revert overwrites

update samples from Release-153 as a part of 1.0.69 SDK release

Dockerfiles/1.0.23/Dockerfile

@@ -0,0 +1,29 @@
+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

@@ -0,0 +1,29 @@
+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

@@ -0,0 +1,29 @@
+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

@@ -0,0 +1,29 @@
+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

@@ -0,0 +1,29 @@
+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"

Licenses/sdk-license/LICENSE

@@ -1,3 +1,4 @@
+    
 This software is made available to you on the condition that you agree to
 [your agreement][1] governing your use of Azure.
 If you do not have an existing agreement governing your use of Azure, you agree that 

NBSETUP.md

@@ -1,6 +1,4 @@
-# Setting up environment
-
----
+# Set up your notebook environment for Azure Machine Learning
 
 To run the notebooks in this repository use one of following options.
 
@@ -12,9 +10,7 @@ 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
-
-    ![set kernel to Python 3.6](images/python36.png)
+    **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.
 
 ## **Option 2: Use your own notebook server**
 
@@ -28,11 +24,8 @@ pip install azureml-sdk
 git clone https://github.com/Azure/MachineLearningNotebooks.git
 
 # below steps are optional
-# install the base SDK and a Jupyter notebook server
-pip install azureml-sdk[notebooks]
-
-# install the data prep component
-pip install azureml-dataprep
+# install the base SDK, Jupyter notebook server and tensorboard
+pip install azureml-sdk[notebooks,tensorboard]
 
 # install model explainability component
 pip install azureml-sdk[explain]
@@ -58,8 +51,7 @@ Please make sure you start with the [Configuration](configuration.ipynb) noteboo
 
 ### Video walkthrough:
 
-[![Get Started video](images/yt_cover.png)](https://youtu.be/VIsXeTuW3FU)
-
+[!VIDEO https://youtu.be/VIsXeTuW3FU]
 
 ## **Option 3: Use Docker**
 
@@ -90,9 +82,6 @@ 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]
 

README.md

@@ -2,7 +2,8 @@
 
 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.
 
-![Azure ML workflow](https://raw.githubusercontent.com/MicrosoftDocs/azure-docs/master/articles/machine-learning/service/media/overview-what-is-azure-ml/aml.png)
+![Azure ML Workflow](https://raw.githubusercontent.com/MicrosoftDocs/azure-docs/master/articles/machine-learning/service/media/concept-azure-machine-learning-architecture/workflow.png)
+
 
 ## Quick installation
 ```sh
@@ -11,7 +12,7 @@ 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.
 
 ## 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. 
+If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, 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. 
 
 If you want to...
 
@@ -20,7 +21,7 @@ If you want to...
  * ...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).
+ * ...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](https://aka.ms/pl-batch-scoring).
  * ...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).
 
 ## Tutorials
@@ -38,6 +39,7 @@ The [How to use Azure ML](./how-to-use-azureml) folder contains specific example
 - [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
+- [Monitor Models](./how-to-use-azureml/monitor-models) - Examples showing how to enable model monitoring services such as DataDrift
 
 ---
 ## Documentation
@@ -48,9 +50,27 @@ The [How to use Azure ML](./how-to-use-azureml) folder contains specific example
 
 ---
 
+
+## Community Repository 
+Visit this [community repository](https://github.com/microsoft/MLOps/tree/master/examples) to find useful end-to-end sample notebooks. Also, please follow these [contribution guidelines](https://github.com/microsoft/MLOps/blob/master/contributing.md) when contributing to this repository.   
+
 ## Projects using Azure Machine Learning
 
 Visit following repos to see projects contributed by Azure ML users:
+ - [AMLSamples](https://github.com/Azure/AMLSamples) Number of end-to-end examples, including face recognition, predictive maintenance, customer churn and sentiment analysis.
+ - [Learn about Natural Language Processing best practices using Azure Machine Learning service](https://github.com/microsoft/nlp)
+ - [Pre-Train BERT 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)
+ - [UMass Amherst Student Samples](https://github.com/katiehouse3/microsoft-azure-ml-notebooks) - A number of end-to-end machine learning notebooks, including machine translation, image classification, and customer churn, created by students in the 696DS course at UMass Amherst.
+ 
+## Data/Telemetry 
+This repository collects usage data and sends it to Mircosoft to help improve our products and services. Read Microsoft's [privacy statement to learn more](https://privacy.microsoft.com/en-US/privacystatement)
 
- - [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)
+To opt out of tracking, please go to the raw markdown or .ipynb files and remove the following line of code:
+
+```sh
+    "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/README.png)"
+```
+This URL will be slightly different depending on the file. 
+
+ ![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/README.png)

configuration.ipynb

@@ -9,6 +9,13 @@
         "Licensed under the MIT License."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/configuration.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -51,7 +58,7 @@
         "\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, inferencing, 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, inference, and the monitoring of deployed models."
       ]
     },
     {
@@ -96,7 +103,7 @@
       "source": [
         "import azureml.core\n",
         "\n",
-        "print(\"This notebook was created using version 1.0.21 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version 1.0.69 of the Azure ML SDK\")\n",
         "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },
@@ -251,7 +258,7 @@
         "```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 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",
+        "* 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",
         "* 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",
@@ -268,14 +275,14 @@
         "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# Choose a name for your CPU cluster\n",
-        "cpu_cluster_name = \"cpucluster\"\n",
+        "cpu_cluster_name = \"cpu-cluster\"\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 cpucluster\")\n",
+        "    print(\"Found existing cpu-cluster\")\n",
         "except ComputeTargetException:\n",
-        "    print(\"Creating new cpucluster\")\n",
+        "    print(\"Creating new cpu-cluster\")\n",
         "    \n",
         "    # Specify the configuration for the new cluster\n",
         "    compute_config = AmlCompute.provisioning_configuration(vm_size=\"STANDARD_D2_V2\",\n",
@@ -306,14 +313,14 @@
         "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# Choose a name for your GPU cluster\n",
-        "gpu_cluster_name = \"gpucluster\"\n",
+        "gpu_cluster_name = \"gpu-cluster\"\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 gpucluster\")\n",
+        "    print(\"Creating new gpu-cluster\")\n",
         "    \n",
         "    # Specify the configuration for the new cluster\n",
         "    compute_config = AmlCompute.provisioning_configuration(vm_size=\"STANDARD_NC6\",\n",

configuration.yml

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

contrib/RAPIDS/README.md

@@ -1,305 +0,0 @@
-## How to use the RAPIDS on AzureML materials
-### Setting up requirements
-The material requires the use of the Azure ML SDK and of the Jupyter Notebook Server to run the interactive execution. Please refer to instructions to [setup the environment.](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-environment#local "Local Computer Set Up") Follow the instructions under **Local Computer**, make sure to run the last step: <span style="font-family: Courier New;">pip install \<new package\></span> with <span style="font-family: Courier New;">new package = progressbar2  (pip install progressbar2)</span>
-  
-After following the directions, the user should end up setting a conda environment (<span style="font-family: Courier New;">myenv</span>)that can be activated in an Anaconda prompt
-
-The user would also require an Azure Subscription with a Machine Learning Services quota on the desired region for 24 nodes or more (to be able to select a vmSize with 4 GPUs as it is used on the Notebook) on the desired VM family ([NC\_v3](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#ncv3-series),  [NC\_v2](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#ncv2-series), [ND](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#nd-series) or [ND_v2](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#ndv2-series-preview)), the specific vmSize to be used within the chosen family would also need to be whitelisted for Machine Learning Services usage.  
-
-&nbsp;  
-### Getting and running the material 
-Clone the AzureML Notebooks repository in GitHub by running the following command on a local_directory: 
-
-* C:\local_directory>git clone https://github.com/Azure/MachineLearningNotebooks.git
-
-On a conda prompt navigate to the local directory, activate the conda environment (<span style="font-family: Courier New;">myenv</span>), where the Azure ML SDK was installed and launch Jupyter Notebook. 
-
-* (<span style="font-family: Courier New;">myenv</span>) C:\local_directory>jupyter notebook
-
-From the resulting browser at http://localhost:8888/tree, navigate to the master notebook: 
-
-* http://localhost:8888/tree/MachineLearningNotebooks/contrib/RAPIDS/azure-ml-with-nvidia-rapids.ipynb
-
-&nbsp;  
-The following notebook will appear:  
-
-![](imgs/NotebookHome.png)
-
-&nbsp;  
-### Master Jupyter Notebook
-The notebook can be executed interactively step by step, by pressing the Run button (In a red circle in the above image.)
-
-The first couple of functional steps import the necessary AzureML libraries.  If you experience any errors please refer back to the [setup the environment.](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-environment#local "Local Computer Set Up") instructions.
-
-&nbsp;  
-#### Setting up a Workspace
-The following step gathers the information necessary to set up a workspace to execute the RAPIDS script. This needs to be done only once, or not at all if you already have a workspace you can use set up on the Azure Portal:
-
-![](imgs/WorkSpaceSetUp.png)
-
-
-It is important to be sure to set the correct values for the subscription\_id, resource\_group, workspace\_name, and region before executing the step. An example is:
-
-    subscription_id = os.environ.get("SUBSCRIPTION_ID", "1358e503-xxxx-4043-xxxx-65b83xxxx32d")
-    resource_group = os.environ.get("RESOURCE_GROUP", "AML-Rapids-Testing")
-    workspace_name = os.environ.get("WORKSPACE_NAME", "AML_Rapids_Tester")
-    workspace_region = os.environ.get("WORKSPACE_REGION", "West US 2")
-
-&nbsp;  
-The resource\_group and workspace_name could take any value, the region should match the region for which the subscription has the required Machine Learning Services node quota.
-
-The first time the code is executed it will redirect to the Azure Portal to validate subscription credentials. After the workspace is created, its related information is stored on a local file so that this step can be subsequently skipped. The immediate step will just load the saved workspace
-
-![](imgs/saved_workspace.png)
-
-Once a workspace has been created the user could skip its creation and just jump to this step. The configuration file resides in:
-
-* C:\local_directory\\MachineLearningNotebooks\contrib\RAPIDS\aml_config\config.json
-
-&nbsp;  
-#### Creating an AML Compute Target 
-Following step, creates an AML Compute Target 
-
-![](imgs/target_creation.png)
-
-Parameter vm\_size on function call AmlCompute.provisioning\_configuration() has to be a member of the VM families ([NC\_v3](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#ncv3-series),  [NC\_v2](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#ncv2-series), [ND](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#nd-series) or [ND_v2](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#ndv2-series-preview)) that are the ones provided with P40 or V100 GPUs, that are the ones supported by RAPIDS. In this particular case an Standard\_NC24s\_V2 was used.
-
-&nbsp;  
-If the output of running the step has an error of the form:
-
-![](imgs/targeterror1.png)
-
-It is an indication that even though the subscription has a node quota for VMs for that family, it does not have a node quota for Machine Learning Services for that family. 
-You will need to request an increase node quota for that family in that region for **Machine Learning Services**.
-
-&nbsp;  
-Another possible error is the following: 
-
-![](imgs/targeterror2.png)
-
-Which indicates that specified vmSize has not been whitelisted for usage on Machine Learning Services and a request to do so should be filled.
-
-The successful creation of the compute target would have an output like the following:
-
-![](imgs/targetsuccess.png)
-&nbsp;  
-#### RAPIDS script uploading and viewing
-The next step copies the RAPIDS script process_data.py, which is a slightly modified implementation of the [RAPIDS E2E example](https://github.com/rapidsai/notebooks/blob/master/mortgage/E2E.ipynb), into a script processing folder and it presents its contents to the user. (The script is discussed in the next section in detail). 
-If the user wants to use a different RAPIDS script, the references to the  <span style="font-family: Courier New;">process_data.py</span> script have to be changed
-
-![](imgs/scriptuploading.png)
-&nbsp;  
-#### Data Uploading
-The RAPIDS script loads and extracts features from the Fannie Mae’s Mortgage Dataset to train an XGBoost prediction model. The script uses two years of data
-
-The next few steps download and decompress the data and is made available to the  script as an [Azure Machine Learning Datastore](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-access-data).
-
-&nbsp;  
-The following functions are used to download and decompress the input data
-
-
-![](imgs/dcf1.png)
-![](imgs/dcf2.png)
-![](imgs/dcf3.png)
-![](imgs/dcf4.png)
-
-&nbsp;  
-The next step uses those functions to download locally file: 
-http://rapidsai-data.s3-website.us-east-2.amazonaws.com/notebook-mortgage-data/mortgage_2000-2001.tgz'
-And to decompress it, into local folder path = .\mortgage_2000-2001
-The step takes several minutes, the intermediate outputs provide progress indicators.
-
-![](imgs/downamddecom.png)
-
-&nbsp;  
-The decompressed data should have the following structure:
-* .\mortgage_2000-2001\acq\Acquisition_<year>Q<num>.txt 
-* .\mortgage_2000-2001\perf\Performance_<year>Q<num>.txt 
-* .\mortgage_2000-2001\names.csv
-
-The data is divided in partitions that roughly correspond to yearly quarters. RAPIDS includes support for multi-node, multi-GPU deployments, enabling scaling up and out on much larger dataset sizes. The user will be able to verify that the number of partitions that the script is able to process increases with the number of GPUs used. The RAPIDS script is implemented for single-machine scenarios. An example supporting multiple nodes will be published later. 
-
-&nbsp;  
-The next step upload the data into the [Azure Machine Learning Datastore](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-access-data) under reference <span style="font-family: Courier New;">fileroot = mortgage_2000-2001</span>
-
-The step takes several minutes to load the data, the output provides a progress indicator.
-
-![](imgs/datastore.png)
-
-Once the data has been loaded into the Azure Machine LEarning Data Store, in subsequent run, the user can comment out the ds.upload line and just make reference to the <span style="font-family: Courier New;">mortgage_2000-2001</blog> data store reference  
-
-&nbsp;  
-#### Setting up required libraries and environment to run RAPIDS code
-There are two options to setup the environment to run RAPIDS code. The following steps shows how to ues a prebuilt conda environment. A recommended alternative is to specify a base Docker image and package dependencies. You can find sample code for that in the notebook.
-
-![](imgs/install2.png)
-
-&nbsp;  
-#### Wrapper function to submit the RAPIDS script as an Azure Machine Learning experiment
-
-The next step consists of the definition of a wrapper function to be used when the user attempts to run the RAPIDS script with different arguments. It takes as arguments: <span style="font-family: Times New Roman;">*cpu\_training*</span>;  a flag that indicates if the run is meant to be processed with CPU-only, <span style="font-family: Times New Roman;">*gpu\_count*</span>; the number of GPUs to be used if they are meant to be used and part_count: the number of data partitions to be used
-
-![](imgs/wrapper.png)
-
-&nbsp;  
-The core of the function resides in configuring the run by the instantiation of a ScriptRunConfig object, which defines the source_directory for the script to be executed, the name of the script and the arguments to be passed to the script.
-In addition to the wrapper function arguments, two other arguments are passed: <span style="font-family: Times New Roman;">*data\_dir*</span>, the directory where the data is stored and <span style="font-family: Times New Roman;">*end_year*</span> is the largest year to use partition from.
-
-
-As mentioned earlier the size of the data that can be processed increases with the number of gpus, in the function, dictionary <span style="font-family: Times New Roman;">*max\_gpu\_count\_data\_partition_mapping*</span> maps the maximum number of partitions that we empirically found that the system can handle given the number of GPUs used. The function throws a warning when the number of partitions for a given number of gpus exceeds the maximum but the script is still executed, however the user should expect an error as an out of memory situation would be encountered
-If the user wants to use a different RAPIDS script, the reference to the process_data.py script has to be changed
-
-&nbsp;  
-#### Submitting Experiments
-We are ready to submit experiments: launching the RAPIDS script with different sets of parameters.
-
-&nbsp;  
-The following couple of steps submit experiments under different conditions. 
-
-![](imgs/submission1.png)
-
-&nbsp;  
-The user can change variable num\_gpu between one and the number of GPUs supported by the chosen vmSize. Variable part\_count can take any value between 1 and 11, but if it exceeds the maximum for num_gpu, the run would result in an error
-
-&nbsp;  
-If the experiment is successfully submitted, it would be placed on a queue for processing, its status would appeared as Queued and an output like the following would appear 
-
-![](imgs/queue.png)
-
-&nbsp;  
-When the experiment starts running, its status would appeared as Running and the output would change to something like this:
-
-![](imgs/running.png)
-
-&nbsp;  
-#### Reproducing the performance gains plot results on the Blog Post
-When the run has finished successfully, its status would appeared as Completed and the output would change to something like this:
-
-&nbsp; 
-![](imgs/completed.png)
-
-Which is the output for an experiment run with three partitions and one GPU, notice that the reported processing time is 49.16 seconds just as depicted on the performance gains plot on the blog post
-
-&nbsp;  
-
-![](imgs/2GPUs.png)
-
-
-This output corresponds to a run with three partitions and two GPUs, notice that the reported processing time is 37.50 seconds just as depicted on the performance gains plot on the blog post
-
-&nbsp;  
-![](imgs/3GPUs.png)
-
-This output corresponds to an experiment run with three partitions and three GPUs, notice that the reported processing time is 24.40 seconds just as depicted on the performance gains plot on the blog post
-
-&nbsp;  
-![](imgs/4gpus.png)
-
-This output corresponds to an experiment run with three partitions and four GPUs, notice that the reported processing time is 23.33 seconds just as depicted on the performance gains plot on the blogpost
-
-&nbsp;  
-![](imgs/CPUBase.png)
-
-This output corresponds to an experiment run with three partitions and using only CPU, notice that the reported processing time is 9 minutes and 1.21 seconds or 541.21 second just as depicted on the performance gains plot on the blog post
-
-&nbsp;  
-![](imgs/OOM.png)
-
-This output corresponds to an experiment run with nine partitions and four GPUs, notice that the notebook throws a warning signaling that the number of partitions exceed the maximum that the system can handle with those many GPUs and the run ends up failing, hence having and status of Failed. 
-
-&nbsp;  
-##### Freeing Resources
-In the last step the notebook deletes the compute target. (This step is optional especially if the min_nodes in the cluster is set to 0 with which the cluster will scale down to 0 nodes when there is no usage.)
-
-![](imgs/clusterdelete.png)
-
-&nbsp;  
-### RAPIDS Script
-The Master Notebook runs experiments by launching a RAPIDS script with different sets of parameters. In this section, the RAPIDS script, process_data.py in the material, is analyzed
-
-The script first imports all the necessary libraries and parses the arguments passed by the Master Notebook.
-
-The all internal functions to be used by the script are defined.
-
-&nbsp;  
-#### Wrapper Auxiliary Functions:
-The below functions are wrappers for a configuration module for librmm, the RAPIDS Memory Manager python interface:
-
-![](imgs/wap1.png)![](imgs/wap2.png)
-
-&nbsp;  
-A couple of other functions are wrappers for the submission of jobs to the DASK client:
-
-![](imgs/wap3.png)
-![](imgs/wap4.png)
-
-&nbsp;  
-#### Data Loading Functions:
-The data is loaded through the use of the following three functions 
-
-![](imgs/DLF1.png)![](imgs/DLF2.png)![](imgs/DLF3.png)
-
-All three functions use library function cudf.read_csv(), cuDF version for the well known counterpart on Pandas.
-
-&nbsp;  
-#### Data Transformation and Feature Extraction Functions:
-The raw data is transformed and processed to extract features by joining, slicing, grouping, aggregating, factoring, etc, the original dataframes just as is done with Pandas. The following functions in the script are used for that purpose:
-![](imgs/fef1.png)![](imgs/fef2.png)![](imgs/fef3.png)![](imgs/fef4.png)![](imgs/fef5.png)
-
-![](imgs/fef6.png)![](imgs/fef7.png)![](imgs/fef8.png)![](imgs/fef9.png)
-
-&nbsp;  
-#### Main() Function
-The previous functions are used in the Main function to accomplish several steps: Set up the Dask client, do all ETL operations, set up and train an XGBoost model, the function also assigns which data needs to be processed by each Dask client
-
-&nbsp;  
-##### Setting Up DASK client:
-The following lines:
-
-![](imgs/daskini.png)
-
-&nbsp;  
-Initialize and set up a DASK client with a number of workers corresponding to the number of GPUs to be used on the run. A successful execution of the set up will result on the following output:
-
-![](imgs/daskoutput.png)
-
-##### All ETL functions are used on single calls to process\_quarter_gpu, one per data partition
-
-![](imgs/ETL.png)
-
-&nbsp;  
-##### Concentrating the data assigned to each DASK worker
-The partitions assigned to each worker are concatenated and set up for training.
-
-![](imgs/Dask2.png)
-
-&nbsp;  
-##### Setting Training Parameters
-The parameters used for the training of a gradient boosted decision tree model are set up in the following code block:
-![](imgs/PArameters.png)
-
-Notice how the parameters are modified when using the CPU-only mode.
-
-&nbsp;  
-##### Launching the training of a gradient boosted decision tree model using XGBoost.
-
-![](imgs/training.png)
-
-The outputs of the script can be observed in the master notebook as the script is executed
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-

contrib/RAPIDS/process_data.py

@@ -15,21 +15,6 @@ 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
@@ -207,26 +192,26 @@ 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()
+    everdf = everdf.groupby('loan_id', method='hash').max().reset_index()
     del(gdf)
-    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')
+    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')
     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()
-    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')
+    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')
     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]'))
@@ -279,16 +264,15 @@ 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'})
-        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 = 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['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')
@@ -329,6 +313,7 @@ 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():
@@ -342,7 +327,6 @@ 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)
@@ -364,7 +348,6 @@ 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))
     
@@ -380,19 +363,17 @@ 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(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('--->>> 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("Reading ...")
     t1 = datetime.datetime.now()
     gpu_dfs = []
@@ -414,14 +395,9 @@ def main():
             
     wait(gpu_dfs)
     t2 = datetime.datetime.now()
-    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())
+    print("Reading time: {0}".format(str(t2-t1)))
+    print('--->>> Number of data parts: {0}'.format(len(gpu_dfs)))
+
     dxgb_gpu_params = {
         'nround':            100,
         'max_depth':         8,
@@ -438,7 +414,7 @@ def main():
         'n_gpus':            1, 
         'distributed_dask':  True,
         'loss':              'ls',
-        'objective':         'gpu:reg:linear',
+        'objective':         'reg:squarederror',
         'max_features':      'auto',
         'criterion':         'friedman_mse',
         'grow_policy':       'lossguide',
@@ -446,13 +422,13 @@ def main():
     }
       
     if cpu_predictor:
-        print('Training using CPUs')
+        print('\n---->>>> Training using CPUs <<<<----\n')
         dxgb_gpu_params['predictor'] = 'cpu_predictor'
         dxgb_gpu_params['tree_method'] = 'hist'
         dxgb_gpu_params['objective'] = 'reg:linear'
         
     else:
-        print('Training using GPUs')
+        print('\n---->>>> Training using GPUs <<<<----\n')
     
     print('Training parameters are {0}'.format(dxgb_gpu_params))
     
@@ -481,14 +457,13 @@ 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("Training time ...")
-    print(t2-t1)
-    print('str(bst) is {0}'.format(str(bst)))
+    print('\n---->>>> Training time: {0} <<<<----\n'.format(str(t2-t1)))
     print('Exiting script')
 
 if __name__ == '__main__':

contrib/RAPIDS/rapids.yml

@@ -1,35 +0,0 @@
-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

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

how-to-use-azureml/README.md

@@ -8,7 +8,7 @@ As a pre-requisite, run the [configuration Notebook](../configuration.ipynb) not
 * [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](./training/logging-api): Learn about the details of logging metrics to run history.
+* [logging-api](./track-and-monitor-experiments/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.

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

@@ -1,8 +1,8 @@
 # Table of Contents
 1. [Automated ML Introduction](#introduction)
-1. [Running samples in Azure Notebooks](#jupyter)
-1. [Running samples in Azure Databricks](#databricks)
-1. [Running samples in a Local Conda environment](#localconda)
+1. [Setup using Azure Notebooks](#jupyter)
+1. [Setup using Azure Databricks](#databricks)
+1. [Setup using a Local Conda environment](#localconda)
 1. [Automated ML SDK Sample Notebooks](#samples)
 1. [Documentation](#documentation)
 1. [Running using python command](#pythoncommand)
@@ -13,15 +13,15 @@
 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, 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 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 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.
+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.
 
-Below are the three execution environments supported by AutoML.
+Below are the three execution environments supported by automated ML.
 
 
  <a name="jupyter"></a>
-## Running samples in Azure Notebooks - Jupyter based notebooks in the Azure cloud
+## Setup using Azure Notebooks - Jupyter based notebooks in the Azure cloud
 
 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.
@@ -29,7 +29,7 @@ Below are the three execution environments supported by AutoML.
 1. Open one of the sample notebooks.
 
  <a name="databricks"></a>
-## Running samples in Azure Databricks
+## Setup using 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.
@@ -39,7 +39,7 @@ Below are the three execution environments supported by AutoML.
 - Attach the notebook to the cluster.
 
 <a name="localconda"></a>
-## Running samples in a Local Conda environment
+## 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.
@@ -49,11 +49,15 @@ 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 AutoML sample notebooks are in the "automl" folder.
+- 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/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.
+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)
 ## 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:
 ```
@@ -81,7 +85,7 @@ 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 AutoML
+- 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:
@@ -103,37 +107,22 @@ jupyter notebook
 
