Delete auto-ml-dataprep-remote-execution.yml

add dataprep dependency to notebook

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,30 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: "[Notebook issue]"
+labels: ''
+assignees: ''
+
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+Provide the following if applicable:
++ Your Python & SDK version 
++ Python Scripts or the full notebook name
++ Pipeline definition 
++ Environment definition 
++ Example data 
++ Any log files. 
++ Run and Workspace Id 
+
+**To Reproduce**
+Steps to reproduce the behavior:
+1. 
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Additional context**
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/notebook-issue.md

@@ -0,0 +1,43 @@
+---
+name: Notebook issue
+about: Describe your notebook issue
+title: "[Notebook] DESCRIPTIVE TITLE"
+labels: notebook
+assignees: ''
+
+---
+
+### DESCRIPTION: Describe clearly + concisely
+
+
+.
+### REPRODUCIBLE: Steps
+
+
+.
+### EXPECTATION: Clear description 
+
+
+.
+### CONFIG/ENVIRONMENT: 
+```Provide where applicable
+
+## Your Python & SDK version:
+
+## Environment definition:
+
+## Notebook name or Python scripts:
+
+## Run and Workspace Id:
+
+## Pipeline definition:
+
+## Example data:
+
+## Any log files:
+
+
+
+
+
+```

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

@@ -24,8 +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
+# install the base SDK, Jupyter notebook server and tensorboard
-pip install azureml-sdk[notebooks]
+pip install azureml-sdk[notebooks,tensorboard]
 
 # install model explainability component
 pip install azureml-sdk[explain]

README.md

@@ -1,8 +1,17 @@
+---
+page_type: sample
+languages:
+- python
+products:
+- azure
+- azure-machine-learning-service
+description: "With Azure Machine Learning service, learn to prep data, train, test, deploy, manage, and track machine learning models in a cloud-based environment."
+---
+
 # Azure Machine Learning service example notebooks
 
 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)
 
 ## Quick installation
 ```sh
@@ -11,7 +20,7 @@ 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 +29,7 @@ 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 +47,7 @@ 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
@@ -52,5 +62,18 @@ The [How to use Azure ML](./how-to-use-azureml) folder contains specific example
 
 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.
  - [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)
+ 
+## 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)
+
+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 1.0.23 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version 1.0.57 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/azure-ml-with-nvidia-rapids.ipynb

@@ -20,7 +20,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-    "The [RAPIDS](https://www.developer.nvidia.com/rapids) suite of software libraries from NVIDIA enables the execution of end-to-end data science and analytics pipelines entirely on GPUs. In many machine learning projects, a significant portion of the model training time is spent in setting up the data; this stage of the process is known as Extraction, Transformation and Loading, or ETL. By using the DataFrame API for ETL and GPU-capable ML algorithms in RAPIDS, data preparation and training models can be done in GPU-accelerated end-to-end pipelines without incurring serialization costs between the pipeline stages. This notebook demonstrates how to use NVIDIA RAPIDS to prepare data and train model in Azure.\n",
+        "The [RAPIDS](https://www.developer.nvidia.com/rapids) suite of software libraries from NVIDIA enables the execution of end-to-end data science and analytics pipelines entirely on GPUs. In many machine learning projects, a significant portion of the model training time is spent in setting up the data; this stage of the process is known as Extraction, Transformation and Loading, or ETL. By using the DataFrame API for ETL\u00c3\u201a\u00c2\u00a0and GPU-capable ML algorithms in RAPIDS, data preparation and training models can be done in GPU-accelerated end-to-end pipelines without incurring serialization costs between the pipeline stages. This notebook demonstrates how to use NVIDIA RAPIDS to prepare data and train model\u00c2\u00a0in Azure.\n",
         " \n",
         "In this notebook, we will do the following:\n",
         " \n",

how-to-use-azureml/README.md

@@ -8,13 +8,10 @@ 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.
 * [enable-app-insights-in-production-service](./deployment/enable-app-insights-in-production-service) Learn how to use App Insights with production web service.
  
 Find quickstarts, end-to-end tutorials, and how-tos on the [official documentation site for Azure Machine Learning service](https://docs.microsoft.com/en-us/azure/machine-learning/service/).
-
-
- ![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/README.png)

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

@@ -115,16 +115,7 @@ jupyter notebook
     - 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)
+- [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 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 automated ML settings as kwargs
-
-- [auto-ml-remote-amlcompute.ipynb](remote-batchai/auto-ml-remote-amlcompute.ipynb)
     - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
     - Example of using automated ML for classification using remote AmlCompute for training
     - Parallel execution of iterations
@@ -133,12 +124,6 @@ jupyter notebook
     - Retrieving models for any iteration or logged metric
     - Specify automated ML settings as kwargs
 
-- [auto-ml-remote-attach.ipynb](remote-attach/auto-ml-remote-attach.ipynb)
-    - Dataset: Scikit learn's [20newsgroup](http://scikit-learn.org/stable/datasets/twenty_newsgroups.html)
-    - handling text data with preprocess flag
-    - Reading data from a blob store for remote executions
-    - using pandas dataframes for reading data
-
 - [auto-ml-missing-data-blacklist-early-termination.ipynb](missing-data-blacklist-early-termination/auto-ml-missing-data-blacklist-early-termination.ipynb)
     - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
     - Blacklist certain pipelines
@@ -156,10 +141,6 @@ jupyter notebook
     - 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 automated ML for classification
@@ -174,11 +155,11 @@ 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)
+- [auto-ml-dataset.ipynb](dataprep/auto-ml-dataset.ipynb)
-    - Using DataPrep for reading data
+    - Using Dataset for reading data
 
-- [auto-ml-dataprep-remote-execution.ipynb](dataprep-remote-execution/auto-ml-dataprep-remote-execution.ipynb)
+- [auto-ml-dataset-remote-execution.ipynb](dataprep-remote-execution/auto-ml-dataset-remote-execution.ipynb)
-    - Using DataPrep for reading data with remote execution
+    - 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)
@@ -194,10 +175,39 @@ jupyter notebook
     - 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 [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
+    - 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.
 

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

@@ -2,6 +2,7 @@ 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
@@ -10,12 +11,15 @@ dependencies:
 - 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
+- pandas>=0.22.0,<=0.23.4
 - py-xgboost<=0.80
+- pyarrow>=0.11.0
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
-  - azureml-sdk[automl,explain]
+  - azureml-defaults
+  - azureml-train-automl
   - azureml-widgets
+  - azureml-explain-model
   - pandas_ml
   

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

@@ -0,0 +1,26 @@
+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>=1.11.0,<=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
+
+- pip:
+  # Required packages for AzureML execution, history, and data preparation.
+  - azureml-defaults
+  - azureml-train-automl
+  - azureml-widgets
+  - azureml-explain-model
+  - pandas_ml
+  

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

@@ -9,6 +9,8 @@ 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 (
@@ -42,6 +44,15 @@ IF NOT "%options%"=="nolaunch" (
 
 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.
 

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

@@ -12,7 +12,7 @@ fi
 
 if [ "$AUTOML_ENV_FILE" == "" ]
 then
-  AUTOML_ENV_FILE="automl_env.yml"
+  AUTOML_ENV_FILE="automl_env_mac.yml"
 fi
 
 if [ ! -f $AUTOML_ENV_FILE ]; then

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

@@ -0,0 +1,718 @@
+{
+  "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",
+        "# project folder\n",
+        "project_folder = './sample_projects/automl-classification-bankmarketing'\n",
+        "\n",
+        "experiment=Experiment(ws, experiment_name)\n",
+        "\n",
+        "output = {}\n",
+        "output['SDK version'] = azureml.core.VERSION\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace'] = ws.name\n",
+        "output['Resource Group'] = ws.resource_group\n",
+        "output['Location'] = ws.location\n",
+        "output['Project Directory'] = project_folder\n",
+        "output['Experiment Name'] = experiment.name\n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
+        "outputDf.T"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 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",
+        "Here load the data in the get_data() script to be utilized in azure compute. To do this  first load all the necessary libraries and dependencies to set up paths for the data and to create the conda_Run_config."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "if not os.path.isdir('data'):\n",
+        "    os.mkdir('data')\n",
+        "    \n",
+        "if not os.path.exists(project_folder):\n",
+        "    os.makedirs(project_folder)"
+      ]
+    },
+    {
+      "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",
+        "Here we create the script to be run in azure comput for loading the data, we load the bank marketing dataset into X_train and y_train. Next X_train and y_train is returned for training 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",
+        "X_train = dataset.drop_columns(columns=['y'])\n",
+        "y_train = dataset.keep_columns(columns=['y'], validate=True)\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",
+        "|**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",
+        "\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",
+        "                             path = project_folder,\n",
+        "                             run_configuration=conda_run_config,\n",
+        "                             X = X_train,\n",
+        "                             y = y_train,\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-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": [
+        "### Create a Container Image\n",
+        "\n",
+        "Next use Azure Container Instances for deploying models as a web service for quickly deploying and validating your model\n",
+        "or when testing a model that is under development."
+      ]
+    },
+    {
+      "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': \"bmData\", '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\n",
+        "\n",
+        "Deploy an image that contains the model and other assets needed by the service."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.webservice import AciWebservice\n",
+        "\n",
+        "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
+        "                                               memory_gb = 1, \n",
+        "                                               tags = {'area': \"bmData\", 'type': \"automl_classification\"}, \n",
+        "                                               description = 'sample service for Automl Classification')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.webservice import Webservice\n",
+        "\n",
+        "aci_service_name = 'automl-sample-bankmarketing'\n",
+        "print(aci_service_name)\n",
+        "aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
+        "                                           image = image,\n",
+        "                                           name = aci_service_name,\n",
+        "                                           workspace = ws)\n",
+        "aci_service.wait_for_deployment(True)\n",
+        "print(aci_service.state)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Delete a Web Service\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 +1,10 @@
+name: auto-ml-classification-bank-marketing
+dependencies:
+- pip:
+  - azureml-sdk
+  - 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 +1,709 @@
+{
+  "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",
+        "# project folder\n",
+        "project_folder = './sample_projects/automl-classification-creditcard'\n",
+        "\n",
+        "experiment=Experiment(ws, experiment_name)\n",
+        "\n",
+        "output = {}\n",
+        "output['SDK version'] = azureml.core.VERSION\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace'] = ws.name\n",
+        "output['Resource Group'] = ws.resource_group\n",
+        "output['Location'] = ws.location\n",
+        "output['Project Directory'] = project_folder\n",
+        "output['Experiment Name'] = experiment.name\n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
+        "outputDf.T"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 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",
+        "Here load the data in the get_data script to be utilized in azure compute. To do this, first load all the necessary libraries and dependencies to set up paths for the data and to create the conda_run_config."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "if not os.path.isdir('data'):\n",
+        "    os.mkdir('data')\n",
+        "    \n",
+        "if not os.path.exists(project_folder):\n",
+        "    os.makedirs(project_folder)"
+      ]
+    },
+    {
+      "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",
+        "Here create the script to be run in azure compute for loading the data, load the credit card dataset into cards and store the Class column (y) in the y variable and store the remaining data in the x variable. Next split the data using random_split and return X_train and y_train for training 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",
+        "X = dataset.drop_columns(columns=['Class'])\n",
+        "y = dataset.keep_columns(columns=['Class'], validate=True)\n",
+        "X_train, X_test = X.random_split(percentage=0.8, seed=223)\n",
+        "y_train, y_test = y.random_split(percentage=0.8, seed=223)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train\n",
+        "\n",
+        "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
+        "\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**task**|classification or regression|\n",
+        "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
+        "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+        "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
+        "|**n_cross_validations**|Number of cross validation splits.|\n",
+        "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+        "|**y**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|\n",
+        "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|\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_20190417.log',\n",
+        "                             path = project_folder,\n",
+        "                             run_configuration=conda_run_config,\n",
+        "                             X = X_train,\n",
+        "                             y = y_train,\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-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": [
+        "### Create a Container Image\n",
+        "\n",
+        "Next use Azure Container Instances for deploying models as a web service for quickly deploying and validating your model\n",
+        "or when testing a model that is under development."
+      ]
+    },
+    {
+      "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': \"cards\", '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\n",
+        "\n",
+        "Deploy an image that contains the model and other assets needed by the service."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.webservice import AciWebservice\n",
+        "\n",
+        "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
+        "                                               memory_gb = 1, \n",
+        "                                               tags = {'area': \"cards\", 'type': \"automl_classification\"}, \n",
+        "                                               description = 'sample service for Automl Classification')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.webservice import Webservice\n",
+        "\n",
+        "aci_service_name = 'automl-sample-creditcard'\n",
+        "print(aci_service_name)\n",
+        "aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
+        "                                           image = image,\n",
+        "                                           name = aci_service_name,\n",
+        "                                           workspace = ws)\n",
+        "aci_service.wait_for_deployment(True)\n",
+        "print(aci_service.state)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Delete a Web Service\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 +1,10 @@
+name: auto-ml-classification-credit-card-fraud
+dependencies:
+- pip:
+  - azureml-sdk
+  - 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": {},
@@ -290,7 +297,7 @@
       "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 +310,7 @@
         "from azureml.core.conda_dependencies import CondaDependencies\n",
         "\n",
         "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn','py-xgboost<=0.80'],\n",
-        "                                 pip_packages=['azureml-sdk[automl]'])\n",
+        "                                 pip_packages=['azureml-train-automl'])\n",
         "\n",
         "conda_env_file_name = 'myenv.yml'\n",
         "myenv.save_to_file('.', conda_env_file_name)"
@@ -323,7 +330,7 @@
         "    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",

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

@@ -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-onnx/auto-ml-classification-with-onnx.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -22,7 +29,6 @@
         "1. [Data](#Data)\n",
         "1. [Train](#Train)\n",
         "1. [Results](#Results)\n",
-        "1. [Test](#Test)\n",
         "\n"
       ]
     },
@@ -32,7 +38,7 @@
       "source": [
         "## Introduction\n",
         "\n",
-        "In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset) to showcase how you can use AutoML for a simple classification problem.\n",
+        "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",
@@ -42,7 +48,8 @@
         "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."
+        "4. Explore the results and save the ONNX model.\n",
+        "5. Inference with the ONNX model."
       ]
     },
     {
@@ -66,11 +73,12 @@
         "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"
+        "from azureml.train.automl import AutoMLConfig, constants"
       ]
     },
     {
@@ -106,7 +114,7 @@
       "source": [
         "## Data\n",
         "\n",
-        "This uses scikit-learn's [load_digits](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) method."
+        "This uses scikit-learn's [load_iris](https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_iris.html) method."
       ]
     },
     {
@@ -115,22 +123,44 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "digits = datasets.load_digits()\n",
+        "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)\n",
         "\n",
-        "# Exclude the first 100 rows from training so that they can be used for test.\n",
+        "\n"
-        "X_train = digits.data[100:,:]\n",
-        "y_train = digits.target[100:]"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Train with enable ONNX compatible models config on\n",
+        "### 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",
-        "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",
+        "**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",
@@ -144,6 +174,13 @@
         "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Set the preprocess=True,  currently the InferenceHelper only supports this mode."
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -158,6 +195,7 @@
         "                             verbosity = logging.INFO,                             \n",
         "                             X = X_train, \n",
         "                             y = y_train,\n",
+        "                             preprocess=True,\n",
         "                             enable_onnx_compatible_models=True,\n",
         "                             path = project_folder)"
       ]
@@ -249,10 +287,69 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.train.automl._vendor.automl.client.core.common.onnx_convert import OnnxConverter\n",
+        "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": {

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",

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": {},
@@ -251,7 +258,11 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "metadata": {},
+      "metadata": {
+        "tags": [
+          "widget-rundetails-sample"
+        ]
+      },
       "outputs": [],
       "source": [
         "from azureml.widgets import RunDetails\n",
@@ -328,6 +339,12 @@
         "            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",
+        "1. Create a `TabularDataset` pointing to the training data.\n",
-        "2. Pass the `Dataflow` to AutoML for a local run.\n",
+        "2. Pass the `TabularDataset` to AutoML for a remote run."
-        "3. Pass the `Dataflow` to AutoML for a remote run."
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Setup\n",
+        "## Setup"
-        "\n",
-        "Currently, Data Prep only supports __Ubuntu 16__ and __Red Hat Enterprise Linux 7__. We are working on supporting more linux distros."
       ]
     },
     {
@@ -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"
       ]
     },
@@ -84,9 +86,9 @@
         "ws = Workspace.from_config()\n",
         "\n",
         "# choose a name for experiment\n",
-        "experiment_name = 'automl-dataprep-remote-dsvm'\n",
+        "experiment_name = 'automl-dataset-remote-bai'\n",
         "# project folder\n",
-        "project_folder = './sample_projects/automl-dataprep-remote-dsvm'\n",
+        "project_folder = './sample_projects/automl-dataprep-remote-bai'\n",
         " \n",
         "experiment = Experiment(ws, experiment_name)\n",
         " \n",
@@ -116,22 +118,21 @@
       "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 a 1MB simple random sample of the Chicago Crime data into a local temporary directory.\n",
-        "# The data referenced here was pulled from `sklearn.datasets.load_digits()`.\n",
+        "example_data = 'https://dprepdata.blob.core.windows.net/demo/crime0-random.csv'\n",
-        "simple_example_data_root = 'https://dprepdata.blob.core.windows.net/automl-notebook-data/'\n",
+        "dataset = Dataset.Tabular.from_delimited_files(example_data)\n",
-        "X = dprep.auto_read_file(simple_example_data_root + 'X.csv').skip(1)  # Remove the header row.\n",
+        "dataset.take(5).to_pandas_dataframe()"
-        "\n",
-        "# You can also use `read_csv` and `to_*` transformations to read (with overridable delimiter)\n",
-        "# and convert column types manually.\n",
-        "# Here we read a comma delimited file and convert all columns to integers.\n",
-        "y = dprep.read_csv(simple_example_data_root + 'y.csv').to_long(dprep.ColumnSelector(term='.*', use_regex = True))"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "You can peek the result of a Dataflow at any range using `skip(i)` and `head(j)`. Doing so evaluates only `j` records for all the steps in the Dataflow, which makes it fast even against large datasets."
+        "### 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 +141,8 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "X.skip(1).head(5)"
+        "X = dataset.drop_columns(columns=['Primary Type', 'FBI Code'])\n",
+        "y = dataset.keep_columns(columns=['Primary Type'], validate=True)"
       ]
     },
     {
@@ -162,9 +164,8 @@
         "    \"iteration_timeout_minutes\" : 10,\n",
         "    \"iterations\" : 2,\n",
         "    \"primary_metric\" : 'AUC_weighted',\n",
-        "    \"preprocess\" : False,\n",
+        "    \"preprocess\" : True,\n",
-        "    \"verbosity\" : logging.INFO,\n",
+        "    \"verbosity\" : logging.INFO\n",
-        "    \"n_cross_validations\": 3\n",
         "}"
       ]
     },
@@ -172,7 +173,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Create or Attach a Remote Linux DSVM"
+        "### Create or Attach an AmlCompute cluster"
       ]
     },
     {
@@ -181,21 +182,37 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "dsvm_name = 'mydsvmc'\n",
+        "from azureml.core.compute import AmlCompute\n",
+        "from azureml.core.compute import ComputeTarget\n",
         "\n",
-        "try:\n",
+        "# Choose a name for your cluster.\n",
-        "    while ws.compute_targets[dsvm_name].provisioning_state == 'Creating':\n",
+        "amlcompute_cluster_name = \"automlc2\"\n",
-        "        time.sleep(1)\n",
         "\n",
-        "    dsvm_compute = DsvmCompute(ws, dsvm_name)\n",
+        "found = False\n",
-        "    print('Found existing DVSM.')\n",
+        "\n",
-        "except:\n",
+        "# Check if this compute target already exists in the workspace.\n",
-        "    print('Creating a new DSVM.')\n",
+        "\n",
-        "    dsvm_config = DsvmCompute.provisioning_configuration(vm_size = \"Standard_D2_v2\")\n",
+        "cts = ws.compute_targets\n",
-        "    dsvm_compute = DsvmCompute.create(ws, name = dsvm_name, provisioning_configuration = dsvm_config)\n",
+        "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
-        "    dsvm_compute.wait_for_completion(show_output = True)\n",
+        "    found = True\n",
-        "    print(\"Waiting one minute for ssh to be accessible\")\n",
+        "    print('Found existing compute target.')\n",
-        "    time.sleep(90) # Wait for ssh to be accessible"
+        "    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 +223,16 @@
       "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 +240,9 @@
       "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."
       ]
     },
     {
@@ -257,6 +278,44 @@
         "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 +435,8 @@
       "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 +445,13 @@
       "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",
+        "df_test = dataset_test.to_pandas_dataframe()\n",
-        "X_test = digits.data[:10, :]\n",
+        "df_test = df_test[pd.notnull(df_test['Primary Type'])]\n",
-        "y_test = digits.target[:10]\n",
+        "\n",
-        "images = digits.images[:10]"
+        "y_test = df_test[['Primary Type']]\n",
+        "X_test = df_test.drop(['Primary Type', 'FBI Code'], axis=1)"
       ]
     },
     {
@@ -398,7 +459,7 @@
       "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 +468,15 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "#Randomly select digits and test\n",
+        "from pandas_ml import ConfusionMatrix\n",
-        "from matplotlib import pyplot as plt\n",
-        "import numpy as np\n",
         "\n",
-        "for index in np.random.choice(len(y_test), 2, replace = False):\n",
+        "ypred = fitted_model.predict(X_test)\n",
-        "    print(index)\n",
-        "    predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
-        "    label = y_test[index]\n",
-        "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
-        "    fig = plt.figure(1, figsize=(3,3))\n",
-        "    ax1 = fig.add_axes((0,0,.8,.8))\n",
-        "    ax1.set_title(title)\n",
-        "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
-        "    plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Appendix"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Capture the `Dataflow` Objects for Later Use in AutoML\n",
         "\n",
-        "`Dataflow` objects are immutable and are composed of a list of data preparation steps. A `Dataflow` object can be branched at any point for further usage."
+        "cm = ConfusionMatrix(y_test['Primary Type'], ypred)\n",
-      ]
+        "\n",
-    },
+        "print(cm)\n",
-    {
+        "\n",
-      "cell_type": "code",
+        "cm.plot()"
-      "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])"
       ]
     }
   ],

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

@@ -0,0 +1,10 @@
+name: auto-ml-dataset-remote-execution
+dependencies:
+- pip:
+  - azureml-sdk
+  - 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",
+        "1. Create a `TabularDataset` pointing to the training data.\n",
-        "2. Pass the `Dataflow` to AutoML for a local run.\n",
+        "2. Pass the `TabularDataset` to AutoML for a local run."
-        "3. Pass the `Dataflow` to AutoML for a remote run."
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Setup\n",
+        "## Setup"
-        "\n",
-        "Currently, Data Prep only supports __Ubuntu 16__ and __Red Hat Enterprise Linux 7__. We are working on supporting more linux distros."
       ]
     },
     {
@@ -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 +86,9 @@
         "ws = Workspace.from_config()\n",
         " \n",
         "# choose a name for experiment\n",
-        "experiment_name = 'automl-dataprep-local'\n",
+        "experiment_name = 'automl-dataset-local'\n",
         "# project folder\n",
-        "project_folder = './sample_projects/automl-dataprep-local'\n",
+        "project_folder = './sample_projects/automl-dataset-local'\n",
         " \n",
         "experiment = Experiment(ws, experiment_name)\n",
         " \n",
@@ -114,24 +118,21 @@
       "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 a 1MB simple random sample of the Chicago Crime data into a local temporary directory.\n",
-        "# The data referenced here was pulled from `sklearn.datasets.load_digits()`.\n",
+        "example_data = 'https://dprepdata.blob.core.windows.net/demo/crime0-random.csv'\n",
-        "simple_example_data_root = 'https://dprepdata.blob.core.windows.net/automl-notebook-data/'\n",
+        "dataset = Dataset.Tabular.from_delimited_files(example_data)\n",
-        "X = dprep.auto_read_file(simple_example_data_root + 'X.csv').skip(1)  # Remove the header row.\n",
+        "dataset.take(5).to_pandas_dataframe()"
-        "\n",
-        "# You can also use `read_csv` and `to_*` transformations to read (with overridable delimiter)\n",
-        "# and convert column types manually.\n",
-        "# Here we read a comma delimited file and convert all columns to integers.\n",
-        "y = dprep.read_csv(simple_example_data_root + 'y.csv').to_long(dprep.ColumnSelector(term='.*', use_regex = True))"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Review the Data Preparation Result\n",
+        "### 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 +141,8 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "X.skip(1).head(5)"
+        "X = dataset.drop_columns(columns=['Primary Type', 'FBI Code'])\n",
+        "y = dataset.keep_columns(columns=['Primary Type'], validate=True)"
       ]
     },
     {
@@ -162,7 +164,7 @@
         "    \"iteration_timeout_minutes\" : 10,\n",
         "    \"iterations\" : 2,\n",
         "    \"primary_metric\" : 'AUC_weighted',\n",
-        "    \"preprocess\" : False,\n",
+        "    \"preprocess\" : True,\n",
         "    \"verbosity\" : logging.INFO\n",
         "}"
       ]
@@ -171,9 +173,9 @@
       "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."
       ]
     },
     {
@@ -326,7 +328,8 @@
       "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."
       ]
     },
     {
@@ -335,12 +338,13 @@
       "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",
+        "df_test = dataset_test.to_pandas_dataframe()\n",
-        "X_test = digits.data[:10, :]\n",
+        "df_test = df_test[pd.notnull(df_test['Primary Type'])]\n",
-        "y_test = digits.target[:10]\n",
+        "\n",
-        "images = digits.images[:10]"
+        "y_test = df_test[['Primary Type']]\n",
+        "X_test = df_test.drop(['Primary Type', 'FBI Code'], axis=1)"
       ]
     },
     {
@@ -348,7 +352,7 @@
       "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."
