeks beyond the latest date in the training data for each series. In this example, we set the forecast horizon to the number of samples per series in the test set (n_test_periods). Generally, the value of this parameter will be dictated by business needs. For example, a demand planning application that estimates the next month of sales should set the horizon according to suitable planning time-scales. Please see the [energy_demand notebook](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand) for more discussion of forecast horizon.\n",
-        "\n",
-        "We note here that AutoML can sweep over two types of time-series models:\n",
-        "* Models that are trained for each series such as ARIMA and Facebook's Prophet.\n",
-        "* Models trained across multiple time-series using a regression approach.\n",
-        "\n",
-        "In the first case, AutoML loops over all time-series in your dataset and trains one model (e.g. AutoArima or Prophet, as the case may be) for each series. This can result in long runtimes to train these models if there are a lot of series in the data. One way to mitigate this problem is to fit models for different series in parallel if you have multiple compute cores available. To enable this behavior, set the `max_cores_per_iteration` parameter in your AutoMLConfig as shown in the example in the next cell. \n",
-        "\n",
-        "\n",
-        "Finally, a note about the cross-validation (CV) procedure for time-series data. AutoML uses out-of-sample error estimates to select a best pipeline/model, so it is important that the CV fold splitting is done correctly. Time-series can violate the basic statistical assumptions of the canonical K-Fold CV strategy, so AutoML implements a [rolling origin validation](https://robjhyndman.com/hyndsight/tscv/) procedure to create CV folds for time-series data. To use this procedure, you could specify the desired number of CV folds and the number of periods between two consecutive folds in the AutoMLConfig object, or AutoMl could set them automatically if you don't specify them. It is also possible to bypass CV and use your own validation set by setting the *validation_data* parameter of AutoMLConfig.\n",
+        "Finally, a note about the cross-validation (CV) procedure for time-series data. AutoML uses out-of-sample error estimates to select a best pipeline/model, so it is important that the CV fold splitting is done correctly. Time-series can violate the basic statistical assumptions of the canonical K-Fold CV strategy, so AutoML implements a [rolling origin validation](https://robjhyndman.com/hyndsight/tscv/) procedure to create CV folds for time-series data. To use this procedure, you just need to specify the desired number of CV folds in the AutoMLConfig object. It is also possible to bypass CV and use your own validation set by setting the *X_valid* and *y_valid* parameters of AutoMLConfig.\n",
         "\n",
         "Here is a summary of AutoMLConfig parameters used for training the OJ model:\n",
         "\n",
@@ -408,17 +237,17 @@
         "|-|-|\n",
         "|**task**|forecasting|\n",
         "|**primary_metric**|This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>\n",
-        "|**experiment_timeout_hours**|Experimentation timeout in hours.|\n",
-        "|**enable_early_stopping**|If early stopping is on, training will stop when the primary metric is no longer improving.|\n",
-        "|**training_data**|Input dataset, containing both features and label column.|\n",
-        "|**label_column_name**|The name of the label column.|\n",
-        "|**compute_target**|The remote compute for training.|\n",
-        "|**n_cross_validations**|Number of cross-validation folds to use for model/pipeline selection. The default value is \"auto\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value.\n",
-        "|**enable_voting_ensemble**|Allow AutoML to create a Voting ensemble of the best performing models|\n",
-        "|**enable_stack_ensemble**|Allow AutoML to create a Stack ensemble of the best performing models|\n",
-        "|**debug_log**|Log file path for writing debugging information|\n",
-        "|**featurization**| 'auto' / 'off' / FeaturizationConfig Indicator for whether featurization step should be done automatically or not, or whether customized featurization should be used. Setting this enables AutoML to perform featurization on the input to handle *missing data*, and to perform some common *feature extraction*.|\n",
-        "|**max_cores_per_iteration**|Maximum number of cores to utilize per iteration. A value of -1 indicates all available cores should be used"
+        "|**iterations**|Number of iterations. In each iteration, Auto ML trains a specific pipeline on the given data|\n",
+        "|**X**|Training matrix of features as a pandas DataFrame, shape = [n_training_samples, n_features]|\n",
+        "|**y**|Target values as a numpy.ndarray, shape = [n_training_samples, ]|\n",
+        "|**n_cross_validations**|Number of cross-validation folds to use for model/pipeline selection|\n",
+        "|**enable_ensembling**|Allow AutoML to create ensembles of the best performing models\n",
+        "|**debug_log**|Log file path for writing debugging information\n",
+        "|**path**|Relative path to the project folder.  AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|\n",
+        "|**time_column_name**|Name of the datetime column in the input data|\n",
+        "|**grain_column_names**|Name(s) of the columns defining individual series in the input data|\n",
+        "|**drop_column_names**|Name(s) of columns to drop prior to modeling|\n",
+        "|**max_horizon**|Maximum desired forecast horizon in units of time-series frequency|"
       ]
     },
     {
@@ -427,39 +256,32 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.automl.core.forecasting_parameters import ForecastingParameters\n",
+        "time_series_settings = {\n",
+        "    'time_column_name': time_column_name,\n",
+        "    'grain_column_names': grain_column_names,\n",
+        "    'drop_column_names': ['logQuantity'],\n",
+        "    'max_horizon': n_test_periods\n",
+        "}\n",
         "\n",
-        "forecasting_parameters = ForecastingParameters(\n",
-        "    time_column_name=time_column_name,\n",
-        "    forecast_horizon=n_test_periods,\n",
-        "    time_series_id_column_names=time_series_id_column_names,\n",
-        "    freq=\"W-THU\",  # Set the forecast frequency to be weekly (start on each Thursday)\n",
-        "    cv_step_size=\"auto\",\n",
-        ")\n",
-        "\n",
-        "automl_config = AutoMLConfig(\n",
-        "    task=\"forecasting\",\n",
-        "    debug_log=\"automl_oj_sales_errors.log\",\n",
-        "    primary_metric=\"normalized_mean_absolute_error\",\n",
-        "    experiment_timeout_hours=0.25,\n",
-        "    training_data=train_dataset,\n",
-        "    label_column_name=target_column_name,\n",
-        "    compute_target=compute_target,\n",
-        "    enable_early_stopping=True,\n",
-        "    featurization=featurization_config,\n",
-        "    n_cross_validations=\"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
-        "    verbosity=logging.INFO,\n",
-        "    max_cores_per_iteration=-1,\n",
-        "    forecasting_parameters=forecasting_parameters,\n",
-        ")"
+        "automl_config = AutoMLConfig(task='forecasting',\n",
+        "                             debug_log='automl_oj_sales_errors.log',\n",
+        "                             primary_metric='normalized_root_mean_squared_error',\n",
+        "                             iterations=10,\n",
+        "                             X=X_train,\n",
+        "                             y=y_train,\n",
+        "                             n_cross_validations=5,\n",
+        "                             enable_ensembling=False,\n",
+        "                             path=project_folder,\n",
+        "                             verbosity=logging.INFO,\n",
+        "                             **time_series_settings)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "You can now submit a new training run. Depending on the data and number of iterations this operation may take several minutes.\n",
-        "Information from each iteration will be printed to the console.  Validation errors and current status will be shown when setting `show_output=True` and the execution will be synchronous."
+        "You can now submit a new training run. For local runs, the execution is synchronous. Depending on the data and number of iterations this operation may take several minutes.\n",
+        "Information from each iteration will be printed to the console."
       ]
     },
     {
@@ -468,7 +290,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "remote_run = experiment.submit(automl_config, show_output=False)"
+        "local_run = experiment.submit(automl_config, show_output=True)"
       ]
     },
     {
@@ -477,15 +299,15 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "remote_run.wait_for_completion()"
+        "local_run"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Retrieve the Best Run details\n",
-        "Below we retrieve the best Run object from among all the runs in the experiment."
+        "### Retrieve the Best Model\n",
+        "Each run within an Experiment stores serialized (i.e. pickled) pipelines from the AutoML iterations. We can now retrieve the pipeline with the best performance on the validation dataset:"
       ]
     },
     {
@@ -494,18 +316,16 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "best_run = remote_run.get_best_child()\n",
-        "model_name = best_run.properties[\"model_name\"]\n",
-        "best_run"
+        "best_run, fitted_pipeline = local_run.get_output()\n",
+        "fitted_pipeline.steps"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Transparency\n",
-        "\n",
-        "View updated featurization summary"
+        "### Make Predictions from the Best Fitted Model\n",
+        "Now that we have retrieved the best pipeline/model, it can be used to make predictions on test data. First, we remove the target values from the test set:"
       ]
     },
     {
@@ -514,37 +334,25 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "# Download the featurization summary JSON file locally\n",
-        "best_run.download_file(\n",
-        "    \"outputs/featurization_summary.json\", \"featurization_summary.json\"\n",
-        ")\n",
-        "\n",
-        "# Render the JSON as a pandas DataFrame\n",
-        "with open(\"featurization_summary.json\", \"r\") as f:\n",
-        "    records = json.load(f)\n",
-        "fs = pd.DataFrame.from_records(records)\n",
-        "\n",
-        "# View a summary of the featurization\n",
-        "fs[\n",
-        "    [\n",
-        "        \"RawFeatureName\",\n",
-        "        \"TypeDetected\",\n",
-        "        \"Dropped\",\n",
-        "        \"EngineeredFeatureCount\",\n",
-        "        \"Transformations\",\n",
-        "    ]\n",
-        "]"
+        "y_test = X_test.pop(target_column_name).values"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X_test.head()"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "# Forecast<a id=\"forecast\"></a>\n",
+        "To produce predictions on the test set, we need to know the feature values at all dates in the test set. This requirement is somewhat reasonable for the OJ sales data since the features mainly consist of price, which is usually set in advance, and customer demographics which are approximately constant for each store over the 20 week forecast horizon in the testing data. \n",
         "\n",
-        "Now that we have retrieved the best pipeline/model, it can be used to make predictions on test data. We will do batch scoring on the test dataset which should have the same schema as training dataset.\n",
-        "\n",
-        "The inference will run on a remote compute. In this example, it will re-use the training compute."
+        "The target predictions can be retrieved by calling the `predict` method on the best model:"
       ]
     },
     {
@@ -553,22 +361,15 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "test_experiment = Experiment(ws, experiment_name + \"_inference\")"
+        "y_pred = fitted_pipeline.predict(X_test)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Retrieving forecasts from the model\n",
-        "We have created a function called `run_forecast` that submits the test data to the best model determined during the training run and retrieves forecasts. This function uses a helper script `forecasting_script` which is uploaded and expecuted on the remote compute."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "To produce predictions on the test set, we need to know the feature values at all dates in the test set. This requirement is somewhat reasonable for the OJ sales data since the features mainly consist of price, which is usually set in advance, and customer demographics which are approximately constant for each store over the 20 week forecast horizon in the testing data."