 - [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
+    - Simple example of using automated ML for classification
     - Uses local compute for training
 
 - [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
+    - Simple example of using automated ML for regression
     - Uses local compute for training
 
-- [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)
+- [auto-ml-remote-amlcompute.ipynb](remote-amlcompute/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
+    - Specify automated ML settings as kwargs
 
 - [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)
@@ -148,17 +137,13 @@ jupyter notebook
 
 - [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)
+    - List all automated ML Runs for a given project
+    - Get details for a automated ML Run. (automated ML 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
+    - Simple example of using automated ML for classification
     - Registering the model
     - Creating Image and creating aci service
     - Testing the aci service
@@ -170,24 +155,58 @@ jupyter notebook
 - [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-dataset.ipynb](dataprep/auto-ml-dataset.ipynb)
+    - Using Dataset 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-dataset-remote-execution.ipynb](dataprep-remote-execution/auto-ml-dataset-remote-execution.ipynb)
+    - Using Dataset 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.
+    - Simple example of using automated 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
+    - Example of using automated ML 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
+    - Example of training an automated ML forecasting model on multiple time-series
+
+- [auto-ml-classification-with-onnx.ipynb](classification-with-onnx/auto-ml-classification-with-onnx.ipynb)
+    - Dataset: scikit learn's [iris dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_iris.html)
+    - Simple example of using automated ML for classification with ONNX models
+    - Uses local compute for training
+
+- [auto-ml-remote-amlcompute-with-onnx.ipynb](remote-amlcompute-with-onnx/auto-ml-remote-amlcompute-with-onnx.ipynb)
+    - Dataset: scikit learn's [iris dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_iris.html)
+    - Example of using automated ML for classification using remote AmlCompute for training
+    - Train the models with ONNX compatible config on
+    - Parallel execution of iterations
+    - Async tracking of progress
+    - Cancelling individual iterations or entire run
+    - Retrieving the ONNX models and do the inference with them
+
+- [auto-ml-bank-marketing-subscribers-with-deployment.ipynb](bank-marketing-subscribers-with-deployment/auto-ml-bank-marketing-with-deployment.ipynb)
+    - Dataset: UCI's [bank marketing dataset](https://www.kaggle.com/janiobachmann/bank-marketing-dataset)
+    - Simple example of using automated ML for classification to predict term deposit subscriptions for a bank
+    - Uses azure compute for training
+
+- [auto-ml-creditcard-with-deployment.ipynb](credit-card-fraud-detection-with-deployment/auto-ml-creditcard-with-deployment.ipynb)
+    - Dataset: Kaggle's [credit card fraud detection dataset](https://www.kaggle.com/mlg-ulb/creditcardfraud)
+    - Simple example of using automated ML for classification to fraudulent credit card transactions
+    - Uses azure compute for training
+
+- [auto-ml-hardware-performance-with-deployment.ipynb](hardware-performance-prediction-with-deployment/auto-ml-hardware-performance-with-deployment.ipynb)
+    - Dataset: UCI's [computer hardware dataset](https://archive.ics.uci.edu/ml/datasets/Computer+Hardware)
+    - Simple example of using automated ML for regression to predict the performance of certain combinations of hardware components
+    - Uses azure compute for training
+
+- [auto-ml-concrete-strength-with-deployment.ipynb](predicting-concrete-strength-with-deployment/auto-ml-concrete-strength-with-deployment.ipynb)
+    - Dataset: UCI's [concrete compressive strength dataset](https://www.kaggle.com/pavanraj159/concrete-compressive-strength-data-set)
+    - Simple example of using automated ML for regression to predict the strength  predict the compressive strength of concrete based off of different ingredient combinations and quantities of those ingredients
+    - Uses azure compute for training
 
 <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.
@@ -206,10 +225,18 @@ 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 4.4.10 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>`. 
+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.
 
 ## configuration.ipynb fails
 1) For local conda, make sure that you have susccessfully run automl_setup first.
@@ -233,13 +260,20 @@ 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.
 
-## Remote run: DsvmCompute.create fails 
+## 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.
+
+## 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
-AutoML uses the SSH protocol to communicate with remote DSVMs.  This defaults to port 22.  Possible causes for this error are:
+Automated ML 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.
 
@@ -250,16 +284,16 @@ 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
-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.
+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.
 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.  AutoML 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.  Automated ML 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

@@ -1,22 +1,27 @@
-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
-  
+name: azure_automl
+dependencies:
+  # The python interpreter version.
+  # Currently Azure ML only supports 3.5.2 and later.
+- pip
+- python>=3.5.2,<3.6.8
+- nb_conda
+- matplotlib==2.1.0
+- numpy>=1.16.0,<=1.16.2
+- cython
+- urllib3<1.24
+- scipy>=1.0.0,<=1.1.0
+- scikit-learn>=0.19.0,<=0.20.3
+- pandas>=0.22.0,<=0.23.4
+- py-xgboost<=0.80
+- pyarrow>=0.11.0
+- conda-forge::fbprophet==0.5
+
+- pip:
+  # Required packages for AzureML execution, history, and data preparation.
+  - azureml-defaults
+  - azureml-train-automl
+  - azureml-widgets
+  - azureml-explain-model
+  - azureml-contrib-interpret
+  - pandas_ml
+  

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

@@ -1,23 +1,28 @@
-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
-  
-
+name: azure_automl
+dependencies:
+  # The python interpreter version.
+  # Currently Azure ML only supports 3.5.2 and later.
+- pip
+- nomkl
+- python>=3.5.2,<3.6.8
+- nb_conda
+- matplotlib==2.1.0
+- numpy>=1.16.0,<=1.16.2
+- cython
+- urllib3<1.24
+- scipy>=1.0.0,<=1.1.0
+- scikit-learn>=0.19.0,<=0.20.3
+- pandas>=0.22.0,<0.23.0
+- py-xgboost<=0.80
+- pyarrow>=0.11.0
+- conda-forge::fbprophet==0.5
+
+- pip:
+  # Required packages for AzureML execution, history, and data preparation.
+  - azureml-defaults
+  - azureml-train-automl
+  - azureml-widgets
+  - azureml-explain-model
+  - azureml-contrib-interpret
+  - pandas_ml
+  

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

@@ -1,51 +1,62 @@
-@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
-
+@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
+
+IF "%CONDA_EXE%"=="" GOTO CondaMissing
+
+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
+
+: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/automl_setup_mac.sh

@@ -31,7 +31,6 @@ 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/classification-bank-marketing/auto-ml-classification-bank-marketing.ipynb