       ]
     },
     {
@@ -357,65 +361,15 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "#Randomly select digits and test\n",
+        "from pandas_ml import ConfusionMatrix\n",
-        "from matplotlib import pyplot as plt\n",
-        "import numpy as np\n",
         "\n",
-        "for index in np.random.choice(len(y_test), 2, replace = False):\n",
+        "ypred = fitted_model.predict(X_test)\n",
-        "    print(index)\n",
-        "    predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
-        "    label = y_test[index]\n",
-        "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
-        "    fig = plt.figure(1, figsize=(3,3))\n",
-        "    ax1 = fig.add_axes((0,0,.8,.8))\n",
-        "    ax1.set_title(title)\n",
-        "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
-        "    plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Appendix"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Capture the `Dataflow` Objects for Later Use in AutoML\n",
         "\n",
-        "`Dataflow` objects are immutable and are composed of a list of data preparation steps. A `Dataflow` object can be branched at any point for further usage."
+        "cm = ConfusionMatrix(y_test['Primary Type'], ypred)\n",
-      ]
+        "\n",
-    },
+        "print(cm)\n",
-    {
+        "\n",
-      "cell_type": "code",
+        "cm.plot()"
-      "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])"
       ]
     }
   ],

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

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

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",
+        "for run_id, metrics in all_metrics.items():\n",
-        "    properties = run.get_properties()\n",
+        "    iteration = int(run_id.split('_')[-1])\n",
-        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+        "    float_metrics = {k: v for k, v in metrics.items() if isinstance(v, float)}\n",
-        "    metricslist[int(properties['iteration'])] = metrics\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

@@ -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-bike-share/auto-ml-forecasting-bike-share.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -29,19 +36,17 @@
       "metadata": {},
       "source": [
         "## Introduction\n",
-        "In this example, we show how AutoML can be used for bike share forecasting.\n",
+        "This notebook demonstrates demand forecasting for a bike-sharing service using AutoML.\n",
         "\n",
-        "The purpose is to demonstrate how to take advantage of the built-in holiday featurization, access the feature names, and further demonstrate how to work 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",
+        "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",
-        "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",
+        "2. Configuration and local run of AutoML for a time-series model with lag and holiday features \n",
-        "3. Training the Model using local compute\n",
+        "3. Viewing the engineered names for featurized data and featurization summary for all raw features\n",
-        "4. Exploring the results\n",
+        "4. Evaluating the fitted model using a rolling test "
-        "5. Viewing the engineered names for featurized data and featurization summary for all raw features\n",
-        "6. Testing the fitted model"
       ]
     },
     {
@@ -62,10 +67,12 @@
         "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",
-        "\n",
         "from azureml.core.workspace import Workspace\n",
         "from azureml.core.experiment import Experiment\n",
         "from azureml.train.automl import AutoMLConfig\n",
@@ -77,7 +84,7 @@
       "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."
       ]
     },
     {
@@ -122,14 +129,15 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "data = pd.read_csv('bike-no.csv', parse_dates=['date'])"
+        "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 abou the dataset. \n",
+        "Let's set up what we know about the dataset. \n",
         "\n",
         "**Target column** is what we want to forecast.\n",
         "\n",
@@ -187,8 +195,7 @@
       "source": [
         "### Setting forecaster maximum horizon \n",
         "\n",
-        "Assuming your test data forms a full and regular time series(regular time intervals and no holes), \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).  "
-        "the maximum horizon you will need to forecast is the length of the longest grain in your test set."
       ]
     },
     {
@@ -197,10 +204,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "if len(grain_column_names) == 0:\n",
+        "max_horizon = 14"
-        "    max_horizon = len(X_test)\n",
-        "else:\n",
-        "    max_horizon = X_test.groupby(grain_column_names)[time_column_name].count().max()"
       ]
     },
     {
@@ -220,7 +224,7 @@
         "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
         "|**y**|(sparse) array-like, shape = [n_samples, ], targets values.|\n",
         "|**n_cross_validations**|Number of cross validation splits.|\n",
-        "|**country**|The country used to generate holiday features. These should be ISO 3166 two-letter country codes (i.e. 'US', 'GB').|\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",
         "|**path**|Relative path to the project folder.  AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder. "
       ]
     },
@@ -230,15 +234,14 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "time_column_name = 'date'\n",
         "automl_settings = {\n",
-        "    \"time_column_name\": time_column_name,\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",
+        "    'drop_column_names': ['casual', 'registered']\n",
-        "    # knowing the country allows Automated ML to bring in holidays\n",
-        "    \"country\" : 'US',\n",
-        "    \"max_horizon\" : max_horizon,\n",
-        "    \"target_lags\": 1    \n",
         "}\n",
         "\n",
         "automl_config = AutoMLConfig(task='forecasting',                             \n",
@@ -257,7 +260,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "We will now run the experiment, starting with 10 iterations of model search. Experiment can be continued for more iterations if the results are not yet good. You will see the currently running iterations printing to the console."
+        "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."
       ]
     },
     {
@@ -342,18 +345,26 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "fitted_model.named_steps['timeseriestransformer'].get_featurization_summary()"
+        "# 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": [
-        "### Test the Best Fitted Model\n",
+        "## 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",
-        "Predict on training and test set, and calculate residual values.\n",
+        "We always score on the original dataset whose schema matches the training set schema."
-        "\n",
-        "We always score on the original dataset whose schema matches the scheme of the training dataset."
       ]
     },
     {
@@ -365,21 +376,12 @@
         "X_test.head()"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "y_query = y_test.copy().astype(np.float)\n",
-        "y_query.fill(np.NaN)\n",
-        "y_fcst, X_trans = fitted_model.forecast(X_test, y_query)"
-      ]
-    },
     {
       "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."
       ]
     },
@@ -389,7 +391,8 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "def align_outputs(y_predicted, X_trans, X_test, y_test, predicted_column_name = 'predicted'):\n",
+        "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",
@@ -401,7 +404,8 @@
         "    * 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",
+        "    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",
@@ -420,7 +424,49 @@
         "    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"
+        "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)"
       ]
     },
     {
@@ -429,6 +475,30 @@
       "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",
@@ -438,8 +508,7 @@
         "    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(actual_safe, pred_safe))"
-        "    return np.mean(APE)"
       ]
     },
     {
@@ -456,18 +525,63 @@
         "print('MAPE: %.2f' % MAPE(df_all[target_column_name], df_all['predicted']))\n",
         "\n",
         "# Plot outputs\n",
-        "%matplotlib notebook\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": "xiaga@microsoft.com, tosingli@microsoft.com"
+        "name": "erwright"
       }
     ],
     "kernelspec": {
@@ -485,7 +599,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.7"
+      "version": "3.6.8"
     }
   },
   "nbformat": 4,

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-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": {},
@@ -28,17 +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",
+        "2. Configuration and local run of AutoML for a simple time-series model\n",
-        "3. Training the Model using local compute\n",
+        "3. View engineered features and prediction results\n",
-        "4. Exploring the results\n",
+        "4. Configuration and local run of AutoML for a time-series model with lag and rolling window features\n",
-        "5. Viewing the engineered names for featurized data and featurization summary for all raw features\n",
+        "5. Estimate feature importance"
-        "6. Testing the fitted model"
       ]
     },
     {
@@ -59,10 +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",
@@ -74,7 +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."
       ]
     },
     {
@@ -110,7 +116,7 @@
       "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. "
       ]
     },
     {
@@ -123,13 +129,20 @@
         "data.head()"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "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."
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {},
       "outputs": [],
       "source": [
-        "# let's take note of what columns means what in the data\n",
+        "# Dataset schema\n",
         "time_column_name = 'timeStamp'\n",
         "target_column_name = 'demand'"
       ]
@@ -138,7 +151,14 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Split the data into train and test sets\n"
+        "### Forecast Horizon\n",
+        "\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."
       ]
     },
     {
@@ -147,8 +167,32 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "X_train = data[data[time_column_name] < '2017-02-01']\n",
+        "max_horizon = 48"
-        "X_test = data[data[time_column_name] >= '2017-02-01']\n",
+      ]
+    },
+    {
+      "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"
       ]
@@ -159,7 +203,7 @@
       "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",
@@ -169,7 +213,7 @@
         "|**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",
-        "|**n_cross_validations**|Number of cross validation splits.|\n",
+        "|**n_cross_validations**|Number of cross validation splits. Rolling Origin Validation is used to split time-series in a temporally consistent way.|\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. "
       ]
     },
@@ -179,14 +223,15 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "automl_settings = {\n",
+        "time_series_settings = {\n",
-        "    \"time_column_name\": time_column_name    \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",
         "                             primary_metric='normalized_root_mean_squared_error',\n",
+        "                             blacklist_models = ['ExtremeRandomTrees'],\n",
         "                             iterations=10,\n",
         "                             iteration_timeout_minutes=5,\n",
         "                             X=X_train,\n",
@@ -194,7 +239,7 @@
         "                             n_cross_validations=3,\n",
         "                             path=project_folder,\n",
         "                             verbosity = logging.INFO,\n",
-        "                            **automl_settings)"
+        "                             **time_series_settings)"
       ]
     },
     {
@@ -351,7 +396,8 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Calculate accuracy metrics\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."
       ]
     },
     {
@@ -387,10 +433,13 @@
         "print('MAPE: %.2f' % MAPE(df_all[target_column_name], df_all['predicted']))\n",
         "\n",
         "# Plot outputs\n",
-        "%matplotlib notebook\n",
+        "%matplotlib inline\n",
-        "test_pred = plt.scatter(df_all[target_column_name], df_all['predicted'], color='b')\n",
+        "pred, = plt.plot(df_all[time_column_name], df_all['predicted'], color='b')\n",
-        "test_test = plt.scatter(y_test, y_test, color='g')\n",
+        "actual, = plt.plot(df_all[time_column_name], df_all[target_column_name], color='g')\n",
-        "plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\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()"
       ]
     },
@@ -405,16 +454,16 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Using lags and rolling window features to improve the forecast"
+        "### 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.\n",
+        "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 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."
+        "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."
       ]
     },
     {
@@ -423,27 +472,32 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "automl_settings_lags = {\n",
+        "time_series_settings_with_lags = {\n",
         "    'time_column_name': time_column_name,\n",
-        "    'target_lags': 1,\n",
+        "    'max_horizon': max_horizon,\n",
-        "    'target_rolling_window_size': 5,\n",
+        "    'target_lags': 12,\n",
-        "    # you MUST set the max_horizon when using lags and rolling windows\n",
+        "    'target_rolling_window_size': 4\n",
-        "    # it is optional when looking-back features are not used \n",
-        "    'max_horizon': len(y_test), # only one grain\n",
         "}\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'],\n",
         "                                  iterations=10,\n",
-        "                             iteration_timeout_minutes = 5,\n",
+        "                                  iteration_timeout_minutes=10,\n",
         "                                  X=X_train,\n",
         "                                  y=y_train,\n",
         "                                  n_cross_validations=3,\n",
         "                                  path=project_folder,\n",
         "                                  verbosity=logging.INFO,\n",
-        "                            **automl_settings_lags)"
+        "                                  **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."
       ]
     },
     {
@@ -490,10 +544,11 @@
         "print('MAPE: %.2f' % MAPE(df_lags[target_column_name], df_lags['predicted']))\n",
         "\n",
         "# Plot outputs\n",
-        "%matplotlib notebook\n",
+        "%matplotlib inline\n",
-        "test_pred = plt.scatter(df_lags[target_column_name], df_lags['predicted'], color='b')\n",
+        "pred, = plt.plot(df_lags[time_column_name], df_lags['predicted'], color='b')\n",
-        "test_test = plt.scatter(y_test, y_test, color='g')\n",
+        "actual, = plt.plot(df_lags[time_column_name], df_lags[target_column_name], color='g')\n",
-        "plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
+        "plt.xticks(fontsize=8)\n",
+        "plt.legend((pred, actual), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
         "plt.show()"
       ]
     },
@@ -513,8 +568,8 @@
         "from azureml.train.automl.automlexplainer import explain_model\n",
         "\n",
         "# feature names are everything in the transformed data except the target\n",
-        "features = X_trans.columns[:-1]\n",
+        "features = X_trans_lags.columns[:-1]\n",
-        "expl = explain_model(fitted_model, X_train, X_test, features = features, best_run=best_run_lags, y_train = y_train)\n",
+        "expl = explain_model(fitted_model_lags, X_train.copy(), X_test.copy(), features=features, best_run=best_run_lags, y_train=y_train)\n",
         "# unpack the tuple\n",
         "shap_values, expected_values, feat_overall_imp, feat_names, per_class_summary, per_class_imp = expl\n",
         "best_run_lags"
@@ -533,7 +588,7 @@
   "metadata": {
     "authors": [
       {
-        "name": "xiaga, tosingli"
+        "name": "erwright"
       }
     ],
     "kernelspec": {
@@ -551,7 +606,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.7"
+      "version": "3.6.8"
     }
   },
   "nbformat": 4,

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

@@ -0,0 +1,10 @@
+name: auto-ml-forecasting-energy-demand
+dependencies:
+- pip:
+  - azureml-sdk
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml
+  - statsmodels
+  - azureml-explain-model

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": {},
@@ -30,16 +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."
       ]
     },
@@ -61,10 +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",
@@ -75,7 +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. "
       ]
     },
     {
@@ -229,7 +230,7 @@
         "\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",
@@ -243,7 +244,8 @@
         "|**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",
@@ -262,7 +264,7 @@
         "    'time_column_name': time_column_name,\n",
         "    'grain_column_names': grain_column_names,\n",
         "    'drop_column_names': ['logQuantity'],\n",
-        "    'max_horizon': n_test_periods # optional\n",
+        "    'max_horizon': n_test_periods\n",
         "}\n",
         "\n",
         "automl_config = AutoMLConfig(task='forecasting',\n",
@@ -271,8 +273,9 @@
         "                             iterations=10,\n",
         "                             X=X_train,\n",
         "                             y=y_train,\n",
-        "                             n_cross_validations=5,\n",
+        "                             n_cross_validations=3,\n",
-        "                             enable_ensembling=False,\n",
+        "                             enable_voting_ensemble=False,\n",
+        "                             enable_stack_ensemble=False,\n",
         "                             path=project_folder,\n",
         "                             verbosity=logging.INFO,\n",
         "                             **time_series_settings)"
@@ -317,7 +320,8 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "# Predict\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:"
       ]
     },
@@ -461,7 +465,7 @@
         "# Plot outputs\n",
         "import matplotlib.pyplot as plt\n",
         "\n",
-        "%matplotlib notebook\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",
@@ -661,10 +665,10 @@
         "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-sdk', 'azureml-core']:\n",
+        "for p in ['azureml-train-automl', 'azureml-core']:\n",
         "    print('{}\\t{}'.format(p, dependencies[p]))\n",
         "\n",
-        "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn'], pip_packages=['azureml-sdk[automl]'])\n",
+        "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn'], pip_packages=['azureml-train-automl'])\n",
         "\n",
         "myenv.save_to_file('.', conda_env_file_name)"
       ]
@@ -686,7 +690,7 @@
         "    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",
@@ -827,7 +831,7 @@
   "metadata": {
     "authors": [
       {
-        "name": "erwright, tosingli"
+        "name": "erwright"
       }
     ],
     "kernelspec": {
@@ -845,7 +849,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.7"
+      "version": "3.6.8"
     }
   },
   "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": {},
@@ -353,7 +360,10 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "fitted_model.named_steps['datatransformer'].get_featurization_summary()"
+        "# 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)"
       ]
     },
     {

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

how-to-use-azureml/automated-machine-learning/model-explanation/auto-ml-model-explanation.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/model-explanation/auto-ml-model-explanation.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

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

@@ -0,0 +1,9 @@
+name: auto-ml-model-explanation
+dependencies:
+- pip:
+  - azureml-sdk
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml
+  - azureml-explain-model

how-to-use-azureml/automated-machine-learning/regression-concrete-strength/auto-ml-regression-concrete-strength.ipynb

@@ -0,0 +1,796 @@
+{
+  "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/regression-concrete-strength/auto-ml-regression-concrete-strength.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "_**Regression with Deployment using Hardware Performance Dataset**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Data](#Data)\n",
+        "1. [Train](#Train)\n",
+        "1. [Results](#Results)\n",
+        "1. [Test](#Test)\n",
+        "1. [Acknowledgements](#Acknowledgements)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "In this example we use the Predicting Compressive Strength of Concrete Dataset to showcase how you can use AutoML for a regression problem. The regression goal is to predict the compressive strength of concrete based off of different ingredient combinations and the quantities of those ingredients.\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` in an existing `Workspace`.\n",
+        "2. Configure AutoML using `AutoMLConfig`.\n",
+        "3. Train the model using local compute.\n",
+        "4. Explore the results.\n",
+        "5. Test the best fitted model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup\n",
+        "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",
+        "import os\n",
+        " \n",
+        "\n",
+        "import azureml.core\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "from azureml.core.dataset import Dataset\n",
+        "from azureml.train.automl import AutoMLConfig"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "# Choose a name for the experiment and specify the project folder.\n",
+        "experiment_name = 'automl-regression-concrete'\n",
+        "project_folder = './sample_projects/automl-regression-concrete'\n",
+        "\n",
+        "experiment = Experiment(ws, experiment_name)\n",
+        "\n",
+        "output = {}\n",
+        "output['SDK version'] = azureml.core.VERSION\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace Name'] = ws.name\n",
+        "output['Resource Group'] = ws.resource_group\n",
+        "output['Location'] = ws.location\n",
+        "output['Project Directory'] = project_folder\n",
+        "output['Experiment Name'] = experiment.name\n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
+        "outputDf.T"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 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",
+        "Here load the data in the get_data script to be utilized in azure compute. To do this, first load all the necessary libraries and dependencies to set up paths for the data and to create the conda_run_config."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "if not os.path.isdir('data'):\n",
+        "    os.mkdir('data')\n",
+        "    \n",
+        "if not os.path.exists(project_folder):\n",
+        "    os.makedirs(project_folder)"
+      ]
+    },
+    {
+      "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",
+        "Here create the script to be run in azure compute for loading the data, load the concrete strength dataset into the X and y  variables. Next, split the data using random_split and return X_train and y_train for training the model. Finally, return X_train and y_train for training the model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/compresive_strength_concrete.csv\"\n",
+        "dataset = Dataset.Tabular.from_delimited_files(data)\n",
+        "X = dataset.drop_columns(columns=['CONCRETE'])\n",
+        "y = dataset.keep_columns(columns=['CONCRETE'], validate=True)\n",
+        "X_train, X_test = X.random_split(percentage=0.8, seed=223)\n",
+        "y_train, y_test = y.random_split(percentage=0.8, seed=223) \n",
+        "dataset.take(5).to_pandas_dataframe()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train\n",
+        "\n",
+        "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
+        "\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**task**|classification or regression|\n",
+        "|**primary_metric**|This is the metric that you want to optimize. Regression supports the following primary metrics: <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>|\n",
+        "|**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, ], 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",
+        "\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\": 5,\n",
+        "    \"primary_metric\": 'spearman_correlation',\n",
+        "    \"preprocess\": True,\n",
+        "    \"max_concurrent_iterations\": 5,\n",
+        "    \"verbosity\": logging.INFO,\n",
+        "}\n",
+        "\n",
+        "automl_config = AutoMLConfig(task = 'regression',\n",
+        "                             debug_log = 'automl.log',\n",
+        "                             path = project_folder,\n",
+        "                             run_configuration=conda_run_config,\n",
+        "                             X = X_train,\n",
+        "                             y = y_train,\n",
+        "                             **automl_settings\n",
+        "                            )"
+      ]
+    },
+    {
+      "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\n",
+        "Widget for Monitoring Runs\n",
+        "The widget will first report a \u00e2\u20ac\u0153loading 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",
+        "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": [
+        "\n",
+        "Retrieve All Child Runs\n",
+        "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "children = list(remote_run.get_children())\n",
+        "metricslist = {}\n",
+        "for run in children:\n",
+        "    properties = run.get_properties()\n",
+        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+        "    metricslist[int(properties['iteration'])] = metrics\n",
+        "\n",
+        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+        "rundata"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Retrieve the Best Model\n",
+        "Below we select the best pipeline from our iterations. The get_output method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing. Overloads on get_output allow you to retrieve the best run and fitted model for any logged metric or for a particular iteration."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run, fitted_model = remote_run.get_output()\n",
+        "print(best_run)\n",
+        "print(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Best Model Based on Any Other Metric\n",
+        "Show the run and the model that has the smallest root_mean_squared_error value (which turned out to be the same as the one with largest spearman_correlation value):"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "lookup_metric = \"root_mean_squared_error\"\n",
+        "best_run, fitted_model = remote_run.get_output(metric = lookup_metric)\n",
+        "print(best_run)\n",
+        "print(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "iteration = 3\n",
+        "third_run, third_model = remote_run.get_output(iteration = iteration)\n",
+        "print(third_run)\n",
+        "print(third_model)"
+      ]
+    },
+    {
+      "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'], pip_packages=['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": [
+        "### Create a Container Image\n",
+        "\n",
+        "Next use Azure Container Instances for deploying models as a web service for quickly deploying and validating your model\n",
+        "or when testing a model that is under development."
+      ]
+    },
+    {
+      "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_regression\"},\n",
+        "                                 description = \"Image for automl regression 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\n",
+        "\n",
+        "Deploy an image that contains the model and other assets needed by the service."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.webservice import AciWebservice\n",
+        "\n",
+        "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
+        "                                               memory_gb = 1, \n",
+        "                                               tags = {'area': \"digits\", 'type': \"automl_regression\"}, \n",
+        "                                               description = 'sample service for Automl Regression')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.webservice import Webservice\n",
+        "\n",
+        "aci_service_name = 'automl-sample-concrete'\n",
+        "print(aci_service_name)\n",
+        "aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
+        "                                           image = image,\n",
+        "                                           name = aci_service_name,\n",
+        "                                           workspace = ws)\n",
+        "aci_service.wait_for_deployment(True)\n",
+        "print(aci_service.state)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Delete a Web Service\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": [
+        "X_test = X_test.to_pandas_dataframe()\n",
+        "y_test = y_test.to_pandas_dataframe()\n",
+        "y_test = np.array(y_test)\n",
+        "y_test = y_test[:,0]\n",
+        "X_train = X_train.to_pandas_dataframe()\n",
+        "y_train = y_train.to_pandas_dataframe()\n",
+        "y_train = np.array(y_train)\n",
+        "y_train = y_train[:,0]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "##### Predict on training and test set, and calculate residual values."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "y_pred_train = fitted_model.predict(X_train)\n",
+        "y_residual_train = y_train - y_pred_train\n",
+        "\n",
+        "y_pred_test = fitted_model.predict(X_test)\n",
+        "y_residual_test = y_test - y_pred_test\n",
+        "\n",
+        "y_residual_train.shape"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%matplotlib inline\n",
+        "from sklearn.metrics import mean_squared_error, r2_score\n",
+        "\n",
+        "# Set up a multi-plot chart.\n",
+        "f, (a0, a1) = plt.subplots(1, 2, gridspec_kw = {'width_ratios':[1, 1], 'wspace':0, 'hspace': 0})\n",
+        "f.suptitle('Regression Residual Values', fontsize = 18)\n",
+        "f.set_figheight(6)\n",
+        "f.set_figwidth(16)\n",
+        "\n",
+        "# Plot residual values of training set.\n",
+        "a0.axis([0, 360, -200, 200])\n",
+        "a0.plot(y_residual_train, 'bo', alpha = 0.5)\n",
+        "a0.plot([-10,360],[0,0], 'r-', lw = 3)\n",
+        "a0.text(16,170,'RMSE = {0:.2f}'.format(np.sqrt(mean_squared_error(y_train, y_pred_train))), fontsize = 12)\n",
+        "a0.text(16,140,'R2 score = {0:.2f}'.format(r2_score(y_train, y_pred_train)), fontsize = 12)\n",
+        "a0.set_xlabel('Training samples', fontsize = 12)\n",
+        "a0.set_ylabel('Residual Values', fontsize = 12)\n",
+        "\n",
+        "# Plot a histogram.\n",
+        "#a0.hist(y_residual_train, orientation = 'horizontal', color = ['b']*len(y_residual_train), bins = 10, histtype = 'step')\n",
+        "#a0.hist(y_residual_train, orientation = 'horizontal', color = ['b']*len(y_residual_train), alpha = 0.2, bins = 10)\n",
+        "\n",
+        "# Plot residual values of test set.\n",
+        "a1.axis([0, 90, -200, 200])\n",
+        "a1.plot(y_residual_test, 'bo', alpha = 0.5)\n",
+        "a1.plot([-10,360],[0,0], 'r-', lw = 3)\n",
+        "a1.text(5,170,'RMSE = {0:.2f}'.format(np.sqrt(mean_squared_error(y_test, y_pred_test))), fontsize = 12)\n",
+        "a1.text(5,140,'R2 score = {0:.2f}'.format(r2_score(y_test, y_pred_test)), fontsize = 12)\n",
+        "a1.set_xlabel('Test samples', fontsize = 12)\n",
+        "a1.set_yticklabels([])\n",
+        "\n",
+        "# Plot a histogram.\n",
+        "#a1.hist(y_residual_test, orientation = 'horizontal', color = ['b']*len(y_residual_test), bins = 10, histtype = 'step')\n",
+        "#a1.hist(y_residual_test, orientation = 'horizontal', color = ['b']*len(y_residual_test), alpha = 0.2, bins = 10)\n",
+        "\n",
+        "plt.show()"
+      ]
+    },
+    {
+      "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": [
+        "# Plot outputs\n",
+        "%matplotlib notebook\n",
+        "test_pred = plt.scatter(y_test, y_pred_test, 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": [
+        "## Acknowledgements\n",
+        "\n",
+        "This Predicting Compressive Strength of Concrete Dataset is made available under the CC0 1.0 Universal (CC0 1.0)\n",
+        "Public Domain Dedication License: https://creativecommons.org/publicdomain/zero/1.0/. Any rights in individual contents of the database are licensed under the CC0 1.0 Universal (CC0 1.0)\n",
+        "Public Domain Dedication License: https://creativecommons.org/publicdomain/zero/1.0/ . The dataset itself can be found here: https://www.kaggle.com/pavanraj159/concrete-compressive-strength-data-set and http://archive.ics.uci.edu/ml/datasets/concrete+compressive+strength\n",
+        "\n",
+        "I-Cheng Yeh, \"Modeling of strength of high performance concrete using artificial neural networks,\" Cement and Concrete Research, Vol. 28, No. 12, pp. 1797-1808 (1998). \n",
+        "\n",
+        "Dua, D. and Graff, C. (2019). UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science."