+        "### Calculate evaluation metrics for the prediction\n",
+        "To evaluate the accuracy of the forecast, we'll compare against the actual sales quantities for some select metrics, included the mean absolute percentage error (MAPE)."
       ]
     },
     {
@@ -577,262 +378,34 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from run_forecast import run_remote_inference\n",
+        "def MAPE(actual, pred):\n",
+        "    \"\"\"\n",
+        "    Calculate mean absolute percentage error.\n",
+        "    Remove NA and values where actual is close to zero\n",
+        "    \"\"\"\n",
+        "    not_na = ~(np.isnan(actual) | np.isnan(pred))\n",
+        "    not_zero = ~np.isclose(actual, 0.0)\n",
+        "    actual_safe = actual[not_na & not_zero]\n",
+        "    pred_safe = pred[not_na & not_zero]\n",
+        "    APE = 100*np.abs((actual_safe - pred_safe)/actual_safe)\n",
+        "    return np.mean(APE)\n",
         "\n",
-        "remote_run_infer = run_remote_inference(\n",
-        "    test_experiment=test_experiment,\n",
-        "    compute_target=compute_target,\n",
-        "    train_run=best_run,\n",
-        "    test_dataset=test_dataset,\n",
-        "    target_column_name=target_column_name,\n",
-        ")\n",
-        "remote_run_infer.wait_for_completion(show_output=False)\n",
-        "\n",
-        "# download the forecast file to the local machine\n",
-        "remote_run_infer.download_file(\"outputs/predictions.csv\", \"predictions.csv\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Evaluate\n",
-        "\n",
-        "To evaluate the accuracy of the forecast, we'll compare against the actual sales quantities for some select metrics, included the mean absolute percentage error (MAPE). For more metrics that can be used for evaluation after training, please see [supported metrics](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#regressionforecasting-metrics), and [how to calculate residuals](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#residuals).\n",
-        "\n",
-        "We'll add predictions and actuals into a single dataframe for convenience in calculating the metrics."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# load forecast data frame\n",
-        "fcst_df = pd.read_csv(\"predictions.csv\", parse_dates=[time_column_name])\n",
-        "fcst_df.head()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.automl.core.shared import constants\n",
-        "from azureml.automl.runtime.shared.score import scoring\n",
-        "from matplotlib import pyplot as plt\n",
-        "\n",
-        "# use automl scoring module\n",
-        "scores = scoring.score_regression(\n",
-        "    y_test=fcst_df[target_column_name],\n",
-        "    y_pred=fcst_df[\"predicted\"],\n",
-        "    metrics=list(constants.Metric.SCALAR_REGRESSION_SET),\n",
-        ")\n",
-        "\n",
-        "print(\"[Test data scores]\\n\")\n",
-        "for key, value in scores.items():\n",
-        "    print(\"{}:   {:.3f}\".format(key, value))\n",
-        "\n",
-        "# Plot outputs\n",
-        "%matplotlib inline\n",
-        "test_pred = plt.scatter(fcst_df[target_column_name], fcst_df[\"predicted\"], color=\"b\")\n",
-        "test_test = plt.scatter(\n",
-        "    fcst_df[target_column_name], fcst_df[target_column_name], color=\"g\"\n",
-        ")\n",
-        "plt.legend(\n",
-        "    (test_pred, test_test), (\"prediction\", \"truth\"), loc=\"upper left\", fontsize=8\n",
-        ")\n",
-        "plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Operationalize<a id=\"operationalize\"></a>"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "_Operationalization_ means getting the model into the cloud so that other can run it after you close the notebook. We will create a docker running on Azure Container Instances with the model."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "description = \"AutoML OJ forecaster\"\n",
-        "tags = None\n",
-        "model = remote_run.register_model(\n",
-        "    model_name=model_name, description=description, tags=tags\n",
-        ")\n",
-        "\n",
-        "print(remote_run.model_id)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Develop the scoring script\n",
-        "\n",
-        "For the deployment we need a function which will run the forecast on serialized data. It can be obtained from the best_run."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "script_file_name = \"score_fcast.py\"\n",
-        "best_run.download_file(\"outputs/scoring_file_v_1_0_0.py\", script_file_name)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Deploy the model as a Web Service on Azure Container Instance"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.model import InferenceConfig\n",
-        "from azureml.core.webservice import AciWebservice\n",
-        "from azureml.core.webservice import Webservice\n",
-        "from azureml.core.model import Model\n",
-        "\n",
-        "inference_config = InferenceConfig(\n",
-        "    environment=best_run.get_environment(), entry_script=script_file_name\n",
-        ")\n",
-        "\n",
-        "aciconfig = AciWebservice.deploy_configuration(\n",
-        "    cpu_cores=2,\n",
-        "    memory_gb=4,\n",
-        "    tags={\"type\": \"automl-forecasting\"},\n",
-        "    description=\"Automl forecasting sample service\",\n",
-        ")\n",
-        "\n",
-        "aci_service_name = \"automl-oj-forecast-03\"\n",
-        "print(aci_service_name)\n",
-        "aci_service = Model.deploy(ws, aci_service_name, [model], inference_config, aciconfig)\n",
-        "aci_service.wait_for_deployment(True)\n",
-        "print(aci_service.state)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "aci_service.get_logs()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Call the service"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import json\n",
-        "\n",
-        "X_query = test.copy()\n",
-        "X_query.pop(target_column_name)\n",
-        "# We have to convert datetime to string, because Timestamps cannot be serialized to JSON.\n",
-        "X_query[time_column_name] = X_query[time_column_name].astype(str)\n",
-        "# The Service object accept the complex dictionary, which is internally converted to JSON string.\n",
-        "# The section 'data' contains the data frame in the form of dictionary.\n",
-        "sample_quantiles = [0.025, 0.975]\n",
-        "test_sample = json.dumps(\n",
-        "    {\"data\": X_query.to_dict(orient=\"records\"), \"quantiles\": sample_quantiles}\n",
-        ")\n",
-        "response = aci_service.run(input_data=test_sample)\n",
-        "# translate from networkese to datascientese\n",
-        "try:\n",
-        "    res_dict = json.loads(response)\n",
-        "    y_fcst_all = pd.DataFrame(res_dict[\"index\"])\n",
-        "    y_fcst_all[time_column_name] = pd.to_datetime(\n",
-        "        y_fcst_all[time_column_name], unit=\"ms\"\n",
-        "    )\n",
-        "    y_fcst_all[\"forecast\"] = res_dict[\"forecast\"]\n",
-        "    y_fcst_all[\"prediction_interval\"] = res_dict[\"prediction_interval\"]\n",
-        "except:\n",
-        "    print(res_dict)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "y_fcst_all.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Delete the web service if desired"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "serv = Webservice(ws, \"automl-oj-forecast-03\")\n",
-        "serv.delete()  # don't do it accidentally"
+        "print(\"[Test Data] \\nRoot Mean squared error: %.2f\" % np.sqrt(mean_squared_error(y_test, y_pred)))\n",
+        "print('mean_absolute_error score: %.2f' % mean_absolute_error(y_test, y_pred))\n",
+        "print('MAPE: %.2f' % MAPE(y_test, y_pred))"
       ]
     }
   ],
   "metadata": {
     "authors": [
       {
-        "name": "jialiu"
+        "name": "erwright"
       }
     ],
-    "category": "tutorial",
-    "celltoolbar": "Raw Cell Format",
-    "compute": [
-      "Remote"
-    ],
-    "datasets": [
-      "Orange Juice Sales"
-    ],
-    "deployment": [
-      "Azure Container Instance"
-    ],
-    "exclude_from_index": false,
-    "framework": [
-      "Azure ML AutoML"
-    ],
-    "friendly_name": "Forecasting orange juice sales with deployment",
-    "index_order": 1,
     "kernelspec": {
-      "display_name": "Python 3.8 - AzureML",
+      "display_name": "Python 3.6",
       "language": "python",
-      "name": "python38-azureml"
+      "name": "python36"
     },
     "language_info": {
       "codemirror_mode": {
@@ -844,18 +417,9 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.8.10"
-    },
-    "tags": [
-      "None"
-    ],
-    "task": "Forecasting",
-    "vscode": {
-      "interpreter": {
-        "hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
-      }
+      "version": "3.6.8"
     }
   },
   "nbformat": 4,
-  "nbformat_minor": 4
+  "nbformat_minor": 2
 }

how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales/forecasting_script.py

@@ -1,61 +0,0 @@
-"""
-This is the script that is executed on the compute instance. It relies
-on the model.pkl file which is uploaded along with this script to the
-compute instance.
-"""
-
-import argparse
-from azureml.core import Dataset, Run
-import joblib
-from pandas.tseries.frequencies import to_offset
-
-parser = argparse.ArgumentParser()
-parser.add_argument(
-    "--target_column_name",
-    type=str,
-    dest="target_column_name",
-    help="Target Column Name",
-)
-parser.add_argument(
-    "--test_dataset", type=str, dest="test_dataset", help="Test Dataset"
-)
-
-args = parser.parse_args()
-target_column_name = args.target_column_name
-test_dataset_id = args.test_dataset
-
-run = Run.get_context()
-ws = run.experiment.workspace
-
-# get the input dataset by id
-test_dataset = Dataset.get_by_id(ws, id=test_dataset_id)
-
-X_test = test_dataset.to_pandas_dataframe().reset_index(drop=True)
-y_test = X_test.pop(target_column_name).values
-
-# generate forecast
-fitted_model = joblib.load("model.pkl")
-# We have default quantiles values set as below(95th percentile)
-quantiles = [0.025, 0.5, 0.975]
-predicted_column_name = "predicted"
-PI = "prediction_interval"
-fitted_model.quantiles = quantiles
-pred_quantiles = fitted_model.forecast_quantiles(X_test)
-pred_quantiles[PI] = pred_quantiles[[min(quantiles), max(quantiles)]].apply(
-    lambda x: "[{}, {}]".format(x[0], x[1]), axis=1
-)
-X_test[target_column_name] = y_test
-X_test[PI] = pred_quantiles[PI]
-X_test[predicted_column_name] = pred_quantiles[0.5]
-# drop rows where prediction or actuals are nan
-# happens because of missing actuals
-# or at edges of time due to lags/rolling windows
-clean = X_test[
-    X_test[[target_column_name, predicted_column_name]].notnull().all(axis=1)
-]
-
-file_name = "outputs/predictions.csv"
-export_csv = clean.to_csv(file_name, header=True, index=False)  # added Index
-
-# Upload the predictions into artifacts
-run.upload_file(name=file_name, path_or_stream=file_name)

how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales/run_forecast.py

@@ -1,49 +0,0 @@
-import os
-import shutil
-from azureml.core import ScriptRunConfig
-
-
-def run_remote_inference(
-    test_experiment,
-    compute_target,
-    train_run,
-    test_dataset,
-    target_column_name,
-    inference_folder="./forecast",
-):
-    # Create local directory to copy the model.pkl and forecsting_script.py files into.