@@ -0,0 +1,655 @@
+{
+  "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-bank-marketing/auto-ml-classification-bank-marketing.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "_**Classification with Deployment using a Bank Marketing Dataset**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Train](#Train)\n",
+        "1. [Results](#Results)\n",
+        "1. [Deploy](#Deploy)\n",
+        "1. [Test](#Test)\n",
+        "1. [Acknowledgements](#Acknowledgements)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "\n",
+        "In this example we use the UCI Bank Marketing dataset to showcase how you can use AutoML for a  classification problem and deploy it to an Azure Container Instance (ACI). The classification goal is to predict if the client will subscribe to a term deposit with the bank.\n",
+        "\n",
+        "If you are using an Azure Machine Learning Notebook VM, 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 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 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": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "# choose a name for experiment\n",
+        "experiment_name = 'automl-classification-bmarketing'\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['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": [
+        "## Create or Attach existing AmlCompute\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",
+        "#### 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 on the default limits and how to request more quota."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.compute import AmlCompute\n",
+        "from azureml.core.compute import ComputeTarget\n",
+        "\n",
+        "# Choose a name for your cluster.\n",
+        "amlcompute_cluster_name = \"automlcl\"\n",
+        "\n",
+        "found = False\n",
+        "# Check if this compute target already exists in the workspace.\n",
+        "cts = ws.compute_targets\n",
+        "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
+        "    found = True\n",
+        "    print('Found existing compute target.')\n",
+        "    compute_target = cts[amlcompute_cluster_name]\n",
+        "    \n",
+        "if not found:\n",
+        "    print('Creating a new compute target...')\n",
+        "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
+        "                                                                #vm_priority = 'lowpriority', # optional\n",
+        "                                                                max_nodes = 6)\n",
+        "\n",
+        "    # Create the cluster.\n",
+        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
+        "    \n",
+        "print('Checking cluster status...')\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(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
+        "    \n",
+        "# For a more detailed view of current AmlCompute status, use get_status()."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Data\n",
+        "\n",
+        "Create a run configuration for the remote run."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.runconfig import RunConfiguration\n",
+        "from azureml.core.conda_dependencies import CondaDependencies\n",
+        "import pkg_resources\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",
+        "conda_run_config.environment.docker.enabled = True\n",
+        "\n",
+        "cd = CondaDependencies.create(conda_packages=['numpy','py-xgboost<=0.80'])\n",
+        "conda_run_config.environment.python.conda_dependencies = cd"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Load Data\n",
+        "\n",
+        "Load the bank marketing 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."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_train.csv\"\n",
+        "dataset = Dataset.Tabular.from_delimited_files(data)\n",
+        "dataset.take(5).to_pandas_dataframe()"
+      ]
+    },
+    {
+      "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",
+        "|**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": {},
+      "outputs": [],
+      "source": [
+        "automl_settings = {\n",
+        "    \"iteration_timeout_minutes\": 5,\n",
+        "    \"iterations\": 10,\n",
+        "    \"n_cross_validations\": 2,\n",
+        "    \"primary_metric\": 'AUC_weighted',\n",
+        "    \"preprocess\": True,\n",
+        "    \"max_concurrent_iterations\": 5,\n",
+        "    \"verbosity\": logging.INFO,\n",
+        "}\n",
+        "\n",
+        "automl_config = AutoMLConfig(task = 'classification',\n",
+        "                             debug_log = 'automl_errors.log',\n",
+        "                             run_configuration=conda_run_config,\n",
+        "                             training_data = dataset,\n",
+        "                             label_column_name = 'y',\n",
+        "                             **automl_settings\n",
+        "                            )"
+      ]
+    },
+    {
+      "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": [
+        "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": [
+        "## 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 = remote_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 trained on bank marketing data to predict if a client will subscribe to a term deposit'\n",
+        "tags = None\n",
+        "model = remote_run.register_model(description = description, tags = tags)\n",
+        "\n",
+        "print(remote_run.model_id) # This will be written to the script file later in the notebook."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create Scoring Script\n",
+        "The scoring script is required to generate the image for deployment. It contains the code to do the predictions on input data."
+      ]
+    },
+    {
+      "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 = np.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": [
+        "dependencies = remote_run.get_run_sdk_dependencies(iteration = 1)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "for p in ['azureml-train-automl', 'azureml-core']:\n",
+        "    print('{}\\t{}'.format(p, dependencies[p]))"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn','py-xgboost<=0.80'],\n",
+        "                                 pip_packages=['azureml-defaults','azureml-train-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-train-automl']))\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>>', remote_run.model_id))"
+      ]
+    },
+    {
+      "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(runtime = \"python\", \n",
+        "                                   entry_script = script_file_name,\n",
+        "                                   conda_file = conda_env_file_name)\n",
+        "\n",
+        "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
+        "                                               memory_gb = 1, \n",
+        "                                               tags = {'area': \"bmData\", 'type': \"automl_classification\"}, \n",
+        "                                               description = 'sample service for Automl Classification')\n",
+        "\n",
+        "aci_service_name = 'automl-sample-bankmarketing'\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": "markdown",
+      "metadata": {},
+      "source": [
+        "### Delete a Web Service\n",
+        "\n",
+        "Deletes the specified 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\n",
+        "\n",
+        "Gets 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\n",
+        "\n",
+        "Now that the model is trained split our 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": [
+        "# Load the bank marketing datasets.\n",
+        "from numpy import array"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_validate.csv\"\n",
+        "dataset = Dataset.Tabular.from_delimited_files(data)\n",
+        "X_test = dataset.drop_columns(columns=['y'])\n",
+        "y_test = dataset.keep_columns(columns=['y'], validate=True)\n",
+        "dataset.take(5).to_pandas_dataframe()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X_test = X_test.to_pandas_dataframe()\n",
+        "y_test = y_test.to_pandas_dataframe()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "y_pred  = fitted_model.predict(X_test)\n",
+        "actual = array(y_test)\n",
+        "actual = actual[:,0]\n",
+        "print(y_pred.shape, \" \", actual.shape)"
+      ]
+    },
+    {
+      "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": [
+        "%matplotlib notebook\n",
+        "test_pred = plt.scatter(actual, y_pred, color='b')\n",
+        "test_test = plt.scatter(actual, actual, color='g')\n",
+        "plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
+        "plt.show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Acknowledgements"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "This Bank Marketing dataset is made available under the Creative Commons (CCO: Public Domain) License: https://creativecommons.org/publicdomain/zero/1.0/. Any rights in individual contents of the database are licensed under the Database Contents License: https://creativecommons.org/publicdomain/zero/1.0/ and is available at: https://www.kaggle.com/janiobachmann/bank-marketing-dataset .\n",
+        "\n",
+        "_**Acknowledgements**_\n",
+        "This data set is originally available within the UCI Machine Learning Database: https://archive.ics.uci.edu/ml/datasets/bank+marketing\n",
+        "\n",
+        "[Moro et al., 2014] S. Moro, P. Cortez and P. Rita. A Data-Driven Approach to Predict the Success of Bank Telemarketing. Decision Support Systems, Elsevier, 62:22-31, June 2014"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "v-rasav"
+      }
+    ],
+    "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": "3.6.7"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/classification-bank-marketing/auto-ml-classification-bank-marketing.yml

@@ -0,0 +1,11 @@
+name: auto-ml-classification-bank-marketing
+dependencies:
+- pip:
+  - azureml-sdk
+  - interpret
+  - azureml-defaults
+  - azureml-explain-model
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml

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

@@ -0,0 +1,648 @@
+{
+  "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 with Deployment using Credit Card Dataset**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Train](#Train)\n",
+        "1. [Results](#Results)\n",
+        "1. [Deploy](#Deploy)\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 and deploy it to an Azure Container Instance (ACI). The classification goal is to predict if a creditcard transaction  is or is not considered a fraudulent charge.\n",
+        "\n",
+        "If you are using an Azure Machine Learning Notebook VM, 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 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 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": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "# choose a name for experiment\n",
+        "experiment_name = 'automl-classification-ccard'\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['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": [
+        "## Create or Attach existing AmlCompute\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",
+        "#### 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 on the default limits and how to request more quota."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.compute import AmlCompute\n",
+        "from azureml.core.compute import ComputeTarget\n",
+        "\n",
+        "# Choose a name for your cluster.\n",
+        "amlcompute_cluster_name = \"automlcl\"\n",
+        "\n",
+        "found = False\n",
+        "# Check if this compute target already exists in the workspace.\n",
+        "cts = ws.compute_targets\n",
+        "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
+        "    found = True\n",
+        "    print('Found existing compute target.')\n",
+        "    compute_target = cts[amlcompute_cluster_name]\n",
+        "    \n",
+        "if not found:\n",
+        "    print('Creating a new compute target...')\n",
+        "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
+        "                                                                #vm_priority = 'lowpriority', # optional\n",
+        "                                                                max_nodes = 6)\n",
+        "\n",
+        "    # Create the cluster.\n",
+        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
+        "    \n",
+        "print('Checking cluster status...')\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(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
+        "\n",
+        "# For a more detailed view of current AmlCompute status, use get_status()."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Data\n",
+        "\n",
+        "Create a run configuration for the remote run."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.runconfig import RunConfiguration\n",
+        "from azureml.core.conda_dependencies import CondaDependencies\n",
+        "import pkg_resources\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",
+        "conda_run_config.environment.docker.enabled = True\n",
+        "\n",
+        "cd = CondaDependencies.create(conda_packages=['numpy','py-xgboost<=0.80'])\n",
+        "conda_run_config.environment.python.conda_dependencies = cd"
+      ]
+    },
+    {
+      "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": {},
+      "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'\n",
+        "X_test = validation_data.drop_columns(columns=[label_column_name])\n",
+        "y_test = validation_data.keep_columns(columns=[label_column_name], validate=True)\n"
+      ]
+    },
+    {
+      "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",
+        "|**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": "markdown",
+      "metadata": {},
+      "source": [
+        "##### If you would like to see even better results increase \"iteration_time_out minutes\" to 10+ mins and increase \"iterations\" to a minimum of 30"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "automl_settings = {\n",
+        "    \"iteration_timeout_minutes\": 5,\n",
+        "    \"iterations\": 10,\n",
+        "    \"n_cross_validations\": 2,\n",
+        "    \"primary_metric\": 'average_precision_score_weighted',\n",
+        "    \"preprocess\": True,\n",
+        "    \"max_concurrent_iterations\": 5,\n",
+        "    \"verbosity\": logging.INFO,\n",
+        "}\n",
+        "\n",
+        "automl_config = AutoMLConfig(task = 'classification',\n",
+        "                             debug_log = 'automl_errors.log',\n",
+        "                             run_configuration=conda_run_config,\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. 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": [
+        "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": [
+        "## 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 = remote_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 = remote_run.register_model(description = description, tags = tags)\n",
+        "\n",
+        "print(remote_run.model_id) # This will be written to the script file later in the notebook."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create Scoring Script\n",
+        "The scoring script is required to generate the image for deployment. It contains the code to do the predictions on input data."
+      ]
+    },
+    {
+      "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",
+        "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": [
+        "dependencies = remote_run.get_run_sdk_dependencies(iteration = 1)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "for p in ['azureml-train-automl', 'azureml-core']:\n",
+        "    print('{}\\t{}'.format(p, dependencies[p]))"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn','py-xgboost<=0.80'],\n",
+        "                                 pip_packages=['azureml-defaults','azureml-train-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-train-automl']))\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>>', remote_run.model_id))"
+      ]
+    },
+    {
+      "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(runtime = \"python\", \n",
+        "                                   entry_script = script_file_name,\n",
+        "                                   conda_file = conda_env_file_name)\n",
+        "\n",
+        "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
+        "                                               memory_gb = 1, \n",
+        "                                               tags = {'area': \"cards\", 'type': \"automl_classification\"}, \n",
+        "                                               description = 'sample service for Automl Classification')\n",
+        "\n",
+        "aci_service_name = 'automl-sample-creditcard'\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": "markdown",
+      "metadata": {},
+      "source": [
+        "### Delete a Web Service\n",
+        "\n",
+        "Deletes the specified 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\n",
+        "\n",
+        "Gets 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\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": [
+        "#Randomly select and test\n",
+        "X_test = X_test.to_pandas_dataframe()\n",
+        "y_test = y_test.to_pandas_dataframe()\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "y_pred = fitted_model.predict(X_test)\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": [
+        "#Randomly select and test\n",
+        "# Plot outputs\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()\n",
+        "\n"
+      ]
+    },
+    {
+      "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",
+        "\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. 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",
+        "Please cite the following works: \n",
+        "\u00e2\u20ac\u00a2\tAndrea 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",
+        "\u00e2\u20ac\u00a2\tDal 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",
+        "\u00e2\u20ac\u00a2\tDal 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",
+        "o\tDal Pozzolo, Andrea Adaptive Machine learning for credit card fraud detection ULB MLG PhD thesis (supervised by G. Bontempi)\n",
+        "\u00e2\u20ac\u00a2\tCarcillo, 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",
+        "\u00e2\u20ac\u00a2\tCarcillo, 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"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "v-rasav"
+      }
+    ],
+    "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": "3.6.7"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

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

@@ -0,0 +1,11 @@
+name: auto-ml-classification-credit-card-fraud
+dependencies:
+- pip:
+  - azureml-sdk
+  - interpret
+  - azureml-defaults
+  - azureml-explain-model
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml

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

@@ -9,6 +9,13 @@
         "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-with-deployment/auto-ml-classification-with-deployment.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -85,8 +92,6 @@
         "\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",
@@ -96,7 +101,6 @@
         "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",
@@ -119,8 +123,7 @@
         "|**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.|"
+        "|**y**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|"
       ]
     },
     {
@@ -139,11 +142,9 @@
         "                             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)"
+        "                             y = y_train)"
       ]
     },
     {
@@ -263,7 +264,7 @@
       "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)."
+        "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. The following cells create a file, myenv.yml, which specifies the dependencies from the run."
       ]
     },
     {
@@ -291,7 +292,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "for p in ['azureml-train-automl', 'azureml-sdk', 'azureml-core']:\n",
+        "for p in ['azureml-train-automl', 'azureml-core']:\n",
         "    print('{}\\t{}'.format(p, dependencies[p]))"
       ]
     },
@@ -303,7 +304,8 @@
       "source": [
         "from azureml.core.conda_dependencies import CondaDependencies\n",
         "\n",
-        "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn'], pip_packages=['azureml-sdk[automl]'])\n",
+        "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn','py-xgboost<=0.80'],\n",
+        "                                 pip_packages=['azureml-defaults','azureml-train-automl'])\n",
         "\n",
         "conda_env_file_name = 'myenv.yml'\n",
         "myenv.save_to_file('.', conda_env_file_name)"
@@ -323,7 +325,7 @@
         "    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",
+        "    cefw.write(content.replace(azureml.core.VERSION, dependencies['azureml-train-automl']))\n",
         "\n",
         "# Substitute the actual model id in the script file.\n",
         "\n",
@@ -340,40 +342,9 @@
       "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"
+        "### Deploy the model as a Web Service on Azure Container Instance\n",
+        "\n",
+        "Create the configuration needed for deploying the model as a web service service."
       ]
     },
     {
@@ -382,8 +353,13 @@
       "metadata": {},
       "outputs": [],
       "source": [
+        "from azureml.core.model import InferenceConfig\n",
         "from azureml.core.webservice import AciWebservice\n",
         "\n",
+        "inference_config = InferenceConfig(runtime = \"python\", \n",
+        "                                   entry_script = script_file_name,\n",
+        "                                   conda_file = conda_env_file_name)\n",
+        "\n",
         "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
         "                                               memory_gb = 1, \n",
         "                                               tags = {'area': \"digits\", 'type': \"automl_classification\"}, \n",
@@ -397,17 +373,33 @@
       "outputs": [],
       "source": [
         "from azureml.core.webservice import Webservice\n",
+        "from azureml.core.model import Model\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 = Model.deploy(ws, aci_service_name, [model], inference_config, aciconfig)\n",
         "aci_service.wait_for_deployment(True)\n",
         "print(aci_service.state)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Get the logs from service deployment"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "if aci_service.state != 'Healthy':\n",
+        "    # run this command for debugging.\n",
+        "    print(aci_service.get_logs())"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -424,22 +416,6 @@
         "#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": {},

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

@@ -0,0 +1,8 @@
+name: auto-ml-classification-with-deployment
+dependencies:
+- pip:
+  - azureml-sdk
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml

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

@@ -0,0 +1,375 @@
+{
+  "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-with-onnx/auto-ml-classification-with-onnx.png)"
+      ]
+    },
+    {
+      "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",
+        "\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "\n",
+        "In this example we use the scikit-learn's [iris dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_iris.html) 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",
+        "Please find the ONNX related documentations [here](https://github.com/onnx/onnx).\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 with ONNX compatible config on.\n",
+        "4. Explore the results and save the ONNX model.\n",
+        "5. Inference with the ONNX 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",
+        "from sklearn.model_selection import train_test_split\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, constants"
+      ]
+    },
+    {
+      "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-classification-onnx'\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['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_iris](https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_iris.html) method."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "iris = datasets.load_iris()\n",
+        "X_train, X_test, y_train, y_test = train_test_split(iris.data, \n",
+        "                                                    iris.target, \n",
+        "                                                    test_size=0.2, \n",
+        "                                                    random_state=0)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Ensure the x_train and x_test are pandas DataFrame."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Convert the X_train and X_test to pandas DataFrame and set column names,\n",
+        "# This is needed for initializing the input variable names of ONNX model, \n",
+        "# and the prediction with the ONNX model using the inference helper.\n",
+        "X_train = pd.DataFrame(X_train, columns=['c1', 'c2', 'c3', 'c4'])\n",
+        "X_test = pd.DataFrame(X_test, columns=['c1', 'c2', 'c3', 'c4'])"
+      ]
+    },
+    {
+      "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",
+        "**Note:** Set the parameter enable_onnx_compatible_models=True, if you also want to generate the ONNX compatible models. Please note, the forecasting task and TensorFlow models are not ONNX compatible yet.\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",
+        "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+        "|**y**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|\n",
+        "|**enable_onnx_compatible_models**|Enable the ONNX compatible models in the experiment.|"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Set the preprocess=True,  currently the InferenceHelper only supports this mode."
+      ]
+    },
+    {
+      "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",
+        "                             verbosity = logging.INFO,                             \n",
+        "                             X = X_train, \n",
+        "                             y = y_train,\n",
+        "                             preprocess=True,\n",
+        "                             enable_onnx_compatible_models=True)"
+      ]
+    },
+    {
+      "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": [
+        "### Retrieve the Best ONNX 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*.\n",
+        "\n",
+        "Set the parameter return_onnx_model=True to retrieve the best ONNX model, instead of the Python model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run, onnx_mdl = local_run.get_output(return_onnx_model=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Save the best ONNX model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.automl.core.onnx_convert import OnnxConverter\n",
+        "onnx_fl_path = \"./best_model.onnx\"\n",
+        "OnnxConverter.save_onnx_model(onnx_mdl, onnx_fl_path)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Predict with the ONNX model, using onnxruntime package"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import sys\n",
+        "import json\n",
+        "from azureml.automl.core.onnx_convert import OnnxConvertConstants\n",
+        "\n",
+        "if sys.version_info < OnnxConvertConstants.OnnxIncompatiblePythonVersion:\n",
+        "    python_version_compatible = True\n",
+        "else:\n",
+        "    python_version_compatible = False\n",
+        "\n",
+        "try:\n",
+        "    import onnxruntime\n",
+        "    from azureml.automl.core.onnx_convert import OnnxInferenceHelper    \n",
+        "    onnxrt_present = True\n",
+        "except ImportError:\n",
+        "    onnxrt_present = False\n",
+        "\n",
+        "def get_onnx_res(run):\n",
+        "    res_path = 'onnx_resource.json'\n",
+        "    run.download_file(name=constants.MODEL_RESOURCE_PATH_ONNX, output_file_path=res_path)\n",
+        "    with open(res_path) as f:\n",
+        "        onnx_res = json.load(f)\n",
+        "    return onnx_res\n",
+        "\n",
+        "if onnxrt_present and python_version_compatible:    \n",
+        "    mdl_bytes = onnx_mdl.SerializeToString()\n",
+        "    onnx_res = get_onnx_res(best_run)\n",
+        "\n",
+        "    onnxrt_helper = OnnxInferenceHelper(mdl_bytes, onnx_res)\n",
+        "    pred_onnx, pred_prob_onnx = onnxrt_helper.predict(X_test)\n",
+        "\n",
+        "    print(pred_onnx)\n",
+        "    print(pred_prob_onnx)\n",
+        "else:\n",
+        "    if not python_version_compatible:\n",
+        "        print('Please use Python version 3.6 or 3.7 to run the inference helper.')    \n",
+        "    if not onnxrt_present:\n",
+        "        print('Please install the onnxruntime package to do the prediction with ONNX model.')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": []
+    }
+  ],
+  "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-onnx/auto-ml-classification-with-onnx.yml

@@ -0,0 +1,9 @@
+name: auto-ml-classification-with-onnx
+dependencies:
+- pip:
+  - azureml-sdk
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml
+  - onnxruntime

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

@@ -9,6 +9,13 @@
         "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-with-whitelisting/auto-ml-classification-with-whitelisting.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -34,7 +41,7 @@
         "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 notebooks shows how can automl can be trained on 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",
@@ -71,11 +78,17 @@
         "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",
+        "import sys\n",
+        "whitelist_models=[\"LightGBM\"]\n",
+        "if \"3.7\" != sys.version[0:3]:\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",
+        "        logging.getLogger().setLevel(logging.ERROR)\n",
+        "    whitelist_models=[\"TensorFlowLinearClassifier\", \"TensorFlowDNN\"]\n",
+        "\n",
         "from azureml.train.automl import AutoMLConfig"
       ]
     },
@@ -87,9 +100,8 @@
       "source": [
         "ws = Workspace.from_config()\n",
         "\n",
-        "# Choose a name for the experiment and specify the project folder.\n",
+        "# Choose a name for the experiment.\n",
         "experiment_name = 'automl-local-whitelist'\n",
-        "project_folder = './sample_projects/automl-local-whitelist'\n",
         "\n",
         "experiment = Experiment(ws, experiment_name)\n",
         "\n",
@@ -99,7 +111,6 @@
         "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",
@@ -145,7 +156,6 @@
         "|**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).|"
       ]
     },
@@ -160,13 +170,11 @@
         "                             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)"
+        "                             whitelist_models=whitelist_models)"
       ]
     },
     {

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

@@ -0,0 +1,8 @@
+name: auto-ml-classification-with-whitelisting
+dependencies:
+- pip:
+  - azureml-sdk
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml

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

@@ -9,6 +9,13 @@
         "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/auto-ml-classification.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -72,6 +79,32 @@
         "from azureml.train.automl import AutoMLConfig"
       ]
     },
+    {
+      "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",
+        "```\n",
+        "from azureml.core.authentication import InteractiveLoginAuthentication\n",
+        "auth = InteractiveLoginAuthentication(tenant_id = 'mytenantid')\n",
+        "ws = Workspace.from_config(auth = auth)\n",
+        "```\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",
+        "```\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](http://aka.ms/aml-notebook-auth)"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -80,9 +113,8 @@
       "source": [
         "ws = Workspace.from_config()\n",
         "\n",
-        "# Choose a name for the experiment and specify the project folder.\n",
+        "# Choose a name for the experiment.\n",
         "experiment_name = 'automl-classification'\n",
-        "project_folder = './sample_projects/automl-classification'\n",
         "\n",
         "experiment = Experiment(ws, experiment_name)\n",
         "\n",
@@ -92,7 +124,6 @@
         "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",
@@ -133,12 +164,17 @@
         "|-|-|\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.|"
+        "|**n_cross_validations**|Number of cross validation splits.|\n",
+        "|\n",
+        "\n",
+        "Automated machine learning trains multiple machine learning pipelines.  Each pipelines training is known as an iteration.\n",
+        "* You can specify a maximum number of iterations using the `iterations` parameter.\n",
+        "* You can specify a maximum time for the run using the `experiment_timeout_minutes` parameter.\n",
+        "* If you specify neither the `iterations` nor the `experiment_timeout_minutes`, automated ML keeps running iterations while it continues to see improvements in the scores.\n",
+        "\n",
+        "The following example doesn't specify `iterations` or `experiment_timeout_minutes` and so runs until the scores stop improving.\n"
       ]
     },
     {
@@ -148,15 +184,10 @@
       "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)"
+        "                             n_cross_validations = 3)"
       ]
     },
     {
@@ -225,7 +256,11 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "metadata": {},
+      "metadata": {
+        "tags": [
+          "widget-rundetails-sample"
+        ]
+      },
       "outputs": [],
       "source": [
         "from azureml.widgets import RunDetails\n",
@@ -302,6 +337,12 @@
         "            print()\n",
         "            for estimator in step[1].estimators:\n",
         "                print_model(estimator[1], estimator[0]+ ' - ')\n",
+        "        elif hasattr(step[1], '_base_learners') and hasattr(step[1], '_meta_learner'):\n",
+        "            print(\"\\nMeta Learner\")\n",
+        "            pprint(step[1]._meta_learner)\n",
+        "            print()\n",
+        "            for estimator in step[1]._base_learners:\n",
+        "                print_model(estimator[1], estimator[0]+ ' - ')\n",
         "        else:\n",
         "            pprint(step[1].get_params())\n",
         "            print()\n",

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

@@ -0,0 +1,8 @@
+name: auto-ml-classification
+dependencies:
+- pip:
+  - azureml-sdk
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml

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

@@ -9,12 +9,19 @@
         "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/dataprep-remote-execution/auto-ml-dataprep-remote-execution.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
         "# Automated Machine Learning\n",
-        "_**Prepare Data using `azureml.dataprep` for Remote Execution (DSVM)**_\n",
+        "_**Load Data using `TabularDataset` for Remote Execution (AmlCompute)**_\n",
         "\n",
         "## Contents\n",
         "1. [Introduction](#Introduction)\n",
@@ -30,23 +37,20 @@
       "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",
+        "In this example we showcase how you can use AzureML Dataset to load data for AutoML.\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."
+        "1. Create a `TabularDataset` pointing to the training data.\n",
+        "2. Pass the `TabularDataset` 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."
+        "## Setup"
       ]
     },
     {
@@ -63,15 +67,13 @@
       "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.core.dataset import Dataset\n",
         "from azureml.train.automl import AutoMLConfig"
       ]
     },
@@ -82,11 +84,9 @@
       "outputs": [],
       "source": [
         "ws = Workspace.from_config()\n",
-        " \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",
+        "experiment_name = 'automl-dataset-remote-bai'\n",
         " \n",
         "experiment = Experiment(ws, experiment_name)\n",
         " \n",
@@ -96,7 +96,6 @@
         "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",
@@ -116,22 +115,21 @@
       "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))"
+        "# The data referenced here was a 1MB simple random sample of the Chicago Crime data into a local temporary directory.\n",
+        "example_data = 'https://dprepdata.blob.core.windows.net/demo/crime0-random.csv'\n",
+        "dataset = Dataset.Tabular.from_delimited_files(example_data)\n",
+        "dataset.take(5).to_pandas_dataframe()"
       ]
     },
     {
       "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."
+        "### Review the data\n",
+        "\n",
+        "You can peek the result of a `TabularDataset` at any range using `skip(i)` and `take(j).to_pandas_dataframe()`. Doing so evaluates only `j` records, which makes it fast even against large datasets.\n",
+        "\n",
+        "`TabularDataset` objects are immutable and are composed of a list of subsetting transformations (optional)."
       ]
     },
     {
@@ -140,7 +138,8 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "X.skip(1).head(5)"
+        "training_data = dataset.drop_columns(columns=['FBI Code'])\n",
+        "label_column_name = 'Primary Type'"
       ]
     },
     {
@@ -162,9 +161,8 @@
         "    \"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",
+        "    \"preprocess\" : True,\n",
+        "    \"verbosity\" : logging.INFO\n",
         "}"
       ]
     },
@@ -172,7 +170,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Create or Attach a Remote Linux DSVM"
+        "### Create or Attach an AmlCompute cluster"
       ]
     },
     {
@@ -181,21 +179,37 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "dsvm_name = 'mydsvmc'\n",
+        "from azureml.core.compute import AmlCompute\n",
+        "from azureml.core.compute import ComputeTarget\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"
+        "# Choose a name for your cluster.\n",
+        "amlcompute_cluster_name = \"automlc2\"\n",
+        "\n",
+        "found = False\n",
+        "\n",
+        "# Check if this compute target already exists in the workspace.\n",
+        "\n",
+        "cts = ws.compute_targets\n",
+        "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
+        "    found = True\n",
+        "    print('Found existing compute target.')\n",
+        "    compute_target = cts[amlcompute_cluster_name]\n",
+        "\n",
+        "if not found:\n",
+        "    print('Creating a new compute target...')\n",
+        "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
+        "                                                                #vm_priority = 'lowpriority', # optional\n",
+        "                                                                max_nodes = 6)\n",
+        "\n",
+        "    # Create the cluster.\\n\",\n",
+        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
+        "\n",
+        "print('Checking cluster status...')\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(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
+        "\n",
+        "# For a more detailed view of current AmlCompute status, use get_status()."
       ]
     },
     {
@@ -206,12 +220,16 @@
       "source": [
         "from azureml.core.runconfig import RunConfiguration\n",
         "from azureml.core.conda_dependencies import CondaDependencies\n",
+        "import pkg_resources\n",
         "\n",
+        "# create a new RunConfig object\n",
         "conda_run_config = RunConfiguration(framework=\"python\")\n",
         "\n",
-        "conda_run_config.target = dsvm_compute\n",
+        "# Set compute target to AmlCompute\n",
+        "conda_run_config.target = compute_target\n",
+        "conda_run_config.environment.docker.enabled = True\n",
         "\n",
-        "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy','py-xgboost<=0.80'])\n",
+        "cd = CondaDependencies.create(conda_packages=['numpy','py-xgboost<=0.80'])\n",
         "conda_run_config.environment.python.conda_dependencies = cd"
       ]
     },
@@ -219,9 +237,9 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Pass Data with `Dataflow` Objects\n",
+        "### Pass Data with `TabularDataset` 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."
+        "The `TabularDataset` objects captured above can also be passed to the `submit` method for a remote run. AutoML will serialize the `TabularDataset` object and send it to the remote compute target. The `TabularDataset` will not be evaluated locally."
       ]
     },
     {
@@ -232,10 +250,9 @@
       "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",
+        "                             training_data = training_data,\n",
+        "                             label_column_name = label_column_name,\n",
         "                             **automl_settings)"
       ]
     },
@@ -257,6 +274,44 @@
         "remote_run"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Pre-process cache cleanup\n",
+        "The preprocess data gets cache at user default file store. When the run is completed the cache can be cleaned by running below cell"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run.clean_preprocessor_cache()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Cancelling Runs\n",
+        "You can cancel ongoing remote runs using the `cancel` and `cancel_iteration` functions."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Cancel the ongoing experiment and stop scheduling new iterations.\n",
+        "# remote_run.cancel()\n",
+        "\n",
+        "# Cancel iteration 1 and move onto iteration 2.\n",
+        "# remote_run.cancel_iteration(1)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -376,7 +431,8 @@
       "source": [
         "## Test\n",
         "\n",
-        "#### Load Test Data"
+        "#### Load Test Data\n",
+        "For the test data, it should have the same preparation step as the train data. Otherwise it might get failed at the preprocessing step."
       ]
     },
     {
@@ -385,12 +441,13 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from sklearn import datasets\n",
+        "dataset_test = Dataset.Tabular.from_delimited_files(path='https://dprepdata.blob.core.windows.net/demo/crime0-test.csv')\n",
         "\n",
-        "digits = datasets.load_digits()\n",
-        "X_test = digits.data[:10, :]\n",
-        "y_test = digits.target[:10]\n",
-        "images = digits.images[:10]"
+        "df_test = dataset_test.to_pandas_dataframe()\n",
+        "df_test = df_test[pd.notnull(df_test['Primary Type'])]\n",
+        "\n",
+        "y_test = df_test[['Primary Type']]\n",
+        "X_test = df_test.drop(['Primary Type', 'FBI Code'], axis=1)"
       ]
     },
     {
@@ -398,7 +455,7 @@
       "metadata": {},
       "source": [
         "#### Testing Our Best Fitted Model\n",
-        "We will try to predict 2 digits and see how our model works."
+        "We will use confusion matrix to see how our model works."
       ]
     },
     {
@@ -407,65 +464,15 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "#Randomly select digits and test\n",
-        "from matplotlib import pyplot as plt\n",
-        "import numpy as np\n",
+        "from pandas_ml import ConfusionMatrix\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",
+        "ypred = fitted_model.predict(X_test)\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])"
+        "cm = ConfusionMatrix(y_test['Primary Type'], ypred)\n",
+        "\n",
+        "print(cm)\n",
+        "\n",
+        "cm.plot()"
       ]
     }
   ],

how-to-use-azureml/automated-machine-learning/dataset-remote-execution/auto-ml-dataset-remote-execution.yml