+      ]
+    }
+  ],
+  "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": "3.7.1"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/regression-concrete-strength/auto-ml-regression-concrete-strength.yml

@@ -0,0 +1,10 @@
+name: auto-ml-regression-concrete-strength
+dependencies:
+- pip:
+  - azureml-sdk
+  - azureml-defaults
+  - azureml-explain-model
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml

how-to-use-azureml/automated-machine-learning/regression-hardware-performance/auto-ml-regression-hardware-performance.ipynb

@@ -0,0 +1,798 @@
+{
+  "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/regression-hardware-performance/auto-ml-regression-hardware-performance.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "_**Regression with Deployment using Hardware Performance Dataset**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Data](#Data)\n",
+        "1. [Train](#Train)\n",
+        "1. [Results](#Results)\n",
+        "1. [Test](#Test)\n",
+        "1. [Acknowledgements](#Acknowledgements)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "In this example we use the Hardware Performance Dataset to showcase how you can use AutoML for a simple regression problem. The Regression goal is to predict the performance of certain combinations of hardware parts.\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` in an existing `Workspace`.\n",
+        "2. Configure AutoML using `AutoMLConfig`.\n",
+        "3. Train the model using local compute.\n",
+        "4. Explore the results.\n",
+        "5. Test the best fitted model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup\n",
+        "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",
+        "import os\n",
+        " \n",
+        "\n",
+        "import azureml.core\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "from azureml.core.dataset import Dataset\n",
+        "from azureml.train.automl import AutoMLConfig"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "# Choose a name for the experiment and specify the project folder.\n",
+        "experiment_name = 'automl-regression-hardware'\n",
+        "project_folder = './sample_projects/automl-remote-regression'\n",
+        "\n",
+        "experiment = Experiment(ws, experiment_name)\n",
+        "\n",
+        "output = {}\n",
+        "output['SDK version'] = azureml.core.VERSION\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace Name'] = ws.name\n",
+        "output['Resource Group'] = ws.resource_group\n",
+        "output['Location'] = ws.location\n",
+        "output['Project Directory'] = project_folder\n",
+        "output['Experiment Name'] = experiment.name\n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
+        "outputDf.T"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 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",
+        "Here load the data in the get_data script to be utilized in azure compute. To do this, first load all the necessary libraries and dependencies to set up paths for the data and to create the conda_run_config."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "if not os.path.isdir('data'):\n",
+        "    os.mkdir('data')\n",
+        "    \n",
+        "if not os.path.exists(project_folder):\n",
+        "    os.makedirs(project_folder)"
+      ]
+    },
+    {
+      "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",
+        "Here create the script to be run in azure compute for loading the data, load the hardware dataset into the X and y variables. Next split the data using random_split and return X_train and y_train for training the model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/machineData.csv\"\n",
+        "dataset = Dataset.Tabular.from_delimited_files(data)\n",
+        "X = dataset.drop_columns(columns=['ERP'])\n",
+        "y = dataset.keep_columns(columns=['ERP'], validate=True)\n",
+        "X_train, X_test = X.random_split(percentage=0.8, seed=223)\n",
+        "y_train, y_test = y.random_split(percentage=0.8, seed=223)\n",
+        "dataset.take(5).to_pandas_dataframe()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "\n",
+        "## Train\n",
+        "\n",
+        "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
+        "\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**task**|classification or regression|\n",
+        "|**primary_metric**|This is the metric that you want to optimize. Regression supports the following primary metrics: <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>|\n",
+        "|**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, ], 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",
+        "\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\": 5,\n",
+        "    \"primary_metric\": 'spearman_correlation',\n",
+        "    \"preprocess\": True,\n",
+        "    \"max_concurrent_iterations\": 5,\n",
+        "    \"verbosity\": logging.INFO,\n",
+        "}\n",
+        "\n",
+        "automl_config = AutoMLConfig(task = 'regression',\n",
+        "                             debug_log = 'automl_errors_20190417.log',\n",
+        "                             path = project_folder,\n",
+        "                             run_configuration=conda_run_config,\n",
+        "                             X = X_train,\n",
+        "                             y = y_train,\n",
+        "                             **automl_settings\n",
+        "                            )"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run = experiment.submit(automl_config, show_output = False)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Results"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Widget for Monitoring Runs\n",
+        "\n",
+        "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+        "\n",
+        "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.widgets import RunDetails\n",
+        "RunDetails(remote_run).show() "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Wait until the run finishes.\n",
+        "remote_run.wait_for_completion(show_output = True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Retrieve All Child Runs\n",
+        "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "children = list(remote_run.get_children())\n",
+        "metricslist = {}\n",
+        "for run in children:\n",
+        "    properties = run.get_properties()\n",
+        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+        "    metricslist[int(properties['iteration'])] = metrics\n",
+        "\n",
+        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+        "rundata"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Retrieve the Best Model\n",
+        "Below we select the best pipeline from our iterations. The get_output method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing. Overloads on get_output allow you to retrieve the best run and fitted model for any logged metric or for a particular iteration."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run, fitted_model = remote_run.get_output()\n",
+        "print(best_run)\n",
+        "print(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Best Model Based on Any Other Metric\n",
+        "Show the run and the model that has the smallest `root_mean_squared_error` value (which turned out to be the same as the one with largest `spearman_correlation` value):"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "lookup_metric = \"root_mean_squared_error\"\n",
+        "best_run, fitted_model = remote_run.get_output(metric = lookup_metric)\n",
+        "print(best_run)\n",
+        "print(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "iteration = 3\n",
+        "third_run, third_model = remote_run.get_output(iteration = iteration)\n",
+        "print(third_run)\n",
+        "print(third_model)"
+      ]
+    },
+    {
+      "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'], pip_packages=['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": [
+        "### Create a Container Image\n",
+        "\n",
+        "Next use Azure Container Instances for deploying models as a web service for quickly deploying and validating your model\n",
+        "or when testing a model that is under development."
+      ]
+    },
+    {
+      "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_regression\"},\n",
+        "                                 description = \"Image for automl regression 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\n",
+        "\n",
+        "Deploy an image that contains the model and other assets needed by the service."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.webservice import AciWebservice\n",
+        "\n",
+        "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
+        "                                               memory_gb = 1, \n",
+        "                                               tags = {'area': \"digits\", 'type': \"automl_regression\"}, \n",
+        "                                               description = 'sample service for Automl Regression')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.webservice import Webservice\n",
+        "\n",
+        "aci_service_name = 'automl-sample-hardware'\n",
+        "print(aci_service_name)\n",
+        "aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
+        "                                           image = image,\n",
+        "                                           name = aci_service_name,\n",
+        "                                           workspace = ws)\n",
+        "aci_service.wait_for_deployment(True)\n",
+        "print(aci_service.state)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Delete a Web Service\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": [
+        "X_test = X_test.to_pandas_dataframe()\n",
+        "y_test = y_test.to_pandas_dataframe()\n",
+        "y_test = np.array(y_test)\n",
+        "y_test = y_test[:,0]\n",
+        "X_train = X_train.to_pandas_dataframe()\n",
+        "y_train = y_train.to_pandas_dataframe()\n",
+        "y_train = np.array(y_train)\n",
+        "y_train = y_train[:,0]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "##### Predict on training and test set, and calculate residual values."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "y_pred_train = fitted_model.predict(X_train)\n",
+        "y_residual_train = y_train - y_pred_train\n",
+        "\n",
+        "y_pred_test = fitted_model.predict(X_test)\n",
+        "y_residual_test = y_test - y_pred_test"
+      ]
+    },
+    {
+      "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 inline\n",
+        "from sklearn.metrics import mean_squared_error, r2_score\n",
+        "\n",
+        "# Set up a multi-plot chart.\n",
+        "f, (a0, a1) = plt.subplots(1, 2, gridspec_kw = {'width_ratios':[1, 1], 'wspace':0, 'hspace': 0})\n",
+        "f.suptitle('Regression Residual Values', fontsize = 18)\n",
+        "f.set_figheight(6)\n",
+        "f.set_figwidth(16)\n",
+        "\n",
+        "# Plot residual values of training set.\n",
+        "a0.axis([0, 360, -200, 200])\n",
+        "a0.plot(y_residual_train, 'bo', alpha = 0.5)\n",
+        "a0.plot([-10,360],[0,0], 'r-', lw = 3)\n",
+        "a0.text(16,170,'RMSE = {0:.2f}'.format(np.sqrt(mean_squared_error(y_train, y_pred_train))), fontsize = 12)\n",
+        "a0.text(16,140,'R2 score = {0:.2f}'.format(r2_score(y_train, y_pred_train)),fontsize = 12)\n",
+        "a0.set_xlabel('Training samples', fontsize = 12)\n",
+        "a0.set_ylabel('Residual Values', fontsize = 12)\n",
+        "\n",
+        "# Plot residual values of test set.\n",
+        "a1.axis([0, 90, -200, 200])\n",
+        "a1.plot(y_residual_test, 'bo', alpha = 0.5)\n",
+        "a1.plot([-10,360],[0,0], 'r-', lw = 3)\n",
+        "a1.text(5,170,'RMSE = {0:.2f}'.format(np.sqrt(mean_squared_error(y_test, y_pred_test))), fontsize = 12)\n",
+        "a1.text(5,140,'R2 score = {0:.2f}'.format(r2_score(y_test, y_pred_test)),fontsize = 12)\n",
+        "a1.set_xlabel('Test samples', fontsize = 12)\n",
+        "a1.set_yticklabels([])\n",
+        "\n",
+        "plt.show()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%matplotlib notebook\n",
+        "test_pred = plt.scatter(y_test, y_pred_test, color='')\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": [
+        "## Acknowledgements\n",
+        "This Predicting Hardware Performance Dataset is made available under the CC0 1.0 Universal (CC0 1.0) Public Domain Dedication License: https://creativecommons.org/publicdomain/zero/1.0/. Any rights in individual contents of the database are licensed under the CC0 1.0 Universal (CC0 1.0) Public Domain Dedication License: https://creativecommons.org/publicdomain/zero/1.0/ . The dataset itself can be found here: https://www.kaggle.com/faizunnabi/comp-hardware-performance and https://archive.ics.uci.edu/ml/datasets/Computer+Hardware\n",
+        "\n",
+        "_**Citation Found Here**_\n"
+      ]
+    }
+  ],
+  "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": "3.7.1"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/regression-hardware-performance/auto-ml-regression-hardware-performance.yml

@@ -0,0 +1,10 @@
+name: auto-ml-regression-hardware-performance
+dependencies:
+- pip:
+  - azureml-sdk
+  - azureml-defaults
+  - azureml-explain-model
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml

how-to-use-azureml/automated-machine-learning/regression/auto-ml-regression.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/regression/auto-ml-regression.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

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

@@ -0,0 +1,9 @@
+name: auto-ml-regression
+dependencies:
+- pip:
+  - azureml-sdk
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml
+  - paramiko<2.5.0

how-to-use-azureml/automated-machine-learning/remote-amlcompute-with-onnx/auto-ml-remote-amlcompute-with-onnx.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/remote-amlcompute/auto-ml-remote-amlcompute.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -21,8 +28,7 @@
         "1. [Setup](#Setup)\n",
         "1. [Data](#Data)\n",
         "1. [Train](#Train)\n",
-        "1. [Results](#Results)\n",
+        "1. [Results](#Results)\n"
-        "1. [Test](#Test)"
       ]
     },
     {
@@ -30,7 +36,7 @@
       "metadata": {},
       "source": [
         "## Introduction\n",
-        "In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset) to showcase how you can use AutoML for a simple classification problem.\n",
+        "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",
@@ -38,9 +44,9 @@
         "1. Create an `Experiment` in an existing `Workspace`.\n",
         "2. Create or Attach existing AmlCompute to a workspace.\n",
         "3. Configure AutoML using `AutoMLConfig`.\n",
-        "4. Train the model using AmlCompute\n",
+        "4. Train the model using AmlCompute with ONNX compatible config on.\n",
-        "5. Explore the results.\n",
+        "5. Explore the results and save the ONNX model.\n",
-        "6. Test the best fitted model.\n",
+        "6. Inference with the ONNX model.\n",
         "\n",
         "In addition this notebook showcases the following features\n",
         "- **Parallel** executions for iterations\n",
@@ -67,16 +73,15 @@
       "source": [
         "import logging\n",
         "import os\n",
-        "import csv\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.core.dataset import Dataset\n",
         "from azureml.train.automl import AutoMLConfig"
       ]
     },
@@ -89,7 +94,7 @@
         "ws = Workspace.from_config()\n",
         "\n",
         "# Choose a name for the run history container in the workspace.\n",
-        "experiment_name = 'automl-remote-amlcompute'\n",
+        "experiment_name = 'automl-remote-amlcompute-with-onnx'\n",
         "project_folder = './project'\n",
         "\n",
         "experiment = Experiment(ws, experiment_name)\n",
@@ -129,7 +134,7 @@
         "from azureml.core.compute import ComputeTarget\n",
         "\n",
         "# Choose a name for your cluster.\n",
-        "amlcompute_cluster_name = \"automlcl\"\n",
+        "amlcompute_cluster_name = \"automlc2\"\n",
         "\n",
         "found = False\n",
         "# Check if this compute target already exists in the workspace.\n",
@@ -145,9 +150,10 @@
         "                                                                #vm_priority = 'lowpriority', # optional\n",
         "                                                                max_nodes = 6)\n",
         "\n",
-        "    # Create the cluster.\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",
@@ -155,13 +161,6 @@
         "# For a more detailed view of current AmlCompute status, use get_status()."
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": []
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -169,7 +168,7 @@
         "## Data\n",
         "For remote executions, you need to make the data accessible from the remote compute.\n",
         "This can be done by uploading the data to DataStore.\n",
-        "In this example, we upload scikit-learn's [load_digits](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) data."
+        "In this example, we upload scikit-learn's [load_iris](https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_iris.html) data."
       ]
     },
     {
@@ -178,7 +177,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "data_train = datasets.load_digits()\n",
+        "iris = datasets.load_iris()\n",
         "\n",
         "if not os.path.isdir('data'):\n",
         "    os.mkdir('data')\n",
@@ -186,18 +185,37 @@
         "if not os.path.exists(project_folder):\n",
         "    os.makedirs(project_folder)\n",
         "\n",
-        "pd.DataFrame(data_train.data).to_csv(\"data/X_train.tsv\", index=False, header=False, quoting=csv.QUOTE_ALL, sep=\"\\t\")\n",
+        "X_train, X_test, y_train, y_test = train_test_split(iris.data, \n",
-        "pd.DataFrame(data_train.target).to_csv(\"data/y_train.tsv\", index=False, header=False, sep=\"\\t\")\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'])\n",
+        "y_train = pd.DataFrame(y_train, columns=['label'])\n",
+        "\n",
+        "X_train.to_csv(\"data/X_train.csv\", index=False)\n",
+        "y_train.to_csv(\"data/y_train.csv\", index=False)\n",
         "\n",
         "ds = ws.get_default_datastore()\n",
-        "ds.upload(src_dir='./data', target_path='bai_data', overwrite=True, show_progress=True)\n",
+        "ds.upload(src_dir='./data', target_path='irisdata', overwrite=True, show_progress=True)"
-        "\n",
-        "from azureml.core.runconfig import DataReferenceConfiguration\n",
-        "dr = DataReferenceConfiguration(datastore_name=ds.name, \n",
-        "                   path_on_datastore='bai_data', \n",
-        "                   path_on_compute='/tmp/azureml_runs',\n",
-        "                   mode='download', # download files from datastore to compute target\n",
-        "                   overwrite=False)"
       ]
     },
     {
@@ -208,6 +226,7 @@
       "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",
@@ -215,30 +234,28 @@
         "# Set compute target to AmlCompute\n",
         "conda_run_config.target = compute_target\n",
         "conda_run_config.environment.docker.enabled = True\n",
-        "conda_run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
         "\n",
-        "# set the data reference of the run coonfiguration\n",
+        "cd = CondaDependencies.create(conda_packages=['numpy','py-xgboost<=0.80'])\n",
-        "conda_run_config.data_references = {ds.name: dr}\n",
-        "\n",
-        "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy'])\n",
         "conda_run_config.environment.python.conda_dependencies = cd"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "###  Creating a TabularDataset\n",
+        "\n",
+        "Defined X and y as `TabularDataset`s, which are passed to automated machine learning in the AutoMLConfig."
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {},
       "outputs": [],
       "source": [
-        "%%writefile $project_folder/get_data.py\n",
+        "X = Dataset.Tabular.from_delimited_files(path=ds.path('irisdata/X_train.csv'))\n",
-        "\n",
+        "y = Dataset.Tabular.from_delimited_files(path=ds.path('irisdata/y_train.csv'))"
-        "import pandas as pd\n",
-        "\n",
-        "def get_data():\n",
-        "    X_train = pd.read_csv(\"/tmp/azureml_runs/bai_data/X_train.tsv\", delimiter=\"\\t\", header=None, quotechar='\"')\n",
-        "    y_train = pd.read_csv(\"/tmp/azureml_runs/bai_data/y_train.tsv\", delimiter=\"\\t\", header=None, quotechar='\"')\n",
-        "\n",
-        "    return { \"X\" : X_train.values, \"y\" : y_train[0].values }\n"
       ]
     },
     {
@@ -249,6 +266,8 @@
         "\n",
         "You can specify `automl_settings` as `**kwargs` as well. Also note that you can use a `get_data()` function for local excutions too.\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",
         "**Note:** When using AmlCompute, you can't pass Numpy arrays directly to the fit method.\n",
         "\n",
         "|Property|Description|\n",
@@ -257,7 +276,15 @@
         "|**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",
-        "|**max_concurrent_iterations**|Maximum number of iterations that would be executed in parallel. This should be less than the number of cores on the DSVM.|"
+        "|**max_concurrent_iterations**|Maximum number of iterations that would be executed in parallel. This should be less than the number of cores on the DSVM.|\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."
       ]
     },
     {
@@ -267,11 +294,11 @@
       "outputs": [],
       "source": [
         "automl_settings = {\n",
-        "    \"iteration_timeout_minutes\": 2,\n",
+        "    \"iteration_timeout_minutes\": 10,\n",
-        "    \"iterations\": 20,\n",
+        "    \"iterations\": 10,\n",
         "    \"n_cross_validations\": 5,\n",
         "    \"primary_metric\": 'AUC_weighted',\n",
-        "    \"preprocess\": False,\n",
+        "    \"preprocess\": True,\n",
         "    \"max_concurrent_iterations\": 5,\n",
         "    \"verbosity\": logging.INFO\n",
         "}\n",
@@ -280,9 +307,11 @@
         "                             debug_log = 'automl_errors.log',\n",
         "                             path = project_folder,\n",
         "                             run_configuration=conda_run_config,\n",
-        "                             data_script = project_folder + \"/get_data.py\",\n",
+        "                             X = X,\n",
+        "                             y = y,\n",
+        "                             enable_onnx_compatible_models=True, # This will generate ONNX compatible models.\n",
         "                             **automl_settings\n",
-        "                            )\n"
+        "                            )"
       ]
     },
     {
@@ -370,32 +399,6 @@
         "remote_run.wait_for_completion(show_output = True)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "\n",
-        "#### Retrieve All Child Runs\n",
-        "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "children = list(remote_run.get_children())\n",
-        "metricslist = {}\n",
-        "for run in children:\n",
-        "    properties = run.get_properties()\n",
-        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
-        "    metricslist[int(properties['iteration'])] = metrics\n",
-        "\n",
-        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
-        "rundata"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -422,69 +425,11 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Retrieve the Best Model\n",
+        "### 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*."
+        "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",
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "best_run, fitted_model = remote_run.get_output()\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Best Model Based on Any Other Metric\n",
-        "Show the run and the model which has the smallest `log_loss` value:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "lookup_metric = \"log_loss\"\n",
-        "best_run, fitted_model = remote_run.get_output(metric = lookup_metric)\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Model from a Specific Iteration\n",
-        "Show the run and the model from the third iteration:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "iteration = 3\n",
-        "third_run, third_model = remote_run.get_output(iteration=iteration)\n",
-        "print(third_run)\n",
-        "print(third_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Test\n",
         "\n",
-        "#### Load Test Data"
+        "Set the parameter return_onnx_model=True to retrieve the best ONNX model, instead of the Python model."
       ]
     },
     {
@@ -493,17 +438,14 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "digits = datasets.load_digits()\n",
+        "best_run, onnx_mdl = remote_run.get_output(return_onnx_model=True)"
-        "X_test = digits.data[:10, :]\n",
-        "y_test = digits.target[:10]\n",
-        "images = digits.images[:10]"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "#### Testing Our Best Fitted Model"
+        "### Save the best ONNX model"
       ]
     },
     {
@@ -512,18 +454,69 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "# Randomly select digits and test.\n",
+        "from azureml.automl.core.onnx_convert import OnnxConverter\n",
-        "for index in np.random.choice(len(y_test), 2, replace = False):\n",
+        "onnx_fl_path = \"./best_model.onnx\"\n",
-        "    print(index)\n",
+        "OnnxConverter.save_onnx_model(onnx_mdl, onnx_fl_path)"
-        "    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": [
+        "### 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",
+        "from azureml.train.automl import constants\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",
+        "        return json.load(f)\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": {

how-to-use-azureml/automated-machine-learning/remote-amlcompute-with-onnx/auto-ml-remote-amlcompute-with-onnx.yml

@@ -0,0 +1,11 @@
+name: auto-ml-remote-amlcompute-with-onnx
+dependencies:
+- pip:
+  - azureml-sdk
+  - azureml-defaults
+  - azureml-explain-model
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml
+  - onnxruntime

how-to-use-azureml/automated-machine-learning/remote-amlcompute/auto-ml-remote-amlcompute.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/remote-amlcompute/auto-ml-remote-amlcompute.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -67,7 +74,6 @@
       "source": [
         "import logging\n",
         "import os\n",
-        "import csv\n",
         "\n",
         "from matplotlib import pyplot as plt\n",
         "import numpy as np\n",
@@ -77,6 +83,7 @@
         "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"
       ]
     },
@@ -129,7 +136,7 @@
         "from azureml.core.compute import ComputeTarget\n",
         "\n",
         "# Choose a name for your cluster.\n",
-        "amlcompute_cluster_name = \"automlcl\"\n",
+        "amlcompute_cluster_name = \"automlc2\"\n",
         "\n",
         "found = False\n",
         "# Check if this compute target already exists in the workspace.\n",
@@ -145,9 +152,10 @@
         "                                                                #vm_priority = 'lowpriority', # optional\n",
         "                                                                max_nodes = 6)\n",
         "\n",
-        "    # Create the cluster.\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",
@@ -155,13 +163,6 @@
         "# For a more detailed view of current AmlCompute status, use get_status()."
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": []
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -186,18 +187,11 @@
         "if not os.path.exists(project_folder):\n",
         "    os.makedirs(project_folder)\n",
         "    \n",
-        "pd.DataFrame(data_train.data).to_csv(\"data/X_train.tsv\", index=False, header=False, quoting=csv.QUOTE_ALL, sep=\"\\t\")\n",
+        "pd.DataFrame(data_train.data[100:,:]).to_csv(\"data/X_train.csv\", index=False)\n",
-        "pd.DataFrame(data_train.target).to_csv(\"data/y_train.tsv\", index=False, header=False, sep=\"\\t\")\n",
+        "pd.DataFrame(data_train.target[100:]).to_csv(\"data/y_train.csv\", index=False)\n",
         "\n",
         "ds = ws.get_default_datastore()\n",
-        "ds.upload(src_dir='./data', target_path='bai_data', overwrite=True, show_progress=True)\n",
+        "ds.upload(src_dir='./data', target_path='digitsdata', overwrite=True, show_progress=True)"
-        "\n",
-        "from azureml.core.runconfig import DataReferenceConfiguration\n",
-        "dr = DataReferenceConfiguration(datastore_name=ds.name, \n",
-        "                   path_on_datastore='bai_data', \n",
-        "                   path_on_compute='/tmp/azureml_runs',\n",
-        "                   mode='download', # download files from datastore to compute target\n",
-        "                   overwrite=False)"
       ]
     },
     {
@@ -208,6 +202,7 @@
       "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",
@@ -215,30 +210,28 @@
         "# Set compute target to AmlCompute\n",
         "conda_run_config.target = compute_target\n",
         "conda_run_config.environment.docker.enabled = True\n",
-        "conda_run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
         "\n",
-        "# set the data reference of the run coonfiguration\n",
+        "cd = CondaDependencies.create(conda_packages=['numpy','py-xgboost<=0.80'])\n",
-        "conda_run_config.data_references = {ds.name: dr}\n",
-        "\n",
-        "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy','py-xgboost<=0.80'])\n",
         "conda_run_config.environment.python.conda_dependencies = cd"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "###  Creating TabularDataset\n",
+        "\n",
+        "Defined X and y as `TabularDataset`s, which are passed to Automated ML in the AutoMLConfig. `from_delimited_files` by default sets the `infer_column_types` to true, which will infer the columns type automatically. If you do wish to manually set the column types, you can set the `set_column_types` argument to manually set the type of each columns."
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {},
       "outputs": [],
       "source": [
-        "%%writefile $project_folder/get_data.py\n",
+        "X = Dataset.Tabular.from_delimited_files(path=ds.path('digitsdata/X_train.csv'))\n",
-        "\n",
+        "y = Dataset.Tabular.from_delimited_files(path=ds.path('digitsdata/y_train.csv'))"
-        "import pandas as pd\n",
-        "\n",
-        "def get_data():\n",
-        "    X_train = pd.read_csv(\"/tmp/azureml_runs/bai_data/X_train.tsv\", delimiter=\"\\t\", header=None, quotechar='\"')\n",
-        "    y_train = pd.read_csv(\"/tmp/azureml_runs/bai_data/y_train.tsv\", delimiter=\"\\t\", header=None, quotechar='\"')\n",
-        "\n",
-        "    return { \"X\" : X_train.values, \"y\" : y_train[0].values }\n"
       ]
     },
     {
@@ -280,7 +273,8 @@
         "                             debug_log = 'automl_errors.log',\n",
         "                             path = project_folder,\n",
         "                             run_configuration=conda_run_config,\n",
-        "                             data_script = project_folder + \"/get_data.py\",\n",
+        "                             X = X,\n",
+        "                             y = y,\n",
         "                             **automl_settings\n",
         "                            )\n"
       ]

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

@@ -0,0 +1,10 @@
+name: auto-ml-remote-amlcompute
+dependencies:
+- pip:
+  - azureml-sdk
+  - azureml-defaults
+  - azureml-explain-model
+  - azureml-train-automl
+  - azureml-widgets
+  - matplotlib
+  - pandas_ml

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

@@ -1,558 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Automated Machine Learning\n",
-        "_**Remote Execution using attach**_\n",
-        "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Data](#Data)\n",
-        "1. [Train](#Train)\n",
-        "1. [Results](#Results)\n",
-        "1. [Test](#Test)\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
-        "In this example we use the scikit-learn's [20newsgroup](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.fetch_20newsgroups.html) to showcase how you can use AutoML to handle text data with remote attach.\n",
-        "\n",
-        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
-        "\n",
-        "In this notebook you will learn how to:\n",
-        "1. Create an `Experiment` in an existing `Workspace`.\n",
-        "2. Attach an existing DSVM to a workspace.\n",
-        "3. Configure AutoML using `AutoMLConfig`.\n",
-        "4. Train the model using the DSVM.\n",
-        "5. Explore the results.\n",
-        "6. Viewing the engineered names for featurized data and featurization summary for all raw features.\n",
-        "7. Test the best fitted model.\n",
-        "\n",
-        "In addition this notebook showcases the following features\n",
-        "- **Parallel** executions for iterations\n",
-        "- **Asynchronous** tracking of progress\n",
-        "- **Cancellation** of individual iterations or the entire run\n",
-        "- Retrieving models for any iteration or logged metric\n",
-        "- Specifying AutoML settings as `**kwargs`\n",
-        "- Handling **text** data using the `preprocess` flag"
-      ]
-    },
-    {
-      "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 os\n",
-        "\n",
-        "import numpy as np\n",
-        "import pandas as pd\n",
-        "\n",
-        "import azureml.core\n",
-        "from azureml.core.experiment import Experiment\n",
-        "from azureml.core.workspace import Workspace\n",
-        "from azureml.train.automl import AutoMLConfig"
-      ]
-    },
-    {
-      "cell_type": "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-remote-attach'\n",
-        "project_folder = './sample_projects/automl-remote-attach'\n",
-        "\n",
-        "experiment = Experiment(ws, experiment_name)\n",
-        "\n",
-        "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
-        "output['Subscription ID'] = ws.subscription_id\n",
-        "output['Workspace'] = ws.name\n",
-        "output['Resource Group'] = ws.resource_group\n",
-        "output['Location'] = ws.location\n",
-        "output['Project Directory'] = project_folder\n",
-        "output['Experiment Name'] = experiment.name\n",
-        "pd.set_option('display.max_colwidth', -1)\n",
-        "outputDf = pd.DataFrame(data = output, index = [''])\n",
-        "outputDf.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Attach a Remote Linux DSVM\n",
-        "To use a remote Docker compute target:\n",
-        "1. Create a Linux DSVM in Azure, following these [instructions](https://docs.microsoft.com/en-us/azure/machine-learning/data-science-virtual-machine/dsvm-ubuntu-intro). Make sure you use the Ubuntu flavor (not CentOS). Make sure that disk space is available under `/tmp` because AutoML creates files under `/tmp/azureml_run`s. The DSVM should have more cores than the number of parallel runs that you plan to enable. It should also have at least 4GB per core.\n",
-        "2. Enter the IP address, user name and password below.\n",
-        "\n",
-        "**Note:** By default, SSH runs on port 22 and you don't need to change the port number below. If you've configured SSH to use a different port, change `dsvm_ssh_port` accordinglyaddress. [Read more](https://docs.microsoft.com/en-us/azure/virtual-machines/troubleshooting/detailed-troubleshoot-ssh-connection) on changing SSH ports for security reasons."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.compute import ComputeTarget, RemoteCompute\n",
-        "import time\n",
-        "\n",
-        "# Add your VM information below\n",
-        "# If a compute with the specified compute_name already exists, it will be used and the dsvm_ip_addr, dsvm_ssh_port, \n",
-        "# dsvm_username and dsvm_password will be ignored.\n",
-        "compute_name  = 'mydsvmb'\n",
-        "dsvm_ip_addr  = '<<ip_addr>>'\n",
-        "dsvm_ssh_port = 22\n",
-        "dsvm_username = '<<username>>'\n",
-        "dsvm_password = '<<password>>'\n",
-        "\n",
-        "if compute_name in ws.compute_targets:\n",
-        "    print('Using existing compute.')\n",
-        "    dsvm_compute = ws.compute_targets[compute_name]\n",
-        "else:\n",
-        "    attach_config = RemoteCompute.attach_configuration(address=dsvm_ip_addr, username=dsvm_username, password=dsvm_password, ssh_port=dsvm_ssh_port)\n",
-        "    ComputeTarget.attach(workspace=ws, name=compute_name, attach_configuration=attach_config)\n",
-        "\n",
-        "    while ws.compute_targets[compute_name].provisioning_state == 'Creating':\n",
-        "        time.sleep(1)\n",
-        "\n",
-        "    dsvm_compute = ws.compute_targets[compute_name]\n",
-        "    \n",
-        "    if dsvm_compute.provisioning_state == 'Failed':\n",
-        "        print('Attached failed.')\n",
-        "        print(dsvm_compute.provisioning_errors)\n",
-        "        dsvm_compute.detach()"
-      ]
-    },
-    {
-      "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 the Linux DSVM\n",
-        "conda_run_config.target = dsvm_compute\n",
-        "\n",
-        "pandas_dependency = 'pandas==' + pkg_resources.get_distribution(\"pandas\").version\n",
-        "\n",
-        "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy','py-xgboost<=0.80',pandas_dependency])\n",
-        "conda_run_config.environment.python.conda_dependencies = cd"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Data\n",
-        "For remote executions you should author a `get_data.py` file containing a `get_data()` function. This file should be in the root directory of the project. You can encapsulate code to read data either from a blob storage or local disk in this file.\n",
-        "In this example, the `get_data()` function returns a [dictionary](README.md#getdata)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "if not os.path.exists(project_folder):\n",
-        "    os.makedirs(project_folder)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "%%writefile $project_folder/get_data.py\n",
-        "\n",
-        "import numpy as np\n",
-        "from sklearn.datasets import fetch_20newsgroups\n",
-        "\n",
-        "def get_data():\n",
-        "    remove = ('headers', 'footers', 'quotes')\n",
-        "    categories = [\n",
-        "        'alt.atheism',\n",
-        "        'talk.religion.misc',\n",
-        "        'comp.graphics',\n",
-        "        'sci.space',\n",
-        "    ]\n",
-        "    data_train = fetch_20newsgroups(subset = 'train', categories = categories,\n",
-        "                                    shuffle = True, random_state = 42,\n",
-        "                                    remove = remove)\n",
-        "    \n",
-        "    X_train = np.array(data_train.data).reshape((len(data_train.data),1))\n",
-        "    y_train = np.array(data_train.target)\n",
-        "    \n",
-        "    return { \"X\" : X_train, \"y\" : y_train }"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Train\n",
-        "\n",
-        "You can specify `automl_settings` as `**kwargs` as well. Also note that you can use a `get_data()` function for local excutions too.\n",
-        "\n",
-        "**Note:** When using Remote DSVM, you can't pass Numpy arrays directly to the fit method.\n",
-        "\n",
-        "|Property|Description|\n",
-        "|-|-|\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",
-        "|**max_concurrent_iterations**|Maximum number of iterations that would be executed in parallel. This should be less than the number of cores on the DSVM.|\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",
-        "|**enable_cache**|Setting this to *True* enables preprocess done once and reuse the same preprocessed data for all the iterations. Default value is True.\n",
-        "|**max_cores_per_iteration**|Indicates how many cores on the compute target would be used to train a single pipeline.<br>Default is *1*; you can set it to *-1* to use all cores.|"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "automl_settings = {\n",
-        "    \"iteration_timeout_minutes\": 60,\n",
-        "    \"iterations\": 4,\n",
-        "    \"n_cross_validations\": 5,\n",
-        "    \"primary_metric\": 'AUC_weighted',\n",
-        "    \"preprocess\": True,\n",
-        "    \"max_cores_per_iteration\": 2\n",
-        "}\n",
-        "\n",
-        "automl_config = AutoMLConfig(task = 'classification',\n",
-        "                             path = project_folder,\n",
-        "                             run_configuration=conda_run_config,\n",
-        "                             data_script = project_folder + \"/get_data.py\",\n",
-        "                             **automl_settings\n",
-        "                            )\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Call the `submit` method on the experiment object and pass the run configuration. For remote runs the execution is asynchronous, so you will see the iterations get populated as they complete. You can interact with the widgets and models even when the experiment is running to retrieve the best model up to that point. Once you are satisfied with the model, you can cancel a particular iteration or the whole run."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run = experiment.submit(automl_config)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Results\n",
-        "#### 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",
-        "You can click on a pipeline to see run properties and output logs.  Logs are also available on the DSVM under `/tmp/azureml_run/{iterationid}/azureml-logs`\n",
-        "\n",
-        "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.widgets import RunDetails\n",
-        "RunDetails(remote_run).show() "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Wait until the run finishes.\n",
-        "remote_run.wait_for_completion(show_output = True)"
-      ]
-    },
-    {
-      "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": [
-        "\n",
-        "#### Retrieve All Child Runs\n",
-        "You can also use SDK methods to fetch all the child runs and see individual metrics that we log. "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "children = list(remote_run.get_children())\n",
-        "metricslist = {}\n",
-        "for run in children:\n",
-        "    properties = run.get_properties()\n",
-        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
-        "    metricslist[int(properties['iteration'])] = metrics\n",
-        "\n",
-        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
-        "rundata"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### 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": {},
-      "source": [
-        "### Retrieve the Best Model\n",
-        "\n",
-        "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "best_run, fitted_model = remote_run.get_output()\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### 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": [
-        "fitted_model.named_steps['datatransformer'].get_featurization_summary()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Best Model Based on Any Other Metric\n",
-        "Show the run and the model which has the smallest `accuracy` value:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# lookup_metric = \"accuracy\"\n",
-        "# best_run, fitted_model = remote_run.get_output(metric = lookup_metric)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Model from a Specific Iteration"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "iteration = 0\n",
-        "zero_run, zero_model = remote_run.get_output(iteration = iteration)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Test"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Load test data.\n",
-        "from pandas_ml import ConfusionMatrix\n",
-        "from sklearn.datasets import fetch_20newsgroups\n",
-        "\n",
-        "remove = ('headers', 'footers', 'quotes')\n",
-        "categories = [\n",
-        "        'alt.atheism',\n",
-        "        'talk.religion.misc',\n",
-        "        'comp.graphics',\n",
-        "        'sci.space',\n",
-        "    ]\n",
-        "\n",
-        "data_test = fetch_20newsgroups(subset = 'test', categories = categories,\n",
-        "                               shuffle = True, random_state = 42,\n",
-        "                               remove = remove)\n",
-        "\n",
-        "X_test = np.array(data_test.data).reshape((len(data_test.data),1))\n",
-        "y_test = data_test.target\n",
-        "\n",
-        "# Test our best pipeline.\n",
-        "\n",
-        "y_pred = fitted_model.predict(X_test)\n",
-        "y_pred_strings = [data_test.target_names[i] for i in y_pred]\n",
-        "y_test_strings = [data_test.target_names[i] for i in y_test]\n",
-        "\n",
-        "cm = ConfusionMatrix(y_test_strings, y_pred_strings)\n",
-        "print(cm)\n",
-        "cm.plot()"
-      ]
-    }
-  ],
-  "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/remote-execution-with-datastore/auto-ml-remote-execution-with-datastore.ipynb

@@ -1,586 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Automated Machine Learning\n",
-        "_**Remote Execution with DataStore**_\n",
-        "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Data](#Data)\n",
-        "1. [Train](#Train)\n",
-        "1. [Results](#Results)\n",
-        "1. [Test](#Test)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
-        "This sample accesses a data file on a remote DSVM through DataStore. Advantages of using data store are:\n",
-        "1. DataStore secures the access details.\n",
-        "2. DataStore supports read, write to blob and file store\n",
-        "3. AutoML natively supports copying data from DataStore to DSVM\n",
-        "\n",
-        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
-        "\n",
-        "In this notebook you would see\n",
-        "1. Storing data in DataStore.\n",
-        "2. get_data returning data from DataStore."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Setup\n",
-        "\n",
-        "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."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import logging\n",
-        "import os\n",
-        "import time\n",
-        "\n",
-        "import numpy as np\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",
-        "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-remote-datastore-file'\n",
-        "# project folder\n",
-        "project_folder = './sample_projects/automl-remote-datastore-file'\n",
-        "\n",
-        "experiment=Experiment(ws, experiment_name)\n",
-        "\n",
-        "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
-        "output['Subscription ID'] = ws.subscription_id\n",
-        "output['Workspace'] = ws.name\n",
-        "output['Resource Group'] = ws.resource_group\n",
-        "output['Location'] = ws.location\n",
-        "output['Project Directory'] = project_folder\n",
-        "output['Experiment Name'] = experiment.name\n",
-        "pd.set_option('display.max_colwidth', -1)\n",
-        "outputDf = pd.DataFrame(data = output, index = [''])\n",
-        "outputDf.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Create a Remote Linux DSVM\n",
-        "Note: If creation fails with a message about Marketplace purchase eligibilty, go to portal.azure.com, start creating DSVM there, and select \"Want to create programmatically\" to enable programmatic creation. Once you've enabled it, you can exit without actually creating VM.\n",
-        "\n",
-        "**Note**: By default SSH runs on port 22 and you don't need to specify it. But if for security reasons you can switch to a different port (such as 5022), you can append the port number to the address. [Read more](https://docs.microsoft.com/en-us/azure/virtual-machines/troubleshooting/detailed-troubleshoot-ssh-connection) on this."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "compute_target_name = 'mydsvmc'\n",
-        "\n",
-        "try:\n",
-        "    while ws.compute_targets[compute_target_name].provisioning_state == 'Creating':\n",
-        "        time.sleep(1)\n",
-        "        \n",
-        "    dsvm_compute = DsvmCompute(workspace=ws, name=compute_target_name)\n",
-        "    print('found existing:', dsvm_compute.name)\n",
-        "except:\n",
-        "    dsvm_config = DsvmCompute.provisioning_configuration(vm_size=\"Standard_D2_v2\")\n",
-        "    dsvm_compute = DsvmCompute.create(ws, name=compute_target_name, provisioning_configuration=dsvm_config)\n",
-        "    dsvm_compute.wait_for_completion(show_output=True)\n",
-        "    print(\"Waiting one minute for ssh to be accessible\")\n",
-        "    time.sleep(90) # Wait for ssh to be accessible"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Data\n",
-        "\n",
-        "### Copy data file to local\n",
-        "\n",
-        "Download the data file.\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "if not os.path.isdir('data'):\n",
-        "    os.mkdir('data')    "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from sklearn.datasets import fetch_20newsgroups\n",
-        "import csv\n",
-        "\n",
-        "remove = ('headers', 'footers', 'quotes')\n",
-        "categories = [\n",
-        "        'alt.atheism',\n",
-        "        'talk.religion.misc',\n",
-        "        'comp.graphics',\n",
-        "        'sci.space',\n",
-        "    ]\n",
-        "data_train = fetch_20newsgroups(subset = 'train', categories = categories,\n",
-        "                                    shuffle = True, random_state = 42,\n",
-        "                                    remove = remove)\n",
-        "    \n",
-        "pd.DataFrame(data_train.data).to_csv(\"data/X_train.tsv\", index=False, header=False, quoting=csv.QUOTE_ALL, sep=\"\\t\")\n",
-        "pd.DataFrame(data_train.target).to_csv(\"data/y_train.tsv\", index=False, header=False, sep=\"\\t\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Upload data to the cloud"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Now make the data accessible remotely by uploading that data from your local machine into Azure so it can be accessed for remote training. The datastore is a convenient construct associated with your workspace for you to upload/download data, and interact with it from your remote compute targets. It is backed by Azure blob storage account.\n",
-        "\n",
-        "The data.tsv files are uploaded into a directory named data at the root of the datastore."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#blob_datastore = Datastore(ws, blob_datastore_name)\n",
-        "ds = ws.get_default_datastore()\n",
-        "print(ds.datastore_type, ds.account_name, ds.container_name)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# ds.upload_files(\"data.tsv\")\n",
-        "ds.upload(src_dir='./data', target_path='data', overwrite=True, show_progress=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Configure & Run\n",
-        "\n",
-        "First let's create a DataReferenceConfigruation object to inform the system what data folder to download to the compute target.\n",
-        "The path_on_compute should be an absolute path to ensure that the data files are downloaded only once.   The get_data method should use this same path to access the data files."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.runconfig import DataReferenceConfiguration\n",
-        "dr = DataReferenceConfiguration(datastore_name=ds.name, \n",
-        "                   path_on_datastore='data', \n",
-        "                   path_on_compute='/tmp/azureml_runs',\n",
-        "                   mode='download', # download files from datastore to compute target\n",
-        "                   overwrite=False)"
-      ]
-    },
-    {
-      "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 the Linux DSVM\n",
-        "conda_run_config.target = dsvm_compute\n",
-        "# set the data reference of the run coonfiguration\n",
-        "conda_run_config.data_references = {ds.name: dr}\n",
-        "\n",
-        "pandas_dependency = 'pandas==' + pkg_resources.get_distribution(\"pandas\").version\n",
-        "\n",
-        "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy','py-xgboost<=0.80',pandas_dependency])\n",
-        "conda_run_config.environment.python.conda_dependencies = cd"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Create Get Data File\n",
-        "For remote executions you should author a get_data.py file containing a get_data() function. This file should be in the root directory of the project. You can encapsulate code to read data either from a blob storage or local disk in this file.\n",
-        "\n",
-        "The *get_data()* function returns a [dictionary](README.md#getdata).\n",
-        "\n",
-        "The read_csv uses the path_on_compute value specified in the DataReferenceConfiguration call plus the path_on_datastore folder and then the actual file name."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "if not os.path.exists(project_folder):\n",
-        "    os.makedirs(project_folder)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "%%writefile $project_folder/get_data.py\n",
-        "\n",
-        "import pandas as pd\n",
-        "\n",
-        "def get_data():\n",
-        "    X_train = pd.read_csv(\"/tmp/azureml_runs/data/X_train.tsv\", delimiter=\"\\t\", header=None, quotechar='\"')\n",
-        "    y_train = pd.read_csv(\"/tmp/azureml_runs/data/y_train.tsv\", delimiter=\"\\t\", header=None, quotechar='\"')\n",
-        "\n",
-        "    return { \"X\" : X_train.values, \"y\" : y_train[0].values }"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Train\n",
-        "\n",
-        "You can specify automl_settings as **kwargs** as well. Also note that you can use the get_data() symantic for local excutions too. \n",
-        "\n",
-        "<i>Note: For Remote DSVM and Batch AI you cannot pass Numpy arrays directly to AutoMLConfig.</i>\n",
-        "\n",
-        "|Property|Description|\n",
-        "|-|-|\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 Auto ML trains a specific pipeline with the data|\n",
-        "|**n_cross_validations**|Number of cross validation splits|\n",
-        "|**max_concurrent_iterations**|Max number of iterations that would be executed in parallel.  This should be less than the number of cores on the DSVM\n",
-        "|**preprocess**| *True/False* <br>Setting this to *True* enables Auto ML to perform preprocessing <br>on the input to handle *missing data*, and perform some common *feature extraction*|\n",
-        "|**enable_cache**|Setting this to *True* enables preprocess done once and reuse the same preprocessed data for all the iterations. Default value is True.|\n",
-        "|**max_cores_per_iteration**| Indicates how many cores on the compute target would be used to train a single pipeline.<br> Default is *1*, you can set it to *-1* to use all cores|"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "automl_settings = {\n",
-        "    \"iteration_timeout_minutes\": 60,\n",
-        "    \"iterations\": 4,\n",
-        "    \"n_cross_validations\": 5,\n",
-        "    \"primary_metric\": 'AUC_weighted',\n",
-        "    \"preprocess\": True,\n",
-        "    \"max_cores_per_iteration\": 1,\n",
-        "    \"verbosity\": logging.INFO\n",
-        "}\n",
-        "automl_config = AutoMLConfig(task = 'classification',\n",
-        "                             debug_log = 'automl_errors.log',\n",
-        "                             path=project_folder,\n",
-        "                             run_configuration=conda_run_config,\n",
-        "                             #compute_target = dsvm_compute,\n",
-        "                             data_script = project_folder + \"/get_data.py\",\n",
-        "                             **automl_settings\n",
-        "                            )"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "For remote runs the execution is asynchronous, so you will see the iterations get populated as they complete. You can interact with the widgets/models even when the experiment is running to retreive the best model up to that point. Once you are satisfied with the model you can cancel a particular iteration or the whole run."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run = experiment.submit(automl_config, show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Results\n",
-        "#### Widget for monitoring runs\n",
-        "\n",
-        "The widget will sit on \"loading\" until the first iteration completed, then you will see an auto-updating graph and table show up. It refreshed once per minute, so you should see the graph update as child runs complete.\n",
-        "\n",
-        "You can click on a pipeline to see run properties and output logs. Logs are also available on the DSVM under /tmp/azureml_run/{iterationid}/azureml-logs\n",
-        "\n",
-        "NOTE: The widget displays a link at the bottom. This links to a web-ui to explore the individual run details."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.widgets import RunDetails\n",
-        "RunDetails(remote_run).show() "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Wait until the run finishes.\n",
-        "remote_run.wait_for_completion(show_output = True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "\n",
-        "#### Retrieve All Child Runs\n",
-        "You can also use sdk methods to fetch all the child runs and see individual metrics that we log. "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "children = list(remote_run.get_children())\n",
-        "metricslist = {}\n",
-        "for run in children:\n",
-        "    properties = run.get_properties()\n",
-        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}    \n",
-        "    metricslist[int(properties['iteration'])] = metrics\n",
-        "\n",
-        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
-        "rundata"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Canceling 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": {},
-      "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": [
-        "### Retrieve the Best Model\n",
-        "\n",
-        "Below we select the best pipeline from our iterations. The *get_output* method returns the best run and the fitted model. 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 = remote_run.get_output()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Best Model based on any other metric"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# lookup_metric = \"accuracy\"\n",
-        "# best_run, fitted_model = remote_run.get_output(metric=lookup_metric)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Model from a specific iteration"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# iteration = 1\n",
-        "# best_run, fitted_model = remote_run.get_output(iteration=iteration)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Test\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Load test data.\n",
-        "from pandas_ml import ConfusionMatrix\n",
-        "\n",
-        "data_test = fetch_20newsgroups(subset = 'test', categories = categories,\n",
-        "                               shuffle = True, random_state = 42,\n",
-        "                               remove = remove)\n",
-        "\n",
-        "X_test = np.array(data_test.data).reshape((len(data_test.data),1))\n",
-        "y_test = data_test.target\n",
-        "\n",
-        "# Test our best pipeline.\n",
-        "\n",
-        "y_pred = fitted_model.predict(X_test)\n",
-        "y_pred_strings = [data_test.target_names[i] for i in y_pred]\n",
-        "y_test_strings = [data_test.target_names[i] for i in y_test]\n",
-        "\n",
-        "cm = ConfusionMatrix(y_test_strings, y_pred_strings)\n",
-        "print(cm)\n",
-        "cm.plot()"
-      ]
-    }
-  ],
-  "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/remote-execution/auto-ml-remote-execution.ipynb

@@ -1,527 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Automated Machine Learning\n",
-        "_**Remote Execution using DSVM (Ubuntu)**_\n",
-        "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Data](#Data)\n",
-        "1. [Train](#Train)\n",
-        "1. [Results](#Results)\n",
-        "1. [Test](#Test)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
-        "In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset) to showcase how you can use AutoML for a simple classification problem.\n",
-        "\n",
-        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
-        "\n",
-        "In this notebook you wiil learn how to:\n",
-        "1. Create an `Experiment` in an existing `Workspace`.\n",
-        "2. Attach an existing DSVM to a workspace.\n",
-        "3. Configure AutoML using `AutoMLConfig`.\n",
-        "4. Train the model using the DSVM.\n",
-        "5. Explore the results.\n",
-        "6. Test the best fitted model.\n",
-        "\n",
-        "In addition, this notebook showcases the following features:\n",
-        "- **Parallel** executions for iterations\n",
-        "- **Asynchronous** tracking of progress\n",
-        "- **Cancellation** of individual iterations or the entire run\n",
-        "- Retrieving models for any iteration or logged metric\n",
-        "- Specifying AutoML settings as `**kwargs`"
-      ]
-    },
-    {
-      "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",
-        "import os\n",
-        "import time\n",
-        "import csv\n",
-        "\n",
-        "from matplotlib import pyplot as plt\n",
-        "import numpy as np\n",
-        "import pandas as pd\n",
-        "from sklearn import datasets\n",
-        "\n",
-        "import azureml.core\n",
-        "from azureml.core.experiment import Experiment\n",
-        "from azureml.core.workspace import Workspace\n",
-        "from azureml.train.automl import AutoMLConfig"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ws = Workspace.from_config()\n",
-        "\n",
-        "# Choose a name for the run history container in the workspace.\n",
-        "experiment_name = 'automl-remote-dsvm'\n",
-        "project_folder = './project'\n",
-        "\n",
-        "experiment = Experiment(ws, experiment_name)\n",
-        "\n",
-        "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
-        "output['Subscription ID'] = ws.subscription_id\n",
-        "output['Workspace Name'] = ws.name\n",
-        "output['Resource Group'] = ws.resource_group\n",
-        "output['Location'] = ws.location\n",
-        "output['Project Directory'] = project_folder\n",
-        "output['Experiment Name'] = experiment.name\n",
-        "pd.set_option('display.max_colwidth', -1)\n",
-        "outputDf = pd.DataFrame(data = output, index = [''])\n",
-        "outputDf.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Create a Remote Linux DSVM\n",
-        "**Note:** If creation fails with a message about Marketplace purchase eligibilty, start creation of a DSVM through the [Azure portal](https://portal.azure.com), and select \"Want to create programmatically\" to enable programmatic creation. Once you've enabled this setting, you can exit the portal without actually creating the DSVM, and creation of the DSVM through the notebook should work.\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.compute import DsvmCompute\n",
-        "\n",
-        "dsvm_name = 'mydsvma'\n",
-        "try:\n",
-        "    dsvm_compute = DsvmCompute(ws, dsvm_name)\n",
-        "    print('Found an existing DSVM.')\n",
-        "except:\n",
-        "    print('Creating a new DSVM.')\n",
-        "    dsvm_config = DsvmCompute.provisioning_configuration(vm_size = \"Standard_D2s_v3\")\n",
-        "    dsvm_compute = DsvmCompute.create(ws, name = dsvm_name, provisioning_configuration = dsvm_config)\n",
-        "    dsvm_compute.wait_for_completion(show_output = True)\n",
-        "    print(\"Waiting one minute for ssh to be accessible\")\n",
-        "    time.sleep(90) # Wait for ssh to be accessible"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Data\n",
-        "For remote executions, you need to make the data accessible from the remote compute.\n",
-        "This can be done by uploading the data to DataStore.\n",
-        "In this example, we upload scikit-learn's [load_digits](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) data."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "data_train = datasets.load_digits()\n",
-        "\n",
-        "if not os.path.isdir('data'):\n",
-        "    os.mkdir('data')\n",
-        "    \n",
-        "if not os.path.exists(project_folder):\n",
-        "    os.makedirs(project_folder)\n",
-        "    \n",
-        "pd.DataFrame(data_train.data).to_csv(\"data/X_train.tsv\", index=False, header=False, quoting=csv.QUOTE_ALL, sep=\"\\t\")\n",
-        "pd.DataFrame(data_train.target).to_csv(\"data/y_train.tsv\", index=False, header=False, sep=\"\\t\")\n",
-        "\n",
-        "ds = ws.get_default_datastore()\n",
-        "ds.upload(src_dir='./data', target_path='re_data', overwrite=True, show_progress=True)\n",
-        "\n",
-        "from azureml.core.runconfig import DataReferenceConfiguration\n",
-        "dr = DataReferenceConfiguration(datastore_name=ds.name, \n",
-        "                   path_on_datastore='re_data', \n",
-        "                   path_on_compute='/tmp/azureml_runs',\n",
-        "                   mode='download', # download files from datastore to compute target\n",
-        "                   overwrite=False)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.runconfig import RunConfiguration\n",
-        "from azureml.core.conda_dependencies import CondaDependencies\n",
-        "\n",
-        "# create a new RunConfig object\n",
-        "conda_run_config = RunConfiguration(framework=\"python\")\n",
-        "\n",
-        "# Set compute target to the Linux DSVM\n",
-        "conda_run_config.target = dsvm_compute\n",
-        "\n",
-        "# set the data reference of the run coonfiguration\n",
-        "conda_run_config.data_references = {ds.name: dr}\n",
-        "\n",
-        "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy','py-xgboost<=0.80'])\n",
-        "conda_run_config.environment.python.conda_dependencies = cd"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "%%writefile $project_folder/get_data.py\n",
-        "\n",
-        "import pandas as pd\n",
-        "\n",
-        "def get_data():\n",
-        "    X_train = pd.read_csv(\"/tmp/azureml_runs/re_data/X_train.tsv\", delimiter=\"\\t\", header=None, quotechar='\"')\n",
-        "    y_train = pd.read_csv(\"/tmp/azureml_runs/re_data/y_train.tsv\", delimiter=\"\\t\", header=None, quotechar='\"')\n",
-        "\n",
-        "    return { \"X\" : X_train.values, \"y\" : y_train[0].values }\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Train\n",
-        "\n",
-        "You can specify `automl_settings` as `**kwargs` as well. Also note that you can use a `get_data()` function for local excutions too.\n",
-        "\n",
-        "**Note:** When using Remote DSVM, you can't pass Numpy arrays directly to the fit method.\n",
-        "\n",
-        "|Property|Description|\n",
-        "|-|-|\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",
-        "|**max_concurrent_iterations**|Maximum number of iterations to execute in parallel. This should be less than the number of cores on the DSVM.|"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "automl_settings = {\n",
-        "    \"iteration_timeout_minutes\": 10,\n",
-        "    \"iterations\": 20,\n",
-        "    \"n_cross_validations\": 5,\n",
-        "    \"primary_metric\": 'AUC_weighted',\n",
-        "    \"preprocess\": False,\n",
-        "    \"max_concurrent_iterations\": 2,\n",
-        "    \"verbosity\": logging.INFO\n",
-        "}\n",
-        "\n",
-        "automl_config = AutoMLConfig(task = 'classification',\n",
-        "                             debug_log = 'automl_errors.log',\n",
-        "                             path = project_folder, \n",
-        "                             run_configuration=conda_run_config,\n",
-        "                             data_script = project_folder + \"/get_data.py\",\n",
-        "                             **automl_settings\n",
-        "                            )\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "**Note:** The first run on a new DSVM may take several minutes to prepare the environment."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Call the `submit` method on the experiment object and pass the run configuration. For remote runs the execution is asynchronous, so you will see the iterations get populated as they complete. You can interact with the widgets and models even when the experiment is running to retrieve the best model up to that point. Once you are satisfied with the model, you can cancel a particular iteration or the whole run.\n",
-        "\n",
-        "In this example, we specify `show_output = False` to suppress console output while the run is in progress."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run = experiment.submit(automl_config, show_output = False)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Results\n",
-        "\n",
-        "#### Loading Executed Runs\n",
-        "In case you need to load a previously executed run, enable the cell below and replace the `run_id` value."
-      ]
-    },
-    {
-      "cell_type": "raw",
-      "metadata": {},
-      "source": [
-        "remote_run = AutoMLRun(experiment=experiment, run_id = 'AutoML_480d3ed6-fc94-44aa-8f4e-0b945db9d3ef')"
-      ]
-    },
-    {
-      "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",
-        "You can click on a pipeline to see run properties and output logs.  Logs are also available on the DSVM under `/tmp/azureml_run/{iterationid}/azureml-logs`\n",
-        "\n",
-        "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.widgets import RunDetails\n",
-        "RunDetails(remote_run).show() "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Wait until the run finishes.\n",
-        "remote_run.wait_for_completion(show_output = True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "\n",
-        "#### Retrieve All Child Runs\n",
-        "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "children = list(remote_run.get_children())\n",
-        "metricslist = {}\n",
-        "for run in children:\n",
-        "    properties = run.get_properties()\n",
-        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}    \n",
-        "    metricslist[int(properties['iteration'])] = metrics\n",
-        "\n",
-        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
-        "rundata"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Cancelling Runs\n",
-        "\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": {},
-      "source": [
-        "### Retrieve the Best Model\n",
-        "\n",
-        "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "best_run, fitted_model = remote_run.get_output()\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Best Model Based on Any Other Metric\n",
-        "Show the run and the model which has the smallest `log_loss` value:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "lookup_metric = \"log_loss\"\n",
-        "best_run, fitted_model = remote_run.get_output(metric = lookup_metric)\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Model from a Specific Iteration\n",
-        "Show the run and the model from the third iteration:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "iteration = 3\n",
-        "third_run, third_model = remote_run.get_output(iteration = iteration)\n",
-        "print(third_run)\n",
-        "print(third_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Test\n",
-        "\n",
-        "#### Load Test Data"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "digits = datasets.load_digits()\n",
-        "X_test = digits.data[:10, :]\n",
-        "y_test = digits.target[:10]\n",
-        "images = digits.images[:10]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Test Our Best Fitted Model"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Randomly select digits and test.\n",
-        "for index in np.random.choice(len(y_test), 2, replace = False):\n",
-        "    print(index)\n",
-        "    predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
-        "    label = y_test[index]\n",
-        "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
-        "    fig = plt.figure(1, figsize=(3,3))\n",
-        "    ax1 = fig.add_axes((0,0,.8,.8))\n",
-        "    ax1.set_title(title)\n",
-        "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
-        "    plt.show()"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "savitam"
-      }
-    ],
-    "kernelspec": {
-      "display_name": "Python 3.6",
-      "language": "python",
-      "name": "python36"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.6.6"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

how-to-use-azureml/automated-machine-learning/sample-weight/auto-ml-sample-weight.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/sample-weight/auto-ml-sample-weight.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

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

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

how-to-use-azureml/automated-machine-learning/sparse-data-train-test-split/auto-ml-sparse-data-train-test-split.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/sparse-data-train-test-split/auto-ml-sparse-data-train-test-split.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

how-to-use-azureml/automated-machine-learning/sparse-data-train-test-split/auto-ml-sparse-data-train-test-split.yml

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

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

@@ -0,0 +1,113 @@
+# Table of Contents
+1. [Introduction](#introduction)
+1. [Setup using Azure Data Studio](#azuredatastudiosetup)
+1. [Energy demand example using Azure Data Studio](#azuredatastudioenergydemand)
+1. [Set using SQL Server Management Studio for SQL Server 2017 on Windows](#ssms2017)
+1. [Set using SQL Server Management Studio for SQL Server 2019 on Linux](#ssms2019)
+1. [Energy demand example using SQL Server Management Studio](#ssmsenergydemand)
+
+
+<a name="introduction"></a>
+# Introduction
+SQL Server 2017 or 2019 can call Azure ML automated machine learning to create models trained on data from SQL Server.
+This uses the sp_execute_external_script stored procedure, which can call Python scripts.
+SQL Server 2017 and SQL Server 2019 can both run on Windows or Linux.
+However, this integration is not available for SQL Server 2017 on Linux. 
+
+This folder shows how to setup the integration and has a sample that uses the integration to train and predict based on an energy demand dataset.
+
+This integration is part of SQL Server and so can be used from any SQL client. 
+These instructions show using it from Azure Data Studio or SQL Server Managment Studio.
+
+<a name="azuredatastudiosetup"></a>
+## Setup using Azure Data Studio
+
+These step show setting up the integration using Azure Data Studio.
+
+1. If you don't already have SQL Server, you can install it from [https://www.microsoft.com/en-us/sql-server/sql-server-downloads](https://www.microsoft.com/en-us/sql-server/sql-server-downloads)
+1. Install Azure Data Studio from [https://docs.microsoft.com/en-us/sql/azure-data-studio/download?view=sql-server-2017](https://docs.microsoft.com/en-us/sql/azure-data-studio/download?view=sql-server-2017)
+1. Start Azure Data Studio and connect to SQL Server. [https://docs.microsoft.com/en-us/sql/azure-data-studio/sql-notebooks?view=sql-server-2017](https://docs.microsoft.com/en-us/sql/azure-data-studio/sql-notebooks?view=sql-server-2017)
+1. Create a database named "automl".
+1. Open the notebook how-to-use-azureml\automated-machine-learning\sql-server\setup\auto-ml-sql-setup.ipynb and follow the instructions in it.
+
+ <a name="azuredatastudioenergydemand"></a>
+## Energy demand example using Azure Data Studio
+
+Once you have completed the setup, you can try the energy demand sample in the notebook energy-demand\auto-ml-sql-energy-demand.ipynb.
+This has cells to train a model, predict based on the model and show metrics for each pipeline run in training the model.
+
+<a name="ssms2017"></a>
+## Setup using SQL Server Management Studio for SQL Server 2017 on Windows
+
+These instruction setup the integration for SQL Server 2017 on Windows.
+
+1. If you don't already have SQL Server, you can install it from [https://www.microsoft.com/en-us/sql-server/sql-server-downloads](https://www.microsoft.com/en-us/sql-server/sql-server-downloads)
+2. Enable external scripts with the following commands: 
+```sh
+   sp_configure 'external scripts enabled',1 
+   reconfigure with override
+```
+3. Stop SQL Server. 
+4. Install the automated machine learning libraries using the following commands from Administrator command prompt (If you are using a non-default SQL Server instance name, replace MSSQLSERVER in the second command with the instance name)
+```sh
+   cd "C:\Program Files\Microsoft SQL Server"
+   cd "MSSQL14.MSSQLSERVER\PYTHON_SERVICES"
+   python.exe -m pip install azureml-sdk[automl]
+   python.exe -m pip install --upgrade numpy
+   python.exe -m pip install --upgrade sklearn
+```
+5. Start SQL Server and the service "SQL Server Launchpad service". 
+6. In Windows Firewall, click on advanced settings and in Outbound Rules, disable "Block network access for R local user accounts in SQL Server instance xxxx". 
+7. Execute the files in the setup folder in SQL Server Management Studio: aml_model.sql, aml_connection.sql, AutoMLGetMetrics.sql, AutoMLPredict.sql and AutoMLTrain.sql 
+8. Create an Azure Machine Learning Workspace.  You can use the instructions at: [https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-workspace ](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-workspace)
+9. Create a config.json file file using the subscription id, resource group name and workspace name that you used to create the workspace.  The file is described at: [https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-environment#workspace](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-environment#workspace)
+10. Create an Azure service principal.  You can do this with the commands: 
+```sh
+   az login 
+   az account set --subscription subscriptionid 
+   az ad sp create-for-rbac --name principlename --password password 
+```
+11. Insert the values \<tenant\>, \<AppId\> and \<password\> returned by create-for-rbac above into the aml_connection table.  Set \<path\> as the absolute path to your config.json file. Set the name to <20>Default<6C>. 
+ 
+<a name="ssms2019"></a>
+## Setup using SQL Server Management Studio for SQL Server 2019 on Linux
+1. Install SQL Server 2019 from: [https://www.microsoft.com/en-us/sql-server/sql-server-downloads](https://www.microsoft.com/en-us/sql-server/sql-server-downloads)
+2. Install machine learning support from: [https://docs.microsoft.com/en-us/sql/linux/sql-server-linux-setup-machine-learning?view=sqlallproducts-allversions#ubuntu](https://docs.microsoft.com/en-us/sql/linux/sql-server-linux-setup-machine-learning?view=sqlallproducts-allversions#ubuntu)
+3. Then install SQL Server management Studio from [https://docs.microsoft.com/en-us/sql/ssms/download-sql-server-management-studio-ssms?view=sql-server-2017](https://docs.microsoft.com/en-us/sql/ssms/download-sql-server-management-studio-ssms?view=sql-server-2017)
+4. Enable external scripts with the following commands: 
+```sh
+   sp_configure 'external scripts enabled',1 
+   reconfigure with override 
+```
+5. Stop SQL Server. 
+6. Install the automated machine learning libraries using the following commands from Administrator command (If you are using a non-default SQL Server instance name, replace MSSQLSERVER in the second command with the instance name): 
+```sh
+   sudo /opt/mssql/mlservices/bin/python/python -m pip install azureml-sdk[automl] 
+   sudo /opt/mssql/mlservices/bin/python/python -m pip install --upgrade numpy 
+   sudo /opt/mssql/mlservices/bin/python/python -m pip install --upgrade sklearn
+```
+7. Start SQL Server. 
+8. Execute the files aml_model.sql, aml_connection.sql, AutoMLGetMetrics.sql, AutoMLPredict.sql, AutoMLForecast.sql and AutoMLTrain.sql in SQL Server Management Studio. 
+9. Create an Azure Machine Learning Workspace.  You can use the instructions at: [https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-workspace](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-workspace)
+10. Create a config.json file file using the subscription id, resource group name and workspace name that you use to create the workspace.  The file is described at: [https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-environment#workspace](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-environment#workspace)
+11. Create an Azure service principal.  You can do this with the commands: 
+```sh
+   az login 
+   az account set --subscription subscriptionid 
+   az ad sp create-for-rbac --name principlename --password password 
+``` 
+12. Insert the values \<tenant\>, \<AppId\> and \<password\> returned by create-for-rbac above into the aml_connection table.  Set \<path\> as the absolute path to your config.json file. Set the name to <20>Default<6C>. 
+ 
+<a name="ssmsenergydemand"></a>
+## Energy demand example using SQL Server Management Studio
+
+Once you have completed the setup, you can try the energy demand sample queries.
+First you need to load the sample data in the database.
+1. In SQL Server Management Studio, you can right-click the database, select Tasks, then Import Flat file. 
+1. Select the file MachineLearningNotebooks\notebooks\how-to-use-azureml\automated-machine-learning\forecasting-energy-demand\nyc_energy.csv. 
+1. When you get to the column definition page, allow nulls for all columns. 
+
+You can then run the queries in the energy-demand folder:
+* TrainEnergyDemand.sql runs AutoML, trains multiple models on data and selects the best model.
+* ForecastEnergyDemand.sql forecasts based on the most recent training run.
+* GetMetrics.sql returns all the metrics for each model in the most recent training run.

how-to-use-azureml/automated-machine-learning/sql-server/energy-demand/ForecastEnergyDemand.sql

@@ -0,0 +1,23 @@
+-- This shows using the AutoMLForecast stored procedure to predict using a forecasting model for the nyc_energy dataset.
+
+DECLARE @Model NVARCHAR(MAX) = (SELECT TOP 1 Model FROM dbo.aml_model
+                                WHERE ExperimentName = 'automl-sql-forecast'
+								ORDER BY CreatedDate DESC)
+
+DECLARE @max_horizon INT = 48
+DECLARE @split_time NVARCHAR(22) = (SELECT DATEADD(hour, -@max_horizon, MAX(timeStamp)) FROM nyc_energy WHERE demand IS NOT NULL)
+
+DECLARE @TestDataQuery NVARCHAR(MAX) = '
+SELECT CAST(timeStamp AS NVARCHAR(30)) AS timeStamp,
+       demand,
+	   precip,
+	   temp
+FROM nyc_energy
+WHERE demand IS NOT NULL AND precip IS NOT NULL AND temp IS NOT NULL
+AND timeStamp > ''' + @split_time + ''''
+
+EXEC dbo.AutoMLForecast @input_query=@TestDataQuery,
+@label_column='demand',
+@time_column_name='timeStamp',
+@model=@model
+WITH RESULT SETS ((timeStamp DATETIME, grain NVARCHAR(255), predicted_demand FLOAT, precip FLOAT, temp FLOAT, actual_demand FLOAT))

how-to-use-azureml/automated-machine-learning/sql-server/energy-demand/GetMetrics.sql

@@ -0,0 +1,10 @@
+-- This lists all the metrics for all iterations for the most recent run.
+
+DECLARE @RunId NVARCHAR(43)
+DECLARE @ExperimentName NVARCHAR(255)
+
+SELECT TOP 1 @ExperimentName=ExperimentName, @RunId=SUBSTRING(RunId, 1, 43)
+FROM aml_model
+ORDER BY CreatedDate DESC
+
+EXEC dbo.AutoMLGetMetrics @RunId, @ExperimentName

how-to-use-azureml/automated-machine-learning/sql-server/energy-demand/PredictEnergyDemand.sql

@@ -0,0 +1,17 @@
+-- This shows using the AutoMLPredict stored procedure to predict using a forecasting model for the nyc_energy dataset.
+
+DECLARE @Model NVARCHAR(MAX) = (SELECT TOP 1 Model FROM dbo.aml_model
+                                WHERE ExperimentName = 'automl-sql-forecast'
+								ORDER BY CreatedDate DESC)
+
+EXEC dbo.AutoMLPredict @input_query='
+SELECT CAST(timeStamp AS NVARCHAR(30)) AS timeStamp,
+       demand,
+	   precip,
+	   temp
+FROM nyc_energy
+WHERE demand IS NOT NULL AND precip IS NOT NULL AND temp IS NOT NULL
+AND timeStamp >= ''2017-02-01''',
+@label_column='demand',
+@model=@model
+WITH RESULT SETS ((timeStamp NVARCHAR(30), actual_demand FLOAT, precip FLOAT, temp FLOAT, predicted_demand FLOAT))

how-to-use-azureml/automated-machine-learning/sql-server/energy-demand/TrainEnergyDemand.sql

@@ -0,0 +1,25 @@
+-- This shows using the AutoMLTrain stored procedure to create a forecasting model for the nyc_energy dataset.
+
+DECLARE @max_horizon INT = 48
+DECLARE @split_time NVARCHAR(22) = (SELECT DATEADD(hour, -@max_horizon, MAX(timeStamp)) FROM nyc_energy WHERE demand IS NOT NULL)
+
+DECLARE @TrainDataQuery NVARCHAR(MAX) = '
+SELECT CAST(timeStamp as NVARCHAR(30)) as timeStamp,
+       demand,
+	   precip,
+	   temp
+FROM nyc_energy
+WHERE demand IS NOT NULL AND precip IS NOT NULL AND temp IS NOT NULL
+and timeStamp < ''' + @split_time + ''''
+
+INSERT INTO dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)
+EXEC dbo.AutoMLTrain @input_query= @TrainDataQuery,
+@label_column='demand',
+@task='forecasting',
+@iterations=10,
+@iteration_timeout_minutes=5,
+@time_column_name='timeStamp',
+@max_horizon=@max_horizon,
+@experiment_name='automl-sql-forecast',
+@primary_metric='normalized_root_mean_squared_error'
+

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

@@ -0,0 +1,141 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Train a model and use it for prediction\r\n",
+        "\r\n",
+        "Before running this notebook, run the auto-ml-sql-setup.ipynb notebook."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/sql-server/energy-demand/auto-ml-sql-energy-demand.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Set the default database"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "USE [automl]\r\n",
+        "GO"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Use the AutoMLTrain stored procedure to create a forecasting model for the nyc_energy dataset."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "INSERT INTO dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)\r\n",
+        "EXEC dbo.AutoMLTrain @input_query='\r\n",
+        "SELECT CAST(timeStamp as NVARCHAR(30)) as timeStamp,\r\n",
+        "       demand,\r\n",
+        "\t   precip,\r\n",
+        "\t   temp,\r\n",
+        "\t   CASE WHEN timeStamp < ''2017-01-01'' THEN 0 ELSE 1 END AS is_validate_column\r\n",
+        "FROM nyc_energy\r\n",
+        "WHERE demand IS NOT NULL AND precip IS NOT NULL AND temp IS NOT NULL\r\n",
+        "and timeStamp < ''2017-02-01''',\r\n",
+        "@label_column='demand',\r\n",
+        "@task='forecasting',\r\n",
+        "@iterations=10,\r\n",
+        "@iteration_timeout_minutes=5,\r\n",
+        "@time_column_name='timeStamp',\r\n",
+        "@is_validate_column='is_validate_column',\r\n",
+        "@experiment_name='automl-sql-forecast',\r\n",
+        "@primary_metric='normalized_root_mean_squared_error'"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Use the AutoMLPredict stored procedure to predict using the forecasting model for the nyc_energy dataset."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "DECLARE @Model NVARCHAR(MAX) = (SELECT TOP 1 Model FROM dbo.aml_model\r\n",
+        "                                WHERE ExperimentName = 'automl-sql-forecast'\r\n",
+        "\t\t\t\t\t\t\t\tORDER BY CreatedDate DESC)\r\n",
+        "\r\n",
+        "EXEC dbo.AutoMLPredict @input_query='\r\n",
+        "SELECT CAST(timeStamp AS NVARCHAR(30)) AS timeStamp,\r\n",
+        "       demand,\r\n",
+        "\t   precip,\r\n",
+        "\t   temp\r\n",
+        "FROM nyc_energy\r\n",
+        "WHERE demand IS NOT NULL AND precip IS NOT NULL AND temp IS NOT NULL\r\n",
+        "AND timeStamp >= ''2017-02-01''',\r\n",
+        "@label_column='demand',\r\n",
+        "@model=@model\r\n",
+        "WITH RESULT SETS ((timeStamp NVARCHAR(30), actual_demand FLOAT, precip FLOAT, temp FLOAT, predicted_demand FLOAT))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## List all the metrics for all iterations for the most recent training run."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "DECLARE @RunId NVARCHAR(43)\r\n",
+        "DECLARE @ExperimentName NVARCHAR(255)\r\n",
+        "\r\n",
+        "SELECT TOP 1 @ExperimentName=ExperimentName, @RunId=SUBSTRING(RunId, 1, 43)\r\n",
+        "FROM aml_model\r\n",
+        "ORDER BY CreatedDate DESC\r\n",
+        "\r\n",
+        "EXEC dbo.AutoMLGetMetrics @RunId, @ExperimentName"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "jeffshep"
+      }
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "sql",
+      "name": "python36"
+    },
+    "language_info": {
+      "name": "sql",
+      "version": ""
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/sql-server/setup/AutoMLForecast.sql

@@ -0,0 +1,92 @@
+-- This procedure forecast values based on a forecasting model returned by AutoMLTrain.
+-- It returns a dataset with the forecasted values.
+SET ANSI_NULLS ON
+GO
+SET QUOTED_IDENTIFIER ON
+GO
+CREATE OR ALTER PROCEDURE [dbo].[AutoMLForecast]
+ (
+   @input_query NVARCHAR(MAX),          -- A SQL query returning data to predict on.
+   @model NVARCHAR(MAX),                -- A model returned from AutoMLTrain.
+   @time_column_name  NVARCHAR(255)='', -- The name of the timestamp column for forecasting.
+   @label_column  NVARCHAR(255)='',     -- Optional name of the column from input_query, which should be ignored when predicting
+   @y_query_column NVARCHAR(255)='',    -- Optional value column that can be used for predicting.
+                                        -- If specified, this can contain values for past times (after the model was trained)
+									    -- and contain Nan for future times.
+   @forecast_column_name NVARCHAR(255) = 'predicted'
+                                        -- The name of the output column containing the forecast value.
+ ) AS 
+BEGIN 
+  
+    EXEC sp_execute_external_script @language = N'Python', @script = N'import pandas as pd 
+import azureml.core  
+import numpy as np 
+from azureml.train.automl import AutoMLConfig  
+import pickle 
+import codecs 
+  
+model_obj = pickle.loads(codecs.decode(model.encode(), "base64")) 
+  
+test_data = input_data.copy() 
+
+if label_column != "" and label_column is not None:
+    y_test = test_data.pop(label_column).values
+else:
+    y_test = None 
+
+if y_query_column != "" and y_query_column is not None:
+    y_query = test_data.pop(y_query_column).values
+else:
+    y_query = np.repeat(np.nan, len(test_data))
+
+X_test = test_data 
+
+if time_column_name != "" and time_column_name is not None:
+    X_test[time_column_name] = pd.to_datetime(X_test[time_column_name])
+
+y_fcst, X_trans = model_obj.forecast(X_test, y_query) 
+
+def align_outputs(y_forecast, X_trans, X_test, y_test, forecast_column_name):
+    # Demonstrates how to get the output aligned to the inputs
+    # using pandas indexes. Helps understand what happened if
+    # the output shape differs from the input shape, or if
+    # the data got re-sorted by time and grain during forecasting.
+    
+    # Typical causes of misalignment are:
+    # * we predicted some periods that were missing in actuals -> drop from eval
+    # * model was asked to predict past max_horizon -> increase max horizon
+    # * data at start of X_test was needed for lags -> provide previous periods
+
+    df_fcst = pd.DataFrame({forecast_column_name : y_forecast})
+    # y and X outputs are aligned by forecast() function contract
+    df_fcst.index = X_trans.index
+    
+    # align original X_test to y_test    
+    X_test_full = X_test.copy()
+    if y_test is not None:
+        X_test_full[label_column] = y_test
+
+    # X_test_full does not include origin, so reset for merge
+    df_fcst.reset_index(inplace=True)
+    X_test_full = X_test_full.reset_index().drop(columns=''index'')
+    together = df_fcst.merge(X_test_full, how=''right'')
+    
+    # drop rows where prediction or actuals are nan 
+    # happens because of missing actuals 
+    # or at edges of time due to lags/rolling windows
+    clean = together[together[[label_column, forecast_column_name]].notnull().all(axis=1)]
+    return(clean)
+
+combined_output = align_outputs(y_fcst, X_trans, X_test, y_test, forecast_column_name)
+  
+' 
+    , @input_data_1 = @input_query 
+    , @input_data_1_name = N'input_data' 
+    , @output_data_1_name = N'combined_output' 
+    , @params = N'@model NVARCHAR(MAX), @time_column_name  NVARCHAR(255), @label_column NVARCHAR(255), @y_query_column NVARCHAR(255), @forecast_column_name NVARCHAR(255)' 
+    , @model = @model 
+	, @time_column_name = @time_column_name
+	, @label_column = @label_column
+	, @y_query_column = @y_query_column
+	, @forecast_column_name = @forecast_column_name
+END

how-to-use-azureml/automated-machine-learning/sql-server/setup/AutoMLGetMetrics.sql

@@ -0,0 +1,70 @@
+-- This procedure returns a list of metrics for each iteration of a run.
+SET ANSI_NULLS ON
+GO
+SET QUOTED_IDENTIFIER ON
+GO
+CREATE OR ALTER PROCEDURE [dbo].[AutoMLGetMetrics]
+ (
+	@run_id NVARCHAR(250),                           -- The RunId
+    @experiment_name NVARCHAR(32)='automl-sql-test', -- This can be used to find the experiment in the Azure Portal.
+    @connection_name NVARCHAR(255)='default'         -- The AML connection to use.
+ ) AS
+BEGIN
+    DECLARE @tenantid NVARCHAR(255)
+    DECLARE @appid NVARCHAR(255)
+    DECLARE @password NVARCHAR(255)
+    DECLARE @config_file NVARCHAR(255)
+
+	SELECT @tenantid=TenantId, @appid=AppId, @password=Password, @config_file=ConfigFile
+	FROM aml_connection
+	WHERE ConnectionName = @connection_name;
+
+    EXEC sp_execute_external_script @language = N'Python', @script = N'import pandas as pd
+import logging 
+import azureml.core 
+import numpy as np
+from azureml.core.experiment import Experiment 
+from azureml.train.automl.run import AutoMLRun
+from azureml.core.authentication import ServicePrincipalAuthentication 
+from azureml.core.workspace import Workspace 
+
+auth = ServicePrincipalAuthentication(tenantid, appid, password) 
+ 
+ws = Workspace.from_config(path=config_file, auth=auth) 
+ 
+experiment = Experiment(ws, experiment_name) 
+
+ml_run = AutoMLRun(experiment = experiment, run_id = run_id)
+
+children = list(ml_run.get_children())
+iterationlist = []
+metricnamelist = []
+metricvaluelist = []
+
+for run in children:
+    properties = run.get_properties()
+    if "iteration" in properties:
+        iteration = int(properties["iteration"])
+        for metric_name, metric_value in run.get_metrics().items():
+            if isinstance(metric_value, float):
+                iterationlist.append(iteration)
+                metricnamelist.append(metric_name)
+                metricvaluelist.append(metric_value)
+             
+metrics = pd.DataFrame({"iteration": iterationlist, "metric_name": metricnamelist, "metric_value": metricvaluelist})
+'
+    , @output_data_1_name = N'metrics'
+	, @params = N'@run_id NVARCHAR(250), 
+				  @experiment_name NVARCHAR(32),
+  				  @tenantid NVARCHAR(255),
+				  @appid NVARCHAR(255),
+				  @password NVARCHAR(255),
+				  @config_file NVARCHAR(255)'
+    , @run_id = @run_id
+	, @experiment_name = @experiment_name
+	, @tenantid = @tenantid
+	, @appid = @appid
+	, @password = @password
+	, @config_file = @config_file
+WITH RESULT SETS ((iteration INT, metric_name NVARCHAR(100), metric_value FLOAT))
+END

how-to-use-azureml/automated-machine-learning/sql-server/setup/AutoMLPredict.sql

@@ -0,0 +1,41 @@
+-- This procedure predicts values based on a model returned by AutoMLTrain and a dataset.
+-- It returns the dataset with a new column added, which is the predicted value.
+SET ANSI_NULLS ON
+GO
+SET QUOTED_IDENTIFIER ON
+GO
+CREATE OR ALTER PROCEDURE [dbo].[AutoMLPredict]
+ (
+   @input_query NVARCHAR(MAX),      -- A SQL query returning data to predict on.
+   @model NVARCHAR(MAX),            -- A model returned from AutoMLTrain.
+   @label_column  NVARCHAR(255)=''  -- Optional name of the column from input_query, which should be ignored when predicting
+ ) AS 
+BEGIN 
+  
+    EXEC sp_execute_external_script @language = N'Python', @script = N'import pandas as pd 
+import azureml.core  
+import numpy as np 
+from azureml.train.automl import AutoMLConfig  
+import pickle 
+import codecs 
+  
+model_obj = pickle.loads(codecs.decode(model.encode(), "base64")) 
+  
+test_data = input_data.copy() 
+
+if label_column != "" and label_column is not None:
+    y_test = test_data.pop(label_column).values 
+X_test = test_data 
+  
+predicted = model_obj.predict(X_test) 
+  
+combined_output = input_data.assign(predicted=predicted)
+  
+' 
+    , @input_data_1 = @input_query 
+    , @input_data_1_name = N'input_data' 
+    , @output_data_1_name = N'combined_output' 
+    , @params = N'@model NVARCHAR(MAX), @label_column  NVARCHAR(255)' 
+    , @model = @model 
+	, @label_column = @label_column
+END

how-to-use-azureml/automated-machine-learning/sql-server/setup/AutoMLTrain.sql

@@ -0,0 +1,240 @@
+-- This stored procedure uses automated machine learning to train several models
+-- and returns the best model.
+--
+-- The result set has several columns:
+--   best_run - iteration ID for the best model
+--   experiment_name - experiment name pass in with the @experiment_name parameter
+--   fitted_model - best model found
+--   log_file_text - AutoML debug_log contents
+--   workspace - name of the Azure ML workspace where run history is stored
+--
+-- An example call for a classification problem is:
+--    insert into dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)
+--    exec dbo.AutoMLTrain @input_query='
+--    SELECT top 100000 
+--          CAST([pickup_datetime] AS NVARCHAR(30)) AS pickup_datetime
+--          ,CAST([dropoff_datetime] AS NVARCHAR(30)) AS dropoff_datetime
+--          ,[passenger_count]
+--          ,[trip_time_in_secs]
+--          ,[trip_distance]
+--          ,[payment_type]
+--          ,[tip_class]
+--      FROM [dbo].[nyctaxi_sample] order by [hack_license] ',
+--      @label_column = 'tip_class',
+--      @iterations=10
+-- 
+-- An example call for forecasting is:
+--      insert into dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)
+--      exec dbo.AutoMLTrain @input_query='
+--      select cast(timeStamp as nvarchar(30)) as timeStamp,
+--             demand,
+--      	   precip,
+--      	   temp,
+--             case when timeStamp < ''2017-01-01'' then 0 else 1 end as is_validate_column
+--      from nyc_energy
+--      where demand is not null and precip is not null and temp is not null
+--      and timeStamp < ''2017-02-01''',
+--      @label_column='demand',
+--      @task='forecasting',
+--      @iterations=10,
+--      @iteration_timeout_minutes=5,
+--      @time_column_name='timeStamp',
+--      @is_validate_column='is_validate_column',
+--      @experiment_name='automl-sql-forecast',
+--      @primary_metric='normalized_root_mean_squared_error'
+
+SET ANSI_NULLS ON
+GO
+SET QUOTED_IDENTIFIER ON
+GO
+CREATE OR ALTER PROCEDURE [dbo].[AutoMLTrain]
+ (
+    @input_query NVARCHAR(MAX),                      -- The SQL Query that will return the data to train and validate the model.
+    @label_column NVARCHAR(255)='Label',             -- The name of the column in the result of @input_query that is the label.
+    @primary_metric NVARCHAR(40)='AUC_weighted',     -- The metric to optimize.
+    @iterations INT=100,                             -- The maximum number of pipelines to train.
+    @task NVARCHAR(40)='classification',             -- The type of task.  Can be classification, regression or forecasting.
+    @experiment_name NVARCHAR(32)='automl-sql-test', -- This can be used to find the experiment in the Azure Portal.
+    @iteration_timeout_minutes INT = 15,             -- The maximum time in minutes for training a single pipeline. 
+    @experiment_timeout_minutes INT = 60,            -- The maximum time in minutes for training all pipelines.
+    @n_cross_validations INT = 3,                    -- The number of cross validations.
+    @blacklist_models NVARCHAR(MAX) = '',            -- A comma separated list of algos that will not be used.
+                                                     -- The list of possible models can be found at:
+                                                     -- https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#configure-your-experiment-settings
+    @whitelist_models NVARCHAR(MAX) = '',            -- A comma separated list of algos that can be used.
+                                                     -- The list of possible models can be found at:
+                                                     -- https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#configure-your-experiment-settings
+    @experiment_exit_score FLOAT = 0,                -- Stop the experiment if this score is acheived.
+    @sample_weight_column NVARCHAR(255)='',          -- The name of the column in the result of  @input_query that gives a sample weight.
+    @is_validate_column NVARCHAR(255)='',            -- The name of the column in the result of  @input_query that indicates if the row is for training or validation.
+	                                                 -- In the values of the column, 0 means for training and 1 means for validation.
+    @time_column_name  NVARCHAR(255)='',             -- The name of the timestamp column for forecasting.
+    @connection_name NVARCHAR(255)='default',        -- The AML connection to use.
+    @max_horizon INT = 0                             -- 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.
+                                                     -- For example, if data is recorded daily and max_horizon is 5, we will predict 5 days ahead.
+ ) AS
+BEGIN
+
+    DECLARE @tenantid NVARCHAR(255)
+    DECLARE @appid NVARCHAR(255)
+    DECLARE @password NVARCHAR(255)
+    DECLARE @config_file NVARCHAR(255)
+
+	SELECT @tenantid=TenantId, @appid=AppId, @password=Password, @config_file=ConfigFile
+	FROM aml_connection
+	WHERE ConnectionName = @connection_name;
+
+	EXEC sp_execute_external_script @language = N'Python', @script = N'import pandas as pd
+import logging 
+import azureml.core 
+import pandas as pd
+import numpy as np
+from azureml.core.experiment import Experiment 
+from azureml.train.automl import AutoMLConfig 
+from sklearn import datasets 
+import pickle
+import codecs
+from azureml.core.authentication import ServicePrincipalAuthentication 
+from azureml.core.workspace import Workspace 
+
+if __name__.startswith("sqlindb"):
+    auth = ServicePrincipalAuthentication(tenantid, appid, password) 
+ 
+    ws = Workspace.from_config(path=config_file, auth=auth) 
+ 
+    project_folder = "./sample_projects/" + experiment_name
+ 
+    experiment = Experiment(ws, experiment_name) 
+
+    data_train = input_data
+    X_valid = None
+    y_valid = None
+    sample_weight_valid = None
+
+    if is_validate_column != "" and is_validate_column is not None:
+        data_train = input_data[input_data[is_validate_column] <= 0]
+        data_valid = input_data[input_data[is_validate_column] > 0]
+        data_train.pop(is_validate_column)
+        data_valid.pop(is_validate_column)
+        y_valid = data_valid.pop(label_column).values
+        if sample_weight_column != "" and sample_weight_column is not None:
+            sample_weight_valid = data_valid.pop(sample_weight_column).values
+        X_valid = data_valid
+        n_cross_validations = None
+
+    y_train = data_train.pop(label_column).values
+
+    sample_weight = None
+    if sample_weight_column != "" and sample_weight_column is not None:
+        sample_weight = data_train.pop(sample_weight_column).values
+
+    X_train = data_train
+
+    if experiment_timeout_minutes == 0:
+        experiment_timeout_minutes = None
+
+    if experiment_exit_score == 0:
+        experiment_exit_score = None
+
+    if blacklist_models == "":
+        blacklist_models = None
+
+    if blacklist_models is not None:
+        blacklist_models = blacklist_models.replace(" ", "").split(",")
+
+    if whitelist_models == "":
+        whitelist_models = None
+
+    if whitelist_models is not None:
+        whitelist_models = whitelist_models.replace(" ", "").split(",")
+
+    automl_settings = {}
+    preprocess = True
+    if time_column_name != "" and time_column_name is not None:
+        automl_settings = { "time_column_name": time_column_name }
+        preprocess = False
+        if max_horizon > 0:
+            automl_settings["max_horizon"] = max_horizon
+
+    log_file_name = "automl_sqlindb_errors.log"
+	 
+    automl_config = AutoMLConfig(task = task, 
+                                 debug_log = log_file_name, 
+                                 primary_metric = primary_metric, 
+                                 iteration_timeout_minutes = iteration_timeout_minutes, 
+                                 experiment_timeout_minutes = experiment_timeout_minutes,
+                                 iterations = iterations, 
+                                 n_cross_validations = n_cross_validations, 
+                                 preprocess = preprocess,
+                                 verbosity = logging.INFO, 
+                                 X = X_train,  
+                                 y = y_train, 
+                                 path = project_folder,
+                                 blacklist_models = blacklist_models,
+                                 whitelist_models = whitelist_models,
+                                 experiment_exit_score = experiment_exit_score,
+                                 sample_weight = sample_weight,
+                                 X_valid = X_valid,
+                                 y_valid = y_valid,
+                                 sample_weight_valid = sample_weight_valid,
+                                 **automl_settings) 
+ 
+    local_run = experiment.submit(automl_config, show_output = True) 
+
+    best_run, fitted_model = local_run.get_output()
+
+    pickled_model = codecs.encode(pickle.dumps(fitted_model), "base64").decode()
+
+    log_file_text = ""
+
+    try:
+        with open(log_file_name, "r") as log_file:
+            log_file_text = log_file.read()
+    except:
+        log_file_text = "Log file not found"
+
+    returned_model = pd.DataFrame({"best_run": [best_run.id], "experiment_name": [experiment_name], "fitted_model": [pickled_model], "log_file_text": [log_file_text], "workspace": [ws.name]}, dtype=np.dtype(np.str))
+'
+	, @input_data_1 = @input_query
+	, @input_data_1_name = N'input_data'
+	, @output_data_1_name = N'returned_model'
+	, @params = N'@label_column NVARCHAR(255), 
+	              @primary_metric NVARCHAR(40),
+				  @iterations INT, @task NVARCHAR(40),
+				  @experiment_name NVARCHAR(32),
+				  @iteration_timeout_minutes INT,
+				  @experiment_timeout_minutes INT,
+				  @n_cross_validations INT,
+				  @blacklist_models NVARCHAR(MAX),
+				  @whitelist_models NVARCHAR(MAX),
+				  @experiment_exit_score FLOAT,
+				  @sample_weight_column NVARCHAR(255),
+				  @is_validate_column NVARCHAR(255),
+				  @time_column_name  NVARCHAR(255),
+				  @tenantid NVARCHAR(255),
+				  @appid NVARCHAR(255),
+				  @password NVARCHAR(255),
+				  @config_file NVARCHAR(255),
+				  @max_horizon INT'
+	, @label_column = @label_column
+	, @primary_metric = @primary_metric
+	, @iterations = @iterations
+	, @task = @task
+	, @experiment_name = @experiment_name
+	, @iteration_timeout_minutes = @iteration_timeout_minutes
+	, @experiment_timeout_minutes = @experiment_timeout_minutes
+	, @n_cross_validations = @n_cross_validations
+	, @blacklist_models = @blacklist_models
+	, @whitelist_models = @whitelist_models
+	, @experiment_exit_score = @experiment_exit_score
+	, @sample_weight_column = @sample_weight_column
+	, @is_validate_column = @is_validate_column
+	, @time_column_name = @time_column_name
+	, @tenantid = @tenantid
+	, @appid = @appid
+	, @password = @password
+	, @config_file = @config_file
+	, @max_horizon = @max_horizon
+WITH RESULT SETS ((best_run NVARCHAR(250), experiment_name NVARCHAR(100), fitted_model VARCHAR(MAX), log_file_text NVARCHAR(MAX), workspace NVARCHAR(100)))
+END

how-to-use-azureml/automated-machine-learning/sql-server/setup/aml_connection.sql

@@ -0,0 +1,18 @@
+-- This is a table to store the Azure ML connection information.
+SET ANSI_NULLS ON
+GO
+
+SET QUOTED_IDENTIFIER ON
+GO
+
+CREATE TABLE [dbo].[aml_connection](
+    [Id] [int] IDENTITY(1,1) NOT NULL PRIMARY KEY,
+	[ConnectionName] [nvarchar](255) NULL,
+	[TenantId] [nvarchar](255) NULL,
+	[AppId] [nvarchar](255) NULL,
+	[Password] [nvarchar](255) NULL,
+	[ConfigFile] [nvarchar](255) NULL
+) ON [PRIMARY]
+GO
+
+

how-to-use-azureml/automated-machine-learning/sql-server/setup/aml_model.sql

@@ -0,0 +1,22 @@
+-- This is a table to hold the results from the AutoMLTrain procedure.
+SET ANSI_NULLS ON
+GO
+
+SET QUOTED_IDENTIFIER ON
+GO
+
+CREATE TABLE [dbo].[aml_model](
+    [Id] [int] IDENTITY(1,1) NOT NULL PRIMARY KEY,
+    [Model] [varchar](max) NOT NULL,        -- The model, which can be passed to AutoMLPredict for testing or prediction.
+    [RunId] [nvarchar](250) NULL,           -- The RunId, which can be used to view the model in the Azure Portal.
+    [CreatedDate] [datetime] NULL,
+    [ExperimentName] [nvarchar](100) NULL,  -- Azure ML Experiment Name
+    [WorkspaceName] [nvarchar](100) NULL,   -- Azure ML Workspace Name
+	[LogFileText] [nvarchar](max) NULL
+) 
+GO
+
+ALTER TABLE [dbo].[aml_model] ADD  DEFAULT (getutcdate()) FOR [CreatedDate]
+GO
+
+

how-to-use-azureml/automated-machine-learning/sql-server/setup/auto-ml-sql-setup.ipynb

@@ -0,0 +1,561 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Set up Azure ML Automated Machine Learning on SQL Server 2019 CTP 2.4 big data cluster\r\n",
+        "\r\n",
+        "\\# Prerequisites:  \r\n",
+        "\\# - An Azure subscription and resource group  \r\n",
+        "\\# - An Azure Machine Learning workspace  \r\n",
+        "\\# - A SQL Server 2019 CTP 2.4 big data cluster with Internet access and a database named 'automl'  \r\n",
+        "\\# - Azure CLI  \r\n",
+        "\\# - kubectl command  \r\n",
+        "\\# - The https://github.com/Azure/MachineLearningNotebooks repository downloaded (cloned) to your local machine\r\n",
+        "\r\n",
+        "\\# In the 'automl' database, create a table named 'dbo.nyc_energy' as follows:  \r\n",
+        "\\# - In SQL Server Management Studio, right-click the 'automl' database, select Tasks, then Import Flat File.  \r\n",
+        "\\# - Select the file AzureMlCli\\notebooks\\how-to-use-azureml\\automated-machine-learning\\forecasting-energy-demand\\nyc_energy.csv.  \r\n",
+        "\\# - Using the \"Modify Columns\" page, allow nulls for all columns. \r\n",
+        "\r\n",
+        "\\# Create an Azure Machine Learning Workspace using the instructions at https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-workspace \r\n",
+        "\r\n",
+        "\\# Create an Azure service principal.  You can do this with the following commands: \r\n",
+        "\r\n",
+        "az login  \r\n",
+        "az account set --subscription *subscriptionid*  \r\n",
+        "\r\n",
+        "\\# The following command prints out the **appId** and **tenant**,  \r\n",
+        "\\# which you insert into the indicated cell later in this notebook  \r\n",
+        "\\# to allow AutoML to authenticate with Azure:  \r\n",
+        "\r\n",
+        "az ad sp create-for-rbac --name *principlename* --password *password*\r\n",
+        "\r\n",
+        "\\# Log into the master instance of SQL Server 2019 CTP 2.4:  \r\n",
+        "kubectl exec -it mssql-master-pool-0 -n *clustername* -c mssql-server -- /bin/bash\r\n",
+        "\r\n",
+        "mkdir /tmp/aml\r\n",
+        "\r\n",
+        "cd /tmp/aml\r\n",
+        "\r\n",
+        "\\# **Modify** the following with your subscription_id, resource_group, and workspace_name:  \r\n",
+        "cat > config.json << EOF  \r\n",
+        "{  \r\n",
+        "    \"subscription_id\": \"123456ab-78cd-0123-45ef-abcd12345678\",  \r\n",
+        "    \"resource_group\": \"myrg1\",  \r\n",
+        "    \"workspace_name\": \"myws1\"  \r\n",
+        "}  \r\n",
+        "EOF\r\n",
+        "\r\n",
+        "\\# The directory referenced below is appropriate for the master instance of SQL Server 2019 CTP 2.4.\r\n",
+        "\r\n",
+        "cd /opt/mssql/mlservices/runtime/python/bin\r\n",
+        "\r\n",
+        "./python -m pip install azureml-sdk[automl]\r\n",
+        "\r\n",
+        "./python -m pip install --upgrade numpy \r\n",
+        "\r\n",
+        "./python -m pip install --upgrade sklearn\r\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/sql-server/setup/auto-ml-sql-setup.png)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "-- Enable external scripts to allow invoking Python\r\n",
+        "sp_configure 'external scripts enabled',1 \r\n",
+        "reconfigure with override \r\n",
+        "GO\r\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "-- Use database 'automl'\r\n",
+        "USE [automl]\r\n",
+        "GO"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "-- This is a table to hold the Azure ML connection information.\r\n",
+        "SET ANSI_NULLS ON\r\n",
+        "GO\r\n",
+        "\r\n",
+        "SET QUOTED_IDENTIFIER ON\r\n",
+        "GO\r\n",
+        "\r\n",
+        "CREATE TABLE [dbo].[aml_connection](\r\n",
+        "    [Id] [int] IDENTITY(1,1) NOT NULL PRIMARY KEY,\r\n",
+        "\t[ConnectionName] [nvarchar](255) NULL,\r\n",
+        "\t[TenantId] [nvarchar](255) NULL,\r\n",
+        "\t[AppId] [nvarchar](255) NULL,\r\n",
+        "\t[Password] [nvarchar](255) NULL,\r\n",
+        "\t[ConfigFile] [nvarchar](255) NULL\r\n",
+        ") ON [PRIMARY]\r\n",
+        "GO"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Copy the values from create-for-rbac above into the cell below"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "-- Use the following values:\r\n",
+        "-- Leave the name as 'Default'\r\n",
+        "-- Insert <tenant> returned by create-for-rbac above\r\n",
+        "-- Insert <AppId> returned by create-for-rbac above\r\n",
+        "-- Insert <password> used in create-for-rbac above\r\n",
+        "-- Leave <path> as '/tmp/aml/config.json'\r\n",
+        "INSERT INTO [dbo].[aml_connection]  \r\n",
+        "VALUES (\r\n",
+        "    N'Default', -- Name\r\n",
+        "    N'11111111-2222-3333-4444-555555555555', -- Tenant\r\n",
+        "    N'aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee', -- AppId\r\n",
+        "    N'insertpasswordhere', -- Password\r\n",
+        "    N'/tmp/aml/config.json' -- Path\r\n",
+        "    );\r\n",
+        "GO"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "-- This is a table to hold the results from the AutoMLTrain procedure.\r\n",
+        "SET ANSI_NULLS ON\r\n",
+        "GO\r\n",
+        "\r\n",
+        "SET QUOTED_IDENTIFIER ON\r\n",
+        "GO\r\n",
+        "\r\n",
+        "CREATE TABLE [dbo].[aml_model](\r\n",
+        "    [Id] [int] IDENTITY(1,1) NOT NULL PRIMARY KEY,\r\n",
+        "    [Model] [varchar](max) NOT NULL,        -- The model, which can be passed to AutoMLPredict for testing or prediction.\r\n",
+        "    [RunId] [nvarchar](250) NULL,           -- The RunId, which can be used to view the model in the Azure Portal.\r\n",
+        "    [CreatedDate] [datetime] NULL,\r\n",
+        "    [ExperimentName] [nvarchar](100) NULL,  -- Azure ML Experiment Name\r\n",
+        "    [WorkspaceName] [nvarchar](100) NULL,   -- Azure ML Workspace Name\r\n",
+        "\t[LogFileText] [nvarchar](max) NULL\r\n",
+        ") \r\n",
+        "GO\r\n",
+        "\r\n",
+        "ALTER TABLE [dbo].[aml_model] ADD  DEFAULT (getutcdate()) FOR [CreatedDate]\r\n",
+        "GO\r\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "-- This stored procedure uses automated machine learning to train several models\r\n",
+        "-- and return the best model.\r\n",
+        "--\r\n",
+        "-- The result set has several columns:\r\n",
+        "--   best_run - ID of the best model found\r\n",
+        "--   experiment_name - training run name\r\n",
+        "--   fitted_model - best model found\r\n",
+        "--   log_file_text - console output\r\n",
+        "--   workspace - name of the Azure ML workspace where run history is stored\r\n",
+        "--\r\n",
+        "-- An example call for a classification problem is:\r\n",
+        "--    insert into dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)\r\n",
+        "--    exec dbo.AutoMLTrain @input_query='\r\n",
+        "--    SELECT top 100000 \r\n",
+        "--          CAST([pickup_datetime] AS NVARCHAR(30)) AS pickup_datetime\r\n",
+        "--          ,CAST([dropoff_datetime] AS NVARCHAR(30)) AS dropoff_datetime\r\n",
+        "--          ,[passenger_count]\r\n",
+        "--          ,[trip_time_in_secs]\r\n",
+        "--          ,[trip_distance]\r\n",
+        "--          ,[payment_type]\r\n",
+        "--          ,[tip_class]\r\n",
+        "--      FROM [dbo].[nyctaxi_sample] order by [hack_license] ',\r\n",
+        "--      @label_column = 'tip_class',\r\n",
+        "--      @iterations=10\r\n",
+        "-- \r\n",
+        "-- An example call for forecasting is:\r\n",
+        "--      insert into dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)\r\n",
+        "--      exec dbo.AutoMLTrain @input_query='\r\n",
+        "--      select cast(timeStamp as nvarchar(30)) as timeStamp,\r\n",
+        "--             demand,\r\n",
+        "--      \t   precip,\r\n",
+        "--      \t   temp,\r\n",
+        "--             case when timeStamp < ''2017-01-01'' then 0 else 1 end as is_validate_column\r\n",
+        "--      from nyc_energy\r\n",
+        "--      where demand is not null and precip is not null and temp is not null\r\n",
+        "--      and timeStamp < ''2017-02-01''',\r\n",
+        "--      @label_column='demand',\r\n",
+        "--      @task='forecasting',\r\n",
+        "--      @iterations=10,\r\n",
+        "--      @iteration_timeout_minutes=5,\r\n",
+        "--      @time_column_name='timeStamp',\r\n",
+        "--      @is_validate_column='is_validate_column',\r\n",
+        "--      @experiment_name='automl-sql-forecast',\r\n",
+        "--      @primary_metric='normalized_root_mean_squared_error'\r\n",
+        "\r\n",
+        "SET ANSI_NULLS ON\r\n",
+        "GO\r\n",
+        "SET QUOTED_IDENTIFIER ON\r\n",
+        "GO\r\n",
+        "CREATE OR ALTER PROCEDURE [dbo].[AutoMLTrain]\r\n",
+        " (\r\n",
+        "    @input_query NVARCHAR(MAX),                      -- The SQL Query that will return the data to train and validate the model.\r\n",
+        "    @label_column NVARCHAR(255)='Label',             -- The name of the column in the result of @input_query that is the label.\r\n",
+        "    @primary_metric NVARCHAR(40)='AUC_weighted',     -- The metric to optimize.\r\n",
+        "    @iterations INT=100,                             -- The maximum number of pipelines to train.\r\n",
+        "    @task NVARCHAR(40)='classification',             -- The type of task.  Can be classification, regression or forecasting.\r\n",
+        "    @experiment_name NVARCHAR(32)='automl-sql-test', -- This can be used to find the experiment in the Azure Portal.\r\n",
+        "    @iteration_timeout_minutes INT = 15,             -- The maximum time in minutes for training a single pipeline. \r\n",
+        "    @experiment_timeout_minutes INT = 60,            -- The maximum time in minutes for training all pipelines.\r\n",
+        "    @n_cross_validations INT = 3,                    -- The number of cross validations.\r\n",
+        "    @blacklist_models NVARCHAR(MAX) = '',            -- A comma separated list of algos that will not be used.\r\n",
+        "                                                     -- The list of possible models can be found at:\r\n",
+        "                                                     -- https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#configure-your-experiment-settings\r\n",
+        "    @whitelist_models NVARCHAR(MAX) = '',            -- A comma separated list of algos that can be used.\r\n",
+        "                                                     -- The list of possible models can be found at:\r\n",
+        "                                                     -- https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#configure-your-experiment-settings\r\n",
+        "    @experiment_exit_score FLOAT = 0,                -- Stop the experiment if this score is acheived.\r\n",
+        "    @sample_weight_column NVARCHAR(255)='',          -- The name of the column in the result of  @input_query that gives a sample weight.\r\n",
+        "    @is_validate_column NVARCHAR(255)='',            -- The name of the column in the result of  @input_query that indicates if the row is for training or validation.\r\n",
+        "\t                                                 -- In the values of the column, 0 means for training and 1 means for validation.\r\n",
+        "    @time_column_name  NVARCHAR(255)='',             -- The name of the timestamp column for forecasting.\r\n",
+        "\t@connection_name NVARCHAR(255)='default'         -- The AML connection to use.\r\n",
+        " ) AS\r\n",
+        "BEGIN\r\n",
+        "\r\n",
+        "    DECLARE @tenantid NVARCHAR(255)\r\n",
+        "    DECLARE @appid NVARCHAR(255)\r\n",
+        "    DECLARE @password NVARCHAR(255)\r\n",
+        "    DECLARE @config_file NVARCHAR(255)\r\n",
+        "\r\n",
+        "\tSELECT @tenantid=TenantId, @appid=AppId, @password=Password, @config_file=ConfigFile\r\n",
+        "\tFROM aml_connection\r\n",
+        "\tWHERE ConnectionName = @connection_name;\r\n",
+        "\r\n",
+        "\tEXEC sp_execute_external_script @language = N'Python', @script = N'import pandas as pd\r\n",
+        "import logging \r\n",
+        "import azureml.core \r\n",
+        "import pandas as pd\r\n",
+        "import numpy as np\r\n",
+        "from azureml.core.experiment import Experiment \r\n",
+        "from azureml.train.automl import AutoMLConfig \r\n",
+        "from sklearn import datasets \r\n",
+        "import pickle\r\n",
+        "import codecs\r\n",
+        "from azureml.core.authentication import ServicePrincipalAuthentication \r\n",
+        "from azureml.core.workspace import Workspace \r\n",
+        "\r\n",
+        "if __name__.startswith(\"sqlindb\"):\r\n",
+        "    auth = ServicePrincipalAuthentication(tenantid, appid, password) \r\n",
+        " \r\n",
+        "    ws = Workspace.from_config(path=config_file, auth=auth) \r\n",
+        " \r\n",
+        "    project_folder = \"./sample_projects/\" + experiment_name\r\n",
+        " \r\n",
+        "    experiment = Experiment(ws, experiment_name) \r\n",
+        "\r\n",
+        "    data_train = input_data\r\n",
+        "    X_valid = None\r\n",
+        "    y_valid = None\r\n",
+        "    sample_weight_valid = None\r\n",
+        "\r\n",
+        "    if is_validate_column != \"\" and is_validate_column is not None:\r\n",
+        "        data_train = input_data[input_data[is_validate_column] <= 0]\r\n",
+        "        data_valid = input_data[input_data[is_validate_column] > 0]\r\n",
+        "        data_train.pop(is_validate_column)\r\n",
+        "        data_valid.pop(is_validate_column)\r\n",
+        "        y_valid = data_valid.pop(label_column).values\r\n",
+        "        if sample_weight_column != \"\" and sample_weight_column is not None:\r\n",
+        "            sample_weight_valid = data_valid.pop(sample_weight_column).values\r\n",
+        "        X_valid = data_valid\r\n",
+        "        n_cross_validations = None\r\n",
+        "\r\n",
+        "    y_train = data_train.pop(label_column).values\r\n",
+        "\r\n",
+        "    sample_weight = None\r\n",
+        "    if sample_weight_column != \"\" and sample_weight_column is not None:\r\n",
+        "        sample_weight = data_train.pop(sample_weight_column).values\r\n",
+        "\r\n",
+        "    X_train = data_train\r\n",
+        "\r\n",
+        "    if experiment_timeout_minutes == 0:\r\n",
+        "        experiment_timeout_minutes = None\r\n",
+        "\r\n",
+        "    if experiment_exit_score == 0:\r\n",
+        "        experiment_exit_score = None\r\n",
+        "\r\n",
+        "    if blacklist_models == \"\":\r\n",
+        "        blacklist_models = None\r\n",
+        "\r\n",
+        "    if blacklist_models is not None:\r\n",
+        "        blacklist_models = blacklist_models.replace(\" \", \"\").split(\",\")\r\n",
+        "\r\n",
+        "    if whitelist_models == \"\":\r\n",
+        "        whitelist_models = None\r\n",
+        "\r\n",
+        "    if whitelist_models is not None:\r\n",
+        "        whitelist_models = whitelist_models.replace(\" \", \"\").split(\",\")\r\n",
+        "\r\n",
+        "    automl_settings = {}\r\n",
+        "    preprocess = True\r\n",
+        "    if time_column_name != \"\" and time_column_name is not None:\r\n",
+        "        automl_settings = { \"time_column_name\": time_column_name }\r\n",
+        "        preprocess = False\r\n",
+        "\r\n",
+        "    log_file_name = \"automl_errors.log\"\r\n",
+        "\t \r\n",
+        "    automl_config = AutoMLConfig(task = task, \r\n",
+        "                                 debug_log = log_file_name, \r\n",
+        "                                 primary_metric = primary_metric, \r\n",
+        "                                 iteration_timeout_minutes = iteration_timeout_minutes, \r\n",
+        "                                 experiment_timeout_minutes = experiment_timeout_minutes,\r\n",
+        "                                 iterations = iterations, \r\n",
+        "                                 n_cross_validations = n_cross_validations, \r\n",
+        "                                 preprocess = preprocess,\r\n",
+        "                                 verbosity = logging.INFO, \r\n",
+        "                                 X = X_train,  \r\n",
+        "                                 y = y_train, \r\n",
+        "                                 path = project_folder,\r\n",
+        "                                 blacklist_models = blacklist_models,\r\n",
+        "                                 whitelist_models = whitelist_models,\r\n",
+        "                                 experiment_exit_score = experiment_exit_score,\r\n",
+        "                                 sample_weight = sample_weight,\r\n",
+        "                                 X_valid = X_valid,\r\n",
+        "                                 y_valid = y_valid,\r\n",
+        "                                 sample_weight_valid = sample_weight_valid,\r\n",
+        "                                 **automl_settings) \r\n",
+        " \r\n",
+        "    local_run = experiment.submit(automl_config, show_output = True) \r\n",
+        "\r\n",
+        "    best_run, fitted_model = local_run.get_output()\r\n",
+        "\r\n",
+        "    pickled_model = codecs.encode(pickle.dumps(fitted_model), \"base64\").decode()\r\n",
+        "\r\n",
+        "    log_file_text = \"\"\r\n",
+        "\r\n",
+        "    try:\r\n",
+        "        with open(log_file_name, \"r\") as log_file:\r\n",
+        "            log_file_text = log_file.read()\r\n",
+        "    except:\r\n",
+        "        log_file_text = \"Log file not found\"\r\n",
+        "\r\n",
+        "    returned_model = pd.DataFrame({\"best_run\": [best_run.id], \"experiment_name\": [experiment_name], \"fitted_model\": [pickled_model], \"log_file_text\": [log_file_text], \"workspace\": [ws.name]}, dtype=np.dtype(np.str))\r\n",
+        "'\r\n",
+        "\t, @input_data_1 = @input_query\r\n",
+        "\t, @input_data_1_name = N'input_data'\r\n",
+        "\t, @output_data_1_name = N'returned_model'\r\n",
+        "\t, @params = N'@label_column NVARCHAR(255), \r\n",
+        "\t              @primary_metric NVARCHAR(40),\r\n",
+        "\t\t\t\t  @iterations INT, @task NVARCHAR(40),\r\n",
+        "\t\t\t\t  @experiment_name NVARCHAR(32),\r\n",
+        "\t\t\t\t  @iteration_timeout_minutes INT,\r\n",
+        "\t\t\t\t  @experiment_timeout_minutes INT,\r\n",
+        "\t\t\t\t  @n_cross_validations INT,\r\n",
+        "\t\t\t\t  @blacklist_models NVARCHAR(MAX),\r\n",
+        "\t\t\t\t  @whitelist_models NVARCHAR(MAX),\r\n",
+        "\t\t\t\t  @experiment_exit_score FLOAT,\r\n",
+        "\t\t\t\t  @sample_weight_column NVARCHAR(255),\r\n",
+        "\t\t\t\t  @is_validate_column NVARCHAR(255),\r\n",
+        "\t\t\t\t  @time_column_name  NVARCHAR(255),\r\n",
+        "\t\t\t\t  @tenantid NVARCHAR(255),\r\n",
+        "\t\t\t\t  @appid NVARCHAR(255),\r\n",
+        "\t\t\t\t  @password NVARCHAR(255),\r\n",
+        "\t\t\t\t  @config_file NVARCHAR(255)'\r\n",
+        "\t, @label_column = @label_column\r\n",
+        "\t, @primary_metric = @primary_metric\r\n",
+        "\t, @iterations = @iterations\r\n",
+        "\t, @task = @task\r\n",
+        "\t, @experiment_name = @experiment_name\r\n",
+        "\t, @iteration_timeout_minutes = @iteration_timeout_minutes\r\n",
+        "\t, @experiment_timeout_minutes = @experiment_timeout_minutes\r\n",
+        "\t, @n_cross_validations = @n_cross_validations\r\n",
+        "\t, @blacklist_models = @blacklist_models\r\n",
+        "\t, @whitelist_models = @whitelist_models\r\n",
+        "\t, @experiment_exit_score = @experiment_exit_score\r\n",
+        "\t, @sample_weight_column = @sample_weight_column\r\n",
+        "\t, @is_validate_column = @is_validate_column\r\n",
+        "\t, @time_column_name = @time_column_name\r\n",
+        "\t, @tenantid = @tenantid\r\n",
+        "\t, @appid = @appid\r\n",
+        "\t, @password = @password\r\n",
+        "\t, @config_file = @config_file\r\n",
+        "WITH RESULT SETS ((best_run NVARCHAR(250), experiment_name NVARCHAR(100), fitted_model VARCHAR(MAX), log_file_text NVARCHAR(MAX), workspace NVARCHAR(100)))\r\n",
+        "END"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "-- This procedure returns a list of metrics for each iteration of a training run.\r\n",
+        "SET ANSI_NULLS ON\r\n",
+        "GO\r\n",
+        "SET QUOTED_IDENTIFIER ON\r\n",
+        "GO\r\n",
+        "CREATE OR ALTER PROCEDURE [dbo].[AutoMLGetMetrics]\r\n",
+        " (\r\n",
+        "\t@run_id NVARCHAR(250),                           -- The RunId\r\n",
+        "    @experiment_name NVARCHAR(32)='automl-sql-test', -- This can be used to find the experiment in the Azure Portal.\r\n",
+        "    @connection_name NVARCHAR(255)='default'         -- The AML connection to use.\r\n",
+        " ) AS\r\n",
+        "BEGIN\r\n",
+        "    DECLARE @tenantid NVARCHAR(255)\r\n",
+        "    DECLARE @appid NVARCHAR(255)\r\n",
+        "    DECLARE @password NVARCHAR(255)\r\n",
+        "    DECLARE @config_file NVARCHAR(255)\r\n",
+        "\r\n",
+        "\tSELECT @tenantid=TenantId, @appid=AppId, @password=Password, @config_file=ConfigFile\r\n",
+        "\tFROM aml_connection\r\n",
+        "\tWHERE ConnectionName = @connection_name;\r\n",
+        "\r\n",
+        "    EXEC sp_execute_external_script @language = N'Python', @script = N'import pandas as pd\r\n",
+        "import logging \r\n",
+        "import azureml.core \r\n",
+        "import numpy as np\r\n",
+        "from azureml.core.experiment import Experiment \r\n",
+        "from azureml.train.automl.run import AutoMLRun\r\n",
+        "from azureml.core.authentication import ServicePrincipalAuthentication \r\n",
+        "from azureml.core.workspace import Workspace \r\n",
+        "\r\n",
+        "auth = ServicePrincipalAuthentication(tenantid, appid, password) \r\n",
+        " \r\n",
+        "ws = Workspace.from_config(path=config_file, auth=auth) \r\n",
+        " \r\n",
+        "experiment = Experiment(ws, experiment_name) \r\n",
+        "\r\n",
+        "ml_run = AutoMLRun(experiment = experiment, run_id = run_id)\r\n",
+        "\r\n",
+        "children = list(ml_run.get_children())\r\n",
+        "iterationlist = []\r\n",
+        "metricnamelist = []\r\n",
+        "metricvaluelist = []\r\n",
+        "\r\n",
+        "for run in children:\r\n",
+        "    properties = run.get_properties()\r\n",
+        "    if \"iteration\" in properties:\r\n",
+        "        iteration = int(properties[\"iteration\"])\r\n",
+        "        for metric_name, metric_value in run.get_metrics().items():\r\n",
+        "            if isinstance(metric_value, float):\r\n",
+        "                iterationlist.append(iteration)\r\n",
+        "                metricnamelist.append(metric_name)\r\n",
+        "                metricvaluelist.append(metric_value)\r\n",
+        "             \r\n",
+        "metrics = pd.DataFrame({\"iteration\": iterationlist, \"metric_name\": metricnamelist, \"metric_value\": metricvaluelist})\r\n",
+        "'\r\n",
+        "    , @output_data_1_name = N'metrics'\r\n",
+        "\t, @params = N'@run_id NVARCHAR(250), \r\n",
+        "\t\t\t\t  @experiment_name NVARCHAR(32),\r\n",
+        "  \t\t\t\t  @tenantid NVARCHAR(255),\r\n",
+        "\t\t\t\t  @appid NVARCHAR(255),\r\n",
+        "\t\t\t\t  @password NVARCHAR(255),\r\n",
+        "\t\t\t\t  @config_file NVARCHAR(255)'\r\n",
+        "    , @run_id = @run_id\r\n",
+        "\t, @experiment_name = @experiment_name\r\n",
+        "\t, @tenantid = @tenantid\r\n",
+        "\t, @appid = @appid\r\n",
+        "\t, @password = @password\r\n",
+        "\t, @config_file = @config_file\r\n",
+        "WITH RESULT SETS ((iteration INT, metric_name NVARCHAR(100), metric_value FLOAT))\r\n",
+        "END"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "-- This procedure predicts values based on a model returned by AutoMLTrain and a dataset.\r\n",
+        "-- It returns the dataset with a new column added, which is the predicted value.\r\n",
+        "SET ANSI_NULLS ON\r\n",
+        "GO\r\n",
+        "SET QUOTED_IDENTIFIER ON\r\n",
+        "GO\r\n",
+        "CREATE OR ALTER PROCEDURE [dbo].[AutoMLPredict]\r\n",
+        " (\r\n",
+        "   @input_query NVARCHAR(MAX),      -- A SQL query returning data to predict on.\r\n",
+        "   @model NVARCHAR(MAX),            -- A model returned from AutoMLTrain.\r\n",
+        "   @label_column  NVARCHAR(255)=''  -- Optional name of the column from input_query, which should be ignored when predicting\r\n",
+        " ) AS \r\n",
+        "BEGIN \r\n",
+        "  \r\n",
+        "    EXEC sp_execute_external_script @language = N'Python', @script = N'import pandas as pd \r\n",
+        "import azureml.core  \r\n",
+        "import numpy as np \r\n",
+        "from azureml.train.automl import AutoMLConfig  \r\n",
+        "import pickle \r\n",
+        "import codecs \r\n",
+        "  \r\n",
+        "model_obj = pickle.loads(codecs.decode(model.encode(), \"base64\")) \r\n",
+        "  \r\n",
+        "test_data = input_data.copy() \r\n",
+        "\r\n",
+        "if label_column != \"\" and label_column is not None:\r\n",
+        "    y_test = test_data.pop(label_column).values \r\n",
+        "X_test = test_data \r\n",
+        "  \r\n",
+        "predicted = model_obj.predict(X_test) \r\n",
+        "  \r\n",
+        "combined_output = input_data.assign(predicted=predicted)\r\n",
+        "  \r\n",
+        "' \r\n",
+        "    , @input_data_1 = @input_query \r\n",
+        "    , @input_data_1_name = N'input_data' \r\n",
+        "    , @output_data_1_name = N'combined_output' \r\n",
+        "    , @params = N'@model NVARCHAR(MAX), @label_column  NVARCHAR(255)' \r\n",
+        "    , @model = @model \r\n",
+        "\t, @label_column = @label_column\r\n",
+        "END"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "jeffshep"
+      }
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "sql",
+      "name": "python36"
+    },
+    "language_info": {
+      "name": "sql",
+      "version": ""
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/subsampling/auto-ml-subsampling-local.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/subsampling/auto-ml-subsampling-local.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

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

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

how-to-use-azureml/azure-databricks/README.md

@@ -27,3 +27,7 @@ You can use Azure Databricks as a compute target from [Azure Machine Learning Pi
 For more on SDK concepts, please refer to [notebooks](https://github.com/Azure/MachineLearningNotebooks).