-    # These files will be uploaded to and executed on the compute instance.
-    os.makedirs(inference_folder, exist_ok=True)
-    shutil.copy("forecasting_script.py", inference_folder)
-
-    train_run.download_file(
-        "outputs/model.pkl", os.path.join(inference_folder, "model.pkl")
-    )
-
-    inference_env = train_run.get_environment()
-
-    config = ScriptRunConfig(
-        source_directory=inference_folder,
-        script="forecasting_script.py",
-        arguments=[
-            "--target_column_name",
-            target_column_name,
-            "--test_dataset",
-            test_dataset.as_named_input(test_dataset.name),
-        ],
-        compute_target=compute_target,
-        environment=inference_env,
-    )
-
-    run = test_experiment.submit(
-        config,
-        tags={
-            "training_run_id": train_run.id,
-            "run_algorithm": train_run.properties["run_algorithm"],
-            "valid_score": train_run.properties["score"],
-            "primary_metric": train_run.properties["primary_metric"],
-        },
-    )
-
-    run.log("run_algorithm", run.tags["run_algorithm"])
-    return run

how-to-use-azureml/automated-machine-learning/forecasting-pipelines/auto-ml-forecasting-pipelines.ipynb

@@ -1,834 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/forecasting-pipelines/auto-ml-forecasting-pipelines.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<font color=\"red\" size=\"5\"><strong>!Important!</strong> </br>This notebook is outdated and is not supported by the AutoML Team. Please use the supported version ([link](https://github.com/Azure/azureml-examples/tree/main/sdk/python/jobs/pipelines/1h_automl_in_pipeline/automl-forecasting-in-pipeline)).</font>\n",
-        "</br>\n",
-        "</br>\n",
-        "<font color=\"red\" size=\"5\">\n",
-        "For examples illustrating how to build pipelines with components, please use the following links:</font>\n",
-        "<ul>\n",
-        "    <li><a href=\"https://github.com/Azure/azureml-examples/tree/main/sdk/python/jobs/pipelines/1k_demand_forecasting_with_pipeline_components/automl-forecasting-demand-many-models-in-pipeline\">Many Models</a></li>\n",
-        "    <li><a href=\"https://github.com/Azure/azureml-examples/tree/main/sdk/python/jobs/pipelines/1k_demand_forecasting_with_pipeline_components/automl-forecasting-demand-hierarchical-timeseries-in-pipeline\">Hierarchical Time Series</a></li>\n",
-        "    <li><a href=\"https://github.com/Azure/azureml-examples/tree/main/sdk/python/jobs/automl-standalone-jobs/automl-forecasting-distributed-tcn\">Distributed TCN</a></li>\n",
-        "</ul>"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Training and Inferencing AutoML Forecasting Model Using Pipelines"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
-        "\n",
-        "In this notebook, we demonstrate how to use piplines to train and inference on AutoML Forecasting model. Two pipelines will be created: one for training AutoML model, and the other is for inference on AutoML model. We'll also demonstrate how to schedule the inference pipeline so you can get inference results periodically (with refreshed test dataset). Make sure you have executed the [configuration notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/configuration.ipynb) before running this notebook. In this notebook you will learn how to:\n",
-        "\n",
-        "- Configure AutoML using AutoMLConfig for forecasting tasks using pipeline AutoMLSteps.\n",
-        "- Create and register an AutoML model using AzureML pipeline.\n",
-        "- Inference and schdelue the pipeline using registered model."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Setup\n",
-        "\n",
-        "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import json\n",
-        "import logging\n",
-        "import os\n",
-        "\n",
-        "import pandas as pd\n",
-        "\n",
-        "import azureml.core\n",
-        "from azureml.core.experiment import Experiment\n",
-        "from azureml.core.workspace import Workspace\n",
-        "from azureml.train.automl import AutoMLConfig"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "print(\"This notebook was created using version 1.38.0 of the Azure ML SDK\")\n",
-        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Accessing the Azure ML workspace requires authentication with Azure.\n",
-        "\n",
-        "The default authentication is interactive authentication using the default tenant. Executing the ws = Workspace.from_config() line in the cell below will prompt for authentication the first time that it is run.\n",
-        "\n",
-        "If you have multiple Azure tenants, you can specify the tenant by replacing the ws = Workspace.from_config() line in the cell below with the following:\n",
-        "```\n",
-        "from azureml.core.authentication import InteractiveLoginAuthentication\n",
-        "auth = InteractiveLoginAuthentication(tenant_id = 'mytenantid')\n",
-        "ws = Workspace.from_config(auth = auth)\n",
-        "```\n",
-        "If you need to run in an environment where interactive login is not possible, you can use Service Principal authentication by replacing the ws = Workspace.from_config() line in the cell below with the following:\n",
-        "```\n",
-        "from azureml.core.authentication import ServicePrincipalAuthentication\n",
-        "auth = ServicePrincipalAuthentication('mytenantid', 'myappid', 'mypassword')\n",
-        "ws = Workspace.from_config(auth = auth)\n",
-        "```\n",
-        "For more details, see aka.ms/aml-notebook-auth"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ws = Workspace.from_config()\n",
-        "dstor = ws.get_default_datastore()\n",
-        "\n",
-        "# Choose a name for the run history container in the workspace.\n",
-        "experiment_name = \"forecasting-pipeline\"\n",
-        "experiment = Experiment(ws, experiment_name)\n",
-        "\n",
-        "output = {}\n",
-        "output[\"Subscription ID\"] = ws.subscription_id\n",
-        "output[\"Workspace\"] = ws.name\n",
-        "output[\"Resource Group\"] = ws.resource_group\n",
-        "output[\"Location\"] = ws.location\n",
-        "output[\"Run History Name\"] = experiment_name\n",
-        "pd.set_option(\"display.max_colwidth\", None)\n",
-        "outputDf = pd.DataFrame(data=output, index=[\"\"])\n",
-        "outputDf.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Compute"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Compute \n",
-        "\n",
-        "#### Create or Attach existing AmlCompute\n",
-        "\n",
-        "You will need to create a compute target for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
-        "\n",
-        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
-        "\n",
-        "#### Creation of AmlCompute takes approximately 5 minutes. \n",
-        "If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
-        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
-        "from azureml.core.compute_target import ComputeTargetException\n",
-        "\n",
-        "# Choose a name for your CPU cluster\n",
-        "amlcompute_cluster_name = \"forecast-step-cluster\"\n",
-        "\n",
-        "# Verify that cluster does not exist already\n",
-        "try:\n",
-        "    compute_target = ComputeTarget(workspace=ws, name=amlcompute_cluster_name)\n",
-        "    print(\"Found existing cluster, use it.\")\n",
-        "except ComputeTargetException:\n",
-        "    compute_config = AmlCompute.provisioning_configuration(\n",
-        "        vm_size=\"STANDARD_DS12_V2\", max_nodes=4\n",
-        "    )\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, compute_config)\n",
-        "compute_target.wait_for_completion(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Data\n",
-        "You are now ready to load the historical orange juice sales data. For demonstration purposes, we extract sales time-series for just a few of the stores. We will load the CSV file into a plain pandas DataFrame; the time column in the CSV is called _WeekStarting_, so it will be specially parsed into the datetime type."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "time_column_name = \"WeekStarting\"\n",
-        "train = pd.read_csv(\"oj-train.csv\", parse_dates=[time_column_name])\n",
-        "\n",
-        "train.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Each row in the DataFrame holds a quantity of weekly sales for an OJ brand at a single store. The data also includes the sales price, a flag indicating if the OJ brand was advertised in the store that week, and some customer demographic information based on the store location. For historical reasons, the data also include the logarithm of the sales quantity. The Dominick's grocery data is commonly used to illustrate econometric modeling techniques where logarithms of quantities are generally preferred.    \n",
-        "\n",
-        "The task is now to build a time-series model for the _Quantity_ column. It is important to note that this dataset is comprised of many individual time-series - one for each unique combination of _Store_ and _Brand_. To distinguish the individual time-series, we define the **time_series_id_column_names** - the columns whose values determine the boundaries between time-series: "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "time_series_id_column_names = [\"Store\", \"Brand\"]\n",
-        "nseries = train.groupby(time_series_id_column_names).ngroups\n",
-        "print(\"Data contains {0} individual time-series.\".format(nseries))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Test Splitting\n",
-        "We now split the data into a training and a testing set for later forecast prediction. The test set will contain the final 4 weeks of observed sales for each time-series. The splits should be stratified by series, so we use a group-by statement on the time series identifier columns."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "n_test_periods = 4\n",
-        "\n",
-        "test = pd.read_csv(\"oj-test.csv\", parse_dates=[time_column_name])"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Upload data to datastore\n",
-        "The [Machine Learning service workspace](https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-workspace), is paired with the storage account, which contains the default data store. We will use it to upload the train and test data and create [tabular datasets](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.tabulardataset?view=azure-ml-py) for training and testing. A tabular dataset defines a series of lazily-evaluated, immutable operations to load data from the data source into tabular representation."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.data.dataset_factory import TabularDatasetFactory\n",
-        "\n",
-        "datastore = ws.get_default_datastore()\n",
-        "train_dataset = TabularDatasetFactory.register_pandas_dataframe(\n",
-        "    train, target=(datastore, \"dataset/\"), name=\"dominicks_OJ_train_pipeline\"\n",
-        ")\n",
-        "\n",
-        "test_dataset = TabularDatasetFactory.register_pandas_dataframe(\n",
-        "    test, target=(datastore, \"dataset/\"), name=\"dominicks_OJ_test_pipeline\"\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Training"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Modeling\n",
-        "\n",
-        "For forecasting tasks, AutoML uses pre-processing and estimation steps that are specific to time-series. AutoML will undertake the following pre-processing steps:\n",
-        "* Detect time-series sample frequency (e.g. hourly, daily, weekly) and create new records for absent time points to make the series regular. A regular time series has a well-defined frequency and has a value at every sample point in a contiguous time span \n",
-        "* Impute missing values in the target (via forward-fill) and feature columns (using median column values) \n",
-        "* Create features based on time series identifiers to enable fixed effects across different series\n",
-        "* Create time-based features to assist in learning seasonal patterns\n",
-        "* Encode categorical variables to numeric quantities\n",
-        "\n",
-        "In this notebook, AutoML will train a single, regression-type model across **all** time-series in a given training set. This allows the model to generalize across related series. If you're looking for training multiple models for different time-series, please see the many-models notebook.\n",
-        "\n",
-        "You are almost ready to start an AutoML training job. First, we need to define the target column."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "target_column_name = \"Quantity\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Forecasting Parameters\n",
-        "To define forecasting parameters for your experiment training, you can leverage the ForecastingParameters class. The table below details the forecasting parameter we will be passing into our experiment.\n",
-        "\n",
-        "\n",
-        "|Property|Description|\n",
-        "|-|-|\n",
-        "|**time_column_name**|The name of your time column.|\n",
-        "|**forecast_horizon**|The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly).|\n",
-        "|**time_series_id_column_names**|The column names used to uniquely identify the time series in data that has multiple rows with the same timestamp. If the time series identifiers are not defined, the data set is assumed to be one time series.|\n",
-        "|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information.\n",
-        "|**cv_step_size**|Number of periods between two consecutive cross-validation folds. The default value is \"auto\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.automl.core.forecasting_parameters import ForecastingParameters\n",
-        "\n",
-        "forecasting_parameters = ForecastingParameters(\n",
-        "    time_column_name=time_column_name,\n",
-        "    forecast_horizon=n_test_periods,\n",
-        "    time_series_id_column_names=time_series_id_column_names,\n",
-        "    freq=\"W-THU\",  # Set the forecast frequency to be weekly (start on each Thursday),\n",
-        "    cv_step_size=\"auto\",\n",
-        ")\n",
-        "\n",
-        "automl_config = AutoMLConfig(\n",
-        "    task=\"forecasting\",\n",
-        "    debug_log=\"automl_oj_sales_errors.log\",\n",
-        "    primary_metric=\"normalized_mean_absolute_error\",\n",
-        "    experiment_timeout_hours=0.25,\n",
-        "    training_data=train_dataset,\n",
-        "    label_column_name=target_column_name,\n",
-        "    compute_target=compute_target,\n",
-        "    enable_early_stopping=True,\n",
-        "    n_cross_validations=\"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
-        "    verbosity=logging.INFO,\n",
-        "    max_cores_per_iteration=-1,\n",
-        "    forecasting_parameters=forecasting_parameters,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.pipeline.core import PipelineData, TrainingOutput\n",
-        "from azureml.pipeline.steps import AutoMLStep\n",
-        "from azureml.pipeline.core import Pipeline, PipelineParameter\n",
-        "from azureml.pipeline.steps import PythonScriptStep\n",
-        "\n",
-        "metrics_output_name = \"metrics_output\"\n",
-        "best_model_output_name = \"best_model_output\"\n",
-        "model_file_name = \"model_file\"\n",
-        "metrics_data_name = \"metrics_data\"\n",
-        "\n",
-        "metrics_data = PipelineData(\n",
-        "    name=metrics_data_name,\n",
-        "    datastore=datastore,\n",
-        "    pipeline_output_name=metrics_output_name,\n",
-        "    training_output=TrainingOutput(type=\"Metrics\"),\n",
-        ")\n",
-        "model_data = PipelineData(\n",
-        "    name=model_file_name,\n",
-        "    datastore=datastore,\n",
-        "    pipeline_output_name=best_model_output_name,\n",
-        "    training_output=TrainingOutput(type=\"Model\"),\n",
-        ")\n",
-        "\n",
-        "automl_step = AutoMLStep(\n",
-        "    name=\"automl_module\",\n",
-        "    automl_config=automl_config,\n",
-        "    outputs=[metrics_data, model_data],\n",
-        "    allow_reuse=False,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Register Model Step"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Run Configuration and Environment\n",
-        "To have a pipeline step run, we first need an environment to run the jobs. The environment can be build using the following code."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.runconfig import CondaDependencies, RunConfiguration\n",
-        "\n",
-        "# create a new RunConfig object\n",
-        "conda_run_config = RunConfiguration(framework=\"python\")\n",
-        "\n",
-        "# Set compute target to AmlCompute\n",
-        "conda_run_config.target = compute_target\n",
-        "\n",
-        "conda_run_config.docker.use_docker = True\n",
-        "\n",
-        "cd = CondaDependencies.create(\n",
-        "    pip_packages=[\n",
-        "        \"azureml-sdk[automl]\",\n",
-        "        \"applicationinsights\",\n",
-        "        \"azureml-opendatasets\",\n",
-        "        \"azureml-defaults\",\n",
-        "    ],\n",
-        "    conda_packages=[\"numpy==1.19.5\"],\n",
-        "    pin_sdk_version=False,\n",
-        ")\n",
-        "conda_run_config.environment.python.conda_dependencies = cd\n",
-        "\n",
-        "print(\"run config is ready\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Step to register the model.\n",