@@ -0,0 +1,11 @@
+name: auto-ml-dataset-remote-execution
+dependencies:
+- pip:
+  - azureml-sdk
+  - interpret
+  - azureml-defaults
+  - azureml-explain-model
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml

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

@@ -1,5 +1,12 @@
 {
   "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/dataprep/auto-ml-dataprep.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -14,7 +21,7 @@
       "metadata": {},
       "source": [
         "# Automated Machine Learning\n",
-        "_**Prepare Data using `azureml.dataprep` for Local Execution**_\n",
+        "_**Load Data using `TabularDataset` for Local Execution**_\n",
         "\n",
         "## Contents\n",
         "1. [Introduction](#Introduction)\n",
@@ -30,23 +37,20 @@
       "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",
+        "In this example we showcase how you can use AzureML Dataset to load data for AutoML.\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."
+        "1. Create a `TabularDataset` pointing to the training data.\n",
+        "2. Pass the `TabularDataset` to AutoML for a local 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."
+        "## Setup"
       ]
     },
     {
@@ -69,7 +73,7 @@
         "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.core.dataset import Dataset\n",
         "from azureml.train.automl import AutoMLConfig"
       ]
     },
@@ -82,9 +86,7 @@
         "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",
+        "experiment_name = 'automl-dataset-local'\n",
         " \n",
         "experiment = Experiment(ws, experiment_name)\n",
         " \n",
@@ -94,7 +96,6 @@
         "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",
@@ -114,24 +115,21 @@
       "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))"
+        "# The data referenced here was a 1MB simple random sample of the Chicago Crime data into a local temporary directory.\n",
+        "example_data = 'https://dprepdata.blob.core.windows.net/demo/crime0-random.csv'\n",
+        "dataset = Dataset.Tabular.from_delimited_files(example_data)\n",
+        "dataset.take(5).to_pandas_dataframe()"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Review the Data Preparation Result\n",
+        "### Review the data\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."
+        "You can peek the result of a `TabularDataset` at any range using `skip(i)` and `take(j).to_pandas_dataframe()`. Doing so evaluates only `j` records, which makes it fast even against large datasets.\n",
+        "\n",
+        "`TabularDataset` objects are immutable and are composed of a list of subsetting transformations (optional)."
       ]
     },
     {
@@ -140,7 +138,8 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "X.skip(1).head(5)"
+        "training_data = dataset.drop_columns(columns=['FBI Code'])\n",
+        "label_column_name = 'Primary Type'"
       ]
     },
     {
@@ -162,9 +161,8 @@
         "    \"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",
+        "    \"preprocess\" : True,\n",
+        "    \"verbosity\" : logging.INFO\n",
         "}"
       ]
     },
@@ -172,9 +170,9 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Pass Data with `Dataflow` Objects\n",
+        "### Pass Data with `TabularDataset` 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."
+        "The `TabularDataset` objects captured above can be passed to the `submit` method for a local run. AutoML will retrieve the results from the `TabularDataset` for model training."
       ]
     },
     {
@@ -185,8 +183,8 @@
       "source": [
         "automl_config = AutoMLConfig(task = 'classification',\n",
         "                             debug_log = 'automl_errors.log',\n",
-        "                             X = X,\n",
-        "                             y = y,\n",
+        "                             training_data = training_data,\n",
+        "                             label_column_name = label_column_name,\n",
         "                             **automl_settings)"
       ]
     },
@@ -327,7 +325,8 @@
       "source": [
         "## Test\n",
         "\n",
-        "#### Load Test Data"
+        "#### Load Test Data\n",
+        "For the test data, it should have the same preparation step as the train data. Otherwise it might get failed at the preprocessing step."
       ]
     },
     {
@@ -336,12 +335,13 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from sklearn import datasets\n",
+        "dataset_test = Dataset.Tabular.from_delimited_files(path='https://dprepdata.blob.core.windows.net/demo/crime0-test.csv')\n",
         "\n",
-        "digits = datasets.load_digits()\n",
-        "X_test = digits.data[:10, :]\n",
-        "y_test = digits.target[:10]\n",
-        "images = digits.images[:10]"
+        "df_test = dataset_test.to_pandas_dataframe()\n",
+        "df_test = df_test[pd.notnull(df_test['Primary Type'])]\n",
+        "\n",
+        "y_test = df_test[['Primary Type']]\n",
+        "X_test = df_test.drop(['Primary Type', 'FBI Code'], axis=1)"
       ]
     },
     {
@@ -349,7 +349,7 @@
       "metadata": {},
       "source": [
         "#### Testing Our Best Fitted Model\n",
-        "We will try to predict 2 digits and see how our model works."
+        "We will use confusion matrix to see how our model works."
       ]
     },
     {
@@ -358,65 +358,15 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "#Randomly select digits and test\n",
-        "from matplotlib import pyplot as plt\n",
-        "import numpy as np\n",
+        "from pandas_ml import ConfusionMatrix\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",
+        "ypred = fitted_model.predict(X_test)\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])"
+        "cm = ConfusionMatrix(y_test['Primary Type'], ypred)\n",
+        "\n",
+        "print(cm)\n",
+        "\n",
+        "cm.plot()"
       ]
     }
   ],

how-to-use-azureml/automated-machine-learning/dataset/auto-ml-dataset.yml

@@ -0,0 +1,9 @@
+name: auto-ml-dataset
+dependencies:
+- pip:
+  - azureml-sdk
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml
+  - azureml-dataprep[pandas]

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

@@ -9,6 +9,13 @@
         "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/exploring-previous-runs/auto-ml-exploring-previous-runs.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -190,12 +197,12 @@
         "display(HTML('<h3>Iterations</h3>'))\n",
         "RunDetails(ml_run).show() \n",
         "\n",
-        "children = list(ml_run.get_children())\n",
+        "all_metrics = ml_run.get_metrics(recursive=True)\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",
+        "for run_id, metrics in all_metrics.items():\n",
+        "    iteration = int(run_id.split('_')[-1])\n",
+        "    float_metrics = {k: v for k, v in metrics.items() if isinstance(v, float)}\n",
+        "    metricslist[iteration] = float_metrics\n",
         "\n",
         "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
         "display(HTML('<h3>Metrics</h3>'))\n",

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

@@ -0,0 +1,8 @@
+name: auto-ml-exploring-previous-runs
+dependencies:
+- pip:
+  - azureml-sdk
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml

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

@@ -0,0 +1,605 @@
+{
+  "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": [
+        "# Automated Machine Learning\n",
+        "**BikeShare Demand 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": {},
+      "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](../../../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": {},
+      "outputs": [],
+      "source": [
+        "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.workspace import Workspace\n",
+        "from azureml.core.experiment import Experiment\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"
+      ]
+    },
+    {
+      "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['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['Run History 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",
+        "Read bike share demand data from file, and preview data."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "data = pd.read_csv('bike-no.csv', parse_dates=['date'])\n",
+        "data.head()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "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",
+        "**Grain** is another word for an individual time series in your dataset. Grains are identified by values of the columns listed `grain_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",
+        "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": {},
+      "outputs": [],
+      "source": [
+        "target_column_name = 'cnt'\n",
+        "time_column_name = 'date'\n",
+        "grain_column_names = []"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Split the data\n",
+        "\n",
+        "The first split we make is into train and test sets. Note we are splitting on time."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "train = data[data[time_column_name] < '2012-09-01']\n",
+        "test = data[data[time_column_name] >= '2012-09-01']\n",
+        "\n",
+        "X_train = train.copy()\n",
+        "y_train = X_train.pop(target_column_name).values\n",
+        "\n",
+        "X_test = test.copy()\n",
+        "y_test = X_test.pop(target_column_name).values\n",
+        "\n",
+        "print(X_train.shape)\n",
+        "print(y_train.shape)\n",
+        "print(X_test.shape)\n",
+        "print(y_test.shape)"
+      ]
+    },
+    {
+      "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": [
+        "max_horizon = 14"
+      ]
+    },
+    {
+      "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",
+        "|**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",
+        "|**training_data**|Input dataset, containing both features and label column.|\n",
+        "|**label_column_name**|The name of the label column.|\n",
+        "|**n_cross_validations**|Number of cross validation splits.|\n",
+        "|**country_or_region**|The country/region used to generate holiday features. These should be ISO 3166 two-letter country/region codes (i.e. 'US', 'GB').|\n",
+        "\n",
+        "This notebook uses the blacklist_models parameter to exclude some models that take a longer time to train on this dataset. You can choose to remove models from the blacklist_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": [
+        "automl_settings = {\n",
+        "    'time_column_name': time_column_name,\n",
+        "    'max_horizon': max_horizon,\n",
+        "    # knowing the country/region allows Automated ML to bring in holidays\n",
+        "    'country_or_region': 'US',\n",
+        "    'target_lags': 1,\n",
+        "    # these columns are a breakdown of the total and therefore a leak\n",
+        "    'drop_column_names': ['casual', 'registered']\n",
+        "}\n",
+        "\n",
+        "automl_config = AutoMLConfig(task='forecasting',                             \n",
+        "                             primary_metric='normalized_root_mean_squared_error',\n",
+        "                             blacklist_models = ['ExtremeRandomTrees'],\n",
+        "                             iterations=10,\n",
+        "                             iteration_timeout_minutes=5,\n",
+        "                             training_data=train,\n",
+        "                             label_column_name=target_column_name,\n",
+        "                             n_cross_validations=3,                             \n",
+        "                             verbosity=logging.INFO,\n",
+        "                            **automl_settings)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "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. You will see the currently running iterations printing to the console."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run = experiment.submit(automl_config, show_output=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Displaying the run objects gives you links to the visual tools in the Azure Portal. Go try them!"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### 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."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run, fitted_model = local_run.get_output()\n",
+        "fitted_model.steps"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### View the engineered names for featurized data\n",
+        "\n",
+        "You can accees the engineered feature names generated in time-series featurization. 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": [
+        "fitted_model.named_steps['timeseriestransformer'].get_engineered_feature_names()"
+      ]
+    },
+    {
+      "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": [
+        "# Get the featurization summary as a list of JSON\n",
+        "featurization_summary = fitted_model.named_steps['timeseriestransformer'].get_featurization_summary()\n",
+        "# View the featurization summary as a pandas dataframe\n",
+        "pd.DataFrame.from_records(featurization_summary)"
+      ]
+    },
+    {
+      "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.  \n",
+        "\n",
+        "We always score on the original dataset whose schema matches the training set schema."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X_test.head()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We now define some functions for aligning output to input and for producing rolling forecasts over the full test set. As previously stated, the forecast horizon of 14 days is shorter than the length of the test set - which is about 120 days. To get predictions over the full test set, we iterate over the test set, making forecasts 14 days at a time and combining the results. We also make sure that each 14-day forecast uses up-to-date actuals - the current context - to construct lag features. \n",
+        "\n",
+        "It is a good practice to always align the output explicitly to the input, as the count and order of the rows may have changed during transformations that span multiple rows."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "def align_outputs(y_predicted, X_trans, X_test, y_test, predicted_column_name='predicted',\n",
+        "                  horizon_colname='horizon_origin'):\n",
+        "    \"\"\"\n",
+        "    Demonstrates how to get the output aligned to the inputs\n",
+        "    using pandas indexes. Helps understand what happened if\n",
+        "    the output's shape differs from the input shape, or if\n",
+        "    the data got re-sorted by time and grain during forecasting.\n",
+        "    \n",
+        "    Typical causes of misalignment are:\n",
+        "    * we predicted some periods that were missing in actuals -> drop from eval\n",
+        "    * model was asked to predict past max_horizon -> increase max horizon\n",
+        "    * data at start of X_test was needed for lags -> provide previous periods\n",
+        "    \"\"\"\n",
+        "    df_fcst = pd.DataFrame({predicted_column_name : y_predicted,\n",
+        "                            horizon_colname: X_trans[horizon_colname]})\n",
+        "    # y and X outputs are aligned by forecast() function contract\n",
+        "    df_fcst.index = X_trans.index\n",
+        "    \n",
+        "    # align original X_test to y_test    \n",
+        "    X_test_full = X_test.copy()\n",
+        "    X_test_full[target_column_name] = y_test\n",
+        "\n",
+        "    # X_test_full's index does not include origin, so reset for merge\n",
+        "    df_fcst.reset_index(inplace=True)\n",
+        "    X_test_full = X_test_full.reset_index().drop(columns='index')\n",
+        "    together = df_fcst.merge(X_test_full, how='right')\n",
+        "    \n",
+        "    # drop rows where prediction or actuals are nan \n",
+        "    # happens because of missing actuals \n",
+        "    # or at edges of time due to lags/rolling windows\n",
+        "    clean = together[together[[target_column_name, predicted_column_name]].notnull().all(axis=1)]\n",
+        "    return(clean)\n",
+        "\n",
+        "def do_rolling_forecast(fitted_model, X_test, y_test, max_horizon, freq='D'):\n",
+        "    \"\"\"\n",
+        "    Produce forecasts on a rolling origin over the given test set.\n",
+        "    \n",
+        "    Each iteration makes a forecast for the next 'max_horizon' periods \n",
+        "    with respect to the current origin, then advances the origin by the horizon time duration. \n",
+        "    The prediction context for each forecast is set so that the forecaster uses \n",
+        "    the actual target values prior to the current origin time for constructing lag features.\n",
+        "    \n",
+        "    This function returns a concatenated DataFrame of rolling forecasts.\n",
+        "     \"\"\"\n",
+        "    df_list = []\n",
+        "    origin_time = X_test[time_column_name].min()\n",
+        "    while origin_time <= X_test[time_column_name].max():\n",
+        "        # Set the horizon time - end date of the forecast\n",
+        "        horizon_time = origin_time + max_horizon * to_offset(freq)\n",
+        "        \n",
+        "        # Extract test data from an expanding window up-to the horizon \n",
+        "        expand_wind = (X_test[time_column_name] < horizon_time)\n",
+        "        X_test_expand = X_test[expand_wind]\n",
+        "        y_query_expand = np.zeros(len(X_test_expand)).astype(np.float)\n",
+        "        y_query_expand.fill(np.NaN)\n",
+        "        \n",
+        "        if origin_time != X_test[time_column_name].min():\n",
+        "            # Set the context by including actuals up-to the origin time\n",
+        "            test_context_expand_wind = (X_test[time_column_name] < origin_time)\n",
+        "            context_expand_wind = (X_test_expand[time_column_name] < origin_time)\n",
+        "            y_query_expand[context_expand_wind] = y_test[test_context_expand_wind]\n",
+        "        \n",
+        "        # Make a forecast out to the maximum horizon\n",
+        "        y_fcst, X_trans = fitted_model.forecast(X_test_expand, y_query_expand)\n",
+        "        \n",
+        "        # Align forecast with test set for dates within the current rolling window \n",
+        "        trans_tindex = X_trans.index.get_level_values(time_column_name)\n",
+        "        trans_roll_wind = (trans_tindex >= origin_time) & (trans_tindex < horizon_time)\n",
+        "        test_roll_wind = expand_wind & (X_test[time_column_name] >= origin_time)\n",
+        "        df_list.append(align_outputs(y_fcst[trans_roll_wind], X_trans[trans_roll_wind],\n",
+        "                                     X_test[test_roll_wind], y_test[test_roll_wind]))\n",
+        "        \n",
+        "        # Advance the origin time\n",
+        "        origin_time = horizon_time\n",
+        "    \n",
+        "    return pd.concat(df_list, ignore_index=True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "df_all = do_rolling_forecast(fitted_model, X_test, y_test, max_horizon)\n",
+        "df_all"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We now calculate some error metrics for the forecasts and vizualize the predictions vs. the actuals."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "def APE(actual, pred):\n",
+        "    \"\"\"\n",
+        "    Calculate absolute percentage error.\n",
+        "    Returns a vector of APE values with same length as actual/pred.\n",
+        "    \"\"\"\n",
+        "    return 100*np.abs((actual - pred)/actual)\n",
+        "\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",
+        "    return np.mean(APE(actual_safe, pred_safe))"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"Simple forecasting model\")\n",
+        "rmse = np.sqrt(mean_squared_error(df_all[target_column_name], df_all['predicted']))\n",
+        "print(\"[Test Data] \\nRoot Mean squared error: %.2f\" % rmse)\n",
+        "mae = mean_absolute_error(df_all[target_column_name], df_all['predicted'])\n",
+        "print('mean_absolute_error score: %.2f' % mae)\n",
+        "print('MAPE: %.2f' % MAPE(df_all[target_column_name], df_all['predicted']))\n",
+        "\n",
+        "# Plot outputs\n",
+        "%matplotlib inline\n",
+        "test_pred = plt.scatter(df_all[target_column_name], df_all['predicted'], 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()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "The MAPE seems high; it is being skewed by an actual with a small absolute value. For a more informative evaluation, we can calculate the metrics by forecast horizon:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "df_all.groupby('horizon_origin').apply(\n",
+        "    lambda df: pd.Series({'MAPE': MAPE(df[target_column_name], df['predicted']),\n",
+        "                          'RMSE': np.sqrt(mean_squared_error(df[target_column_name], df['predicted'])),\n",
+        "                          'MAE': mean_absolute_error(df[target_column_name], df['predicted'])}))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "It's also interesting to see the distributions of APE (absolute percentage error) by horizon. On a log scale, the outlying APE in the horizon-3 group is clear."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "df_all_APE = df_all.assign(APE=APE(df_all[target_column_name], df_all['predicted']))\n",
+        "APEs = [df_all_APE[df_all['horizon_origin'] == h].APE.values for h in range(1, max_horizon + 1)]\n",
+        "\n",
+        "%matplotlib inline\n",
+        "plt.boxplot(APEs)\n",
+        "plt.yscale('log')\n",
+        "plt.xlabel('horizon')\n",
+        "plt.ylabel('APE (%)')\n",
+        "plt.title('Absolute Percentage Errors by Forecast Horizon')\n",
+        "\n",
+        "plt.show()"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "erwright"
+      }
+    ],
+    "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": "3.6.8"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