 
 **Please let us know your feedback.**
+
+ 
+
+![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/azure-databricks/README.png) 

how-to-use-azureml/azure-databricks/amlsdk/build-model-run-history-03.ipynb

@@ -11,6 +11,13 @@
         "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/azure-databricks/amlsdk/build-model-run-history-03.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -333,6 +340,13 @@
       "source": [
         "dbutils.notebook.exit(\"success\")"
       ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/azure-databricks/amlsdk/build-model-run-history-03.png)"
+      ]
     }
   ],
   "metadata": {

how-to-use-azureml/azure-databricks/amlsdk/deploy-to-aci-04.ipynb

@@ -11,6 +11,13 @@
         "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/azure-databricks/amlsdk/deploy-to-aci-04.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -277,6 +284,13 @@
         "#comment to not delete the web service\n",
         "myservice.delete()"
       ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/azure-databricks/amlsdk/deploy-to-aci-04.png)"
+      ]
     }
   ],
   "metadata": {

how-to-use-azureml/azure-databricks/amlsdk/deploy-to-aks-existingimage-05.ipynb

@@ -11,6 +11,13 @@
         "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/azure-databricks/amlsdk/deploy-to-aks-existingimage-05.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -203,6 +210,13 @@
         "#model.delete()\n",
         "aks_target.delete() "
       ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/azure-databricks/amlsdk/deploy-to-aks-existingimage-05.png)"
+      ]
     }
   ],
   "metadata": {

how-to-use-azureml/azure-databricks/amlsdk/ingest-data-02.ipynb

@@ -11,6 +11,13 @@
         "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/azure-databricks/amlsdk/ingest-data-02.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -139,6 +146,13 @@
       "metadata": {},
       "outputs": [],
       "source": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/azure-databricks/amlsdk/ingest-data-02.png)"
+      ]
     }
   ],
   "metadata": {

how-to-use-azureml/azure-databricks/amlsdk/installation-and-configuration-01.ipynb

@@ -11,6 +11,13 @@
         "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/azure-databricks/amlsdk/installation-and-configuration-01.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -143,6 +150,13 @@
         "      'Subscription id: ' + ws.subscription_id, \n",
         "      'Resource group: ' + ws.resource_group, sep = '\\n')"
       ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/azure-databricks/amlsdk/installation-and-configuration-01.png)"
+      ]
     }
   ],
   "metadata": {

how-to-use-azureml/azure-databricks/automl/automl-databricks-local-01.ipynb

@@ -314,25 +314,18 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Load Training Data Using DataPrep"
+        "## Load Training Data Using Dataset"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Automated ML takes a Dataflow as input.\n",
+        "Automated ML takes a `TabularDataset` as input.\n",
         "\n",
-        "If you are familiar with Pandas and have done your data preparation work in Pandas already, you can use the `read_pandas_dataframe` method in dprep to convert the DataFrame to a Dataflow.\n",
+        "You are free to use the data preparation libraries/tools of your choice to do the require preparation and once you are done, you can write it to a datastore and create a TabularDataset from it.\n",
-        "```python\n",
-        "df = pd.read_csv(...)\n",
-        "# apply some transforms\n",
-        "dprep.read_pandas_dataframe(df, temp_folder='/path/accessible/by/both/driver/and/worker')\n",
-        "```\n",
         "\n",
-        "If you just need to ingest data without doing any preparation, you can directly use AzureML Data Prep (Data Prep) to do so. The code below demonstrates this scenario. Data Prep also has data preparation capabilities, we have many [sample notebooks](https://github.com/Microsoft/AMLDataPrepDocs) demonstrating the capabilities.\n",
+        "You will get the datastore you registered previously and pass it to Dataset for reading. The data comes from the digits dataset: `sklearn.datasets.load_digits()`. `DataPath` points to a specific location within a datastore. "
-        "\n",
-        "You will get the datastore you registered previously and pass it to Data Prep for reading. The data comes from the digits dataset: `sklearn.datasets.load_digits()`. `DataPath` points to a specific location within a datastore. "
       ]
     },
     {
@@ -341,21 +334,21 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "import azureml.dataprep as dprep\n",
+        "from azureml.core.dataset import Dataset\n",
         "from azureml.data.datapath import DataPath\n",
         "\n",
         "datastore = Datastore.get(workspace = ws, datastore_name = datastore_name)\n",
         "\n",
-        "X_train = dprep.read_csv(datastore.path('X.csv'))\n",
+        "X_train = Dataset.Tabular.from_delimited_files(datastore.path('X.csv'))\n",
-        "y_train = dprep.read_csv(datastore.path('y.csv')).to_long(dprep.ColumnSelector(term='.*', use_regex = True))"
+        "y_train = Dataset.Tabular.from_delimited_files(datastore.path('y.csv'))"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Review the Data Preparation Result\n",
+        "## Review the TabularDataset\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 for all the steps in the TabularDataset, which makes it fast even against large datasets."
       ]
     },
     {
@@ -364,7 +357,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "X_train.get_profile()"
+        "X_train.take(5).to_pandas_dataframe()"
       ]
     },
     {
@@ -373,7 +366,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "y_train.get_profile()"
+        "y_train.take(5).to_pandas_dataframe()"
       ]
     },
     {
@@ -593,7 +586,10 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "fitted_model.named_steps['datatransformer'].get_featurization_summary()"
+        "# 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)"
       ]
     },
     {
@@ -660,6 +656,13 @@
       "metadata": {},
       "outputs": [],
       "source": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/azure-databricks/automl/automl-databricks-local-01.png)"
+      ]
     }
   ],
   "metadata": {

how-to-use-azureml/azure-databricks/automl/automl-databricks-local-with-deployment.ipynb

@@ -331,25 +331,18 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Load Training Data Using DataPrep"
+        "## Load Training Data Using Dataset"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Automated ML takes a Dataflow as input.\n",
+        "Automated ML takes a `TabularDataset` as input.\n",
         "\n",
-        "If you are familiar with Pandas and have done your data preparation work in Pandas already, you can use the `read_pandas_dataframe` method in dprep to convert the DataFrame to a Dataflow.\n",
+        "You are free to use the data preparation libraries/tools of your choice to do the require preparation and once you are done, you can write it to a datastore and create a TabularDataset from it.\n",
-        "```python\n",
-        "df = pd.read_csv(...)\n",
-        "# apply some transforms\n",
-        "dprep.read_pandas_dataframe(df, temp_folder='/path/accessible/by/both/driver/and/worker')\n",
-        "```\n",
         "\n",
-        "If you just need to ingest data without doing any preparation, you can directly use AzureML Data Prep (Data Prep) to do so. The code below demonstrates this scenario. Data Prep also has data preparation capabilities, we have many [sample notebooks](https://github.com/Microsoft/AMLDataPrepDocs) demonstrating the capabilities.\n",
+        "You will get the datastore you registered previously and pass it to Dataset for reading. The data comes from the digits dataset: `sklearn.datasets.load_digits()`. `DataPath` points to a specific location within a datastore. "
-        "\n",
-        "You will get the datastore you registered previously and pass it to Data Prep for reading. The data comes from the digits dataset: `sklearn.datasets.load_digits()`. `DataPath` points to a specific location within a datastore. "
       ]
     },
     {
@@ -358,21 +351,21 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "import azureml.dataprep as dprep\n",
+        "from azureml.core.dataset import Dataset\n",
         "from azureml.data.datapath import DataPath\n",
         "\n",
         "datastore = Datastore.get(workspace = ws, datastore_name = datastore_name)\n",
         "\n",
-        "X_train = dprep.read_csv(datastore.path('X.csv'))\n",
+        "X_train = Dataset.Tabular.from_delimited_files(datastore.path('X.csv'))\n",
-        "y_train = dprep.read_csv(datastore.path('y.csv')).to_long(dprep.ColumnSelector(term='.*', use_regex = True))"
+        "y_train = Dataset.Tabular.from_delimited_files(datastore.path('y.csv'))"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Review the Data Preparation Result\n",
+        "## Review the TabularDataset\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 for all the steps in the TabularDataset, which makes it fast even against large datasets."
       ]
     },
     {
@@ -381,7 +374,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "X_train.get_profile()"
+        "X_train.take(5).to_pandas_dataframe()"
       ]
     },
     {
@@ -390,7 +383,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "y_train.get_profile()"
+        "y_train.take(5).to_pandas_dataframe()"
       ]
     },
     {
@@ -796,6 +789,13 @@
       "source": [
         "myservice.delete()"
       ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/azure-databricks/automl/automl-databricks-local-with-deployment.png)"
+      ]
     }
   ],
   "metadata": {

how-to-use-azureml/azure-databricks/databricks-as-remote-compute-target/aml-pipelines-use-databricks-as-compute-target.ipynb

@@ -13,7 +13,7 @@
       "metadata": {},
       "source": [
         "# Using Databricks as a Compute Target from Azure Machine Learning Pipeline\n",
-        "To use Databricks as a compute target from [Azure Machine Learning Pipeline](https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-ml-pipelines), a [DatabricksStep](https://docs.microsoft.com/en-us/python/api/azureml-pipeline-steps/azureml.pipeline.steps.databricks_step.databricksstep?view=azure-ml-py) is used. This notebook demonstrates the use of DatabricksStep in Azure Machine Learning Pipeline.\n",
+        "To use Databricks as a compute target from [Azure Machine Learning Pipeline](https://aka.ms/pl-concept), a [DatabricksStep](https://docs.microsoft.com/en-us/python/api/azureml-pipeline-steps/azureml.pipeline.steps.databricks_step.databricksstep?view=azure-ml-py) is used. This notebook demonstrates the use of DatabricksStep in Azure Machine Learning Pipeline.\n",
         "\n",
         "The notebook will show:\n",
         "1. Running an arbitrary Databricks notebook that the customer has in Databricks workspace\n",
@@ -675,7 +675,14 @@
       "metadata": {},
       "source": [
         "# Next: ADLA as a Compute Target\n",
-        "To use ADLA as a compute target from Azure Machine Learning Pipeline, a AdlaStep is used. This [notebook](./aml-pipelines-use-adla-as-compute-target.ipynb) demonstrates the use of AdlaStep in Azure Machine Learning Pipeline."
+        "To use ADLA as a compute target from Azure Machine Learning Pipeline, a AdlaStep is used. This [notebook](https://aka.ms/pl-adla) demonstrates the use of AdlaStep in Azure Machine Learning Pipeline."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/azure-databricks/databricks-as-remote-compute-target/aml-pipelines-use-databricks-as-compute-target.png)"
       ]
     }
   ],

how-to-use-azureml/azure-hdi/automl_hdi_local_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/azure-hdi/automl_hdi_local_classification.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -119,25 +126,6 @@
         "**Note:** Creation of a new workspace can take several minutes."
       ]
     },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "##TESTONLY\n",
-    "# Import the Workspace class and check the Azure ML SDK version.\n",
-    "from azureml.core import Workspace\n",
-    "\n",
-    "ws = Workspace.create(name = workspace_name,\n",
-    "                      subscription_id = subscription_id,\n",
-    "                      resource_group = resource_group, \n",
-    "                      location = workspace_region,\n",
-    "                      auth = auth_sp,\n",
-    "                      exist_ok=True)\n",
-    "ws.get_details()"
-   ]
-  },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -605,7 +593,7 @@
     "kernelspec": {
       "display_name": "Python 3.6",
       "language": "Python",
-   "name": "Python36"
+      "name": "python36"
     },
     "language_info": {
       "codemirror_mode": {

how-to-use-azureml/deploy-to-cloud/README.md

@@ -1,5 +1,4 @@
 # Model Deployment with Azure ML service
-
 You can use Azure Machine Learning to package, debug, validate and deploy inference containers to a variety of compute targets. This process is known as "MLOps" (ML operationalization).
 For more information please check out this article: https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-deploy-and-where
 
@@ -9,17 +8,5 @@ For more information please check out this article: https://docs.microsoft.com/e
 
 ## Deploy to the cloud
 You can deploy to the cloud using the Azure ML CLI or the Azure ML SDK.
-
+- CLI example: https://aka.ms/azmlcli
-### Deploy with the CLI
-```
-az extension add -n azure-cli-ml
-az ml folder attach -w myworkspace -g myresourcegroup
-az ml model register -n sklearn_regression_model.pkl -p sklearn_regression_model.pkl -t model.json
-az ml model deploy -n acicicd -f model.json --ic inferenceConfig.yml --dc deploymentConfig.yml
-```
-
-Here is an [Azure DevOps Pipelines model deployment example](./azure-pipelines-model-deploy.yml)
-[![Build Status](https://aidemos.visualstudio.com/azmlcli/_apis/build/status/Azure.MachineLearningNotebooks?branchName=cli-ga)](https://aidemos.visualstudio.com/azmlcli/_build/latest?definitionId=87&branchName=cli-ga)
-
-### Deploy from a notebook
 - Notebook example: [model-register-and-deploy](./model-register-and-deploy.ipynb).

how-to-use-azureml/deploy-to-cloud/azure-pipelines-model-deploy.yml

@@ -1,50 +0,0 @@
-trigger:
-- master
-
-pool:
-  vmImage: 'Ubuntu-16.04'
-
-steps:
-- task: DownloadSecureFile@1
-  inputs:
-    name: config.json
-    secureFile: config.json
- 
-- script: cp $(Agent.TempDirectory)/config.json $(Build.SourcesDirectory)
-
-- task: AzureCLI@1
-  displayName: 'Install the CLI'
-  inputs:
-    azureSubscription: 'azmldemows'
-    scriptLocation: inlineScript
-    inlineScript: 'az extension add -n azure-cli-ml'
-
-- task: AzureCLI@1
-  displayName: 'Attach folder to workspace'
-  inputs:
-    azureSubscription: 'azmldemows'
-    scriptLocation: inlineScript
-    inlineScript: 'az ml folder attach'
-
-- task: AzureCLI@1
-  displayName: 'Register model'
-  inputs:
-    azureSubscription: 'azmldemows'
-    scriptLocation: inlineScript
-    inlineScript: 'az ml model register -n sklearn_regression_model.pkl -p sklearn_regression_model.pkl -t model.json'
-    workingDirectory: 'how-to-use-azureml/deploy-to-cloud/'
-
-- task: AzureCLI@1
-  displayName: 'Deploy model'
-  inputs:
-    azureSubscription: 'azmldemows'
-    scriptLocation: inlineScript
-    inlineScript: 'az ml model deploy -n acicicd -f model.json --ic inferenceConfig.yml --dc deploymentConfig.yml'
-    workingDirectory: 'how-to-use-azureml/deploy-to-cloud/'
-
-- task: AzureCLI@1
-  displayName: 'Delete deployed service'
-  inputs:
-    azureSubscription: 'azmldemows'
-    scriptLocation: inlineScript
-    inlineScript: 'az ml service delete -n acicicd'

how-to-use-azureml/deploy-to-cloud/deploymentConfig.yml

@@ -1,5 +0,0 @@
----
-containerResourceRequirements:
-  cpu: 1
-  memoryInGB: 1
-computeType: ACI

how-to-use-azureml/deploy-to-cloud/deploymentconfig.json

@@ -1,7 +0,0 @@
-{
-   "containerResourceRequirements": {
-      "cpu": 1,
-      "memoryInGB": 1
-   },
-   "computeType": "ACI"
-}

how-to-use-azureml/deploy-to-cloud/inferenceConfig.yml

@@ -1,9 +0,0 @@
-entryScript: score.py
-runtime: python
-condaFile: myenv.yml
-extraDockerfileSteps:
-schemaFile:
-dependencies:
-enableGpu: False
-baseImage:
-baseImageRegistry:

how-to-use-azureml/deploy-to-cloud/inferenceconfig.json

@@ -1,11 +0,0 @@
-{
-   "entryScript": "score.py",
-   "runtime": "python",
-   "condaFile": "myenv.yml",
-   "extraDockerfileSteps": null,
-   "schemaFile": null,
-   "dependencies": null,
-   "enableGpu": false,
-   "baseImage": null,
-   "baseImageRegistry": null
-}

how-to-use-azureml/deploy-to-cloud/model-register-and-deploy.ipynb

@@ -9,6 +9,20 @@
         "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/deploy-to-cloud/model-register-and-deploy.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/deploy-to-cloud/model-register-and-deploy.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -26,7 +40,7 @@
       "metadata": {},
       "source": [
         "## Prerequisites\n",
-        "Make sure you go through the [configuration](../../../configuration.ipynb) Notebook first if you haven't."
+        "If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, make sure you go through the [configuration](../../../configuration.ipynb) Notebook first if you haven't."
       ]
     },
     {
@@ -101,6 +115,36 @@
         "                       workspace=ws)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create Environment"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can now create and/or use an Environment object when deploying a Webservice. The Environment can have been previously registered with your Workspace, or it will be registered with it as a part of the Webservice deployment. Only Environments that were created using azureml-defaults version 1.0.48 or later will work with this new handling however.\n",
+        "\n",
+        "More information can be found in our [using environments notebook](../training/using-environments/using-environments.ipynb)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core import Environment\n",
+        "\n",
+        "env = Environment.from_conda_specification(name='deploytocloudenv', file_path='myenv.yml')\n",
+        "\n",
+        "# This is optional at this point\n",
+        "# env.register(workspace=ws)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -139,10 +183,7 @@
       "source": [
         "from azureml.core.model import InferenceConfig\n",
         "\n",
-        "inference_config = InferenceConfig(runtime= \"python\", \n",
+        "inference_config = InferenceConfig(entry_script=\"score.py\", environment=env)"
-        "                                   entry_script=\"score.py\",\n",
-        "                                   conda_file=\"myenv.yml\", \n",
-        "                                   extra_docker_file_steps=\"helloworld.txt\")"
       ]
     },
     {
@@ -233,15 +274,38 @@
       "source": [
         "### Model Profiling\n",
         "\n",
-        "you can also take advantage of profiling feature for model\n",
+        "You can also take advantage of the profiling feature to estimate CPU and memory requirements for models.\n",
         "\n",
         "```python\n",
-        "\n",
+        "profile = Model.profile(ws, \"profilename\", [model], inference_config, test_sample)\n",
-        "profile = model.profile(ws, \"profilename\", [model], inference_config, test_sample)\n",
         "profile.wait_for_profiling(True)\n",
         "profiling_results = profile.get_results()\n",
         "print(profiling_results)\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Model Packaging\n",
         "\n",
+        "If you want to build a Docker image that encapsulates your model and its dependencies, you can use the model packaging option. The output image will be pushed to your workspace's ACR.\n",
+        "\n",
+        "You must include an Environment object in your inference configuration to use `Model.package()`.\n",
+        "\n",
+        "```python\n",
+        "package = Model.package(ws, [model], inference_config)\n",
+        "package.wait_for_creation(show_output=True)  # Or show_output=False to hide the Docker build logs.\n",
+        "package.pull()\n",
+        "```\n",
+        "\n",
+        "Instead of a fully-built image, you can also generate a Dockerfile and download all the assets needed to build an image on top of your Environment.\n",
+        "\n",
+        "```python\n",
+        "package = Model.package(ws, [model], inference_config, generate_dockerfile=True)\n",
+        "package.wait_for_creation(show_output=True)\n",
+        "package.save(\"./local_context_dir\")\n",
         "```"
       ]
     }

how-to-use-azureml/deploy-to-cloud/model-register-and-deploy.yml

@@ -0,0 +1,4 @@
+name: model-register-and-deploy
+dependencies:
+- pip:
+  - azureml-sdk

how-to-use-azureml/deploy-to-cloud/mylib.py

@@ -1,8 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-# Licensed under the MIT license.
-
-import numpy as np
-
-def get_alphas():
-    # list of numbers from 0.0 to 1.0 with a 0.05 interval
-    return np.arange(0.0, 1.0, 0.05)

how-to-use-azureml/deploy-to-cloud/train.py

@@ -1,45 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-# Licensed under the MIT license.
-
-from sklearn.datasets import load_diabetes
-from sklearn.linear_model import Ridge
-from sklearn.metrics import mean_squared_error
-from sklearn.model_selection import train_test_split
-from azureml.core.run import Run
-from sklearn.externals import joblib
-import os
-import numpy as np
-import mylib
-
-os.makedirs('./outputs', exist_ok=True)
-
-X, y = load_diabetes(return_X_y=True)
-
-run = Run.get_context()
-
-X_train, X_test, y_train, y_test = train_test_split(X, y,
-                                                    test_size=0.2,
-                                                    random_state=0)
-data = {"train": {"X": X_train, "y": y_train},
-        "test": {"X": X_test, "y": y_test}}
-
-# list of numbers from 0.0 to 1.0 with a 0.05 interval
-alphas = mylib.get_alphas()
-
-for alpha in alphas:
-    # Use Ridge algorithm to create a regression model
-    reg = Ridge(alpha=alpha)
-    reg.fit(data["train"]["X"], data["train"]["y"])
-
-    preds = reg.predict(data["test"]["X"])
-    mse = mean_squared_error(preds, data["test"]["y"])
-    run.log('alpha', alpha)
-    run.log('mse', mse)
-
-    model_file_name = 'ridge_{0:.2f}.pkl'.format(alpha)
-    # save model in the outputs folder so it automatically get uploaded
-    with open(model_file_name, "wb") as file:
-        joblib.dump(value=reg, filename=os.path.join('./outputs/',
-                                                     model_file_name))
-
-    print('alpha is {0:.2f}, and mse is {1:0.2f}'.format(alpha, mse))

how-to-use-azureml/deploy-to-local/register-model-deploy-local-advanced.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/deploy-to-local/register-model-deploy-local-advanced.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -28,7 +35,7 @@
       "metadata": {},
       "source": [
         "## Prerequisites\n",
-        "Make sure you go through the [configuration](../../../configuration.ipynb) Notebook first if you haven't."
+        "If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, make sure you go through the [configuration](../../../configuration.ipynb) Notebook first if you haven't."
       ]
     },
     {
@@ -264,15 +271,10 @@
         "\n",
         "NOTE:\n",
         "\n",
-        "we require docker running with linux container. If you are running Docker for Windows, you need to ensure the Linux Engine is running\n",
+        "The Docker image runs as a Linux container. If you are running Docker for Windows, you need to ensure the Linux Engine is running:\n",
         "\n",
-        "    powershell command to switch to linux engine\n",
+        "    # PowerShell command to switch to Linux engine\n",
-        "    & 'C:\\Program Files\\Docker\\Docker\\DockerCli.exe' -SwitchLinuxEngine\n",
+        "    & 'C:\\Program Files\\Docker\\Docker\\DockerCli.exe' -SwitchLinuxEngine"
-        "\n",
-        "and c drive is shared https://docs.docker.com/docker-for-windows/#shared-drives\n",
-        "sometimes you have to reshare c drive as docker \n",
-        "\n",
-        "<img src=\"./dockerSharedDrive.JPG\" align=\"left\"/>"
       ]
     },
     {
@@ -288,7 +290,7 @@
       "source": [
         "from azureml.core.webservice import LocalWebservice\n",
         "\n",
-        "#this is optional, if not provided we choose random port\n",
+        "# This is optional, if not provided Docker will choose a random unused port.\n",
         "deployment_config = LocalWebservice.deploy_configuration(port=6789)\n",
         "\n",
         "local_service = Model.deploy(ws, \"test\", [model], inference_config, deployment_config)\n",
@@ -420,9 +422,8 @@
         "local_service.reload()\n",
         "print(\"--------------------------------------------------------------\")\n",
         "\n",
-        "# after reload now if you call run this will return updated return message\n",
+        "# After calling reload(), run() will return the updated message.\n",
-        "\n",
+        "local_service.run(input_data=sample_input)"
-        "print(local_service.run(input_data=sample_input))"
       ]
     },
     {
@@ -461,7 +462,7 @@
   "metadata": {
     "authors": [
       {
-        "name": "raymondl"
+        "name": "keriehm"
       }
     ],
     "kernelspec": {

how-to-use-azureml/deploy-to-local/register-model-deploy-local.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/deploy-to-local/register-model-deploy-local.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -28,7 +35,7 @@
       "metadata": {},
       "source": [
         "## Prerequisites\n",
-        "Make sure you go through the [configuration](../../../configuration.ipynb) Notebook first if you haven't."
+        "If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, make sure you go through the [configuration](../../../configuration.ipynb) Notebook first if you haven't."
       ]
     },
     {
@@ -99,6 +106,26 @@
         "                       workspace=ws)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Create Environment"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.conda_dependencies import CondaDependencies\n",
+        "from azureml.core.environment import Environment\n",
+        "\n",
+        "environment = Environment(\"LocalDeploy\")\n",
+        "environment.python.conda_dependencies = CondaDependencies(\"myenv.yml\")"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -114,9 +141,8 @@
       "source": [
         "from azureml.core.model import InferenceConfig\n",
         "\n",
-        "inference_config = InferenceConfig(runtime= \"python\", \n",
+        "inference_config = InferenceConfig(entry_script=\"score.py\",\n",
-        "                                   entry_script=\"score.py\",\n",
+        "                                   environment=environment)"
-        "                                   conda_file=\"myenv.yml\")"
       ]
     },
     {
@@ -131,15 +157,10 @@
         "\n",
         "NOTE:\n",
         "\n",
-        "we require docker running with linux container. If you are running Docker for Windows, you need to ensure the Linux Engine is running\n",
+        "The Docker image runs as a Linux container. If you are running Docker for Windows, you need to ensure the Linux Engine is running:\n",
         "\n",
-        "    powershell command to switch to linux engine\n",
+        "    # PowerShell command to switch to Linux engine\n",
-        "    & 'C:\\Program Files\\Docker\\Docker\\DockerCli.exe' -SwitchLinuxEngine\n",
+        "    & 'C:\\Program Files\\Docker\\Docker\\DockerCli.exe' -SwitchLinuxEngine"
-        "\n",
-        "and c drive is shared https://docs.docker.com/docker-for-windows/#shared-drives\n",
-        "sometimes you have to reshare c drive as docker \n",
-        "\n",
-        "<img src=\"./dockerSharedDrive.JPG\" align=\"left\"/>"
       ]
     },
     {
@@ -150,7 +171,7 @@
       "source": [
         "from azureml.core.webservice import LocalWebservice\n",
         "\n",
-        "#this is optional, if not provided we choose random port\n",
+        "# This is optional, if not provided Docker will choose a random unused port.\n",
         "deployment_config = LocalWebservice.deploy_configuration(port=6789)\n",
         "\n",
         "local_service = Model.deploy(ws, \"test\", [model], inference_config, deployment_config)\n",
@@ -214,7 +235,7 @@
         "\n",
         "sample_input = bytes(sample_input, encoding='utf-8')\n",
         "\n",
-        "print(local_service.run(input_data=sample_input))"
+        "local_service.run(input_data=sample_input)"
       ]
     },
     {
@@ -275,9 +296,8 @@
         "local_service.reload()\n",
         "print(\"--------------------------------------------------------------\")\n",
         "\n",
-        "# after reload now if you call run this will return updated return message\n",
+        "# After calling reload(), run() will return the updated message.\n",
-        "\n",
+        "local_service.run(input_data=sample_input)"
-        "print(local_service.run(input_data=sample_input))"
       ]
     },
     {
@@ -289,10 +309,9 @@
         "If you want to change your model(s), Conda dependencies, or deployment configuration, call `update()` to rebuild the Docker image.\n",
         "\n",
         "```python\n",
-        "\n",
         "local_service.update(models=[SomeOtherModelObject],\n",
-        "             deployment_config = local_config,\n",
+        "                     inference_config=inference_config,\n",
-        "             inference_config = inference_config)\n",
+        "                     deployment_config=local_config)\n",
         "```"
       ]
     },
@@ -316,7 +335,7 @@
   "metadata": {
     "authors": [
       {
-        "name": "raymondl"
+        "name": "keriehm"
       }
     ],
     "kernelspec": {