-        "The following code generates a step to register the model to the workspace from previous step. "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# The model name with which to register the trained model in the workspace.\n",
-        "model_name_str = \"ojmodel\"\n",
-        "model_name = PipelineParameter(\"model_name\", default_value=model_name_str)\n",
-        "\n",
-        "\n",
-        "register_model_step = PythonScriptStep(\n",
-        "    script_name=\"register_model.py\",\n",
-        "    name=\"register_model\",\n",
-        "    source_directory=\"scripts\",\n",
-        "    allow_reuse=False,\n",
-        "    arguments=[\n",
-        "        \"--model_name\",\n",
-        "        model_name,\n",
-        "        \"--model_path\",\n",
-        "        model_data,\n",
-        "        \"--ds_name\",\n",
-        "        \"dominicks_OJ_train\",\n",
-        "    ],\n",
-        "    inputs=[model_data],\n",
-        "    compute_target=compute_target,\n",
-        "    runconfig=conda_run_config,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Build the Pipeline"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "training_pipeline = Pipeline(\n",
-        "    description=\"training_pipeline\",\n",
-        "    workspace=ws,\n",
-        "    steps=[automl_step, register_model_step],\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Submit Pipeline Run"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "training_pipeline_run = experiment.submit(training_pipeline)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "training_pipeline_run.wait_for_completion(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Get metrics for each runs"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "output_dir = \"train_output\"\n",
-        "pipeline_output = training_pipeline_run.get_pipeline_output(\"metrics_output\")\n",
-        "pipeline_output.download(output_dir)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "file_path = os.path.join(output_dir, pipeline_output.path_on_datastore)\n",
-        "with open(file_path) as f:\n",
-        "    metrics = json.load(f)\n",
-        "for run_id, metrics in metrics.items():\n",
-        "    print(\"{}: {}\".format(run_id, metrics[\"normalized_root_mean_squared_error\"][0]))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Inference"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "There are several ways to do the inference, for here we will demonstrate how to use the registered model and pipeline to do the inference. (how to register a model https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.model.model?view=azure-ml-py)."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Get Inference Pipeline Environment\n",
-        "To trigger an inference pipeline run, we first need a running environment for run that contains all the appropriate packages for the model unpickling. This environment can be either assess from the training run or using the `yml` file that comes with the model."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.train.automl.run import AutoMLRun\n",
-        "\n",
-        "for step in training_pipeline_run.get_steps():\n",
-        "    if step.properties.get(\"StepType\") == \"AutoMLStep\":\n",
-        "        automl_run = AutoMLRun(experiment, step.id)\n",
-        "        break\n",
-        "\n",
-        "best_run = automl_run.get_best_child()\n",
-        "inference_env = best_run.get_environment()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "After we have the environment for the inference, we could build run config based on this environment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "run_config = RunConfiguration()\n",
-        "run_config.environment = inference_env"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Build and submit the inference pipeline"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "The inference pipeline will create two different format of outputs, 1) a tabular dataset that contains the prediction and 2) an `OutputFileDatasetConfig` that can be used for the sequential pipeline steps."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.data import OutputFileDatasetConfig\n",
-        "\n",
-        "output_data = OutputFileDatasetConfig(name=\"prediction_result\")\n",
-        "\n",
-        "output_ds_name = \"oj-output\"\n",
-        "\n",
-        "inference_step = PythonScriptStep(\n",
-        "    name=\"infer-results\",\n",
-        "    source_directory=\"scripts\",\n",
-        "    script_name=\"infer.py\",\n",
-        "    arguments=[\n",
-        "        \"--model_name\",\n",
-        "        model_name_str,\n",
-        "        \"--ouput_dataset_name\",\n",
-        "        output_ds_name,\n",
-        "        \"--test_dataset_name\",\n",
-        "        test_dataset.name,\n",
-        "        \"--target_column_name\",\n",
-        "        target_column_name,\n",
-        "        \"--output_path\",\n",
-        "        output_data,\n",
-        "    ],\n",
-        "    compute_target=compute_target,\n",
-        "    allow_reuse=False,\n",
-        "    runconfig=run_config,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "inference_pipeline = Pipeline(ws, [inference_step])\n",
-        "inference_run = experiment.submit(inference_pipeline)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "inference_run.wait_for_completion(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Get the predicted data"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core import Dataset\n",
-        "\n",
-        "inference_ds = Dataset.get_by_name(ws, output_ds_name)\n",
-        "inference_df = inference_ds.to_pandas_dataframe()\n",
-        "inference_df.tail(5)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Schedule Pipeline"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "This section is about how to schedule a pipeline for periodically predictions. For more info about pipeline schedule and pipeline endpoint, please follow this [notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-setup-schedule-for-a-published-pipeline.ipynb)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "inference_published_pipeline = inference_pipeline.publish(\n",
-        "    name=\"OJ Inference Test\", description=\"OJ Inference Test\"\n",
-        ")\n",
-        "print(\"Newly published pipeline id: {}\".format(inference_published_pipeline.id))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "If `test_dataset` is going to refresh every 4 weeks before Friday 16:00 and we want to predict every 4 weeks (forecast_horizon), we can schedule our pipeline to run every 4 weeks at 16:00 to get daily inference results. You can refresh your test dataset (a newer version will be created) periodically when new data is available (i.e. target column in test dataset would have values in the beginning as context data, and followed by NaNs to be predicted). The inference pipeline will pick up context to further improve the forecast accuracy."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# schedule\n",
-        "\n",
-        "from azureml.pipeline.core.schedule import ScheduleRecurrence, Schedule\n",
-        "\n",
-        "recurrence = ScheduleRecurrence(\n",
-        "    frequency=\"Week\", interval=4, week_days=[\"Friday\"], hours=[16], minutes=[0]\n",
-        ")\n",
-        "\n",
-        "schedule = Schedule.create(\n",
-        "    workspace=ws,\n",
-        "    name=\"OJ_Inference_schedule\",\n",
-        "    pipeline_id=inference_published_pipeline.id,\n",
-        "    experiment_name=\"Schedule-run-OJ\",\n",
-        "    recurrence=recurrence,\n",
-        "    wait_for_provisioning=True,\n",
-        "    description=\"Schedule Run\",\n",
-        ")\n",
-        "\n",
-        "# You may want to make sure that the schedule is provisioned properly\n",
-        "# before making any further changes to the schedule\n",
-        "\n",
-        "print(\"Created schedule with id: {}\".format(schedule.id))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### [Optional] Disable schedule"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "schedule.disable()"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "jialiu"
-      }
-    ],
-    "category": "tutorial",
-    "celltoolbar": "Raw Cell Format",
-    "compute": [
-      "Remote"
-    ],
-    "datasets": [
-      "Orange Juice Sales"
-    ],
-    "deployment": [
-      "Azure Container Instance"
-    ],
-    "exclude_from_index": false,
-    "framework": [
-      "Azure ML AutoML"
-    ],
-    "friendly_name": "Forecasting orange juice sales with deployment",
-    "index_order": 1,
-    "kernelspec": {
-      "display_name": "Python 3.8 - AzureML",
-      "language": "python",
-      "name": "python38-azureml"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.8.5"
-    },
-    "tags": [
-      "None"
-    ],
-    "task": "Forecasting",
-    "vscode": {
-      "interpreter": {
-        "hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
-      }
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 4
-}

how-to-use-azureml/automated-machine-learning/forecasting-pipelines/oj-test.csv

@@ -1,37 +0,0 @@
-WeekStarting,Store,Brand,Advert,Price,Age60,COLLEGE,INCOME,Hincome150,Large HH,Minorities,WorkingWoman,SSTRDIST,SSTRVOL,CPDIST5,CPWVOL5
-1992-09-10,2,dominicks,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-10,2,minute.maid,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-10,2,tropicana,0,2.64,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-10,5,dominicks,0,1.85,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-10,5,minute.maid,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-10,5,tropicana,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-10,8,dominicks,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-10,8,minute.maid,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-10,8,tropicana,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-17,2,dominicks,0,1.77,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-17,2,minute.maid,0,2.83,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-17,2,tropicana,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-17,5,dominicks,0,1.85,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-17,5,minute.maid,0,2.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-17,5,tropicana,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-17,8,dominicks,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-17,8,minute.maid,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-17,8,tropicana,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-24,2,dominicks,0,1.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-24,2,minute.maid,0,2.67,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-24,2,tropicana,1,2.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-24,5,dominicks,0,1.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-24,5,minute.maid,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-24,5,tropicana,1,2.78,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-24,8,dominicks,0,1.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-24,8,minute.maid,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-24,8,tropicana,1,2.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-10-01,2,dominicks,0,1.82,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-10-01,2,minute.maid,1,2.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-10-01,2,tropicana,0,2.97,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-10-01,5,dominicks,0,1.85,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-10-01,5,minute.maid,1,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-10-01,5,tropicana,0,2.78,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-10-01,8,dominicks,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-10-01,8,minute.maid,1,2.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-10-01,8,tropicana,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947

how-to-use-azureml/automated-machine-learning/forecasting-pipelines/oj-train.csv

@@ -1,997 +0,0 @@
-WeekStarting,Store,Brand,Quantity,Advert,Price,Age60,COLLEGE,INCOME,Hincome150,Large HH,Minorities,WorkingWoman,SSTRDIST,SSTRVOL,CPDIST5,CPWVOL5
-1990-06-14,2,dominicks,10560,1,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-06-14,2,minute.maid,4480,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-06-14,2,tropicana,8256,0,3.87,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-06-14,5,dominicks,1792,1,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-06-14,5,minute.maid,4224,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-06-14,5,tropicana,5888,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-06-14,8,dominicks,14336,1,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-06-14,8,minute.maid,6080,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-06-14,8,tropicana,8896,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-06-21,8,dominicks,6400,0,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-06-21,8,minute.maid,51968,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-06-21,8,tropicana,7296,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-06-28,5,dominicks,2496,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-06-28,5,minute.maid,4352,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-06-28,5,tropicana,6976,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-06-28,8,dominicks,3968,0,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-06-28,8,minute.maid,4928,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-06-28,8,tropicana,10368,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-05,5,dominicks,2944,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-07-05,5,minute.maid,4928,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-07-05,5,tropicana,6528,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-07-05,8,dominicks,4352,0,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-05,8,minute.maid,5312,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-05,8,tropicana,6976,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-12,5,dominicks,1024,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-07-12,5,minute.maid,31168,1,2.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-07-12,5,tropicana,4928,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-07-12,8,dominicks,3520,0,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-12,8,minute.maid,39424,1,2.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-12,8,tropicana,6464,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-19,8,dominicks,6464,0,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-19,8,minute.maid,5568,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-19,8,tropicana,8192,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-26,2,dominicks,8000,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-07-26,2,minute.maid,4672,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-07-26,2,tropicana,6144,0,3.87,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-07-26,5,dominicks,4224,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-07-26,5,minute.maid,10048,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-07-26,5,tropicana,5312,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-07-26,8,dominicks,5952,0,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-26,8,minute.maid,14592,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-26,8,tropicana,7936,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-02,2,dominicks,6848,1,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-02,2,minute.maid,20160,1,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-02,2,tropicana,3840,0,3.87,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-02,5,dominicks,4544,1,2.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-02,5,minute.maid,21760,1,2.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-02,5,tropicana,5120,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-02,8,dominicks,8832,1,2.09,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-02,8,minute.maid,22208,1,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-02,8,tropicana,6656,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-09,2,dominicks,2880,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-09,2,minute.maid,2688,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-09,2,tropicana,8000,0,3.87,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-09,5,dominicks,1728,0,2.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-09,5,minute.maid,4544,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-09,5,tropicana,7936,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-09,8,dominicks,7232,0,2.09,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-09,8,minute.maid,5760,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-09,8,tropicana,8256,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-16,5,dominicks,1216,0,2.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-16,5,minute.maid,52224,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-16,5,tropicana,6080,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-16,8,dominicks,5504,0,2.09,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-16,8,minute.maid,54016,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-16,8,tropicana,5568,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-23,2,dominicks,1600,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-23,2,minute.maid,3008,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-23,2,tropicana,8896,0,3.87,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-23,5,dominicks,1152,0,2.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-23,5,minute.maid,3584,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-23,5,tropicana,4160,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-23,8,dominicks,4800,0,2.09,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-23,8,minute.maid,5824,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-23,8,tropicana,7488,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-30,2,dominicks,25344,1,1.89,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-30,2,minute.maid,4672,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-30,2,tropicana,7168,0,3.87,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-30,5,dominicks,30144,1,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-30,5,minute.maid,5120,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-30,5,tropicana,5888,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-30,8,dominicks,52672,1,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-30,8,minute.maid,6528,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-30,8,tropicana,6144,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-06,2,dominicks,10752,0,1.89,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-09-06,2,minute.maid,2752,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-09-06,2,tropicana,10880,0,3.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-09-06,5,dominicks,8960,0,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-06,5,minute.maid,4416,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-06,5,tropicana,9536,0,3.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-06,8,dominicks,16448,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-06,8,minute.maid,5440,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-06,8,tropicana,11008,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-13,2,dominicks,6656,0,1.89,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-09-13,2,minute.maid,26176,1,2.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-09-13,2,tropicana,7744,0,3.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-09-13,5,dominicks,8192,0,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-13,5,minute.maid,30208,1,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-13,5,tropicana,8320,0,3.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-13,8,dominicks,19072,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-13,8,minute.maid,36544,1,2.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-13,8,tropicana,5760,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-20,2,dominicks,6592,0,1.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-09-20,2,minute.maid,3712,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-09-20,2,tropicana,8512,0,3.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-09-20,5,dominicks,6528,0,1.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-20,5,minute.maid,4160,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-20,5,tropicana,8000,0,3.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-20,8,dominicks,13376,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-20,8,minute.maid,3776,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-20,8,tropicana,10112,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-27,5,dominicks,34688,1,1.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-27,5,minute.maid,4992,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-27,5,tropicana,5824,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-27,8,dominicks,61440,1,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-27,8,minute.maid,5504,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-27,8,tropicana,8448,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-04,5,dominicks,4672,0,1.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-04,5,minute.maid,13952,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-04,5,tropicana,10624,1,3.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-04,8,dominicks,13760,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-04,8,minute.maid,12416,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-04,8,tropicana,8448,1,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-11,2,dominicks,1728,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-10-11,2,minute.maid,30656,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-10-11,2,tropicana,5504,0,3.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-10-11,5,dominicks,1088,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-11,5,minute.maid,47680,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-11,5,tropicana,6656,0,3.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-11,8,dominicks,3136,0,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-11,8,minute.maid,53696,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-11,8,tropicana,7424,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-18,2,dominicks,33792,1,1.24,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-10-18,2,minute.maid,3840,0,2.98,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-10-18,2,tropicana,5888,0,3.56,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-10-18,5,dominicks,69440,1,1.24,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-18,5,minute.maid,7616,0,2.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-18,5,tropicana,5184,0,3.51,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-18,8,dominicks,186176,1,1.14,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-18,8,minute.maid,5696,0,2.51,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-18,8,tropicana,5824,0,3.04,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-25,2,dominicks,1920,0,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-10-25,2,minute.maid,2816,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-10-25,2,tropicana,8384,0,3.56,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-10-25,5,dominicks,1280,0,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-25,5,minute.maid,8896,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-25,5,tropicana,4928,0,3.51,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-25,8,dominicks,3712,0,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-25,8,minute.maid,4864,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-25,8,tropicana,6656,0,3.04,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-01,2,dominicks,8960,1,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-01,2,minute.maid,23104,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-01,2,tropicana,5952,0,3.56,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-01,5,dominicks,35456,1,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-01,5,minute.maid,28544,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-01,5,tropicana,5888,0,3.51,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-01,8,dominicks,35776,1,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-01,8,minute.maid,37184,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-01,8,tropicana,6272,0,3.04,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-08,2,dominicks,11392,0,1.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-08,2,minute.maid,3392,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-08,2,tropicana,6848,0,3.56,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-08,5,dominicks,13824,0,1.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-08,5,minute.maid,5440,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-08,5,tropicana,5312,0,3.51,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-08,8,dominicks,26880,0,1.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-08,8,minute.maid,5504,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-08,8,tropicana,6912,0,3.04,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-15,2,dominicks,28416,0,0.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-15,2,minute.maid,26304,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-15,2,tropicana,9216,0,3.87,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-15,5,dominicks,14208,0,0.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-15,5,minute.maid,52416,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-15,5,tropicana,9984,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-15,8,dominicks,71680,0,0.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-15,8,minute.maid,51008,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-15,8,tropicana,10496,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-22,2,dominicks,17152,1,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-22,2,minute.maid,6336,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-22,2,tropicana,12160,0,2.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-22,5,dominicks,29312,1,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-22,5,minute.maid,11712,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-22,5,tropicana,8448,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-22,8,dominicks,25088,1,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-22,8,minute.maid,11072,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-22,8,tropicana,11840,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-29,2,dominicks,26560,1,2.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-29,2,minute.maid,9920,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-29,2,tropicana,12672,0,2.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-29,5,dominicks,52992,1,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-29,5,minute.maid,13952,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-29,5,tropicana,10880,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-29,8,dominicks,91456,1,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-29,8,minute.maid,12160,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-29,8,tropicana,9664,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-06,2,dominicks,6336,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-06,2,minute.maid,25280,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-06,2,tropicana,6528,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-06,5,dominicks,15680,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-06,5,minute.maid,36160,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-06,5,tropicana,5696,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-06,8,dominicks,23808,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-06,8,minute.maid,30528,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-06,8,tropicana,6272,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-13,2,dominicks,26368,1,1.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-13,2,minute.maid,14848,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-13,2,tropicana,6144,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-13,5,dominicks,43520,1,1.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-13,5,minute.maid,12864,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-13,5,tropicana,5696,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-13,8,dominicks,89856,1,1.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-13,8,minute.maid,12096,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-13,8,tropicana,7168,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-20,2,dominicks,896,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-20,2,minute.maid,12288,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-20,2,tropicana,21120,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-20,5,dominicks,3904,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-20,5,minute.maid,22208,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-20,5,tropicana,32384,0,2.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-20,8,dominicks,12224,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-20,8,minute.maid,16448,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-20,8,tropicana,29504,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-27,2,dominicks,1472,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-27,2,minute.maid,6272,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-27,2,tropicana,12416,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-27,5,dominicks,896,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-27,5,minute.maid,9984,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-27,5,tropicana,10752,0,2.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-27,8,dominicks,3776,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-27,8,minute.maid,9344,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-27,8,tropicana,8704,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-03,2,dominicks,1344,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-03,2,minute.maid,9152,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-03,2,tropicana,9472,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-03,5,dominicks,2240,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-03,5,minute.maid,14016,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-03,5,tropicana,6912,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-03,8,dominicks,13824,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-03,8,minute.maid,16128,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-03,8,tropicana,9280,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-10,2,dominicks,111680,1,0.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-10,2,minute.maid,4160,0,2.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-10,2,tropicana,17920,0,2.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-10,5,dominicks,125760,1,0.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-10,5,minute.maid,6080,0,2.46,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-10,5,tropicana,13440,0,2.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-10,8,dominicks,251072,1,0.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-10,8,minute.maid,5376,0,2.17,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-10,8,tropicana,12224,0,2.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-17,2,dominicks,1856,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-17,2,minute.maid,10176,0,2.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-17,2,tropicana,9408,0,2.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-17,5,dominicks,1408,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-17,5,minute.maid,7808,0,2.46,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-17,5,tropicana,7808,0,2.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-17,8,dominicks,4864,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-17,8,minute.maid,6656,0,2.17,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-17,8,tropicana,10368,0,2.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-24,2,dominicks,5568,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-24,2,minute.maid,29056,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-24,2,tropicana,6272,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-24,5,dominicks,7232,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-24,5,minute.maid,40896,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-24,5,tropicana,5248,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-24,8,dominicks,10176,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-24,8,minute.maid,59712,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-24,8,tropicana,8128,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-31,2,dominicks,32064,1,1.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-31,2,minute.maid,7104,0,2.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-31,2,tropicana,6912,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-31,5,dominicks,41216,1,1.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-31,5,minute.maid,6272,0,2.46,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-31,5,tropicana,6208,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-31,8,dominicks,105344,1,1.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-31,8,minute.maid,9856,0,2.17,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-31,8,tropicana,5952,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-07,2,dominicks,4352,0,1.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-07,2,minute.maid,7488,0,2.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-07,2,tropicana,16768,0,2.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-07,5,dominicks,9024,0,1.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-07,5,minute.maid,7872,0,2.41,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-07,5,tropicana,21440,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-07,8,dominicks,33600,0,1.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-07,8,minute.maid,6720,0,2.12,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-07,8,tropicana,21696,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-14,2,dominicks,704,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-14,2,minute.maid,4224,0,2.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-14,2,tropicana,6272,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-14,5,dominicks,1600,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-14,5,minute.maid,6144,0,2.41,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-14,5,tropicana,7360,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-14,8,dominicks,4736,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-14,8,minute.maid,4224,0,2.12,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-14,8,tropicana,7808,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-21,2,dominicks,13760,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-21,2,minute.maid,8960,0,2.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-21,2,tropicana,7936,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-21,5,dominicks,2496,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-21,5,minute.maid,8448,0,2.41,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-21,5,tropicana,6720,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-21,8,dominicks,10304,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-21,8,minute.maid,9728,0,2.12,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-21,8,tropicana,8128,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-28,2,dominicks,43328,1,1.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-28,2,minute.maid,22464,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-28,2,tropicana,6144,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-28,5,dominicks,6336,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-28,5,minute.maid,18688,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-28,5,tropicana,6656,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-28,8,dominicks,5056,1,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-28,8,minute.maid,40320,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-28,8,tropicana,7424,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-07,2,dominicks,57600,1,1.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-07,2,minute.maid,3840,0,2.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-07,2,tropicana,7936,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-07,5,dominicks,56384,1,1.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-07,5,minute.maid,6272,0,2.46,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-07,5,tropicana,6016,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-07,8,dominicks,179968,1,0.94,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-07,8,minute.maid,5120,0,2.17,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-07,8,tropicana,5952,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-14,2,dominicks,704,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-14,2,minute.maid,12992,0,2.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-14,2,tropicana,7808,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-14,5,dominicks,1600,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-14,5,minute.maid,12096,0,2.46,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-14,5,tropicana,6144,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-14,8,dominicks,4992,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-14,8,minute.maid,19264,0,2.17,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-14,8,tropicana,7616,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-21,2,dominicks,6016,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-21,2,minute.maid,70144,1,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-21,2,tropicana,6080,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-21,5,dominicks,2944,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-21,5,minute.maid,73216,1,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-21,5,tropicana,4928,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-21,8,dominicks,6400,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-21,8,minute.maid,170432,1,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-21,8,tropicana,5312,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-28,2,dominicks,10368,1,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-28,2,minute.maid,21248,0,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-28,2,tropicana,42176,1,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-28,5,dominicks,13504,1,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-28,5,minute.maid,18944,0,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-28,5,tropicana,67712,1,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-28,8,dominicks,14912,1,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-28,8,minute.maid,39680,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-28,8,tropicana,161792,1,1.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-04,2,dominicks,12608,0,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-04,2,minute.maid,5696,1,2.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-04,2,tropicana,4928,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-04,5,dominicks,5376,0,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-04,5,minute.maid,6400,1,2.46,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-04,5,tropicana,8640,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-04,8,dominicks,34624,0,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-04,8,minute.maid,8128,1,2.17,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-04,8,tropicana,17280,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-11,2,dominicks,6336,0,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-11,2,minute.maid,7680,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-11,2,tropicana,29504,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-11,5,dominicks,6656,0,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-11,5,minute.maid,8640,0,2.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-11,5,tropicana,35520,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-11,8,dominicks,10368,0,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-11,8,minute.maid,9088,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-11,8,tropicana,47040,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-18,2,dominicks,140736,1,0.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-18,2,minute.maid,6336,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-18,2,tropicana,9984,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-18,5,dominicks,95680,1,0.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-18,5,minute.maid,7296,0,2.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-18,5,tropicana,9664,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-18,8,dominicks,194880,1,0.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-18,8,minute.maid,6720,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-18,8,tropicana,14464,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-25,2,dominicks,960,1,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-25,2,minute.maid,8576,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-25,2,tropicana,35200,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-25,5,dominicks,896,1,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-25,5,minute.maid,12480,0,2.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-25,5,tropicana,49088,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-25,8,dominicks,5696,1,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-25,8,minute.maid,7552,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-25,8,tropicana,52928,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-05-02,2,dominicks,1216,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-02,2,minute.maid,15104,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-02,2,tropicana,23936,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-02,5,dominicks,1728,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-02,5,minute.maid,14144,0,2.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-02,5,tropicana,14912,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-02,8,dominicks,7168,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-05-02,8,minute.maid,24768,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-05-02,8,tropicana,21184,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-05-09,2,dominicks,1664,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-09,2,minute.maid,76480,1,1.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-09,2,tropicana,7104,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-09,5,dominicks,1280,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-09,5,minute.maid,88256,1,1.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-09,5,tropicana,6464,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-09,8,dominicks,2880,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-05-09,8,minute.maid,183296,1,1.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-05-09,8,tropicana,7360,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-05-16,2,dominicks,4992,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-16,2,minute.maid,5056,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-16,2,tropicana,24512,1,2.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-16,5,dominicks,5696,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-16,5,minute.maid,6848,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-16,5,tropicana,25024,1,2.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-16,8,dominicks,12288,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-05-16,8,minute.maid,8896,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-05-16,8,tropicana,15744,1,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-05-23,2,dominicks,27968,1,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-23,2,minute.maid,4736,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-23,2,tropicana,6336,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-23,5,dominicks,28288,1,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-23,5,minute.maid,7808,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-23,5,tropicana,6272,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-30,2,dominicks,12160,0,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-30,2,minute.maid,4480,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-30,2,tropicana,6080,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-30,5,dominicks,4864,0,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-30,5,minute.maid,6272,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-30,5,tropicana,5056,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-06,2,dominicks,2240,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-06,2,minute.maid,4032,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-06,2,tropicana,33536,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-06,5,dominicks,2880,0,2.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-06,5,minute.maid,6144,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-06,5,tropicana,47616,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-06,8,dominicks,9280,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-06,8,minute.maid,6656,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-06,8,tropicana,46912,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-13,2,dominicks,5504,1,1.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-13,2,minute.maid,14784,1,1.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-13,2,tropicana,13248,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-13,5,dominicks,5760,1,1.41,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-13,5,minute.maid,27776,1,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-13,5,tropicana,13888,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-13,8,dominicks,25856,1,1.26,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-13,8,minute.maid,35456,1,1.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-13,8,tropicana,18240,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-20,2,dominicks,8832,0,1.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-20,2,minute.maid,12096,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-20,2,tropicana,6208,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-20,5,dominicks,15040,0,1.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-20,5,minute.maid,20800,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-20,5,tropicana,6144,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-20,8,dominicks,19264,0,1.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-20,8,minute.maid,17408,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-20,8,tropicana,6464,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-27,2,dominicks,2624,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-27,2,minute.maid,41792,1,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-27,2,tropicana,10624,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-27,5,dominicks,5120,0,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-27,5,minute.maid,45696,1,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-27,5,tropicana,9344,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-27,8,dominicks,6848,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-27,8,minute.maid,75520,1,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-27,8,tropicana,8512,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-04,2,dominicks,10432,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-07-04,2,minute.maid,10560,0,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-07-04,2,tropicana,44672,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-07-04,5,dominicks,3264,0,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-04,5,minute.maid,14336,0,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-04,5,tropicana,32896,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-04,8,dominicks,12928,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-04,8,minute.maid,21632,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-04,8,tropicana,28416,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-11,5,dominicks,9536,1,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-11,5,minute.maid,4928,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-11,5,tropicana,21056,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-11,8,dominicks,44032,1,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-11,8,minute.maid,8384,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-11,8,tropicana,16960,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-18,2,dominicks,8320,0,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-07-18,2,minute.maid,4224,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-07-18,2,tropicana,20096,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-07-18,5,dominicks,6208,0,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-18,5,minute.maid,4608,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-18,5,tropicana,15360,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-18,8,dominicks,25408,0,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-18,8,minute.maid,9920,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-18,8,tropicana,8320,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-25,2,dominicks,6784,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-07-25,2,minute.maid,2880,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-07-25,2,tropicana,9152,1,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-07-25,5,dominicks,6592,0,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-25,5,minute.maid,5248,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-25,5,tropicana,8000,1,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-25,8,dominicks,38336,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-25,8,minute.maid,6592,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-25,8,tropicana,11136,1,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-01,2,dominicks,60544,1,0.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-08-01,2,minute.maid,3968,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-08-01,2,tropicana,21952,0,2.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-08-01,5,dominicks,63552,1,0.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-01,5,minute.maid,4224,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-01,5,tropicana,21120,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-01,8,dominicks,152384,1,0.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-01,8,minute.maid,7168,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-01,8,tropicana,27712,0,2.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-08,2,dominicks,20608,0,0.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-08-08,2,minute.maid,3712,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-08-08,2,tropicana,13568,0,2.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-08-08,5,dominicks,27968,0,0.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-08,5,minute.maid,4288,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-08,5,tropicana,11904,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-08,8,dominicks,54464,0,0.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-08,8,minute.maid,6208,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-08,8,tropicana,7744,0,2.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-15,5,dominicks,21760,1,1.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-15,5,minute.maid,16896,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-15,5,tropicana,5056,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-15,8,dominicks,47680,1,1.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-15,8,minute.maid,30528,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-15,8,tropicana,5184,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-22,5,dominicks,2688,0,1.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-22,5,minute.maid,77184,1,1.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-22,5,tropicana,4608,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-22,8,dominicks,14720,0,1.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-22,8,minute.maid,155840,1,1.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-22,8,tropicana,6272,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-29,2,dominicks,16064,0,1.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-08-29,2,minute.maid,2816,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-08-29,2,tropicana,4160,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-08-29,5,dominicks,10432,0,1.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-29,5,minute.maid,5184,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-29,5,tropicana,6016,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-29,8,dominicks,53248,0,1.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-29,8,minute.maid,10752,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-29,8,tropicana,7744,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-05,2,dominicks,12480,0,1.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-05,2,minute.maid,4288,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-05,2,tropicana,39424,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-05,5,dominicks,9792,0,1.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-09-05,5,minute.maid,5248,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-09-05,5,tropicana,50752,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-09-05,8,dominicks,40576,0,1.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-05,8,minute.maid,6976,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-05,8,tropicana,53184,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-12,2,dominicks,17024,0,1.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-12,2,minute.maid,18240,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-12,2,tropicana,5632,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-12,5,dominicks,8448,0,1.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-09-12,5,minute.maid,20672,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-09-12,5,tropicana,5632,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-09-12,8,dominicks,25856,0,1.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-12,8,minute.maid,31872,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-12,8,tropicana,6784,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-19,2,dominicks,13440,1,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-19,2,minute.maid,7360,0,1.95,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-19,2,tropicana,9024,1,2.68,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-19,8,dominicks,24064,1,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-19,8,minute.maid,5312,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-19,8,tropicana,8000,1,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-26,2,dominicks,10112,0,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-26,2,minute.maid,7808,0,1.83,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-26,2,tropicana,6016,0,3.44,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-26,5,dominicks,6912,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-09-26,5,minute.maid,12352,0,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-09-26,5,tropicana,6400,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-09-26,8,dominicks,15680,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-26,8,minute.maid,33344,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-26,8,tropicana,6592,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-03,2,dominicks,9088,0,1.56,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-03,2,minute.maid,13504,0,1.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-03,2,tropicana,7744,0,3.14,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-03,5,dominicks,8256,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-03,5,minute.maid,12032,0,1.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-03,5,tropicana,5440,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-03,8,dominicks,16576,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-03,8,minute.maid,13504,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-03,8,tropicana,5248,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-10,2,dominicks,22848,1,1.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-10,2,minute.maid,10048,0,1.91,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-10,2,tropicana,6784,0,3.07,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-10,5,dominicks,28672,1,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-10,5,minute.maid,13440,0,1.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-10,5,tropicana,8128,0,2.94,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-10,8,dominicks,49664,1,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-10,8,minute.maid,13504,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-10,8,tropicana,6592,0,2.94,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-17,2,dominicks,6976,0,1.65,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-17,2,minute.maid,135936,1,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-17,2,tropicana,6784,0,3.07,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-17,8,dominicks,10752,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-17,8,minute.maid,335808,1,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-17,8,tropicana,5888,0,2.94,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-24,2,dominicks,4160,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-24,2,minute.maid,5056,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-24,2,tropicana,6272,0,3.07,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-24,5,dominicks,4416,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-24,5,minute.maid,5824,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-24,5,tropicana,7232,0,2.94,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-24,8,dominicks,9792,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-24,8,minute.maid,13120,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-24,8,tropicana,6336,0,2.94,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-31,2,dominicks,3328,0,1.83,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-31,2,minute.maid,27968,0,1.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-31,2,tropicana,5312,0,3.07,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-31,5,dominicks,1856,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-31,5,minute.maid,50112,0,1.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-31,5,tropicana,7168,0,2.94,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-31,8,dominicks,7104,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-31,8,minute.maid,49664,0,1.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-31,8,tropicana,5888,0,2.94,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-07,2,dominicks,12096,1,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-07,2,minute.maid,4736,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-07,2,tropicana,9216,0,3.11,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-07,5,dominicks,6528,1,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-07,5,minute.maid,5184,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-07,5,tropicana,7872,0,2.94,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-07,8,dominicks,9216,1,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-07,8,minute.maid,10880,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-07,8,tropicana,6080,0,2.94,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-14,2,dominicks,6208,0,1.76,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-14,2,minute.maid,7808,0,2.14,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-14,2,tropicana,7296,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-14,5,dominicks,6080,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-14,5,minute.maid,8384,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-14,5,tropicana,7552,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-14,8,dominicks,12608,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-14,8,minute.maid,9984,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-14,8,tropicana,6848,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-21,2,dominicks,3008,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-21,2,minute.maid,12480,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-21,2,tropicana,34240,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-21,5,dominicks,3456,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-21,5,minute.maid,10112,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-21,5,tropicana,69504,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-21,8,dominicks,16448,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-21,8,minute.maid,9216,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-21,8,tropicana,54016,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-28,2,dominicks,19456,1,1.5,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-28,2,minute.maid,9664,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-28,2,tropicana,7168,0,2.64,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-28,5,dominicks,25856,1,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-28,5,minute.maid,8384,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-28,5,tropicana,8960,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-28,8,dominicks,27968,1,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-28,8,minute.maid,7680,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-28,8,tropicana,10368,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-05,2,dominicks,16768,0,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-05,2,minute.maid,7168,0,2.06,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-05,2,tropicana,6080,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-05,5,dominicks,25728,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-05,5,minute.maid,11456,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-05,5,tropicana,6912,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-05,8,dominicks,37824,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-05,8,minute.maid,7296,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-05,8,tropicana,5568,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-12,2,dominicks,13568,1,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-12,2,minute.maid,4480,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-12,2,tropicana,5120,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-12,5,dominicks,23552,1,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-12,5,minute.maid,5952,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-12,5,tropicana,6656,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-12,8,dominicks,33664,1,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-12,8,minute.maid,8192,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-12,8,tropicana,4864,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-19,2,dominicks,6080,0,1.61,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-19,2,minute.maid,5952,0,2.22,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-19,2,tropicana,8320,0,2.74,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-19,5,dominicks,2944,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-19,5,minute.maid,8512,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-19,5,tropicana,8192,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-19,8,dominicks,17728,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-19,8,minute.maid,6080,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-19,8,tropicana,7232,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-26,2,dominicks,10432,1,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-26,2,minute.maid,21696,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-26,2,tropicana,17728,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-26,5,dominicks,5888,1,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-26,5,minute.maid,27968,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-26,5,tropicana,13440,0,2.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-26,8,dominicks,25088,1,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-26,8,minute.maid,15040,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-26,8,tropicana,15232,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-02,2,dominicks,11712,0,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-02,2,minute.maid,12032,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-02,2,tropicana,13120,0,2.35,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-02,5,dominicks,6848,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-02,5,minute.maid,24000,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-02,5,tropicana,12160,0,2.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-02,8,dominicks,13184,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-02,8,minute.maid,9472,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-02,8,tropicana,47040,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-09,2,dominicks,4032,0,1.76,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-09,2,minute.maid,7040,0,2.12,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-09,2,tropicana,13120,0,2.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-09,5,dominicks,1792,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-09,5,minute.maid,6848,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-09,5,tropicana,11840,0,2.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-09,8,dominicks,3136,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-09,8,minute.maid,5888,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-09,8,tropicana,9280,0,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-16,2,dominicks,6336,0,1.82,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-16,2,minute.maid,10240,1,2.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-16,2,tropicana,9792,0,2.43,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-16,5,dominicks,5248,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-16,5,minute.maid,15104,1,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-16,5,tropicana,8640,0,2.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-16,8,dominicks,5696,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-16,8,minute.maid,14336,1,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-16,8,tropicana,6720,0,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-23,2,dominicks,13632,0,1.47,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-23,2,minute.maid,6848,1,2.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-23,2,tropicana,3520,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-23,5,dominicks,16768,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-23,5,minute.maid,11392,1,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-23,5,tropicana,5888,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-23,8,dominicks,19008,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-23,8,minute.maid,11712,1,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-23,8,tropicana,5056,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-30,2,dominicks,45120,0,1.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-30,2,minute.maid,3968,0,2.61,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-30,2,tropicana,5504,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-30,5,dominicks,52160,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-30,5,minute.maid,5824,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-30,5,tropicana,7424,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-30,8,dominicks,121664,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-30,8,minute.maid,7936,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-30,8,tropicana,6080,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-06,2,dominicks,9984,0,1.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-06,2,minute.maid,5888,0,2.26,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-06,2,tropicana,6720,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-06,5,dominicks,16640,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-06,5,minute.maid,7488,0,2.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-06,5,tropicana,5632,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-06,8,dominicks,38848,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-06,8,minute.maid,5184,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-06,8,tropicana,10496,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-13,2,dominicks,4800,0,1.82,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-13,2,minute.maid,6208,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-13,2,tropicana,20224,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-13,5,dominicks,1344,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-13,5,minute.maid,8320,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-13,5,tropicana,33600,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-13,8,dominicks,6144,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-13,8,minute.maid,7168,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-13,8,tropicana,39040,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-20,2,dominicks,11776,0,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-20,2,minute.maid,72256,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-20,2,tropicana,5056,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-20,5,dominicks,4608,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-20,5,minute.maid,99904,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-20,5,tropicana,5376,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-20,8,dominicks,13632,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-20,8,minute.maid,216064,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-20,8,tropicana,4480,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-27,2,dominicks,11584,0,1.54,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-27,2,minute.maid,11520,0,2.11,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-27,2,tropicana,43584,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-27,5,dominicks,12672,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-27,5,minute.maid,6976,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-27,5,tropicana,54272,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-27,8,dominicks,9792,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-27,8,minute.maid,15040,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-27,8,tropicana,61760,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-05,2,dominicks,51264,1,1.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-05,2,minute.maid,5824,0,2.35,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-05,2,tropicana,25728,0,1.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-05,5,dominicks,48640,1,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-05,5,minute.maid,9984,0,2.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-05,5,tropicana,33600,0,1.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-05,8,dominicks,86912,1,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-05,8,minute.maid,11840,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-05,8,tropicana,15360,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-12,2,dominicks,14976,0,1.44,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-12,2,minute.maid,19392,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-12,2,tropicana,31808,0,1.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-12,5,dominicks,13248,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-12,5,minute.maid,32832,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-12,5,tropicana,24448,0,1.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-12,8,dominicks,24512,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-12,8,minute.maid,25472,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-12,8,tropicana,54976,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-19,2,dominicks,30784,0,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-19,2,minute.maid,9536,0,2.1,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-19,2,tropicana,20736,0,1.91,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-19,5,dominicks,29248,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-19,5,minute.maid,8128,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-19,5,tropicana,22784,0,1.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-19,8,dominicks,58048,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-19,8,minute.maid,16384,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-19,8,tropicana,34368,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-26,2,dominicks,12480,0,1.6,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-26,2,minute.maid,5312,0,2.28,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-26,2,tropicana,15168,0,2.81,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-26,5,dominicks,4608,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-26,5,minute.maid,6464,0,2.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-26,5,tropicana,19008,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-26,8,dominicks,13952,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-26,8,minute.maid,20480,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-26,8,tropicana,10752,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-02,2,dominicks,3264,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-02,2,minute.maid,14528,1,1.9,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-02,2,tropicana,28096,1,2.5,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-02,5,dominicks,3136,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-02,5,minute.maid,36800,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-02,5,tropicana,15808,1,2.5,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-02,8,dominicks,15168,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-02,8,minute.maid,34688,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-02,8,tropicana,20096,1,2.5,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-09,2,dominicks,8768,0,1.48,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-09,2,minute.maid,12416,0,2.12,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-09,2,tropicana,12416,0,2.58,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-09,5,dominicks,13184,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-09,5,minute.maid,12928,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-09,5,tropicana,14144,0,2.5,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-09,8,dominicks,14592,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-09,8,minute.maid,22400,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-09,8,tropicana,16192,0,2.5,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-16,2,dominicks,70848,1,1.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-16,2,minute.maid,5376,0,2.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-16,2,tropicana,5376,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-16,5,dominicks,67712,1,1.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-16,5,minute.maid,7424,0,2.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-16,5,tropicana,9600,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-16,8,dominicks,145088,1,1.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-16,8,minute.maid,7808,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-16,8,tropicana,6528,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-23,2,dominicks,18560,0,1.42,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-23,2,minute.maid,19008,1,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-23,2,tropicana,9792,0,2.67,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-23,5,dominicks,18880,0,1.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-23,5,minute.maid,34176,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-23,5,tropicana,10112,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-23,8,dominicks,43712,0,1.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-23,8,minute.maid,48064,1,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-23,8,tropicana,8320,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-30,2,dominicks,9152,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-30,2,minute.maid,3904,0,2.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-30,2,tropicana,16960,1,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-30,5,dominicks,6208,0,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-30,5,minute.maid,4160,0,2.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-30,5,tropicana,31872,1,2.24,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-30,8,dominicks,20608,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-30,8,minute.maid,7360,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-30,8,tropicana,30784,1,2.16,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-07,2,dominicks,9600,0,2.0,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-07,2,minute.maid,6336,0,2.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-07,2,tropicana,8320,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-07,5,dominicks,5952,0,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-07,5,minute.maid,5952,0,2.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-07,5,tropicana,9280,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-07,8,dominicks,18752,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-07,8,minute.maid,6272,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-07,8,tropicana,18048,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-14,2,dominicks,4800,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-14,2,minute.maid,5440,0,2.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-14,2,tropicana,6912,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-14,5,dominicks,4160,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-14,5,minute.maid,6528,0,2.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-14,5,tropicana,7680,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-14,8,dominicks,20160,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-14,8,minute.maid,6400,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-14,8,tropicana,12864,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-21,2,dominicks,9664,0,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-21,2,minute.maid,22400,1,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-21,2,tropicana,6976,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-21,5,dominicks,23488,0,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-21,5,minute.maid,30656,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-21,5,tropicana,8704,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-21,8,dominicks,18688,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-21,8,minute.maid,54592,1,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-21,8,tropicana,7168,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-28,2,dominicks,45568,0,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-28,2,minute.maid,3968,0,2.84,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-28,2,tropicana,7232,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-28,5,dominicks,60480,0,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-28,5,minute.maid,6656,0,2.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-28,5,tropicana,9920,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-28,8,dominicks,133824,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-28,8,minute.maid,8128,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-28,8,tropicana,9024,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-06-04,2,dominicks,20992,0,1.74,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-04,2,minute.maid,3264,0,2.89,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-04,2,tropicana,51520,1,2.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-04,5,dominicks,20416,0,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-06-04,5,minute.maid,4416,0,2.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-06-04,5,tropicana,91968,1,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-06-04,8,dominicks,63488,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-06-04,8,minute.maid,4928,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-06-04,8,tropicana,84992,1,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-06-11,2,dominicks,6592,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-11,2,minute.maid,4352,0,2.89,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-11,2,tropicana,22272,0,2.21,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-11,5,dominicks,6336,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-06-11,5,minute.maid,5696,0,2.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-06-11,5,tropicana,44096,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-06-11,8,dominicks,71040,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-06-11,8,minute.maid,5440,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-06-11,8,tropicana,14144,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-06-18,2,dominicks,4992,0,2.05,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-18,2,minute.maid,4480,0,2.89,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-18,2,tropicana,46144,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-25,2,dominicks,8064,0,1.24,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-25,2,minute.maid,3840,0,2.52,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-25,2,tropicana,4352,1,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-25,5,dominicks,1408,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-06-25,5,minute.maid,5696,0,2.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-06-25,5,tropicana,7296,1,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-06-25,8,dominicks,15360,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-06-25,8,minute.maid,5888,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-06-25,8,tropicana,7488,1,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-02,2,dominicks,7360,0,1.61,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-02,2,minute.maid,13312,1,2.0,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-02,2,tropicana,17280,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-02,5,dominicks,4672,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-02,5,minute.maid,39680,1,2.01,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-02,5,tropicana,12928,0,2.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-02,8,dominicks,17728,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-02,8,minute.maid,23872,1,2.02,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-02,8,tropicana,12352,0,2.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-09,2,dominicks,10048,0,1.4,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-09,2,minute.maid,3776,1,2.33,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-09,2,tropicana,5696,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-09,5,dominicks,19520,0,1.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-09,5,minute.maid,6208,1,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-09,5,tropicana,6848,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-09,8,dominicks,24256,0,1.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-09,8,minute.maid,6848,1,2.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-09,8,tropicana,5696,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-16,2,dominicks,10112,0,1.91,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-16,2,minute.maid,4800,0,2.89,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-16,2,tropicana,6848,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-16,5,dominicks,7872,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-16,5,minute.maid,7872,0,2.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-16,5,tropicana,8064,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-16,8,dominicks,19968,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-16,8,minute.maid,8192,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-16,8,tropicana,7680,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-23,2,dominicks,9152,0,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-23,2,minute.maid,24960,1,2.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-23,2,tropicana,4416,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-23,5,dominicks,5184,0,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-23,5,minute.maid,54528,1,2.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-23,5,tropicana,4992,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-23,8,dominicks,15936,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-23,8,minute.maid,55040,1,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-23,8,tropicana,5440,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-30,2,dominicks,36288,1,1.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-30,2,minute.maid,4544,0,2.86,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-30,2,tropicana,4672,0,3.16,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-30,5,dominicks,42240,1,1.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-30,5,minute.maid,6400,0,2.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-30,5,tropicana,7360,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-30,8,dominicks,76352,1,1.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-30,8,minute.maid,6528,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-30,8,tropicana,5632,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-06,2,dominicks,3776,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-06,2,minute.maid,3968,1,2.81,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-06,2,tropicana,7168,1,3.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-06,5,dominicks,6592,1,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-06,5,minute.maid,5888,1,2.65,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-06,5,tropicana,8384,1,2.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-06,8,dominicks,17408,1,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-06,8,minute.maid,6208,1,2.45,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-06,8,tropicana,8960,1,2.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-13,2,dominicks,3328,0,1.97,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-13,2,minute.maid,49600,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-13,2,tropicana,5056,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-13,5,dominicks,2112,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-13,5,minute.maid,56384,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-13,5,tropicana,8832,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-13,8,dominicks,17536,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-13,8,minute.maid,94720,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-13,8,tropicana,6080,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-20,2,dominicks,13824,0,1.36,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-20,2,minute.maid,23488,1,1.94,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-20,2,tropicana,13376,1,2.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-20,5,dominicks,21248,0,1.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-20,5,minute.maid,27072,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-20,5,tropicana,17728,1,2.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-20,8,dominicks,31232,0,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-20,8,minute.maid,55552,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-20,8,tropicana,8576,1,2.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-27,2,dominicks,9024,0,1.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-27,2,minute.maid,19008,0,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-27,2,tropicana,8128,0,2.75,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-27,5,dominicks,1856,0,1.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-27,5,minute.maid,3840,0,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-27,5,tropicana,9600,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-27,8,dominicks,19200,0,1.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-27,8,minute.maid,18688,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-27,8,tropicana,8000,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-03,2,dominicks,2048,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-03,2,minute.maid,11584,0,1.81,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-03,2,tropicana,19456,1,2.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-03,5,dominicks,3712,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-03,5,minute.maid,6144,0,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-03,5,tropicana,25664,1,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-03,8,dominicks,12800,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-03,8,minute.maid,14656,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-03,8,tropicana,21760,1,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947