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

@@ -0,0 +1,9 @@
+name: auto-ml-forecasting-bike-share
+dependencies:
+- pip:
+  - azureml-sdk
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml
+  - statsmodels

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

@@ -0,0 +1,732 @@
+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-energy-demand/auto-ml-forecasting-energy-demand.ipynb

@@ -9,6 +9,13 @@
         "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": {},
@@ -28,16 +35,16 @@
       "metadata": {},
       "source": [
         "## Introduction\n",
-        "In this example, we show how AutoML can be used for energy demand forecasting.\n",
+        "In this example, we show how AutoML can be used to forecast a single time-series in the energy demand application area. \n",
         "\n",
         "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
         "\n",
-        "In this notebook you would see\n",
+        "Notebook synopsis:\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"
+        "2. Configuration and local run of AutoML for a simple time-series model\n",
+        "3. View engineered features and prediction results\n",
+        "4. Configuration and local run of AutoML for a time-series model with lag and rolling window features\n",
+        "5. Estimate feature importance"
       ]
     },
     {
@@ -58,10 +65,10 @@
         "import numpy as np\n",
         "import logging\n",
         "import warnings\n",
+        "\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.core.experiment import Experiment\n",
         "from azureml.train.automl import AutoMLConfig\n",
@@ -73,7 +80,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "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."
+        "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."
       ]
     },
     {
@@ -86,8 +93,6 @@
         "\n",
         "# choose a name for the run history container in the workspace\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",
@@ -97,7 +102,6 @@
         "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",
@@ -109,7 +113,7 @@
       "metadata": {},
       "source": [
         "## Data\n",
-        "Read energy demanding data from file, and preview data."
+        "We will use energy consumption data from New York City for model training. The data is stored in a tabular format and includes energy demand and basic weather data at an hourly frequency. Pandas CSV reader is used to read the file into memory. Special attention is given to the \"timeStamp\" column in the data since it contains text which should be parsed as datetime-type objects. "
       ]
     },
     {
@@ -126,8 +130,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Split the data to train and test\n",
-        "\n"
+        "We must now define the schema of this dataset. Every time-series must have a time column and a target. The target quantity is what will be eventually forecasted by a trained model. In this case, the target is the \"demand\" column. The other columns, \"temp\" and \"precip,\" are implicitly designated as features."
       ]
     },
     {
@@ -136,34 +139,23 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "train = data[data['timeStamp'] < '2017-02-01']\n",
-        "test = data[data['timeStamp'] >= '2017-02-01']\n"
+        "# Dataset schema\n",
+        "time_column_name = 'timeStamp'\n",
+        "target_column_name = 'demand'"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Prepare the test data, we will feed X_test to the fitted model and get prediction"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "y_test = test.pop('demand').values\n",
-        "X_test = test"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Split the train data to train and valid\n",
+        "### Forecast Horizon\n",
         "\n",
-        "Use one month's data as valid data\n"
+        "In addition to the data schema, we must also specify the forecast horizon. A forecast horizon is a time span into the future (or just beyond the latest date in the training data) where forecasts of the target quantity are needed. Choosing a forecast horizon is application specific, but a rule-of-thumb is that **the horizon should be the time-frame where you need actionable decisions based on the forecast.** The horizon usually has a strong relationship with the frequency of the time-series data, that is, the sampling interval of the target quantity and the features. For instance, the NYC energy demand data has an hourly frequency. A decision that requires a demand forecast to the hour is unlikely to be made weeks or months in advance, particularly if we expect weather to be a strong determinant of demand. We may have fairly accurate meteorological forecasts of the hourly temperature and precipitation on a the time-scale of a day or two, however.\n",
+        "\n",
+        "Given the above discussion, we 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 the user should consider carefully how they set this value. If a long horizon forecast really is necessary, it may be good practice to aggregate the series to a coarser time scale.  \n",
+        "\n",
+        "\n",
+        "Forecast horizons in AutoML are given as integer multiples of the time-series frequency. In this example, we set the horizon to 48 hours."
       ]
     },
     {
@@ -172,14 +164,34 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "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)"
+        "max_horizon = 48"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Split the data into train and test sets\n",
+        "We now split the data into a train and a test set so that we may evaluate model performance. We note that the tail of the dataset contains a large number of NA values in the target column, so we designate the test set as the 48 hour window ending on the latest date of known energy demand. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Find time point to split on\n",
+        "latest_known_time = data[~pd.isnull(data[target_column_name])][time_column_name].max()\n",
+        "split_time = latest_known_time - pd.Timedelta(hours=max_horizon)\n",
+        "\n",
+        "# Split into train/test sets\n",
+        "X_train = data[data[time_column_name] <= split_time]\n",
+        "X_test = data[(data[time_column_name] > split_time) & (data[time_column_name] <= latest_known_time)]\n",
+        "\n",
+        "# Move the target values into their own arrays \n",
+        "y_train = X_train.pop(target_column_name).values\n",
+        "y_test = X_test.pop(target_column_name).values"
       ]
     },
     {
@@ -188,7 +200,7 @@
       "source": [
         "## Train\n",
         "\n",
-        "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
+        "We now instantiate an AutoMLConfig object. This config defines the settings and data used to run the experiment. For forecasting tasks, we must provide extra configuration related to the time-series data schema and forecasting context. Here, only the name of the time column and the maximum forecast horizon are needed. Other settings are described below:\n",
         "\n",
         "|Property|Description|\n",
         "|-|-|\n",
@@ -198,9 +210,7 @@
         "|**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. "
+        "|**n_cross_validations**|Number of cross validation splits. Rolling Origin Validation is used to split time-series in a temporally consistent way.|"
       ]
     },
     {
@@ -209,31 +219,30 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "time_column_name = 'timeStamp'\n",
-        "automl_settings = {\n",
-        "    \"time_column_name\": time_column_name,\n",
+        "time_series_settings = {\n",
+        "    'time_column_name': time_column_name,\n",
+        "    'max_horizon': max_horizon\n",
         "}\n",
         "\n",
-        "\n",
-        "automl_config = AutoMLConfig(task = 'forecasting',\n",
-        "                             debug_log = 'automl_nyc_energy_errors.log',\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",
+        "                             blacklist_models = ['ExtremeRandomTrees', 'AutoArima'],\n",
+        "                             iterations=10,\n",
+        "                             iteration_timeout_minutes=5,\n",
+        "                             X=X_train,\n",
+        "                             y=y_train,\n",
+        "                             n_cross_validations=3,\n",
         "                             verbosity = logging.INFO,\n",
-        "                            **automl_settings)"
+        "                             **time_series_settings)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "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",
+        "Submitting the configuration will start a new run in this experiment. For local runs, the execution is synchronous. Depending on the data and number of iterations, this can run for a while. Parameters controlling concurrency may speed up the process, depending on your hardware.\n",
+        "\n",
         "You will see the currently running iterations printing to the console."
       ]
     },
@@ -273,13 +282,34 @@
         "fitted_model.steps"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### View the engineered names for featurized data\n",
+        "Below we display the engineered feature names generated for the featurized data using the time-series featurization."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "fitted_model.named_steps['timeseriestransformer'].get_engineered_feature_names()"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
         "### Test the Best Fitted Model\n",
         "\n",
-        "Predict on training and test set, and calculate residual values."
+        "For forecasting, we will use the `forecast` function instead of the `predict` function. There are two reasons for this.\n",
+        "\n",
+        "We need to pass the recent values of the target variable `y`, whereas the scikit-compatible `predict` function only takes the non-target variables `X`. In our case, the test data immediately follows the training data, and we fill the `y` variable with `NaN`. The `NaN` serves as a question mark for the forecaster to fill with the actuals. Using the forecast function will produce forecasts using the shortest possible forecast horizon. The last time at which a definite (non-NaN) value is seen is the _forecast origin_ - the last time when the value of the target is known. \n",
+        "\n",
+        "Using the `predict` method would result in getting predictions for EVERY horizon the forecaster can predict at. This is useful when training and evaluating the performance of the forecaster at various horizons, but the level of detail is excessive for normal use."
       ]
     },
     {
@@ -288,15 +318,64 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "y_pred = fitted_model.predict(X_test)\n",
-        "y_pred"
+        "# Replace ALL values in y_pred by NaN. \n",
+        "# The forecast origin will be at the beginning of the first forecast period\n",
+        "# (which is the same time as the end of the last training period).\n",
+        "y_query = y_test.copy().astype(np.float)\n",
+        "y_query.fill(np.nan)\n",
+        "# The featurized data, aligned to y, will also be returned.\n",
+        "# This contains the assumptions that were made in the forecast\n",
+        "# and helps align the forecast to the original data\n",
+        "y_fcst, X_trans = fitted_model.forecast(X_test, y_query)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# limit the evaluation to data where y_test has actuals\n",
+        "def align_outputs(y_predicted, X_trans, X_test, y_test, predicted_column_name = 'predicted'):\n",
+        "    \"\"\"\n",
+        "    Demonstrates how to get the output aligned to the inputs\n",
+        "    using pandas indexes. Helps understand what happened if\n",
+        "    the output's shape differs from the input shape, or if\n",
+        "    the data got re-sorted by time and grain during forecasting.\n",
+        "    \n",
+        "    Typical causes of misalignment are:\n",
+        "    * we predicted some periods that were missing in actuals -> drop from eval\n",
+        "    * model was asked to predict past max_horizon -> increase max horizon\n",
+        "    * data at start of X_test was needed for lags -> provide previous periods\n",
+        "    \"\"\"\n",
+        "    df_fcst = pd.DataFrame({predicted_column_name : y_predicted})\n",
+        "    # y and X outputs are aligned by forecast() function contract\n",
+        "    df_fcst.index = X_trans.index\n",
+        "    \n",
+        "    # align original X_test to y_test    \n",
+        "    X_test_full = X_test.copy()\n",
+        "    X_test_full[target_column_name] = y_test\n",
+        "\n",
+        "    # X_test_full's does not include origin, so reset for merge\n",
+        "    df_fcst.reset_index(inplace=True)\n",
+        "    X_test_full = X_test_full.reset_index().drop(columns='index')\n",
+        "    together = df_fcst.merge(X_test_full, how='right')\n",
+        "    \n",
+        "    # drop rows where prediction or actuals are nan \n",
+        "    # happens because of missing actuals \n",
+        "    # or at edges of time due to lags/rolling windows\n",
+        "    clean = together[together[[target_column_name, predicted_column_name]].notnull().all(axis=1)]\n",
+        "    return(clean)\n",
+        "\n",
+        "df_all = align_outputs(y_fcst, X_trans, X_test, y_test)\n",
+        "df_all.head()"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Use the Check Data Function to remove the nan values from y_test to avoid error when calculate metrics "
+        "Looking at `X_trans` is also useful to see what featurization happened to the data."
       ]
     },
     {
@@ -305,29 +384,15 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "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",
-        "# 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))]"
+        "X_trans"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Calculate metrics for the prediction\n"
+        "### Calculate accuracy metrics\n",
+        "Finally, we calculate some accuracy metrics for the forecast and plot the predictions vs. the actuals over the time range in the test set."
       ]
     },
     {
@@ -336,26 +401,264 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "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",
-        "\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)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"Simple forecasting model\")\n",
+        "rmse = np.sqrt(mean_squared_error(df_all[target_column_name], df_all['predicted']))\n",
+        "print(\"[Test Data] \\nRoot Mean squared error: %.2f\" % rmse)\n",
+        "mae = mean_absolute_error(df_all[target_column_name], df_all['predicted'])\n",
+        "print('mean_absolute_error score: %.2f' % mae)\n",
+        "print('MAPE: %.2f' % MAPE(df_all[target_column_name], df_all['predicted']))\n",
         "\n",
         "# Plot outputs\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",
+        "%matplotlib inline\n",
+        "pred, = plt.plot(df_all[time_column_name], df_all['predicted'], color='b')\n",
+        "actual, = plt.plot(df_all[time_column_name], df_all[target_column_name], color='g')\n",
+        "plt.xticks(fontsize=8)\n",
+        "plt.legend((pred, actual), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
+        "plt.title('Prediction vs. Actual Time-Series')\n",
+        "\n",
         "plt.show()"
       ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "The distribution looks a little heavy tailed: we underestimate the excursions of the extremes. A normal-quantile transform of the target might help, but let's first try using some past data with the lags and rolling window transforms.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Using lags and rolling window features"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We did not use lags in the previous model specification. In effect, the prediction was the result of a simple regression on date, grain 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.\n",
+        "\n",
+        "Now that we configured target lags, that is the previous values of the target variables, and the prediction is no longer horizon-less. We therefore must still specify the `max_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 blacklist_models parameter to exclude some models that take a longer time to train on this dataset.  You can choose to remove models from the blacklist_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": [
+        "time_series_settings_with_lags = {\n",
+        "    'time_column_name': time_column_name,\n",
+        "    'max_horizon': max_horizon,\n",
+        "    'target_lags': 12,\n",
+        "    'target_rolling_window_size': 4\n",
+        "}\n",
+        "\n",
+        "automl_config_lags = AutoMLConfig(task='forecasting',\n",
+        "                                  debug_log='automl_nyc_energy_errors.log',\n",
+        "                                  primary_metric='normalized_root_mean_squared_error',\n",
+        "                                  blacklist_models=['ElasticNet','ExtremeRandomTrees','GradientBoosting','XGBoostRegressor'],\n",
+        "                                  iterations=10,\n",
+        "                                  iteration_timeout_minutes=10,\n",
+        "                                  X=X_train,\n",
+        "                                  y=y_train,\n",
+        "                                  n_cross_validations=3,\n",
+        "                                  verbosity=logging.INFO,\n",
+        "                                  **time_series_settings_with_lags)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We now start a new local 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": [
+        "local_run_lags = experiment.submit(automl_config_lags, show_output=True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run_lags, fitted_model_lags = local_run_lags.get_output()\n",
+        "y_fcst_lags, X_trans_lags = fitted_model_lags.forecast(X_test, y_query)\n",
+        "df_lags = align_outputs(y_fcst_lags, X_trans_lags, X_test, y_test)\n",
+        "df_lags.head()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X_trans_lags"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"Forecasting model with lags\")\n",
+        "rmse = np.sqrt(mean_squared_error(df_lags[target_column_name], df_lags['predicted']))\n",
+        "print(\"[Test Data] \\nRoot Mean squared error: %.2f\" % rmse)\n",
+        "mae = mean_absolute_error(df_lags[target_column_name], df_lags['predicted'])\n",
+        "print('mean_absolute_error score: %.2f' % mae)\n",
+        "print('MAPE: %.2f' % MAPE(df_lags[target_column_name], df_lags['predicted']))\n",
+        "\n",
+        "# Plot outputs\n",
+        "%matplotlib inline\n",
+        "pred, = plt.plot(df_lags[time_column_name], df_lags['predicted'], color='b')\n",
+        "actual, = plt.plot(df_lags[time_column_name], df_lags[target_column_name], color='g')\n",
+        "plt.xticks(fontsize=8)\n",
+        "plt.legend((pred, actual), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
+        "plt.show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### What features matter for the forecast?\n",
+        "The following steps will allow you to compute and visualize engineered feature importance based on your test data for forecasting. "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Setup the model explanations for AutoML models\n",
+        "The *fitted_model* can generate the following which will be used for getting the engineered and raw feature explanations using *automl_setup_model_explanations*:-\n",
+        "1. Featurized data from train samples/test samples \n",
+        "2. Gather engineered and raw feature name lists\n",
+        "3. Find the classes in your labeled column in classification scenarios\n",
+        "\n",
+        "The *automl_explainer_setup_obj* contains all the structures from above list. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.train.automl.automl_explain_utilities import AutoMLExplainerSetupClass, automl_setup_model_explanations\n",
+        "automl_explainer_setup_obj = automl_setup_model_explanations(fitted_model, X=X_train.copy(), \n",
+        "                                                             X_test=X_test.copy(), y=y_train, \n",
+        "                                                             task='forecasting')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Initialize the Mimic Explainer for feature importance\n",
+        "For explaining the AutoML models, use the *MimicWrapper* from *azureml.explain.model* package. The *MimicWrapper* can be initialized with fields in *automl_explainer_setup_obj*, your workspace and a LightGBM model which acts as a surrogate model to explain the AutoML model (*fitted_model* here). The *MimicWrapper* also takes the *best_run* object where the raw and engineered explanations will be uploaded."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.explain.model.mimic.models.lightgbm_model import LGBMExplainableModel\n",
+        "from azureml.explain.model.mimic_wrapper import MimicWrapper\n",
+        "explainer = MimicWrapper(ws, automl_explainer_setup_obj.automl_estimator, LGBMExplainableModel, \n",
+        "                         init_dataset=automl_explainer_setup_obj.X_transform, run=best_run,\n",
+        "                         features=automl_explainer_setup_obj.engineered_feature_names, \n",
+        "                         feature_maps=[automl_explainer_setup_obj.feature_map])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Use Mimic Explainer for computing and visualizing engineered feature importance\n",
+        "The *explain()* method in *MimicWrapper* can be called with the transformed test samples to get the feature importance for the generated engineered features. You can also use *ExplanationDashboard* to view the dash board visualization of the feature importance values of the generated engineered features by AutoML featurizers."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "engineered_explanations = explainer.explain(['local', 'global'], eval_dataset=automl_explainer_setup_obj.X_test_transform)\n",
+        "print(engineered_explanations.get_feature_importance_dict())\n",
+        "from azureml.contrib.interpret.visualize import ExplanationDashboard\n",
+        "ExplanationDashboard(engineered_explanations, automl_explainer_setup_obj.automl_estimator, automl_explainer_setup_obj.X_test_transform)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Use Mimic Explainer for computing and visualizing raw feature importance\n",
+        "The *explain()* method in *MimicWrapper* can be again called with the transformed test samples and setting *get_raw* to *True* to get the feature importance for the raw features. You can also use *ExplanationDashboard* to view the dash board visualization of the feature importance values of the raw features."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "raw_explanations = explainer.explain(['local', 'global'], get_raw=True, \n",
+        "                                     raw_feature_names=automl_explainer_setup_obj.raw_feature_names,\n",
+        "                                     eval_dataset=automl_explainer_setup_obj.X_test_transform)\n",
+        "print(raw_explanations.get_feature_importance_dict())\n",
+        "from azureml.contrib.interpret.visualize import ExplanationDashboard\n",
+        "ExplanationDashboard(raw_explanations, automl_explainer_setup_obj.automl_pipeline, automl_explainer_setup_obj.X_test_raw)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Please go to the Azure Portal's best run to see the top features chart.\n",
+        "\n",
+        "The informative features make all sorts of intuitive sense. Temperature is a strong driver of heating and cooling demand in NYC. Apart from that, the daily life cycle, expressed by `hour`, and the weekly cycle, expressed by `wday` drives people's energy use habits."
+      ]
     }
   ],
   "metadata": {
     "authors": [
       {
-        "name": "xiaga"
+        "name": "erwright"
       }
     ],
     "kernelspec": {

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

@@ -0,0 +1,12 @@
+name: auto-ml-forecasting-energy-demand
+dependencies:
+- pip:
+  - azureml-sdk
+  - interpret
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml
+  - statsmodels
+  - azureml-explain-model
+  - azureml-contrib-interpret

how-to-use-azureml/automated-machine-learning/forecasting-high-frequency/automl-forecasting-function.ipynb

@@ -0,0 +1,615 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "\n",
+        "## Forecasting away from training data\n",
+        "\n",
+        "This notebook demonstrates the full interface to 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",
+        "* forecast horizon: the number of forecast periods\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.ipynb` notebook so that your ML workspace information is saved in the config file."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "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",
+        "np.set_printoptions(precision=4, suppress=True, linewidth=120)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import azureml.core\n",
+        "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['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['Run History 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",
+        "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",
+        "GRAIN_COLUMN_NAME = 'grain'\n",
+        "TARGET_COLUMN_NAME = 'y'\n",
+        "\n",
+        "def get_timeseries(train_len: int,\n",
+        "                   test_len: int,\n",
+        "                   time_column_name: str,\n",
+        "                   target_column_name: str,\n",
+        "                   grain_column_name: str,\n",
+        "                   grains: int = 1,\n",
+        "                   freq: str = 'H'):\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\n",
+        "    :param grains: The number of grains.\n",
+        "    :type grains: 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(grains):\n",
+        "        X = pd.DataFrame({\n",
+        "            time_column_name: pd.date_range(start='2000-01-01',\n",
+        "                                            periods=data_length,\n",
+        "                                            freq=freq),\n",
+        "            target_column_name: np.arange(data_length).astype(float) + np.random.rand(data_length) + i*5,\n",
+        "            'ext_predictor': np.asarray(range(42, 42 + data_length)),\n",
+        "            grain_column_name: np.repeat('g{}'.format(i), data_length)\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_test_periods = 6\n",
+        "n_train_periods = 30\n",
+        "X_train, y_train, X_test, y_test = get_timeseries(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",
+        "                                                  grain_column_name=GRAIN_COLUMN_NAME,\n",
+        "                                                  grains=2)"
+      ]
+    },
+    {
+      "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",
+        "whole_data = X_train.copy()\n",
+        "whole_data['y'] = y_train\n",
+        "for g in whole_data.groupby('grain'):    \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": [
+        "## Create the configuration and train a forecaster\n",
+        "First generate the configuration, in which we:\n",
+        "* Set metadata columns: target, time column and grain column names.\n",
+        "* Ask for 10 iterations through models, last of which will represent the Ensemble of previous ones.\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",
+        "\n",
+        "* Finally, we set the task to be forecasting.\n",
+        "* By default, we apply the lag lead operator and rolling window to the target value i.e. we use the previous values as a predictor for the future ones."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "lags = [1,2,3]\n",
+        "rolling_window_length = 0 # don't do rolling windows\n",
+        "max_horizon = n_test_periods\n",
+        "time_series_settings = {    \n",
+        "    'time_column_name': TIME_COLUMN_NAME,\n",
+        "    'grain_column_names': [ GRAIN_COLUMN_NAME ],\n",
+        "    'max_horizon': max_horizon,\n",
+        "    'target_lags': lags\n",
+        "}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Run the model selection and training process."
+      ]
+    },
+    {
+      "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(task='forecasting',\n",
+        "                             debug_log='automl_forecasting_function.log',\n",
+        "                             primary_metric='normalized_root_mean_squared_error',                             \n",
+        "                             iterations=10,                             \n",
+        "                             X=X_train,\n",
+        "                             y=y_train,\n",
+        "                             n_cross_validations=3,\n",
+        "                             verbosity = logging.INFO,\n",
+        "                             **time_series_settings)\n",
+        "\n",
+        "local_run = experiment.submit(automl_config, show_output=True)\n",
+        "\n",
+        "# Retrieve the best model to use it further.\n",
+        "_, fitted_model = local_run.get_output()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Forecasting from the trained model"
+      ]
+    },
+    {
+      "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",
+        "The `X_test` and `y_query` below, taken together, form the **forecast request**. The two are interpreted as aligned - `y_query` could actally be a column in `X_test`. `NaN`s in `y_query` are the question marks. These will be filled with the forecasts.\n",
+        "\n",
+        "When the forecast period immediately follows the training period, the models retain the last few points of data. You can simply fill `y_query` filled with question marks - the model has the data for the lookback already.\n"
+      ]
+    },
+    {
+      "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_query = np.repeat(np.NaN, X_test.shape[0])\n",
+        "y_pred_no_gap, xy_nogap =  fitted_model.forecast(X_test, y_query)\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": [
+        "#### 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 of 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, y_query)\n",
+        "\n",
+        "# it all nicely aligns column-wise\n",
+        "pd.concat([X_test.reset_index(), pd.DataFrame({'query' : y_query}), y_pred_quantiles], axis=1)"
+      ]
+    },
+    {
+      "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, becaus eit 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 maximum 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\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 grain, so each grain 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(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",
+        "                                      grain_column_name=GRAIN_COLUMN_NAME,\n",
+        "                                      grains=2)\n",
+        "\n",
+        "# end of the data we trained on\n",
+        "print(X_train.groupby(GRAIN_COLUMN_NAME)[TIME_COLUMN_NAME].max())\n",
+        "# start of the data we want to predict on\n",
+        "print(X_away.groupby(GRAIN_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_query = y_away.copy()\n",
+        "    y_query.fill(np.NaN)\n",
+        "    y_pred_away, xy_away = fitted_model.forecast(X_away, y_query)\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 themodel saw an actual values of `y` (the target). That was at the end of the training data! Because the model received all `NaN` (and not an actual target value), it is attempting to forecast from the end of training data. But the requested forecast periods are past the maximum 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(fulldata, time_column_name, target_column_name, forecast_origin, horizon, lookback):\n",
+        "\n",
+        "    \"\"\"\n",
+        "    This function will take the full dataset, and create the query\n",
+        "    to predict all values of the grain 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[ (fulldata[ time_column_name ] > forecast_origin - lookback) &\n",
+        "                       (fulldata[ time_column_name ] <= forecast_origin)\n",
+        "                     ]\n",
+        "\n",
+        "    X_future = fulldata[ (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(np.float)\n",
+        "    y_future = X_future.pop(target_column_name).values.astype(np.float)\n",
+        "\n",
+        "    # Now take y_future and turn it into question marks\n",
+        "    y_query = y_future.copy().astype(np.float)  # because sometimes life hands you an int\n",
+        "    y_query.fill(np.NaN)\n",
+        "\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",
+        "\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(X_context.groupby(GRAIN_COLUMN_NAME)[TIME_COLUMN_NAME].agg(['min','max','count']))\n",
+        "print(   X_away.groupby(GRAIN_COLUMN_NAME)[TIME_COLUMN_NAME].agg(['min','max','count']))\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(max(lags), rolling_window_length)\n",
+        "lookback = pd.DateOffset(hours=n_lookback_periods)\n",
+        "\n",
+        "horizon = pd.DateOffset(hours=max_horizon)\n",
+        "\n",
+        "# now make the forecast query from context (refer to figure)\n",
+        "X_pred, y_pred = make_forecasting_query(fulldata, TIME_COLUMN_NAME, TARGET_COLUMN_NAME,\n",
+        "                                        forecast_origin, horizon, lookback)\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 grains, 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', 'grain', 'ext_predictor', '_automl_target_col']]\n",
+        "# prediction is in _automl_target_col"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "erwright, nirovins"
+      }
+    ],
+    "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": "3.6.7"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/forecasting-high-frequency/automl-forecasting-function.yml

@@ -0,0 +1,9 @@
+name: automl-forecasting-function
+dependencies:
+- pip:
+  - azureml-sdk
+  - azureml-train-automl
+  - azureml-widgets
+  - pandas_ml
+  - statsmodels
+  - matplotlib

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

@@ -9,6 +9,13 @@
         "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": {},
@@ -20,7 +27,9 @@
         "1. [Introduction](#Introduction)\n",
         "1. [Setup](#Setup)\n",
         "1. [Data](#Data)\n",
-        "1. [Train](#Train)"
+        "1. [Train](#Train)\n",
+        "1. [Predict](#Predict)\n",
+        "1. [Operationalize](#Operationalize)"
       ]
     },
     {
@@ -28,16 +37,10 @@
       "metadata": {},
       "source": [
         "## Introduction\n",
-        "In this example, we use AutoML to find and tune a time-series forecasting model.\n",
+        "In this example, we use AutoML to train, select, and operationalize a time-series forecasting model for multiple time-series.\n",
         "\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."
       ]
     },
@@ -59,10 +62,10 @@
         "import numpy as np\n",
         "import logging\n",
         "import warnings\n",
+        "\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.core.experiment import Experiment\n",
         "from azureml.train.automl import AutoMLConfig\n",
@@ -73,7 +76,7 @@
       "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 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. "
+        "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. "
       ]
     },
     {
@@ -85,9 +88,7 @@
         "ws = Workspace.from_config()\n",
         "\n",
         "# choose a name for the run history container in the workspace\n",
-        "experiment_name = 'automl-ojsalesforecasting'\n",
-        "# project folder\n",
-        "project_folder = './sample_projects/automl-local-ojsalesforecasting'\n",
+        "experiment_name = 'automl-ojforecasting'\n",
         "\n",
         "experiment = Experiment(ws, experiment_name)\n",
         "\n",
@@ -97,7 +98,6 @@
         "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",
@@ -227,7 +227,7 @@
         "\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",
+        "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. 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",
         "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",
@@ -241,9 +241,9 @@
         "|**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",
+        "|**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",
-        "|**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",
@@ -265,13 +265,13 @@
         "\n",
         "automl_config = AutoMLConfig(task='forecasting',\n",
         "                             debug_log='automl_oj_sales_errors.log',\n",
-        "                             primary_metric='normalized_root_mean_squared_error',\n",
+        "                             primary_metric='normalized_mean_absolute_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",
+        "                             n_cross_validations=3,\n",
+        "                             enable_voting_ensemble=False,\n",
+        "                             enable_stack_ensemble=False,\n",
         "                             verbosity=logging.INFO,\n",
         "                             **time_series_settings)"
       ]
@@ -293,15 +293,6 @@
         "local_run = experiment.submit(automl_config, show_output=True)"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "local_run"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -324,7 +315,8 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Make Predictions from the Best Fitted Model\n",
+        "# Forecasting\n",
+        "\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:"
       ]
     },
@@ -352,7 +344,7 @@
       "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. \n",
         "\n",
-        "The target predictions can be retrieved by calling the `predict` method on the best model:"
+        "We will first create a query `y_query`, which is aligned index-for-index to `X_test`. This is a vector of target values where each `NaN` serves the function of the question mark to be replaced by forecast. Passing definite values in the `y` argument allows the `forecast` function to make predictions on data that does not immediately follow the train data which contains `y`. In each grain, the last time point where the model sees a definite value of `y` is that grain's _forecast origin_."
       ]
     },
     {
@@ -361,15 +353,76 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "y_pred = fitted_pipeline.predict(X_test)"
+        "# Replace ALL values in y_pred by NaN.\n",
+        "# The forecast origin will be at the beginning of the first forecast period.\n",
+        "# (Which is the same time as the end of the last training period.)\n",
+        "y_query = y_test.copy().astype(np.float)\n",
+        "y_query.fill(np.nan)\n",
+        "# The featurized data, aligned to y, will also be returned.\n",
+        "# This contains the assumptions that were made in the forecast\n",
+        "# and helps align the forecast to the original data\n",
+        "y_pred, X_trans = fitted_pipeline.forecast(X_test, y_query)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### 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)."
+        "If you are used to scikit pipelines, perhaps you expected `predict(X_test)`. However, forecasting requires a more general interface that also supplies the past target `y` values. Please use `forecast(X,y)` as `predict(X)` is reserved for internal purposes on forecasting models.\n",
+        "\n",
+        "The [energy demand forecasting notebook](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand) demonstrates the use of the forecast function in more detail in the context of using lags and rolling window features. "
+      ]
+    },
+    {
+      "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). \n",
+        "\n",
+        "It is a good practice to always align the output explicitly to the input, as the count and order of the rows may have changed during transformations that span multiple rows."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "def align_outputs(y_predicted, X_trans, X_test, y_test, predicted_column_name = 'predicted'):\n",
+        "    \"\"\"\n",
+        "    Demonstrates how to get the output aligned to the inputs\n",
+        "    using pandas indexes. Helps understand what happened if\n",
+        "    the output's shape differs from the input shape, or if\n",
+        "    the data got re-sorted by time and grain during forecasting.\n",
+        "    \n",
+        "    Typical causes of misalignment are:\n",
+        "    * we predicted some periods that were missing in actuals -> drop from eval\n",
+        "    * model was asked to predict past max_horizon -> increase max horizon\n",
+        "    * data at start of X_test was needed for lags -> provide previous periods in y\n",
+        "    \"\"\"\n",
+        "    \n",
+        "    df_fcst = pd.DataFrame({predicted_column_name : y_predicted})\n",
+        "    # y and X outputs are aligned by forecast() function contract\n",
+        "    df_fcst.index = X_trans.index\n",
+        "    \n",
+        "    # align original X_test to y_test    \n",
+        "    X_test_full = X_test.copy()\n",
+        "    X_test_full[target_column_name] = y_test\n",
+        "\n",
+        "    # X_test_full's index does not include origin, so reset for merge\n",
+        "    df_fcst.reset_index(inplace=True)\n",
+        "    X_test_full = X_test_full.reset_index().drop(columns='index')\n",
+        "    together = df_fcst.merge(X_test_full, how='right')\n",
+        "    \n",
+        "    # drop rows where prediction or actuals are nan \n",
+        "    # happens because of missing actuals \n",
+        "    # or at edges of time due to lags/rolling windows\n",
+        "    clean = together[together[[target_column_name, predicted_column_name]].notnull().all(axis=1)]\n",
+        "    return(clean)\n",
+        "\n",
+        "df_all = align_outputs(y_pred, X_trans, X_test, y_test)"
       ]
     },
     {
@@ -388,11 +441,346 @@
         "    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",
+        "    return np.mean(APE)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"Simple forecasting model\")\n",
+        "rmse = np.sqrt(mean_squared_error(df_all[target_column_name], df_all['predicted']))\n",
+        "print(\"[Test Data] \\nRoot Mean squared error: %.2f\" % rmse)\n",
+        "mae = mean_absolute_error(df_all[target_column_name], df_all['predicted'])\n",
+        "print('mean_absolute_error score: %.2f' % mae)\n",
+        "print('MAPE: %.2f' % MAPE(df_all[target_column_name], df_all['predicted']))\n",
         "\n",
-        "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))"
+        "# Plot outputs\n",
+        "import matplotlib.pyplot as plt\n",
+        "\n",
+        "%matplotlib inline\n",
+        "test_pred = plt.scatter(df_all[target_column_name], df_all['predicted'], 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()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Operationalize"
+      ]
+    },
+    {
+      "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 = local_run.register_model(description = description, tags = tags)\n",
+        "\n",
+        "print(local_run.model_id)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Develop the scoring script\n",
+        "\n",
+        "Serializing and deserializing complex data frames may be tricky. We first develop the `run()` function of the scoring script locally, then write it into a scoring script. It is much easier to debug any quirks of the scoring function without crossing two compute environments. For this exercise, we handle a common quirk of how pandas dataframes serialize time stamp values."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# this is where we test the run function of the scoring script interactively\n",
+        "# before putting it in the scoring script\n",
+        "\n",
+        "timestamp_columns = ['WeekStarting']\n",
+        "\n",
+        "def run(rawdata, test_model = None):\n",
+        "    \"\"\"\n",
+        "    Intended to process 'rawdata' string produced by\n",
+        "    \n",
+        "    {'X': X_test.to_json(), y' : y_test.to_json()}\n",
+        "    \n",
+        "    Don't convert the X payload to numpy.array, use it as pandas.DataFrame\n",
+        "    \"\"\"\n",
+        "    try:\n",
+        "        # unpack the data frame with timestamp        \n",
+        "        rawobj = json.loads(rawdata)                    # rawobj is now a dict of strings        \n",
+        "        X_pred = pd.read_json(rawobj['X'], convert_dates=False)   # load the pandas DF from a json string\n",
+        "        for col in timestamp_columns:                             # fix timestamps\n",
+        "            X_pred[col] = pd.to_datetime(X_pred[col], unit='ms') \n",
+        "        \n",
+        "        y_pred = np.array(rawobj['y'])                    # reconstitute numpy array from serialized list\n",
+        "        \n",
+        "        if test_model is None:\n",
+        "            result = model.forecast(X_pred, y_pred)       # use the global model from init function\n",
+        "        else:\n",
+        "            result = test_model.forecast(X_pred, y_pred)  # use the model on which we are testing\n",
+        "        \n",
+        "    except Exception as e:\n",
+        "        result = str(e)\n",
+        "        return json.dumps({\"error\": result})\n",
+        "    \n",
+        "    forecast_as_list = result[0].tolist()\n",
+        "    index_as_df = result[1].index.to_frame().reset_index(drop=True)\n",
+        "    \n",
+        "    return json.dumps({\"forecast\": forecast_as_list,   # return the minimum over the wire: \n",
+        "                       \"index\": index_as_df.to_json()  # no forecast and its featurized values\n",
+        "                      })"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# test the run function here before putting in the scoring script\n",
+        "import json\n",
+        "\n",
+        "test_sample = json.dumps({'X': X_test.to_json(), 'y' : y_query.tolist()})\n",
+        "response = run(test_sample, fitted_pipeline)\n",
+        "\n",
+        "# unpack the response, dealing with the timestamp serialization again\n",
+        "res_dict = json.loads(response)\n",
+        "y_fcst_all = pd.read_json(res_dict['index'])\n",
+        "y_fcst_all[time_column_name] = pd.to_datetime(y_fcst_all[time_column_name], unit = 'ms')\n",
+        "y_fcst_all['forecast'] = res_dict['forecast']\n",
+        "y_fcst_all.head()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Now that the function works locally in the notebook, let's write it down into the scoring script. The scoring script is authored by the data scientist. Adjust it to taste, adding inputs, outputs and processing as needed."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%writefile score_fcast.py\n",
+        "import pickle\n",
+        "import json\n",
+        "import numpy as np\n",
+        "import pandas as pd\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",
+        "timestamp_columns = ['WeekStarting']\n",
+        "\n",
+        "def run(rawdata, test_model = None):\n",
+        "    \"\"\"\n",
+        "    Intended to process 'rawdata' string produced by\n",
+        "    \n",
+        "    {'X': X_test.to_json(), y' : y_test.to_json()}\n",
+        "    \n",
+        "    Don't convert the X payload to numpy.array, use it as pandas.DataFrame\n",
+        "    \"\"\"\n",
+        "    try:\n",
+        "        # unpack the data frame with timestamp        \n",
+        "        rawobj = json.loads(rawdata)                    # rawobj is now a dict of strings        \n",
+        "        X_pred = pd.read_json(rawobj['X'], convert_dates=False)   # load the pandas DF from a json string\n",
+        "        for col in timestamp_columns:                             # fix timestamps\n",
+        "            X_pred[col] = pd.to_datetime(X_pred[col], unit='ms') \n",
+        "        \n",
+        "        y_pred = np.array(rawobj['y'])                    # reconstitute numpy array from serialized list\n",
+        "        \n",
+        "        if test_model is None:\n",
+        "            result = model.forecast(X_pred, y_pred)       # use the global model from init function\n",
+        "        else:\n",
+        "            result = test_model.forecast(X_pred, y_pred)  # use the model on which we are testing\n",
+        "        \n",
+        "    except Exception as e:\n",
+        "        result = str(e)\n",
+        "        return json.dumps({\"error\": result})\n",
+        "    \n",
+        "    # prepare to send over wire as json\n",
+        "    forecast_as_list = result[0].tolist()\n",
+        "    index_as_df = result[1].index.to_frame().reset_index(drop=True)\n",
+        "    \n",
+        "    return json.dumps({\"forecast\": forecast_as_list,   # return the minimum over the wire: \n",
+        "                       \"index\": index_as_df.to_json()  # no forecast and its featurized values\n",
+        "                      })"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# get the model\n",
+        "from azureml.train.automl.run import AutoMLRun\n",
+        "\n",
+        "experiment = Experiment(ws, experiment_name)\n",
+        "ml_run = AutoMLRun(experiment = experiment, run_id = local_run.id)\n",
+        "best_iteration = int(str.split(best_run.id,'_')[-1])      # the iteration number is a postfix of the run ID."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# get the best model's dependencies and write them into this file\n",
+        "from azureml.core.conda_dependencies import CondaDependencies\n",
+        "\n",
+        "conda_env_file_name = 'fcast_env.yml'\n",
+        "\n",
+        "dependencies = ml_run.get_run_sdk_dependencies(iteration = best_iteration)\n",
+        "for p in ['azureml-train-automl', 'azureml-core']:\n",
+        "    print('{}\\t{}'.format(p, dependencies[p]))\n",
+        "\n",
+        "myenv = CondaDependencies.create(conda_packages=['numpy>=1.16.0,<=1.16.2','scikit-learn','fbprophet==0.5'], pip_packages=['azureml-defaults','azureml-train-automl'])\n",
+        "\n",
+        "myenv.save_to_file('.', conda_env_file_name)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# this is the script file name we wrote a few cells above\n",
+        "script_file_name = 'score_fcast.py'\n",
+        "\n",
+        "# 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-train-automl']))\n",
+        "\n",
+        "# Substitute the actual model id in the script file.\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": [
+        "### 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(runtime = \"python\", \n",
+        "                                   entry_script = script_file_name,\n",
+        "                                   conda_file = conda_env_file_name)\n",
+        "\n",
+        "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
+        "                                               memory_gb = 2, \n",
+        "                                               tags = {'type': \"automl-forecasting\"},\n",
+        "                                               description = \"Automl forecasting sample service\")\n",
+        "\n",
+        "aci_service_name = 'automl-forecast-01'\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": "markdown",
+      "metadata": {},
+      "source": [
+        "### Call the service"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# we send the data to the service serialized into a json string\n",
+        "test_sample = json.dumps({'X':X_test.to_json(), 'y' : y_query.tolist()})\n",
+        "response = aci_service.run(input_data = test_sample)\n",
+        "\n",
+        "# translate from networkese to datascientese\n",
+        "try: \n",
+        "    res_dict = json.loads(response)\n",
+        "    y_fcst_all = pd.read_json(res_dict['index'])\n",
+        "    y_fcst_all[time_column_name] = pd.to_datetime(y_fcst_all[time_column_name], unit = 'ms')\n",
+        "    y_fcst_all['forecast'] = res_dict['forecast']    \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-forecast-01')\n",
+        "# serv.delete()     # don't do it accidentally"
       ]
     }
   ],
@@ -417,7 +805,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.8"
+      "version": "3.6.7"
     }
   },
   "nbformat": 4,

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

@@ -0,0 +1,9 @@
+name: auto-ml-forecasting-orange-juice-sales
+dependencies:
+- pip:
+  - azureml-sdk
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml
+  - statsmodels

how-to-use-azureml/automated-machine-learning/missing-data-blacklist-early-termination/auto-ml-missing-data-blacklist-early-termination.ipynb

@@ -9,6 +9,13 @@
         "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/missing-data-blacklist-early-termination/auto-ml-missing-data-blacklist-early-termination.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -37,8 +44,9 @@
         "In this notebook you will learn how to:\n",
         "1. Create an `Experiment` in an existing `Workspace`.\n",
         "2. Configure AutoML using `AutoMLConfig`.\n",
-        "4. Train the model.\n",
-        "5. Explore the results.\n",
+        "3. Train the model.\n",
+        "4. Explore the results.\n",
+        "5. Viewing the engineered names for featurized data and featurization summary for all raw features.\n",
         "6. Test the best fitted model.\n",
         "\n",
         "In addition this notebook showcases the following features\n",
@@ -85,7 +93,6 @@
         "\n",
         "# Choose a name for the experiment.\n",
         "experiment_name = 'automl-local-missing-data'\n",
-        "project_folder = './sample_projects/automl-local-missing-data'\n",
         "\n",
         "experiment = Experiment(ws, experiment_name)\n",
         "\n",
@@ -95,7 +102,6 @@
         "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",
@@ -154,13 +160,11 @@
         "|**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",
         "|**preprocess**|Setting this to *True* enables AutoML to perform preprocessing on the input to handle *missing data*, and to perform some common *feature extraction*.|\n",
         "|**experiment_exit_score**|*double* value indicating the target for *primary_metric*. <br>Once the target is surpassed the run terminates.|\n",
         "|**blacklist_models**|*List* of *strings* indicating machine learning algorithms for AutoML to avoid in this run.<br><br> Allowed values for **Classification**<br><i>LogisticRegression</i><br><i>SGD</i><br><i>MultinomialNaiveBayes</i><br><i>BernoulliNaiveBayes</i><br><i>SVM</i><br><i>LinearSVM</i><br><i>KNN</i><br><i>DecisionTree</i><br><i>RandomForest</i><br><i>ExtremeRandomTrees</i><br><i>LightGBM</i><br><i>GradientBoosting</i><br><i>TensorFlowDNN</i><br><i>TensorFlowLinearClassifier</i><br><br>Allowed values for **Regression**<br><i>ElasticNet</i><br><i>GradientBoosting</i><br><i>DecisionTree</i><br><i>KNN</i><br><i>LassoLars</i><br><i>SGD</i><br><i>RandomForest</i><br><i>ExtremeRandomTrees</i><br><i>LightGBM</i><br><i>TensorFlowLinearRegressor</i><br><i>TensorFlowDNN</i>|\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.|"
+        "|**y**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|"
       ]
     },
     {
@@ -174,14 +178,12 @@
         "                             primary_metric = 'AUC_weighted',\n",
         "                             iteration_timeout_minutes = 60,\n",
         "                             iterations = 20,\n",
-        "                             n_cross_validations = 5,\n",
         "                             preprocess = True,\n",
         "                             experiment_exit_score = 0.9984,\n",
         "                             blacklist_models = ['KNN','LinearSVM'],\n",
         "                             verbosity = logging.INFO,\n",
         "                             X = X_train, \n",
-        "                             y = y_train,\n",
-        "                             path = project_folder)"
+        "                             y = y_train)"
       ]
     },
     {
@@ -318,6 +320,48 @@
         "# best_run, fitted_model = local_run.get_output(iteration = iteration)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### View the engineered names for featurized data\n",
+        "Below we display the engineered feature names generated for the featurized data using the preprocessing featurization."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "fitted_model.named_steps['datatransformer'].get_engineered_feature_names()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### View the featurization summary\n",
+        "Below we display the featurization that was performed on different raw features in the user data. For each raw feature in the user data, the following information is displayed:-\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": [
+        "# Get the featurization summary as a list of JSON\n",
+        "featurization_summary = fitted_model.named_steps['datatransformer'].get_featurization_summary()\n",
+        "# View the featurization summary as a pandas dataframe\n",
+        "pd.DataFrame.from_records(featurization_summary)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

how-to-use-azureml/automated-machine-learning/missing-data-blacklist-early-termination/auto-ml-missing-data-blacklist-early-termination.yml

@@ -0,0 +1,8 @@
+name: auto-ml-missing-data-blacklist-early-termination
+dependencies:
+- pip:
+  - azureml-sdk
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml