Update 12/2 2

Dockerfiles/1.0.10/Dockerfile

@@ -1,29 +0,0 @@
-FROM continuumio/miniconda:4.5.11
-
-# install git
-RUN apt-get update && apt-get upgrade -y && apt-get install -y git
-
-# create a new conda environment named azureml
-RUN conda create -n azureml -y -q Python=3.6
-
-# install additional packages used by sample notebooks. this is optional
-RUN ["/bin/bash", "-c", "source activate azureml && conda install -y tqdm cython matplotlib scikit-learn"]
-
-# install azurmel-sdk components
-RUN ["/bin/bash", "-c", "source activate azureml && pip install azureml-sdk[notebooks]==1.0.10"]
-
-# clone Azure ML GitHub sample notebooks
-RUN cd /home && git clone -b "azureml-sdk-1.0.10" --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/1.0.2/Dockerfile

@@ -1,29 +0,0 @@
-FROM continuumio/miniconda:4.5.11
-
-# install git
-RUN apt-get update && apt-get upgrade -y && apt-get install -y git
-
-# create a new conda environment named azureml
-RUN conda create -n azureml -y -q Python=3.6
-
-# install additional packages used by sample notebooks. this is optional
-RUN ["/bin/bash", "-c", "source activate azureml && conda install -y tqdm cython matplotlib scikit-learn"]
-
-# install azurmel-sdk components
-RUN ["/bin/bash", "-c", "source activate azureml && pip install azureml-sdk[notebooks]==1.0.2"]
-
-# clone Azure ML GitHub sample notebooks
-RUN cd /home && git clone -b "azureml-sdk-1.0.2" --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/1.0.6/Dockerfile

@@ -1,29 +0,0 @@
-FROM continuumio/miniconda:4.5.11
-
-# install git
-RUN apt-get update && apt-get upgrade -y && apt-get install -y git
-
-# create a new conda environment named azureml
-RUN conda create -n azureml -y -q Python=3.6
-
-# install additional packages used by sample notebooks. this is optional
-RUN ["/bin/bash", "-c", "source activate azureml && conda install -y tqdm cython matplotlib scikit-learn"]
-
-# install azurmel-sdk components
-RUN ["/bin/bash", "-c", "source activate azureml && pip install azureml-sdk[notebooks]==1.0.6"]
-
-# clone Azure ML GitHub sample notebooks
-RUN cd /home && git clone -b "azureml-sdk-1.0.6" --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/1.0.8/Dockerfile

@@ -1,29 +0,0 @@
-FROM continuumio/miniconda:4.5.11
-
-# install git
-RUN apt-get update && apt-get upgrade -y && apt-get install -y git
-
-# create a new conda environment named azureml
-RUN conda create -n azureml -y -q Python=3.6
-
-# install additional packages used by sample notebooks. this is optional
-RUN ["/bin/bash", "-c", "source activate azureml && conda install -y tqdm cython matplotlib scikit-learn"]
-
-# install azurmel-sdk components
-RUN ["/bin/bash", "-c", "source activate azureml && pip install azureml-sdk[notebooks]==1.0.8"]
-
-# clone Azure ML GitHub sample notebooks
-RUN cd /home && git clone -b "azureml-sdk-1.0.8" --single-branch https://github.com/Azure/MachineLearningNotebooks.git
-
-# generate jupyter configuration file
-RUN ["/bin/bash", "-c", "source activate azureml && mkdir ~/.jupyter && cd ~/.jupyter && jupyter notebook --generate-config"]
-
-# set an emtpy token for Jupyter to remove authentication. 
-# this is NOT recommended for production environment
-RUN echo "c.NotebookApp.token = ''" >> ~/.jupyter/jupyter_notebook_config.py
-
-# open up port 8887 on the container
-EXPOSE 8887
-
-# start Jupyter notebook server on port 8887 when the container starts
-CMD /bin/bash -c "cd /home/MachineLearningNotebooks && source activate azureml && jupyter notebook --port 8887 --no-browser --ip 0.0.0.0 --allow-root"

NBSETUP.md

@@ -1,34 +0,0 @@
-# Notebook setup
-
----
-
-To run the notebooks in this repository use one of these methods:
-
-## Use Azure Notebooks - Jupyter based notebooks in the Azure cloud
-
-1. [![Azure Notebooks](https://notebooks.azure.com/launch.png)](https://aka.ms/aml-clone-azure-notebooks)
-[Import sample notebooks ](https://aka.ms/aml-clone-azure-notebooks) into Azure Notebooks
-1. Follow the instructions in the [Configuration](configuration.ipynb) notebook to create and connect to a workspace
-1. Open one of the sample notebooks
-
-    **Make sure the Azure Notebook kernel is set to `Python 3.6`** when you open a notebook
-
-    ![set kernel to Python 3.6](images/python36.png)
-
-## **Use your own notebook server**
-
-Video walkthrough:
-
-[![Get Started video](images/yt_cover.png)](https://youtu.be/VIsXeTuW3FU)
-
-1. Setup a Jupyter Notebook server and [install the Azure Machine Learning SDK](https://docs.microsoft.com/en-us/azure/machine-learning/service/quickstart-create-workspace-with-python)
-1. Clone [this repository](https://aka.ms/aml-notebooks)
-1. You may need to install other packages for specific notebook
-    - For example, to run the Azure Machine Learning Data Prep notebooks, install the extra dataprep SDK:
-    ```bash
-     pip install azureml-dataprep
-    ```
-
-1. Start your notebook server
-1. Follow the instructions in the [Configuration](configuration.ipynb) notebook to create and connect to a workspace
-1. Open one of the sample notebooks

README.md

@@ -1,58 +1,53 @@
-# Azure Machine Learning service example notebooks
+For full documentation for Azure Machine Learning service, visit **https://aka.ms/aml-docs**.
+# Sample Notebooks for Azure Machine Learning service
 
-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.
+To run the notebooks in this repository use one of these methods:
 
-![Azure ML workflow](https://raw.githubusercontent.com/MicrosoftDocs/azure-docs/master/articles/machine-learning/service/media/overview-what-is-azure-ml/aml.png)
+## Use Azure Notebooks - Jupyter based notebooks in the Azure cloud
 
-## Quick installation
-```sh
-pip install azureml-sdk
-```
-Read more detailed instructions on [how to set up your environment](./NBSETUP.md).
+1. [![Azure Notebooks](https://notebooks.azure.com/launch.png)](https://aka.ms/aml-clone-azure-notebooks)
+[Import sample notebooks ](https://aka.ms/aml-clone-azure-notebooks) into Azure Notebooks.
+1. Follow the instructions in the [00.configuration](00.configuration.ipynb) notebook to create and connect to a workspace.
+1. Open one of the sample notebooks.
     
-## 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. 
+    **Make sure the Azure Notebook kernel is set to `Python 3.6`** when you open a notebook.  
     
-If you want to...
-
- * ...try out and explore Azure ML, start with image classification tutorials [part 1 training](./tutorials/img-classification-part1-training.ipynb) and [part 2 deployment](./tutorials/img-classification-part2-deploy.ipynb).
- * ...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 model as 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 batch scoring service, first [train a model within Notebook](./how-to-use-azureml/training/train-within-notebook/train-within-notebook.ipynb), learn how to [register and manage models](./how-to-use-azureml/deployment/register-model-create-image-deploy-service/register-model-create-image-deploy-service.ipynb), then [create Machine Learning Compute for scoring compute](./how-to-use-azureml/training/train-on-amlcompute/train-on-amlcompute.ipynb), and [use Machine Learning Pipelines to deploy your model](./how-to-use-azureml/machine-learning-pipelines/pipeline-mpi-batch-prediction.ipynb).
- * ...monitor your deployed models, learn about using [App Insights](./how-to-use-azureml/deployment/enable-app-insights-in-production-service/enable-app-insights-in-production-service.ipynb) and [model data collection](./how-to-use-azureml/deployment/enable-data-collection-for-models-in-aks/enable-data-collection-for-models-in-aks.ipynb).
-
-## Tutorials
-
-The [Tutorials](./tutorials) folder contains notebooks for the tutorials described in the [Azure Machine Learning documentation](https://aka.ms/aml-docs)
-  
-## How to use Azure ML
-
-The [How to use Azure ML](./how-to-use-azureml) folder contains specific examples demonstrating the features of the Azure Machine Learning SDK
-
-- [Training](./how-to-use-azureml/training) - Examples of how to build models using Azure ML's logging and execution capabilities on local and remote compute targets.
-- [Training with Deep Learning](./how-to-use-azureml/training-with-deep-learning) - Examples demonstrating how to build deep learning models using estimators and parameter sweeps
-- [Automated Machine Learning](./how-to-use-azureml/automated-machine-learning) - Examples using Automated Machine Learning to automatically generate optimal machine learning pipelines and models
-- [Machine Learning Pipelines](./how-to-use-azureml/machine-learning-pipelines) - Examples showing how to create and use reusable pipelines for training and batch scoring
-- [Deployment](./how-to-use-azureml/deployment) - Examples showing how to deploy and manage machine learning models and solutions
-- [Azure Databricks](./how-to-use-azureml/azure-databricks) - Examples showing how to use Azure ML with Azure Databricks
-
----
-## Documentation
-
- * Quickstarts, end-to-end tutorials, and how-tos on the [official documentation site for Azure Machine Learning service](https://docs.microsoft.com/en-us/azure/machine-learning/service/).
-
- * [Python SDK reference]( https://docs.microsoft.com/en-us/python/api/overview/azure/ml/intro?view=azure-ml-py)
+    ![set kernel to Python 3.6](images/python36.png)
 
 
----
+## **Use your own notebook server**
 
-## Projects using Azure Machine Learning
+Video walkthrough:
 
-Visit following repos to see projects contributed by Azure ML users:
+[![get started video](images/yt_cover.png)](https://youtu.be/VIsXeTuW3FU)
 
- - [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)
+1. Setup a Jupyter Notebook server and [install the Azure Machine Learning SDK](https://docs.microsoft.com/en-us/azure/machine-learning/service/quickstart-create-workspace-with-python).
+1. Clone [this repository](https://aka.ms/aml-notebooks).
+1. You may need to install other packages for specific notebook. 
+    - For example, to run the Azure Machine Learning Data Prep notebooks, install the extra dataprep SDK:
+    ```
+     pip install --upgrade azureml-dataprep
+    ```
+
+1. Start your notebook server.
+1. Follow the instructions in the [00.configuration](00.configuration.ipynb) notebook to create and connect to a workspace.
+1. Open one of the sample notebooks.
+
+
+
+> Note: **Looking for automated machine learning samples?**
+> For your convenience, you can use an installation script instead of the steps below for the automated ML notebooks. Go to the [automl folder README](automl/README.md) and follow the instructions.  The script installs all  packages needed for notebooks in that folder.
+
+# Contributing
+
+This project welcomes contributions and suggestions.  Most contributions require you to agree to a
+Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us
+the rights to use your contribution. For details, visit https://cla.microsoft.com.
+
+When you submit a pull request, a CLA-bot will automatically determine whether you need to provide
+a CLA and decorate the PR appropriately (e.g., label, comment). Simply follow the instructions
+provided by the bot. You will only need to do this once across all repos using our CLA.
+
+This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
+For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or
+contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.

configuration.ipynb

@@ -96,7 +96,7 @@
       "source": [
         "import azureml.core\n",
         "\n",
-        "print(\"This notebook was created using version 1.0.10 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version 1.0.2 of the Azure ML SDK\")\n",
         "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },
@@ -368,7 +368,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.5"
+      "version": "3.6.7"
     }
   },
   "nbformat": 4,

contrib/RAPIDS/azure-ml-with-nvidia-rapids.ipynb

@@ -1,409 +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": [
-        "# NVIDIA RAPIDS in Azure Machine Learning"
-      ]
-    },
-    {
-      "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",
-        " \n",
-        "In this notebook, we will do the following:\n",
-        " \n",
-        "* Create an Azure Machine Learning Workspace\n",
-        "* Create an AMLCompute target\n",
-        "* Use a script to process our data and train a model\n",
-        "* Obtain the data required to run this sample\n",
-        "* Create an AML run configuration to launch a machine learning job\n",
-        "* Run the script to prepare data for training and train the model\n",
-        " \n",
-        "Prerequisites:\n",
-        "* An Azure subscription to create a Machine Learning Workspace\n",
-        "* Familiarity with the Azure ML SDK (refer to [notebook samples](https://github.com/Azure/MachineLearningNotebooks))\n",
-        "* A Jupyter notebook environment with Azure Machine Learning SDK installed. Refer to instructions to [setup the environment](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-environment#local)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Verify if Azure ML SDK is installed"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import azureml.core\n",
-        "print(\"SDK version:\", azureml.core.VERSION)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "from azureml.core import Workspace, Experiment\n",
-        "from azureml.core.compute import AmlCompute, ComputeTarget\n",
-        "from azureml.data.data_reference import DataReference\n",
-        "from azureml.core.runconfig import RunConfiguration\n",
-        "from azureml.core import ScriptRunConfig\n",
-        "from azureml.widgets import RunDetails"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Create Azure ML Workspace"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "The following step is optional if you already have a workspace. If you want to use an existing workspace, then\n",
-        "skip this workspace creation step and move on to the next step to load the workspace.\n",
-        " \n",
-        "<font color='red'>Important</font>: in the code cell below, be sure to set the correct values for the subscription_id, \n",
-        "resource_group, workspace_name, region before executing this code cell."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "subscription_id = os.environ.get(\"SUBSCRIPTION_ID\", \"<subscription_id>\")\n",
-        "resource_group = os.environ.get(\"RESOURCE_GROUP\", \"<resource_group>\")\n",
-        "workspace_name = os.environ.get(\"WORKSPACE_NAME\", \"<workspace_name>\")\n",
-        "workspace_region = os.environ.get(\"WORKSPACE_REGION\", \"<region>\")\n",
-        "\n",
-        "ws = Workspace.create(workspace_name, subscription_id=subscription_id, resource_group=resource_group, location=workspace_region)\n",
-        "\n",
-        "# write config to a local directory for future use\n",
-        "ws.write_config()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Load existing Workspace"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ws = Workspace.from_config()\n",
-        "# if a locally-saved configuration file for the workspace is not available, use the following to load workspace\n",
-        "# ws = Workspace(subscription_id=subscription_id, resource_group=resource_group, workspace_name=workspace_name)\n",
-        "print('Workspace name: ' + ws.name, \n",
-        "      'Azure region: ' + ws.location, \n",
-        "      'Subscription id: ' + ws.subscription_id, \n",
-        "      'Resource group: ' + ws.resource_group, sep = '\\n')\n",
-        "\n",
-        "scripts_folder = \"scripts_folder\"\n",
-        "\n",
-        "if not os.path.isdir(scripts_folder):\n",
-        "    os.mkdir(scripts_folder)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Create AML Compute Target"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Because NVIDIA RAPIDS requires P40 or V100 GPUs, the user needs to specify compute targets from one of [NC_v3](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#ncv3-series), [NC_v2](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#ncv2-series), [ND](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#nd-series) or [ND_v2](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#ndv2-series-preview) virtual machine types in Azure; these are the families of virtual machines in Azure that are provisioned with these GPUs.\n",
-        " \n",
-        "Pick one of the supported VM SKUs based on the number of GPUs you want to use for ETL and training in RAPIDS.\n",
-        " \n",
-        "The script in this notebook is implemented for single-machine scenarios. An example supporting multiple nodes will be published later."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "gpu_cluster_name = \"gpucluster\"\n",
-        "\n",
-        "if gpu_cluster_name in ws.compute_targets:\n",
-        "    gpu_cluster = ws.compute_targets[gpu_cluster_name]\n",
-        "    if gpu_cluster and type(gpu_cluster) is AmlCompute:\n",
-        "        print('found compute target. just use it. ' + gpu_cluster_name)\n",
-        "else:\n",
-        "    print(\"creating new cluster\")\n",
-        "    # vm_size parameter below could be modified to one of the RAPIDS-supported VM types\n",
-        "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"Standard_NC6s_v2\", min_nodes=1, max_nodes = 1)\n",
-        "\n",
-        "    # create the cluster\n",
-        "    gpu_cluster = ComputeTarget.create(ws, gpu_cluster_name, provisioning_config)\n",
-        "    gpu_cluster.wait_for_completion(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Script to process data and train model"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "The _process&#95;data.py_ script used in the step below is a slightly modified implementation of [RAPIDS E2E example](https://github.com/rapidsai/notebooks/blob/master/mortgage/E2E.ipynb)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# copy process_data.py into the script folder\n",
-        "import shutil\n",
-        "shutil.copy('./process_data.py', os.path.join(scripts_folder, 'process_data.py'))\n",
-        "\n",
-        "with open(os.path.join(scripts_folder, './process_data.py'), 'r') as process_data_script:\n",
-        "    print(process_data_script.read())"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Data required to run this sample"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "This sample uses [Fannie Mae\u00e2\u20ac\u2122s Single-Family Loan Performance Data](http://www.fanniemae.com/portal/funding-the-market/data/loan-performance-data.html). Refer to the 'Available mortgage datasets' section in [instructions](https://rapidsai.github.io/demos/datasets/mortgage-data) to get sample data.\n",
-        "\n",
-        "Once you obtain access to the data, you will need to make this data available in an [Azure Machine Learning Datastore](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-access-data), for use in this sample."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<font color='red'>Important</font>: The following step assumes the data is uploaded to the Workspace's default data store under a folder named 'mortgagedata2000_01'. Note that uploading data to the Workspace's default data store is not necessary and the data can be referenced from any datastore, e.g., from Azure Blob or File service, once it is added as a datastore to the workspace. The path_on_datastore parameter needs to be updated, depending on where the data is available.  The directory where the data is available should have the following folder structure, as the process_data.py script expects this directory structure:\n",
-        "* _&lt;data directory>_/acq\n",
-        "* _&lt;data directory>_/perf\n",
-        "* _names.csv_\n",
-        "\n",
-        "The 'acq' and 'perf' refer to directories containing data files. The _&lt;data directory>_ is the path specified in _path&#95;on&#95;datastore_ parameter in the step below."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ds = ws.get_default_datastore()\n",
-        "\n",
-        "# download and uncompress data in a local directory before uploading to data store\n",
-        "# directory specified in src_dir parameter below should have the acq, perf directories with data and names.csv file\n",
-        "# ds.upload(src_dir='<local directory that has data>', target_path='mortgagedata2000_01', overwrite=True, show_progress=True)\n",
-        "\n",
-        "# data already uploaded to the datastore\n",
-        "data_ref = DataReference(data_reference_name='data', datastore=ds, path_on_datastore='mortgagedata2000_01')"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Create AML run configuration to launch a machine learning job"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "AML allows the option of using existing Docker images with prebuilt conda environments. The following step use an existing image from [Docker Hub](https://hub.docker.com/r/rapidsai/rapidsai/)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "run_config = RunConfiguration()\n",
-        "run_config.framework = 'python'\n",
-        "run_config.environment.python.user_managed_dependencies = True\n",
-        "# use conda environment named 'rapids' available in the Docker image\n",
-        "# this conda environment does not include azureml-defaults package that is required for using AML functionality like metrics tracking, model management etc.\n",
-        "run_config.environment.python.interpreter_path = '/conda/envs/rapids/bin/python'\n",
-        "run_config.target = gpu_cluster_name\n",
-        "run_config.environment.docker.enabled = True\n",
-        "run_config.environment.docker.gpu_support = True\n",
-        "# if registry is not mentioned the image is pulled from Docker Hub\n",
-        "run_config.environment.docker.base_image = \"rapidsai/rapidsai:cuda9.2_ubuntu16.04_root\"\n",
-        "run_config.environment.spark.precache_packages = False\n",
-        "run_config.data_references={'data':data_ref.to_config()}"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Wrapper function to submit Azure Machine Learning experiment"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# parameter cpu_predictor indicates if training should be done on CPU. If set to true, GPUs are used *only* for ETL and *not* for training\n",
-        "# parameter num_gpu indicates number of GPUs to use among the GPUs available in the VM for ETL and if cpu_predictor is false, for training as well \n",
-        "def run_rapids_experiment(cpu_training, gpu_count):\n",
-        "    # any value between 1-4 is allowed here depending the type of VMs available in gpu_cluster\n",
-        "    if gpu_count not in [1, 2, 3, 4]:\n",
-        "        raise Exception('Value specified for the number of GPUs to use {0} is invalid'.format(gpu_count))\n",
-        "\n",
-        "    # following data partition mapping is empirical (specific to GPUs used and current data partitioning scheme) and may need to be tweaked\n",
-        "    gpu_count_data_partition_mapping = {1: 2, 2: 4, 3: 5, 4: 7}\n",
-        "    part_count = gpu_count_data_partition_mapping[gpu_count]\n",
-        "\n",
-        "    end_year = 2000\n",
-        "    if gpu_count > 2:\n",
-        "        end_year = 2001 # use more data with more GPUs\n",
-        "\n",
-        "    src = ScriptRunConfig(source_directory=scripts_folder, \n",
-        "                          script='process_data.py', \n",
-        "                          arguments = ['--num_gpu', gpu_count, '--data_dir', str(data_ref),\n",
-        "                                      '--part_count', part_count, '--end_year', end_year,\n",
-        "                                      '--cpu_predictor', cpu_training\n",
-        "                                      ],\n",
-        "                          run_config=run_config\n",
-        "                         )\n",
-        "\n",
-        "    exp = Experiment(ws, 'rapidstest')\n",
-        "    run = exp.submit(config=src)\n",
-        "    RunDetails(run).show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Submit experiment (ETL & training on GPU)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "cpu_predictor = False\n",
-        "# the value for num_gpu should be less than or equal to the number of GPUs available in the VM\n",
-        "num_gpu = 1 \n",
-        "# train using CPU, use GPU for both ETL and training\n",
-        "run_rapids_experiment(cpu_predictor, num_gpu)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Submit experiment (ETL on GPU, training on CPU)\n",
-        "\n",
-        "To observe performance difference between GPU-accelerated RAPIDS based training with CPU-only training, set 'cpu_predictor' predictor to 'True' and rerun the experiment"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "cpu_predictor = True\n",
-        "# the value for num_gpu should be less than or equal to the number of GPUs available in the VM\n",
-        "num_gpu = 1\n",
-        "# train using CPU, use GPU for ETL\n",
-        "run_rapids_experiment(cpu_predictor, num_gpu)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Delete cluster"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# delete the cluster\n",
-        "# gpu_cluster.delete()"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "ksivas"
-      }
-    ],
-    "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
-}

contrib/RAPIDS/process_data.py

@@ -1,500 +0,0 @@
-# License Info: https://github.com/rapidsai/notebooks/blob/master/LICENSE
-import numpy as np
-import datetime
-import dask_xgboost as dxgb_gpu
-import dask
-import dask_cudf
-from dask.delayed import delayed
-from dask.distributed import Client, wait
-import xgboost as xgb
-import cudf
-from cudf.dataframe import DataFrame
-from collections import OrderedDict
-import gc
-from glob import glob
-import os
-import argparse
-
-parser = argparse.ArgumentParser("rapidssample")
-parser.add_argument("--data_dir", type=str, help="location of data")
-parser.add_argument("--num_gpu", type=int, help="Number of GPUs to use", default=1)
-parser.add_argument("--part_count", type=int, help="Number of data files to train against", default=2)
-parser.add_argument("--end_year", type=int, help="Year to end the data load", default=2000)
-parser.add_argument("--cpu_predictor", type=str, help="Flag to use CPU for prediction", default='False')
-parser.add_argument('-f', type=str, default='') # added for notebook execution scenarios
-args = parser.parse_args()
-data_dir = args.data_dir
-num_gpu = args.num_gpu
-part_count = args.part_count
-end_year = args.end_year
-cpu_predictor = args.cpu_predictor.lower() in ('yes', 'true', 't', 'y', '1')
-
-print('data_dir = {0}'.format(data_dir))
-print('num_gpu = {0}'.format(num_gpu))
-print('part_count = {0}'.format(part_count))
-part_count = part_count + 1 # adding one because the usage below is not inclusive
-print('end_year = {0}'.format(end_year))
-print('cpu_predictor = {0}'.format(cpu_predictor))
-
-import subprocess
-
-cmd = "hostname --all-ip-addresses"
-process = subprocess.Popen(cmd.split(), stdout=subprocess.PIPE)
-output, error = process.communicate()
-IPADDR = str(output.decode()).split()[0]
-print('IPADDR is {0}'.format(IPADDR))
-
-cmd = "/rapids/notebooks/utils/dask-setup.sh 0"
-process = subprocess.Popen(cmd.split(), stdout=subprocess.PIPE)
-output, error = process.communicate()
-
-cmd = "/rapids/notebooks/utils/dask-setup.sh rapids " + str(num_gpu) + " 8786 8787 8790 " + str(IPADDR) + " MASTER"
-process = subprocess.Popen(cmd.split(), stdout=subprocess.PIPE)
-output, error = process.communicate()
-
-print(output.decode())
-
-import dask
-from dask.delayed import delayed
-from dask.distributed import Client, wait
-
-_client = IPADDR + str(":8786")
-
-client = dask.distributed.Client(_client)
-
-def initialize_rmm_pool():
-    from librmm_cffi import librmm_config as rmm_cfg
-
-    rmm_cfg.use_pool_allocator = True
-    #rmm_cfg.initial_pool_size = 2<<30 # set to 2GiB. Default is 1/2 total GPU memory
-    import cudf
-    return cudf._gdf.rmm_initialize()
-
-def initialize_rmm_no_pool():
-    from librmm_cffi import librmm_config as rmm_cfg
-    
-    rmm_cfg.use_pool_allocator = False
-    import cudf
-    return cudf._gdf.rmm_initialize()
-
-def run_dask_task(func, **kwargs):
-    task = func(**kwargs)
-    return task
-
-def process_quarter_gpu(year=2000, quarter=1, perf_file=""):
-    ml_arrays = run_dask_task(delayed(run_gpu_workflow),
-                                          quarter=quarter,
-                                          year=year,
-                                          perf_file=perf_file)
-    return client.compute(ml_arrays,
-                          optimize_graph=False,
-                          fifo_timeout="0ms"
-                         )
-
-def null_workaround(df, **kwargs):
-    for column, data_type in df.dtypes.items():
-        if str(data_type) == "category":
-            df[column] = df[column].astype('int32').fillna(-1)
-        if str(data_type) in ['int8', 'int16', 'int32', 'int64', 'float32', 'float64']:
-            df[column] = df[column].fillna(-1)
-    return df
-
-def run_gpu_workflow(quarter=1, year=2000, perf_file="", **kwargs):
-    names = gpu_load_names()
-    acq_gdf = gpu_load_acquisition_csv(acquisition_path= acq_data_path + "/Acquisition_"
-                                      + str(year) + "Q" + str(quarter) + ".txt")
-    acq_gdf = acq_gdf.merge(names, how='left', on=['seller_name'])
-    acq_gdf.drop_column('seller_name')
-    acq_gdf['seller_name'] = acq_gdf['new']
-    acq_gdf.drop_column('new')
-    perf_df_tmp = gpu_load_performance_csv(perf_file)
-    gdf = perf_df_tmp
-    everdf = create_ever_features(gdf)
-    delinq_merge = create_delinq_features(gdf)
-    everdf = join_ever_delinq_features(everdf, delinq_merge)
-    del(delinq_merge)
-    joined_df = create_joined_df(gdf, everdf)
-    testdf = create_12_mon_features(joined_df)
-    joined_df = combine_joined_12_mon(joined_df, testdf)
-    del(testdf)
-    perf_df = final_performance_delinquency(gdf, joined_df)
-    del(gdf, joined_df)
-    final_gdf = join_perf_acq_gdfs(perf_df, acq_gdf)
-    del(perf_df)
-    del(acq_gdf)
-    final_gdf = last_mile_cleaning(final_gdf)
-    return final_gdf
-
-def gpu_load_performance_csv(performance_path, **kwargs):
-    """ Loads performance data
-
-    Returns
-    -------
-    GPU DataFrame
-    """
-    
-    cols = [
-        "loan_id", "monthly_reporting_period", "servicer", "interest_rate", "current_actual_upb",
-        "loan_age", "remaining_months_to_legal_maturity", "adj_remaining_months_to_maturity",
-        "maturity_date", "msa", "current_loan_delinquency_status", "mod_flag", "zero_balance_code",
-        "zero_balance_effective_date", "last_paid_installment_date", "foreclosed_after",
-        "disposition_date", "foreclosure_costs", "prop_preservation_and_repair_costs",
-        "asset_recovery_costs", "misc_holding_expenses", "holding_taxes", "net_sale_proceeds",
-        "credit_enhancement_proceeds", "repurchase_make_whole_proceeds", "other_foreclosure_proceeds",
-        "non_interest_bearing_upb", "principal_forgiveness_upb", "repurchase_make_whole_proceeds_flag",
-        "foreclosure_principal_write_off_amount", "servicing_activity_indicator"
-    ]
-    
-    dtypes = OrderedDict([
-        ("loan_id", "int64"),
-        ("monthly_reporting_period", "date"),
-        ("servicer", "category"),
-        ("interest_rate", "float64"),
-        ("current_actual_upb", "float64"),
-        ("loan_age", "float64"),
-        ("remaining_months_to_legal_maturity", "float64"),
-        ("adj_remaining_months_to_maturity", "float64"),
-        ("maturity_date", "date"),
-        ("msa", "float64"),
-        ("current_loan_delinquency_status", "int32"),
-        ("mod_flag", "category"),
-        ("zero_balance_code", "category"),
-        ("zero_balance_effective_date", "date"),
-        ("last_paid_installment_date", "date"),
-        ("foreclosed_after", "date"),
-        ("disposition_date", "date"),
-        ("foreclosure_costs", "float64"),
-        ("prop_preservation_and_repair_costs", "float64"),
-        ("asset_recovery_costs", "float64"),
-        ("misc_holding_expenses", "float64"),
-        ("holding_taxes", "float64"),
-        ("net_sale_proceeds", "float64"),
-        ("credit_enhancement_proceeds", "float64"),
-        ("repurchase_make_whole_proceeds", "float64"),
-        ("other_foreclosure_proceeds", "float64"),
-        ("non_interest_bearing_upb", "float64"),
-        ("principal_forgiveness_upb", "float64"),
-        ("repurchase_make_whole_proceeds_flag", "category"),
-        ("foreclosure_principal_write_off_amount", "float64"),
-        ("servicing_activity_indicator", "category")
-    ])
-
-    print(performance_path)
-    
-    return cudf.read_csv(performance_path, names=cols, delimiter='|', dtype=list(dtypes.values()), skiprows=1)
-
-def gpu_load_acquisition_csv(acquisition_path, **kwargs):
-    """ Loads acquisition data
-
-    Returns
-    -------
-    GPU DataFrame
-    """
-    
-    cols = [
-        'loan_id', 'orig_channel', 'seller_name', 'orig_interest_rate', 'orig_upb', 'orig_loan_term', 
-        'orig_date', 'first_pay_date', 'orig_ltv', 'orig_cltv', 'num_borrowers', 'dti', 'borrower_credit_score', 
-        'first_home_buyer', 'loan_purpose', 'property_type', 'num_units', 'occupancy_status', 'property_state',
-        'zip', 'mortgage_insurance_percent', 'product_type', 'coborrow_credit_score', 'mortgage_insurance_type', 
-        'relocation_mortgage_indicator'
-    ]
-    
-    dtypes = OrderedDict([
-        ("loan_id", "int64"),
-        ("orig_channel", "category"),
-        ("seller_name", "category"),
-        ("orig_interest_rate", "float64"),
-        ("orig_upb", "int64"),
-        ("orig_loan_term", "int64"),
-        ("orig_date", "date"),
-        ("first_pay_date", "date"),
-        ("orig_ltv", "float64"),
-        ("orig_cltv", "float64"),
-        ("num_borrowers", "float64"),
-        ("dti", "float64"),
-        ("borrower_credit_score", "float64"),
-        ("first_home_buyer", "category"),
-        ("loan_purpose", "category"),
-        ("property_type", "category"),
-        ("num_units", "int64"),
-        ("occupancy_status", "category"),
-        ("property_state", "category"),
-        ("zip", "int64"),
-        ("mortgage_insurance_percent", "float64"),
-        ("product_type", "category"),
-        ("coborrow_credit_score", "float64"),
-        ("mortgage_insurance_type", "float64"),
-        ("relocation_mortgage_indicator", "category")
-    ])
-    
-    print(acquisition_path)
-    
-    return cudf.read_csv(acquisition_path, names=cols, delimiter='|', dtype=list(dtypes.values()), skiprows=1)
-
-def gpu_load_names(**kwargs):
-    """ Loads names used for renaming the banks
-    
-    Returns
-    -------
-    GPU DataFrame
-    """
-
-    cols = [
-        'seller_name', 'new'
-    ]
-    
-    dtypes = OrderedDict([
-        ("seller_name", "category"),
-        ("new", "category"),
-    ])
-
-    return cudf.read_csv(col_names_path, names=cols, delimiter='|', dtype=list(dtypes.values()), skiprows=1)
-
-def create_ever_features(gdf, **kwargs):
-    everdf = gdf[['loan_id', 'current_loan_delinquency_status']]
-    everdf = everdf.groupby('loan_id', method='hash').max()
-    del(gdf)
-    everdf['ever_30'] = (everdf['max_current_loan_delinquency_status'] >= 1).astype('int8')
-    everdf['ever_90'] = (everdf['max_current_loan_delinquency_status'] >= 3).astype('int8')
-    everdf['ever_180'] = (everdf['max_current_loan_delinquency_status'] >= 6).astype('int8')
-    everdf.drop_column('max_current_loan_delinquency_status')
-    return everdf
-
-def create_delinq_features(gdf, **kwargs):
-    delinq_gdf = gdf[['loan_id', 'monthly_reporting_period', 'current_loan_delinquency_status']]
-    del(gdf)
-    delinq_30 = delinq_gdf.query('current_loan_delinquency_status >= 1')[['loan_id', 'monthly_reporting_period']].groupby('loan_id', method='hash').min()
-    delinq_30['delinquency_30'] = delinq_30['min_monthly_reporting_period']
-    delinq_30.drop_column('min_monthly_reporting_period')
-    delinq_90 = delinq_gdf.query('current_loan_delinquency_status >= 3')[['loan_id', 'monthly_reporting_period']].groupby('loan_id', method='hash').min()
-    delinq_90['delinquency_90'] = delinq_90['min_monthly_reporting_period']
-    delinq_90.drop_column('min_monthly_reporting_period')
-    delinq_180 = delinq_gdf.query('current_loan_delinquency_status >= 6')[['loan_id', 'monthly_reporting_period']].groupby('loan_id', method='hash').min()
-    delinq_180['delinquency_180'] = delinq_180['min_monthly_reporting_period']
-    delinq_180.drop_column('min_monthly_reporting_period')
-    del(delinq_gdf)
-    delinq_merge = delinq_30.merge(delinq_90, how='left', on=['loan_id'], type='hash')
-    delinq_merge['delinquency_90'] = delinq_merge['delinquency_90'].fillna(np.dtype('datetime64[ms]').type('1970-01-01').astype('datetime64[ms]'))
-    delinq_merge = delinq_merge.merge(delinq_180, how='left', on=['loan_id'], type='hash')
-    delinq_merge['delinquency_180'] = delinq_merge['delinquency_180'].fillna(np.dtype('datetime64[ms]').type('1970-01-01').astype('datetime64[ms]'))
-    del(delinq_30)
-    del(delinq_90)
-    del(delinq_180)
-    return delinq_merge
-
-def join_ever_delinq_features(everdf_tmp, delinq_merge, **kwargs):
-    everdf = everdf_tmp.merge(delinq_merge, on=['loan_id'], how='left', type='hash')
-    del(everdf_tmp)
-    del(delinq_merge)
-    everdf['delinquency_30'] = everdf['delinquency_30'].fillna(np.dtype('datetime64[ms]').type('1970-01-01').astype('datetime64[ms]'))
-    everdf['delinquency_90'] = everdf['delinquency_90'].fillna(np.dtype('datetime64[ms]').type('1970-01-01').astype('datetime64[ms]'))
-    everdf['delinquency_180'] = everdf['delinquency_180'].fillna(np.dtype('datetime64[ms]').type('1970-01-01').astype('datetime64[ms]'))
-    return everdf
-
-def create_joined_df(gdf, everdf, **kwargs):
-    test = gdf[['loan_id', 'monthly_reporting_period', 'current_loan_delinquency_status', 'current_actual_upb']]
-    del(gdf)
-    test['timestamp'] = test['monthly_reporting_period']
-    test.drop_column('monthly_reporting_period')
-    test['timestamp_month'] = test['timestamp'].dt.month
-    test['timestamp_year'] = test['timestamp'].dt.year
-    test['delinquency_12'] = test['current_loan_delinquency_status']
-    test.drop_column('current_loan_delinquency_status')
-    test['upb_12'] = test['current_actual_upb']
-    test.drop_column('current_actual_upb')
-    test['upb_12'] = test['upb_12'].fillna(999999999)
-    test['delinquency_12'] = test['delinquency_12'].fillna(-1)
-    
-    joined_df = test.merge(everdf, how='left', on=['loan_id'], type='hash')
-    del(everdf)
-    del(test)
-    
-    joined_df['ever_30'] = joined_df['ever_30'].fillna(-1)
-    joined_df['ever_90'] = joined_df['ever_90'].fillna(-1)
-    joined_df['ever_180'] = joined_df['ever_180'].fillna(-1)
-    joined_df['delinquency_30'] = joined_df['delinquency_30'].fillna(-1)
-    joined_df['delinquency_90'] = joined_df['delinquency_90'].fillna(-1)
-    joined_df['delinquency_180'] = joined_df['delinquency_180'].fillna(-1)
-    
-    joined_df['timestamp_year'] = joined_df['timestamp_year'].astype('int32')
-    joined_df['timestamp_month'] = joined_df['timestamp_month'].astype('int32')
-    
-    return joined_df
-
-def create_12_mon_features(joined_df, **kwargs):
-    testdfs = []
-    n_months = 12
-    for y in range(1, n_months + 1):
-        tmpdf = joined_df[['loan_id', 'timestamp_year', 'timestamp_month', 'delinquency_12', 'upb_12']]
-        tmpdf['josh_months'] = tmpdf['timestamp_year'] * 12 + tmpdf['timestamp_month']
-        tmpdf['josh_mody_n'] = ((tmpdf['josh_months'].astype('float64') - 24000 - y) / 12).floor()
-        tmpdf = tmpdf.groupby(['loan_id', 'josh_mody_n'], method='hash').agg({'delinquency_12': 'max','upb_12': 'min'})
-        tmpdf['delinquency_12'] = (tmpdf['max_delinquency_12']>3).astype('int32')
-        tmpdf['delinquency_12'] +=(tmpdf['min_upb_12']==0).astype('int32')
-        tmpdf.drop_column('max_delinquency_12')
-        tmpdf['upb_12'] = tmpdf['min_upb_12']
-        tmpdf.drop_column('min_upb_12')
-        tmpdf['timestamp_year'] = (((tmpdf['josh_mody_n'] * n_months) + 24000 + (y - 1)) / 12).floor().astype('int16')
-        tmpdf['timestamp_month'] = np.int8(y)
-        tmpdf.drop_column('josh_mody_n')
-        testdfs.append(tmpdf)
-        del(tmpdf)
-    del(joined_df)
-
-    return cudf.concat(testdfs)
-
-def combine_joined_12_mon(joined_df, testdf, **kwargs):
-    joined_df.drop_column('delinquency_12')
-    joined_df.drop_column('upb_12')
-    joined_df['timestamp_year'] = joined_df['timestamp_year'].astype('int16')
-    joined_df['timestamp_month'] = joined_df['timestamp_month'].astype('int8')
-    return joined_df.merge(testdf, how='left', on=['loan_id', 'timestamp_year', 'timestamp_month'], type='hash')
-
-def final_performance_delinquency(gdf, joined_df, **kwargs):
-    merged = null_workaround(gdf)
-    joined_df = null_workaround(joined_df)
-    merged['timestamp_month'] = merged['monthly_reporting_period'].dt.month
-    merged['timestamp_month'] = merged['timestamp_month'].astype('int8')
-    merged['timestamp_year'] = merged['monthly_reporting_period'].dt.year
-    merged['timestamp_year'] = merged['timestamp_year'].astype('int16')
-    merged = merged.merge(joined_df, how='left', on=['loan_id', 'timestamp_year', 'timestamp_month'], type='hash')
-    merged.drop_column('timestamp_year')
-    merged.drop_column('timestamp_month')
-    return merged
-
-def join_perf_acq_gdfs(perf, acq, **kwargs):
-    perf = null_workaround(perf)
-    acq = null_workaround(acq)
-    return perf.merge(acq, how='left', on=['loan_id'], type='hash')
-
-def last_mile_cleaning(df, **kwargs):
-    drop_list = [
-        'loan_id', 'orig_date', 'first_pay_date', 'seller_name',
-        'monthly_reporting_period', 'last_paid_installment_date', 'maturity_date', 'ever_30', 'ever_90', 'ever_180',
-        'delinquency_30', 'delinquency_90', 'delinquency_180', 'upb_12',
-        'zero_balance_effective_date','foreclosed_after', 'disposition_date','timestamp'
-    ]
-    for column in drop_list:
-        df.drop_column(column)
-    for col, dtype in df.dtypes.iteritems():
-        if str(dtype)=='category':
-            df[col] = df[col].cat.codes
-        df[col] = df[col].astype('float32')
-    df['delinquency_12'] = df['delinquency_12'] > 0
-    df['delinquency_12'] = df['delinquency_12'].fillna(False).astype('int32')
-    for column in df.columns:
-        df[column] = df[column].fillna(-1)
-    return df.to_arrow(index=False)
-
-
-# to download data for this notebook, visit https://rapidsai.github.io/demos/datasets/mortgage-data and update the following paths accordingly
-acq_data_path = "{0}/acq".format(data_dir) #"/rapids/data/mortgage/acq"
-perf_data_path = "{0}/perf".format(data_dir) #"/rapids/data/mortgage/perf"
-col_names_path = "{0}/names.csv".format(data_dir) # "/rapids/data/mortgage/names.csv"
-start_year = 2000
-#end_year = 2000 # end_year is inclusive -- converted to parameter
-#part_count = 2 # the number of data files to train against -- converted to parameter
-
-client.run(initialize_rmm_pool)
-
-# NOTE: The ETL calculates additional features which are then dropped before creating the XGBoost DMatrix.
-# This can be optimized to avoid calculating the dropped features.
-print("Reading ...")
-t1 = datetime.datetime.now()
-gpu_dfs = []
-gpu_time = 0
-quarter = 1
-year = start_year
-count = 0
-while year <= end_year:
-    for file in glob(os.path.join(perf_data_path + "/Performance_" + str(year) + "Q" + str(quarter) + "*")):
-        if count < part_count:
-            gpu_dfs.append(process_quarter_gpu(year=year, quarter=quarter, perf_file=file))
-            count += 1
-            print('file: {0}'.format(file))
-            print('count: {0}'.format(count))
-    quarter += 1
-    if quarter == 5:
-        year += 1
-        quarter = 1
-        
-wait(gpu_dfs)
-t2 = datetime.datetime.now()
-print("Reading time ...")
-print(t2-t1)
-print('len(gpu_dfs) is {0}'.format(len(gpu_dfs)))
-
-client.run(cudf._gdf.rmm_finalize)
-client.run(initialize_rmm_no_pool)
-
-dxgb_gpu_params = {
-    'nround':            100,
-    'max_depth':         8,
-    'max_leaves':        2**8,
-    'alpha':             0.9,
-    'eta':               0.1,
-    'gamma':             0.1,
-    'learning_rate':     0.1,
-    'subsample':         1,
-    'reg_lambda':        1,
-    'scale_pos_weight':  2,
-    'min_child_weight':  30,
-    'tree_method':       'gpu_hist',
-    'n_gpus':            1, 
-    'distributed_dask':  True,
-    'loss':              'ls',
-    'objective':         'gpu:reg:linear',
-    'max_features':      'auto',
-    'criterion':         'friedman_mse',
-    'grow_policy':       'lossguide',
-    'verbose':           True
-}
-  
-if cpu_predictor:
-    print('Training using CPUs')
-    dxgb_gpu_params['predictor'] = 'cpu_predictor'
-    dxgb_gpu_params['tree_method'] = 'hist'
-    dxgb_gpu_params['objective'] = 'reg:linear'
-    
-else:
-    print('Training using GPUs')
-
-print('Training parameters are {0}'.format(dxgb_gpu_params))
-
-gpu_dfs = [delayed(DataFrame.from_arrow)(gpu_df) for gpu_df in gpu_dfs[:part_count]]
-    
-gpu_dfs = [gpu_df for gpu_df in gpu_dfs]
-
-wait(gpu_dfs)
-tmp_map = [(gpu_df, list(client.who_has(gpu_df).values())[0]) for gpu_df in gpu_dfs]
-new_map = {}
-for key, value in tmp_map:
-    if value not in new_map:
-        new_map[value] = [key]
-    else:
-        new_map[value].append(key)
-
-del(tmp_map)
-gpu_dfs = []
-for list_delayed in new_map.values():
-    gpu_dfs.append(delayed(cudf.concat)(list_delayed))
-
-del(new_map)
-gpu_dfs = [(gpu_df[['delinquency_12']], gpu_df[delayed(list)(gpu_df.columns.difference(['delinquency_12']))]) for gpu_df in gpu_dfs]
-gpu_dfs = [(gpu_df[0].persist(), gpu_df[1].persist()) for gpu_df in gpu_dfs]
-gpu_dfs = [dask.delayed(xgb.DMatrix)(gpu_df[1], gpu_df[0]) for gpu_df in gpu_dfs]
-gpu_dfs = [gpu_df.persist() for gpu_df in gpu_dfs]
-
-gc.collect()
-labels = None
-
-print('str(gpu_dfs) is {0}'.format(str(gpu_dfs)))
-
-wait(gpu_dfs)
-t1 = datetime.datetime.now()
-bst = dxgb_gpu.train(client, dxgb_gpu_params, gpu_dfs, labels, num_boost_round=dxgb_gpu_params['nround'])
-t2 = datetime.datetime.now()
-print("Training time ...")
-print(t2-t1)
-print('str(bst) is {0}'.format(str(bst)))
-print('Exiting script')

how-to-use-azureml/README.md

@@ -4,13 +4,13 @@ Learn how to use Azure Machine Learning services for experimentation and model m
 
 As a pre-requisite, run the [configuration Notebook](../configuration.ipynb) notebook first to set up your Azure ML Workspace. Then, run the notebooks in following recommended order.
 
- * [train-within-notebook](./training/train-within-notebook): Train a model hile tracking run history, and learn how to deploy the model as web service to Azure Container Instance.
- * [train-on-local](./training/train-on-local): Learn how to submit a run and use Azure ML managed run configuration.
-* [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.
-* [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.
+ * [train-within-notebook](train-within-notebook/train-within-notebook.ipynb): Train a model hile tracking run history, and learn how to deploy the model as web service to Azure Container Instance.
+ * [train-on-local](train-on-local/train-on-local.ipynb): Learn how to submit a run and use Azure ML managed run configuration.
+* [train-on-aci](train-on-aci/train-on-aci.ipynb): Submit a remote run on serverless Docker-based compute.
+* [train-on-remote-vm](train-on-remote-vm/train-on-remote-vm.ipynb): Use Data Science Virtual Machine as a target for remote runs.
+* [logging-api](logging-api/logging-api.ipynb): Learn about the details of logging metrics to run history.
+* [register-model-create-image-deploy-service](register-model-create-image-deploy-service/register-model-create-image-deploy-service.ipynb): Learn about the details of model management.
+* [production-deploy-to-aks](production-deploy-to-aks/production-deploy-to-aks.ipynb) Deploy a model to production at scale on Azure Kubernetes Service.
+* [enable-data-collection-for-models-in-aks](enable-data-collection-for-models-in-aks/enable-data-collection-for-models-in-aks.ipynb) Learn about data collection APIs for deployed model.
+* [enable-app-insights-in-production-service](enable-app-insights-in-production-serviceenable-app-insights-in-production-service.ipynb) Learn how to use App Insights with production web service.
  
-Find quickstarts, end-to-end tutorials, and how-tos on the [official documentation site for Azure Machine Learning service](https://docs.microsoft.com/en-us/azure/machine-learning/service/).

how-to-use-azureml/automated-machine-learning/01.auto-ml-classification.ipynb

@@ -0,0 +1,414 @@
+{
+ "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": [
+    "# AutoML 01: Classification with Local Compute\n",
+    "\n",
+    "In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset) to showcase how you can use AutoML for a simple classification problem.\n",
+    "\n",
+    "Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
+    "\n",
+    "In this notebook you will learn how to:\n",
+    "1. Create an `Experiment` in an existing `Workspace`.\n",
+    "2. Configure AutoML using `AutoMLConfig`.\n",
+    "3. Train the model using local compute.\n",
+    "4. Explore the results.\n",
+    "5. Test the best fitted model.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create an Experiment\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 random\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn import datasets\n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# Choose a name for the experiment and specify the project folder.\n",
+    "experiment_name = 'automl-local-classification'\n",
+    "project_folder = './sample_projects/automl-local-classification'\n",
+    "\n",
+    "experiment = Experiment(ws, experiment_name)\n",
+    "\n",
+    "output = {}\n",
+    "output['SDK version'] = azureml.core.VERSION\n",
+    "output['Subscription ID'] = ws.subscription_id\n",
+    "output['Workspace Name'] = ws.name\n",
+    "output['Resource Group'] = ws.resource_group\n",
+    "output['Location'] = ws.location\n",
+    "output['Project Directory'] = project_folder\n",
+    "output['Experiment Name'] = experiment.name\n",
+    "pd.set_option('display.max_colwidth', -1)\n",
+    "pd.DataFrame(data = output, index = ['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Load Training Data\n",
+    "\n",
+    "This uses scikit-learn's [load_digits](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) method."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn import datasets\n",
+    "\n",
+    "digits = datasets.load_digits()\n",
+    "\n",
+    "# Exclude the first 100 rows from training so that they can be used for test.\n",
+    "X_train = digits.data[100:,:]\n",
+    "y_train = digits.target[100:]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Configure AutoML\n",
+    "\n",
+    "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
+    "\n",
+    "|Property|Description|\n",
+    "|-|-|\n",
+    "|**task**|classification or regression|\n",
+    "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
+    "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+    "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
+    "|**n_cross_validations**|Number of cross validation splits.|\n",
+    "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+    "|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\n",
+    "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_config = AutoMLConfig(task = 'classification',\n",
+    "                             debug_log = 'automl_errors.log',\n",
+    "                             primary_metric = 'AUC_weighted',\n",
+    "                             iteration_timeout_minutes = 60,\n",
+    "                             iterations = 25,\n",
+    "                             n_cross_validations = 3,\n",
+    "                             verbosity = logging.INFO,\n",
+    "                             X = X_train, \n",
+    "                             y = y_train,\n",
+    "                             path = project_folder)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Train the Models\n",
+    "\n",
+    "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
+    "In this example, we specify `show_output = True` to print currently running iterations to the console."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run = experiment.submit(automl_config, show_output = True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Optionally, you can continue an interrupted local run by calling `continue_experiment` without the `iterations` parameter, or run more iterations for a completed run by specifying the `iterations` parameter:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run = local_run.continue_experiment(X = X_train, \n",
+    "                                          y = y_train, \n",
+    "                                          show_output = True,\n",
+    "                                          iterations = 5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Explore the Results"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Widget for Monitoring Runs\n",
+    "\n",
+    "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+    "\n",
+    "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.widgets import RunDetails\n",
+    "RunDetails(local_run).show() "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\n",
+    "#### Retrieve All Child Runs\n",
+    "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "children = list(local_run.get_children())\n",
+    "metricslist = {}\n",
+    "for run in children:\n",
+    "    properties = run.get_properties()\n",
+    "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+    "    metricslist[int(properties['iteration'])] = metrics\n",
+    "\n",
+    "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+    "rundata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Retrieve the Best Model\n",
+    "\n",
+    "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_model = local_run.get_output()\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Best Model Based on Any Other Metric\n",
+    "Show the run and the model that has the smallest `log_loss` value:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lookup_metric = \"log_loss\"\n",
+    "best_run, fitted_model = local_run.get_output(metric = lookup_metric)\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Model from a Specific Iteration\n",
+    "Show the run and the model from the third iteration:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "iteration = 3\n",
+    "third_run, third_model = local_run.get_output(iteration = iteration)\n",
+    "print(third_run)\n",
+    "print(third_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Test the Best Fitted Model\n",
+    "\n",
+    "#### Load Test Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "digits = datasets.load_digits()\n",
+    "X_test = digits.data[:10, :]\n",
+    "y_test = digits.target[:10]\n",
+    "images = digits.images[:10]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Testing Our Best Fitted Model\n",
+    "We will try to predict 2 digits and see how our model works."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Randomly select digits and test.\n",
+    "for index in np.random.choice(len(y_test), 2, replace = False):\n",
+    "    print(index)\n",
+    "    predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
+    "    label = y_test[index]\n",
+    "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
+    "    fig = plt.figure(1, figsize = (3,3))\n",
+    "    ax1 = fig.add_axes((0,0,.8,.8))\n",
+    "    ax1.set_title(title)\n",
+    "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
+    "    plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "savitam"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3.6",
+   "language": "python",
+   "name": "python36"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/02.auto-ml-regression.ipynb

@@ -0,0 +1,415 @@
+{
+ "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": [
+    "# AutoML 02: Regression with Local Compute\n",
+    "\n",
+    "In this example we use the scikit-learn's [diabetes dataset](http://scikit-learn.org/stable/datasets/index.html#diabetes-dataset) to showcase how you can use AutoML for a simple regression problem.\n",
+    "\n",
+    "Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
+    "\n",
+    "In this notebook you will learn how to:\n",
+    "1. Create an `Experiment` in an existing `Workspace`.\n",
+    "2. Configure AutoML using `AutoMLConfig`.\n",
+    "3. Train the model using local compute.\n",
+    "4. Explore the results.\n",
+    "5. Test the best fitted model.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create an Experiment\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 random\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn import datasets\n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# Choose a name for the experiment and specify the project folder.\n",
+    "experiment_name = 'automl-local-regression'\n",
+    "project_folder = './sample_projects/automl-local-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",
+    "pd.DataFrame(data = output, index = ['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Load Training Data\n",
+    "This uses scikit-learn's [load_diabetes](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_diabetes.html) method."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load the diabetes dataset, a well-known built-in small dataset that comes with scikit-learn.\n",
+    "from sklearn.datasets import load_diabetes\n",
+    "from sklearn.linear_model import Ridge\n",
+    "from sklearn.metrics import mean_squared_error\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "\n",
+    "X, y = load_diabetes(return_X_y = True)\n",
+    "\n",
+    "columns = ['age', 'gender', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']\n",
+    "\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Configure AutoML\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, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\n",
+    "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_config = AutoMLConfig(task = 'regression',\n",
+    "                             iteration_timeout_minutes = 10,\n",
+    "                             iterations = 10,\n",
+    "                             primary_metric = 'spearman_correlation',\n",
+    "                             n_cross_validations = 5,\n",
+    "                             debug_log = 'automl.log',\n",
+    "                             verbosity = logging.INFO,\n",
+    "                             X = X_train, \n",
+    "                             y = y_train,\n",
+    "                             path = project_folder)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Train the Models\n",
+    "\n",
+    "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
+    "In this example, we specify `show_output = True` to print currently running iterations to the console."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run = experiment.submit(automl_config, show_output = True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Explore the Results"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Widget for Monitoring Runs\n",
+    "\n",
+    "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+    "\n",
+    "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.widgets import RunDetails\n",
+    "RunDetails(local_run).show() "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\n",
+    "#### Retrieve All Child Runs\n",
+    "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "children = list(local_run.get_children())\n",
+    "metricslist = {}\n",
+    "for run in children:\n",
+    "    properties = run.get_properties()\n",
+    "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+    "    metricslist[int(properties['iteration'])] = metrics\n",
+    "\n",
+    "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+    "rundata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Retrieve the Best Model\n",
+    "\n",
+    "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_model = local_run.get_output()\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Best Model Based on Any Other Metric\n",
+    "Show the run and the model that has the smallest `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 = local_run.get_output(metric = lookup_metric)\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Model from a Specific Iteration\n",
+    "Show the run and the model from the third iteration:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "iteration = 3\n",
+    "third_run, third_model = local_run.get_output(iteration = iteration)\n",
+    "print(third_run)\n",
+    "print(third_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Test the Best Fitted Model"
+   ]
+  },
+  {
+   "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": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib inline\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "from sklearn import datasets\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', bins = 10, histtype = 'step');\n",
+    "a0.hist(y_residual_train, orientation = 'horizontal', color = 'b', 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', bins = 10, histtype = 'step')\n",
+    "a1.hist(y_residual_test, orientation = 'horizontal', color = 'b', alpha = 0.2, bins = 10)\n",
+    "\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/03.auto-ml-remote-execution.ipynb

@@ -0,0 +1,507 @@
+{
+ "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": [
+    "# AutoML 03: Remote Execution using DSVM (Ubuntu)\n",
+    "\n",
+    "In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset) to showcase how you can use AutoML for a simple classification problem.\n",
+    "\n",
+    "Make sure you have executed the [00.configuration](00.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`\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create an Experiment\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 random\n",
+    "import time\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn import datasets\n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# Choose a name for the run history container in the workspace.\n",
+    "experiment_name = 'automl-remote-dsvm4'\n",
+    "project_folder = './sample_projects/automl-remote-dsvm4'\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",
+    "pd.DataFrame(data = output, index = ['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics = True)"
+   ]
+  },
+  {
+   "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_D2_v2\")\n",
+    "    dsvm_compute = DsvmCompute.create(ws, name = dsvm_name, provisioning_configuration = dsvm_config)\n",
+    "    dsvm_compute.wait_for_completion(show_output = True)\n",
+    "    print(\"Waiting one minute for ssh to be accessible\")\n",
+    "    time.sleep(60) # Wait for ssh to be accessible"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.runconfig import RunConfiguration\n",
+    "from azureml.core.conda_dependencies import CondaDependencies\n",
+    "\n",
+    "# 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",
+    "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": [
+    "## 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",
+    "In this example, the `get_data()` function returns data using scikit-learn's [load_digits](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) method."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "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",
+    "from sklearn import datasets\n",
+    "from scipy import sparse\n",
+    "import numpy as np\n",
+    "\n",
+    "def get_data():\n",
+    "    \n",
+    "    digits = datasets.load_digits()\n",
+    "    X_train = digits.data[100:,:]\n",
+    "    y_train = digits.target[100:]\n",
+    "\n",
+    "    return { \"X\" : X_train, \"y\" : y_train }"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Configure AutoML <a class=\"anchor\" id=\"Instantiate-AutoML-Remote-DSVM\"></a>\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": [
+    "## Train the Models\n",
+    "\n",
+    "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": "markdown",
+   "metadata": {},
+   "source": [
+    "## Explore the 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 the Best Fitted Model <a class=\"anchor\" id=\"Testing-the-Fitted-Model-Remote-DSVM\"></a>\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/03b.auto-ml-remote-batchai.ipynb

@@ -0,0 +1,528 @@
+{
+ "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": [
+    "# AutoML 03: Remote Execution using Batch AI\n",
+    "\n",
+    "In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset) to showcase how you can use AutoML for a simple classification problem.\n",
+    "\n",
+    "Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
+    "\n",
+    "In this notebook you would see\n",
+    "1. Create an `Experiment` in an existing `Workspace`.\n",
+    "2. Attach an existing Batch AI compute to a workspace.\n",
+    "3. Configure AutoML using `AutoMLConfig`.\n",
+    "4. Train the model using Batch AI.\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`\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create an Experiment\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 random\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn import datasets\n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# Choose a name for the run history container in the workspace.\n",
+    "experiment_name = 'automl-remote-batchai'\n",
+    "project_folder = './sample_projects/automl-remote-batchai'\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",
+    "pd.DataFrame(data = output, index = ['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create Batch AI Cluster\n",
+    "The cluster is created as Machine Learning Compute and will appear under your workspace.\n",
+    "\n",
+    "**Note:** The creation of the Batch AI cluster can take over 10 minutes, please be patient.\n",
+    "\n",
+    "As with other Azure services, there are limits on certain resources (e.g. Batch AI cluster size) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.compute import AmlCompute\n",
+    "from azureml.core.compute import ComputeTarget\n",
+    "\n",
+    "# Choose a name for your cluster.\n",
+    "batchai_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 batchai_cluster_name in cts and cts[batchai_cluster_name].type == 'BatchAI':\n",
+    "    found = True\n",
+    "    print('Found existing compute target.')\n",
+    "    compute_target = cts[batchai_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, batchai_cluster_name, provisioning_config)\n",
+    "    \n",
+    "    # Can poll for a minimum number of nodes and for a specific timeout.\n",
+    "    # If no min_node_count is provided, it will use the scale settings for the cluster.\n",
+    "    compute_target.wait_for_completion(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
+    "    \n",
+    "     # For a more detailed view of current Batch AI cluster status, use the 'status' property."
+   ]
+  },
+  {
+   "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 Batch AI cluster\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",
+    "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": [
+    "## 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",
+    "In this example, the `get_data()` function returns data using scikit-learn's [load_digits](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) method."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "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",
+    "from sklearn import datasets\n",
+    "from scipy import sparse\n",
+    "import numpy as np\n",
+    "\n",
+    "def get_data():\n",
+    "    \n",
+    "    digits = datasets.load_digits()\n",
+    "    X_train = digits.data\n",
+    "    y_train = digits.target\n",
+    "\n",
+    "    return { \"X\" : X_train, \"y\" : y_train }"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiate AutoML <a class=\"anchor\" id=\"Instatiate-AutoML-Remote-DSVM\"></a>\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 Batch AI, 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.|"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_settings = {\n",
+    "    \"iteration_timeout_minutes\": 2,\n",
+    "    \"iterations\": 20,\n",
+    "    \"n_cross_validations\": 5,\n",
+    "    \"primary_metric\": 'AUC_weighted',\n",
+    "    \"preprocess\": False,\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",
+    "                             data_script = project_folder + \"/get_data.py\",\n",
+    "                             **automl_settings\n",
+    "                            )\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Train the Models\n",
+    "\n",
+    "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",
+    "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": "markdown",
+   "metadata": {},
+   "source": [
+    "## Explore the 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_5db13491-c92a-4f1d-b622-8ab8d973a058')"
+   ]
+  },
+  {
+   "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": [
+    "remote_run"
+   ]
+  },
+  {
+   "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": [
+    "### Testing the Fitted Model <a class=\"anchor\" id=\"Testing-the-Fitted-Model-Remote-DSVM\"></a>\n",
+    "\n",
+    "#### Load Test Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "digits = datasets.load_digits()\n",
+    "X_test = digits.data[:10, :]\n",
+    "y_test = digits.target[:10]\n",
+    "images = digits.images[:10]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Testing Our Best Fitted Model"
+   ]
+  },
+  {
+   "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/04.auto-ml-remote-execution-text-data-blob-store.ipynb

@@ -0,0 +1,539 @@
+{
+ "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": [
+    "# Auto ML 04: Remote Execution with Text Data from Azure Blob Storage\n",
+    "\n",
+    "In this example we use the [Burning Man 2016 dataset](https://innovate.burningman.org/datasets-page/) to showcase how you can use AutoML to handle text data from Azure Blob Storage.\n",
+    "\n",
+    "Make sure you have executed the [00.configuration](00.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. 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\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create an Experiment\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 random\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn import datasets\n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# Choose a name for the run history container in the workspace.\n",
+    "experiment_name = 'automl-remote-dsvm-blobstore'\n",
+    "project_folder = './sample_projects/automl-remote-dsvm-blobstore'\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",
+    "pd.DataFrame(data=output, index=['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics = True)"
+   ]
+  },
+  {
+   "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 [quick instructions](https://docs.microsoft.com/en-us/azure/machine-learning/desktop-workbench/how-to-create-dsvm-hdi). 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://render.githubusercontent.com/documentation/sdk/ssh-issue.md) 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",
+    "\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",
+    "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": [
+    "## 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",
+    "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 pandas as pd\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "\n",
+    "def get_data():\n",
+    "    # Load Burning Man 2016 data.\n",
+    "    df = pd.read_csv(\"https://automldemods.blob.core.windows.net/datasets/PlayaEvents2016,_1.6MB,_3.4k-rows.cleaned.2.tsv\",\n",
+    "                     delimiter=\"\\t\", quotechar='\"')\n",
+    "    # Get integer labels.\n",
+    "    le = LabelEncoder()\n",
+    "    le.fit(df[\"Label\"].values)\n",
+    "    y = le.transform(df[\"Label\"].values)\n",
+    "    X = df.drop([\"Label\"], axis=1)\n",
+    "\n",
+    "    X_train, _, y_train, _ = train_test_split(X, y, test_size = 0.1, random_state = 42)\n",
+    "\n",
+    "    return { \"X\" : X_train, \"y\" : y_train }"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### View data\n",
+    "\n",
+    "You can execute the `get_data()` function locally to view the training data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%run  $project_folder/get_data.py\n",
+    "data_dict = get_data()\n",
+    "df = data_dict[\"X\"]\n",
+    "y = data_dict[\"y\"]\n",
+    "pd.set_option('display.max_colwidth', 15)\n",
+    "df['Label'] = pd.Series(y, index=df.index)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Configure AutoML <a class=\"anchor\" id=\"Instatiate-AutoML-Remote-DSVM\"></a>\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": [
+    "## Train the Models <a class=\"anchor\" id=\"Training-the-model-Remote-DSVM\"></a>\n",
+    "\n",
+    "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": "markdown",
+   "metadata": {},
+   "source": [
+    "## Exploring the Results <a class=\"anchor\" id=\"Exploring-the-Results-Remote-DSVM\"></a>\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": [
+    "#### 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": [
+    "### Testing the Fitted Model <a class=\"anchor\" id=\"Testing-the-Fitted-Model-Remote-DSVM\"></a>\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sklearn\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "from pandas_ml import ConfusionMatrix\n",
+    "\n",
+    "df = pd.read_csv(\"https://automldemods.blob.core.windows.net/datasets/PlayaEvents2016,_1.6MB,_3.4k-rows.cleaned.2.tsv\",\n",
+    "                     delimiter=\"\\t\", quotechar='\"')\n",
+    "\n",
+    "# get integer labels\n",
+    "le = LabelEncoder()\n",
+    "le.fit(df[\"Label\"].values)\n",
+    "y = le.transform(df[\"Label\"].values)\n",
+    "X = df.drop([\"Label\"], axis=1)\n",
+    "\n",
+    "_, X_test, _, y_test = train_test_split(X, y, test_size=0.1, random_state=42)\n",
+    "\n",
+    "\n",
+    "ypred = fitted_model.predict(X_test.values)\n",
+    "\n",
+    "\n",
+    "ypred_strings = le.inverse_transform(ypred)\n",
+    "ytest_strings = le.inverse_transform(y_test)\n",
+    "\n",
+    "cm = ConfusionMatrix(ytest_strings, ypred_strings)\n",
+    "\n",
+    "print(cm)\n",
+    "\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/05.auto-ml-missing-data-Blacklist-Early-Termination.ipynb

@@ -0,0 +1,381 @@
+{
+ "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": [
+    "# AutoML 05: Blacklisting Models, Early Termination, and Handling Missing Data\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 handling missing values in data. We also provide a stopping metric indicating a target for the primary metrics so that AutoML can terminate the run without necessarly going through all the iterations. Finally, if you want to avoid a certain pipeline, we allow you to specify a blacklist of algorithms that AutoML will ignore for this run.\n",
+    "\n",
+    "Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
+    "\n",
+    "In this notebook you will learn how to:\n",
+    "1. Create an `Experiment` in an existing `Workspace`.\n",
+    "2. Configure AutoML using `AutoMLConfig`.\n",
+    "4. Train the model.\n",
+    "5. Explore the results.\n",
+    "6. Test the best fitted model.\n",
+    "\n",
+    "In addition this notebook showcases the following features\n",
+    "- **Blacklisting** certain pipelines\n",
+    "- Specifying **target metrics** to indicate stopping criteria\n",
+    "- Handling **missing data** in the input\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create an Experiment\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 random\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn import datasets\n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# Choose a name for the experiment.\n",
+    "experiment_name = 'automl-local-missing-data'\n",
+    "project_folder = './sample_projects/automl-local-missing-data'\n",
+    "\n",
+    "experiment = Experiment(ws, experiment_name)\n",
+    "\n",
+    "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",
+    "pd.DataFrame(data=output, index=['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Creating missing data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from scipy import sparse\n",
+    "\n",
+    "digits = datasets.load_digits()\n",
+    "X_train = digits.data[10:,:]\n",
+    "y_train = digits.target[10:]\n",
+    "\n",
+    "# Add missing values in 75% of the lines.\n",
+    "missing_rate = 0.75\n",
+    "n_missing_samples = int(np.floor(X_train.shape[0] * missing_rate))\n",
+    "missing_samples = np.hstack((np.zeros(X_train.shape[0] - n_missing_samples, dtype=np.bool), np.ones(n_missing_samples, dtype=np.bool)))\n",
+    "rng = np.random.RandomState(0)\n",
+    "rng.shuffle(missing_samples)\n",
+    "missing_features = rng.randint(0, X_train.shape[1], n_missing_samples)\n",
+    "X_train[np.where(missing_samples)[0], missing_features] = np.nan"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.DataFrame(data = X_train)\n",
+    "df['Label'] = pd.Series(y_train, index=df.index)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Configure AutoML\n",
+    "\n",
+    "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.  This includes setting `experiment_exit_score`, which should cause the run to complete before the `iterations` count is reached.\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",
+    "|**preprocess**|Setting this to *True* enables AutoML to perform preprocessing on the input to handle *missing data*, and to perform some common *feature extraction*.|\n",
+    "|**experiment_exit_score**|*double* value indicating the target for *primary_metric*. <br>Once the target is surpassed the run terminates.|\n",
+    "|**blacklist_models**|*List* of *strings* indicating machine learning algorithms for AutoML to avoid in this run.<br><br> Allowed values for **Classification**<br><i>LogisticRegression</i><br><i>SGD</i><br><i>MultinomialNaiveBayes</i><br><i>BernoulliNaiveBayes</i><br><i>SVM</i><br><i>LinearSVM</i><br><i>KNN</i><br><i>DecisionTree</i><br><i>RandomForest</i><br><i>ExtremeRandomTrees</i><br><i>LightGBM</i><br><i>GradientBoosting</i><br><i>TensorFlowDNN</i><br><i>TensorFlowLinearClassifier</i><br><br>Allowed values for **Regression**<br><i>ElasticNet</i><br><i>GradientBoosting</i><br><i>DecisionTree</i><br><i>KNN</i><br><i>LassoLars</i><br><i>SGD</i><br><i>RandomForest</i><br><i>ExtremeRandomTrees</i><br><i>LightGBM</i><br><i>TensorFlowLinearRegressor</i><br><i>TensorFlowDNN</i>|\n",
+    "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+    "|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification.  This should be an array of integers.|\n",
+    "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_config = AutoMLConfig(task = 'classification',\n",
+    "                             debug_log = 'automl_errors.log',\n",
+    "                             primary_metric = 'AUC_weighted',\n",
+    "                             iteration_timeout_minutes = 60,\n",
+    "                             iterations = 20,\n",
+    "                             n_cross_validations = 5,\n",
+    "                             preprocess = True,\n",
+    "                             experiment_exit_score = 0.9984,\n",
+    "                             blacklist_models = ['KNN','LinearSVM'],\n",
+    "                             verbosity = logging.INFO,\n",
+    "                             X = X_train, \n",
+    "                             y = y_train,\n",
+    "                             path = project_folder)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Train the Models\n",
+    "\n",
+    "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
+    "In this example, we specify `show_output = True` to print currently running iterations to the console."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run = experiment.submit(automl_config, show_output = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Explore the Results"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Widget for Monitoring Runs\n",
+    "\n",
+    "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+    "\n",
+    "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.widgets import RunDetails\n",
+    "RunDetails(local_run).show() "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\n",
+    "#### Retrieve All Child Runs\n",
+    "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "children = list(local_run.get_children())\n",
+    "metricslist = {}\n",
+    "for run in children:\n",
+    "    properties = run.get_properties()\n",
+    "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+    "    metricslist[int(properties['iteration'])] = metrics\n",
+    "\n",
+    "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+    "rundata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Retrieve the Best Model\n",
+    "\n",
+    "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_model = local_run.get_output()"
+   ]
+  },
+  {
+   "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 = local_run.get_output(metric = lookup_metric)"
+   ]
+  },
+  {
+   "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",
+    "# best_run, fitted_model = local_run.get_output(iteration = iteration)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Testing the best Fitted Model"
+   ]
+  },
+  {
+   "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]\n",
+    "\n",
+    "# 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()\n"
+   ]
+  }
+ ],
+ "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/06.auto-ml-sparse-data-train-test-split.ipynb

@@ -0,0 +1,384 @@
+{
+ "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": [
+    "# AutoML 06: Train Test Split and Handling Sparse Data\n",
+    "\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 for handling sparse data and how to specify custom cross validations splits.\n",
+    "\n",
+    "Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
+    "\n",
+    "In this notebook you will learn how to:\n",
+    "1. Create an `Experiment` in an existing `Workspace`.\n",
+    "2. Configure AutoML using `AutoMLConfig`.\n",
+    "4. Train the model.\n",
+    "5. Explore the results.\n",
+    "6. Test the best fitted model.\n",
+    "\n",
+    "In addition this notebook showcases the following features\n",
+    "- Explicit train test splits \n",
+    "- Handling **sparse data** in the input"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create an Experiment\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 random\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn import datasets\n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# choose a name for the experiment\n",
+    "experiment_name = 'automl-local-missing-data'\n",
+    "# project folder\n",
+    "project_folder = './sample_projects/automl-local-missing-data'\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",
+    "pd.DataFrame(data=output, index=['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Creating Sparse Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.datasets import fetch_20newsgroups\n",
+    "from sklearn.feature_extraction.text import HashingVectorizer\n",
+    "from sklearn.model_selection import train_test_split\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",
+    "X_train, X_valid, y_train, y_valid = train_test_split(data_train.data, data_train.target, test_size = 0.33, random_state = 42)\n",
+    "\n",
+    "\n",
+    "vectorizer = HashingVectorizer(stop_words = 'english', alternate_sign = False,\n",
+    "                               n_features = 2**16)\n",
+    "X_train = vectorizer.transform(X_train)\n",
+    "X_valid = vectorizer.transform(X_valid)\n",
+    "\n",
+    "summary_df = pd.DataFrame(index = ['No of Samples', 'No of Features'])\n",
+    "summary_df['Train Set'] = [X_train.shape[0], X_train.shape[1]]\n",
+    "summary_df['Validation Set'] = [X_valid.shape[0], X_valid.shape[1]]\n",
+    "summary_df"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Configure AutoML\n",
+    "\n",
+    "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
+    "\n",
+    "|Property|Description|\n",
+    "|-|-|\n",
+    "|**task**|classification or regression|\n",
+    "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
+    "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+    "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
+    "|**preprocess**|Setting this to *True* enables AutoML to perform preprocessing on the input to handle *missing data*, and to perform some common *feature extraction*.<br>**Note:** If input data is sparse, you cannot use *True*.|\n",
+    "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+    "|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\n",
+    "|**X_valid**|(sparse) array-like, shape = [n_samples, n_features] for the custom validation set.|\n",
+    "|**y_valid**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification for the custom validation set.|\n",
+    "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_config = AutoMLConfig(task = 'classification',\n",
+    "                             debug_log = 'automl_errors.log',\n",
+    "                             primary_metric = 'AUC_weighted',\n",
+    "                             iteration_timeout_minutes = 60,\n",
+    "                             iterations = 5,\n",
+    "                             preprocess = False,\n",
+    "                             verbosity = logging.INFO,\n",
+    "                             X = X_train, \n",
+    "                             y = y_train,\n",
+    "                             X_valid = X_valid, \n",
+    "                             y_valid = y_valid, \n",
+    "                             path = project_folder)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Train the Models\n",
+    "\n",
+    "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
+    "In this example, we specify `show_output = True` to print currently running iterations to the console."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run = experiment.submit(automl_config, show_output=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Explore the Results"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Widget for Monitoring Runs\n",
+    "\n",
+    "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+    "\n",
+    "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.widgets import RunDetails\n",
+    "RunDetails(local_run).show() "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\n",
+    "#### Retrieve All Child Runs\n",
+    "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "children = list(local_run.get_children())\n",
+    "metricslist = {}\n",
+    "for run in children:\n",
+    "    properties = run.get_properties()\n",
+    "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+    "    metricslist[int(properties['iteration'])] = metrics\n",
+    "    \n",
+    "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+    "rundata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Retrieve the Best Model\n",
+    "\n",
+    "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_model = local_run.get_output()"
+   ]
+  },
+  {
+   "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 = local_run.get_output(metric = lookup_metric)"
+   ]
+  },
+  {
+   "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",
+    "# best_run, fitted_model = local_run.get_output(iteration = iteration)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Testing the Best Fitted Model"
+   ]
+  },
+  {
+   "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 = vectorizer.transform(data_test.data)\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/07.auto-ml-exploring-previous-runs.ipynb

@@ -0,0 +1,336 @@
+{
+ "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": [
+    "# AutoML 07: Exploring Previous Runs\n",
+    "\n",
+    "In this example we present some examples on navigating previously executed runs. We also show how you can download a fitted model for any previous run.\n",
+    "\n",
+    "Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
+    "\n",
+    "In this notebook you will learn how to:\n",
+    "1. List all experiments in a workspace.\n",
+    "2. List all AutoML runs in an experiment.\n",
+    "3. Get details for an AutoML run, including settings, run widget, and all metrics.\n",
+    "4. Download a fitted pipeline for any iteration.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# List all AutoML Experiments in a Workspace"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import logging\n",
+    "import os\n",
+    "import random\n",
+    "import re\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\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.run import Run\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "experiment_list = Experiment.list(workspace=ws)\n",
+    "\n",
+    "summary_df = pd.DataFrame(index = ['No of Runs'])\n",
+    "pattern = re.compile('^AutoML_[^_]*$')\n",
+    "for experiment in experiment_list:\n",
+    "    all_runs = list(experiment.get_runs())\n",
+    "    automl_runs = []\n",
+    "    for run in all_runs:\n",
+    "        if(pattern.match(run.id)):\n",
+    "            automl_runs.append(run)    \n",
+    "    summary_df[experiment.name] = [len(automl_runs)]\n",
+    "    \n",
+    "pd.set_option('display.max_colwidth', -1)\n",
+    "summary_df.T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# List AutoML runs for an experiment\n",
+    "Set `experiment_name` to any experiment name from the result of the Experiment.list cell to load the AutoML runs."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "experiment_name = 'automl-local-classification' # Replace this with any project name from previous cell.\n",
+    "\n",
+    "proj = ws.experiments[experiment_name]\n",
+    "summary_df = pd.DataFrame(index = ['Type', 'Status', 'Primary Metric', 'Iterations', 'Compute', 'Name'])\n",
+    "pattern = re.compile('^AutoML_[^_]*$')\n",
+    "all_runs = list(proj.get_runs(properties={'azureml.runsource': 'automl'}))\n",
+    "automl_runs_project = []\n",
+    "for run in all_runs:\n",
+    "    if(pattern.match(run.id)):\n",
+    "        properties = run.get_properties()\n",
+    "        tags = run.get_tags()\n",
+    "        amlsettings = eval(properties['RawAMLSettingsString'])\n",
+    "        if 'iterations' in tags:\n",
+    "            iterations = tags['iterations']\n",
+    "        else:\n",
+    "            iterations = properties['num_iterations']\n",
+    "        summary_df[run.id] = [amlsettings['task_type'], run.get_details()['status'], properties['primary_metric'], iterations, properties['target'], amlsettings['name']]\n",
+    "        if run.get_details()['status'] == 'Completed':\n",
+    "            automl_runs_project.append(run.id)\n",
+    "    \n",
+    "from IPython.display import HTML\n",
+    "projname_html = HTML(\"<h3>{}</h3>\".format(proj.name))\n",
+    "\n",
+    "from IPython.display import display\n",
+    "display(projname_html)\n",
+    "display(summary_df.T)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Get details for an AutoML run\n",
+    "\n",
+    "Copy the project name and run id from the previous cell output to find more details on a particular run."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "run_id = automl_runs_project[0]  # Replace with your own run_id from above run ids\n",
+    "assert (run_id in summary_df.keys()), \"Run id not found! Please set run id to a value from above run ids\"\n",
+    "\n",
+    "from azureml.widgets import RunDetails\n",
+    "\n",
+    "experiment = Experiment(ws, experiment_name)\n",
+    "ml_run = AutoMLRun(experiment = experiment, run_id = run_id)\n",
+    "\n",
+    "summary_df = pd.DataFrame(index = ['Type', 'Status', 'Primary Metric', 'Iterations', 'Compute', 'Name', 'Start Time', 'End Time'])\n",
+    "properties = ml_run.get_properties()\n",
+    "tags = ml_run.get_tags()\n",
+    "status = ml_run.get_details()\n",
+    "amlsettings = eval(properties['RawAMLSettingsString'])\n",
+    "if 'iterations' in tags:\n",
+    "    iterations = tags['iterations']\n",
+    "else:\n",
+    "    iterations = properties['num_iterations']\n",
+    "start_time = None\n",
+    "if 'startTimeUtc' in status:\n",
+    "    start_time = status['startTimeUtc']\n",
+    "end_time = None\n",
+    "if 'endTimeUtc' in status:\n",
+    "    end_time = status['endTimeUtc']\n",
+    "summary_df[ml_run.id] = [amlsettings['task_type'], status['status'], properties['primary_metric'], iterations, properties['target'], amlsettings['name'], start_time, end_time]\n",
+    "display(HTML('<h3>Runtime Details</h3>'))\n",
+    "display(summary_df)\n",
+    "\n",
+    "#settings_df = pd.DataFrame(data = amlsettings, index = [''])\n",
+    "display(HTML('<h3>AutoML Settings</h3>'))\n",
+    "display(amlsettings)\n",
+    "\n",
+    "display(HTML('<h3>Iterations</h3>'))\n",
+    "RunDetails(ml_run).show() \n",
+    "\n",
+    "children = list(ml_run.get_children())\n",
+    "metricslist = {}\n",
+    "for run in children:\n",
+    "    properties = run.get_properties()\n",
+    "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+    "    metricslist[int(properties['iteration'])] = metrics\n",
+    "\n",
+    "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+    "display(HTML('<h3>Metrics</h3>'))\n",
+    "display(rundata)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Download fitted models"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Download the Best Model for Any Given Metric"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "metric = 'AUC_weighted' # Replace with a metric name.\n",
+    "best_run, fitted_model = ml_run.get_output(metric = metric)\n",
+    "fitted_model"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Download the Model for Any Given Iteration"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "iteration = 1 # Replace with an iteration number.\n",
+    "best_run, fitted_model = ml_run.get_output(iteration = iteration)\n",
+    "fitted_model"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Register fitted model for deployment\n",
+    "If neither `metric` nor `iteration` are specified in the `register_model` call, the iteration with the best primary metric is registered."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "description = 'AutoML Model'\n",
+    "tags = None\n",
+    "ml_run.register_model(description = description, tags = tags)\n",
+    "ml_run.model_id # Use this id to deploy the model as a web service in Azure."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Register the Best Model for Any Given Metric"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "metric = 'AUC_weighted' # Replace with a metric name.\n",
+    "description = 'AutoML Model'\n",
+    "tags = None\n",
+    "ml_run.register_model(description = description, tags = tags, metric = metric)\n",
+    "print(ml_run.model_id) # Use this id to deploy the model as a web service in Azure."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Register the Model for Any Given Iteration"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "iteration = 1 # Replace with an iteration number.\n",
+    "description = 'AutoML Model'\n",
+    "tags = None\n",
+    "ml_run.register_model(description = description, tags = tags, iteration = iteration)\n",
+    "print(ml_run.model_id) # Use this id to deploy the model as a web service in Azure."
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "savitam"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3.6",
+   "language": "python",
+   "name": "python36"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/08.auto-ml-remote-execution-with-DataStore.ipynb

@@ -0,0 +1,588 @@
+{
+ "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": [
+    "# AutoML 08: Remote Execution with DataStore\n",
+    "\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 [00.configuration](00.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.\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create Experiment\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 random\n",
+    "import time\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn import datasets\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\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# choose a name for experiment\n",
+    "experiment_name = 'automl-remote-datastore-file'\n",
+    "# project folder\n",
+    "project_folder = './sample_projects/automl-remote-dsvm-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",
+    "pd.DataFrame(data=output, index=['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics=True)"
+   ]
+  },
+  {
+   "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://render.githubusercontent.com/documentation/sdk/ssh-issue.md) 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(60) # Wait for ssh to be accessible"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Copy data file to local\n",
+    "\n",
+    "Download the data file.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mkdir data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv(\"https://automldemods.blob.core.windows.net/datasets/PlayaEvents2016,_1.6MB,_3.4k-rows.cleaned.2.tsv\",\n",
+    "                     delimiter=\"\\t\", quotechar='\"')\n",
+    "df.to_csv(\"data/data.tsv\", sep=\"\\t\", quotechar='\"', index=False)"
+   ]
+  },
+  {
+   "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": [
+    "from azureml.core import Workspace, Datastore\n",
+    "#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",
+    "\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",
+    "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": [
+    "## 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",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "import os\n",
+    "from os.path import expanduser, join, dirname\n",
+    "\n",
+    "def get_data():\n",
+    "    # Burning man 2016 data\n",
+    "    df = pd.read_csv(\"/tmp/azureml_runs/data/data.tsv\", delimiter=\"\\t\", quotechar='\"')\n",
+    "    # get integer labels\n",
+    "    le = LabelEncoder()\n",
+    "    le.fit(df[\"Label\"].values)\n",
+    "    y = le.transform(df[\"Label\"].values)\n",
+    "    X = df.drop([\"Label\"], axis=1)\n",
+    "\n",
+    "    X_train, _, y_train, _ = train_test_split(X, y, test_size=0.1, random_state=42)\n",
+    "\n",
+    "    return { \"X\" : X_train.values, \"y\" : y_train }"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiate AutoML <a class=\"anchor\" id=\"Instatiate-AutoML-Remote-DSVM\"></a>\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": [
+    "## Training the Models <a class=\"anchor\" id=\"Training-the-model-Remote-DSVM\"></a>\n",
+    "\n",
+    "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": "markdown",
+   "metadata": {},
+   "source": [
+    "## Exploring the Results <a class=\"anchor\" id=\"Exploring-the-Results-Remote-DSVM\"></a>\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": [
+    "### Testing the Best Fitted Model <a class=\"anchor\" id=\"Testing-the-Fitted-Model-Remote-DSVM\"></a>\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sklearn\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "from pandas_ml import ConfusionMatrix\n",
+    "\n",
+    "df = pd.read_csv(\"https://automldemods.blob.core.windows.net/datasets/PlayaEvents2016,_1.6MB,_3.4k-rows.cleaned.2.tsv\",\n",
+    "                     delimiter=\"\\t\", quotechar='\"')\n",
+    "\n",
+    "# get integer labels\n",
+    "le = LabelEncoder()\n",
+    "le.fit(df[\"Label\"].values)\n",
+    "y = le.transform(df[\"Label\"].values)\n",
+    "X = df.drop([\"Label\"], axis=1)\n",
+    "\n",
+    "_, X_test, _, y_test = train_test_split(X, y, test_size=0.1, random_state=42)\n",
+    "\n",
+    "ypred = fitted_model.predict(X_test.values)\n",
+    "\n",
+    "ypred_strings = le.inverse_transform(ypred)\n",
+    "ytest_strings = le.inverse_transform(y_test)\n",
+    "\n",
+    "cm = ConfusionMatrix(ytest_strings, ypred_strings)\n",
+    "\n",
+    "print(cm)\n",
+    "\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/08b.auto-ml-remote-execution-with-dataprep.ipynb

@@ -0,0 +1,568 @@
+{
+ "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": [
+    "# AutoML 08b: Remote Execution with DataPrep\n",
+    "\n",
+    "This sample accesses a data file on a remote DSVM through Datastore using DataPrep. Advantages of using DataPrep are:\n",
+    "1. DataPrep supports reading from and writing to datastores.\n",
+    "2. DataPrep supports automatic file type and column type detection.\n",
+    "3. DataPrep makes passing data into AutoML really simple.\n",
+    "\n",
+    "More DataPrep documentation and examples can be found [here](https://github.com/Microsoft/AMLDataPrepDocs).\n",
+    "\n",
+    "Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
+    "\n",
+    "In this notebook you would see\n",
+    "1. Storing data in DataStore.\n",
+    "2. Doing some basic data preparation using DataPrep and passing the prepared data (DataFlow) to AutoML for training (classficiation).\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create Experiment\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 random\n",
+    "import time\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn import datasets\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\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# choose a name for experiment\n",
+    "experiment_name = 'automl-remote-datastore-file'\n",
+    "# project folder\n",
+    "project_folder = './sample_projects/automl-remote-dsvm-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",
+    "pd.DataFrame(data=output, index=['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics=True)"
+   ]
+  },
+  {
+   "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://render.githubusercontent.com/documentation/sdk/ssh-issue.md) on this."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "compute_target_name = 'automl-dataprep'\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)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Copy data file to local\n",
+    "\n",
+    "We will download a 1MB simple random sample of the Chicago Crime data into a local temporary directory."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import tempfile\n",
+    "import requests\n",
+    "\n",
+    "temp_folder = tempfile.mkdtemp()\n",
+    "temp_tsv = os.path.join(temp_folder, 'crime0.csv')\n",
+    "\n",
+    "request = requests.get('https://dprepdata.blob.core.windows.net/demo/crime0-random.csv')\n",
+    "with open(temp_tsv, 'w', encoding='utf-8') as f:\n",
+    "    f.write(request.text)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Upload data to the cloud"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now let's make the data available in your datastore. Datastore is a convenient construct associated with your workspace for you to  reference different types of cloud storage locations (e.g. Azure Blob Containers, Azure File Shares, Azure Data Lake Stores, etc.). The benefit Datastore brings is you only need to register datastores once and you will be able to access them by name and will not need to expose secrets in your code. When you first create a workspace, a default datastore is registered for you which references the Azure Blob Container that was provisioned with the workspace. Let's upload the data we just got from the public location to the default datastore.\n",
+    "\n",
+    "The `csv` file is uploaded into a directory named `datasets` at the root of the datastore."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core import Workspace, Datastore\n",
+    "\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(src_dir=temp_folder, target_path='datasets', overwrite=True, show_progress=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create Dataflow using DataPrep\n",
+    "Let's use DataPrep to read the `csv` file from the datastore we just uploaded to and get the data profile to make sure our data looks good. We will predict the type of the offense (`Primary Type`)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import azureml.dataprep as dprep\n",
+    "\n",
+    "dflow = dprep.read_csv(path=ds.path('datasets/crime0.csv'))\n",
+    "dflow.get_profile()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Let's also take a look at the first 5 rows of the data to give ourselves an idea of what the data looks like."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dflow.head(5)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "From the first 5 rows, we see that there are some rows that have no value in the label column (`Primary Type`). Let's remove those rows."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dflow = dflow.drop_nulls('Primary Type')\n",
+    "dflow.head(5)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now that we've removed those rows, let's split the dataflow into a features dataflow and a label dataflow."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = dflow.drop_columns(columns=['Primary Type', 'FBI Code'])\n",
+    "y = dflow.keep_columns(columns=['Primary Type'])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiate AutoML <a class=\"anchor\" id=\"Instatiate-AutoML-Remote-DSVM\"></a>\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": [
+    "from azureml.core.runconfig import RunConfiguration\n",
+    "from azureml.core.conda_dependencies import CondaDependencies\n",
+    "\n",
+    "conda_run_config = RunConfiguration(framework=\"python\")\n",
+    "\n",
+    "conda_run_config.target = dsvm_compute\n",
+    "\n",
+    "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]==0.1.0.1918169'], conda_packages=['numpy'], pin_sdk_version=False, pip_indexurl='https://azuremlsdktestpypi.azureedge.net/sdk-release/master/588E708E0DF342C4A80BD954289657CF')\n",
+    "conda_run_config.environment.python.conda_dependencies = cd"
+   ]
+  },
+  {
+   "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\": 'accuracy',\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",
+    "                             X=X,\n",
+    "                             y=y,\n",
+    "                             **automl_settings)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Training the Models <a class=\"anchor\" id=\"Training-the-model-Remote-DSVM\"></a>\n",
+    "\n",
+    "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": "markdown",
+   "metadata": {},
+   "source": [
+    "## Exploring the Results <a class=\"anchor\" id=\"Exploring-the-Results-Remote-DSVM\"></a>\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": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "remote_run"
+   ]
+  },
+  {
+   "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": [
+    "### Testing the Best Fitted Model <a class=\"anchor\" id=\"Testing-the-Fitted-Model-Remote-DSVM\"></a>\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dflow = dprep.read_csv(path='https://dprepdata.blob.core.windows.net/demo/crime0-test.csv')\n",
+    "dflow.head(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pandas_ml import ConfusionMatrix\n",
+    "\n",
+    "y_test = dflow.keep_columns(columns=['Primary Type']).to_pandas_dataframe()\n",
+    "X_test = dflow.drop_columns(columns=['Primary Type', 'FBI Code']).to_pandas_dataframe()\n",
+    "\n",
+    "ypred = fitted_model.predict(X_test.values)\n",
+    "\n",
+    "cm = ConfusionMatrix(y_test['Primary Type'], ypred)\n",
+    "\n",
+    "print(cm)\n",
+    "\n",
+    "cm.plot()"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "savitam"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python [conda env:cli_dev]",
+   "language": "python",
+   "name": "conda-env-cli_dev-py"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/09.auto-ml-classification-with-deployment.ipynb

@@ -0,0 +1,501 @@
+{
+ "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": [
+    "# AutoML 09: Classification with Deployment\n",
+    "\n",
+    "In this example we use the scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) to showcase how you can use AutoML for a simple classification problem and deploy it to an Azure Container Instance (ACI).\n",
+    "\n",
+    "Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
+    "\n",
+    "In this notebook you will learn how to:\n",
+    "1. Create an experiment using an existing workspace.\n",
+    "2. Configure AutoML using `AutoMLConfig`.\n",
+    "3. Train the model using local compute.\n",
+    "4. Explore the results.\n",
+    "5. Register the model.\n",
+    "6. Create a container image.\n",
+    "7. Create an Azure Container Instance (ACI) service.\n",
+    "8. Test the ACI service.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create an Experiment\n",
+    "\n",
+    "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "import logging\n",
+    "import os\n",
+    "import random\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn import datasets\n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# choose a name for experiment\n",
+    "experiment_name = 'automl-local-classification'\n",
+    "# project folder\n",
+    "project_folder = './sample_projects/automl-local-classification'\n",
+    "\n",
+    "experiment=Experiment(ws, experiment_name)\n",
+    "\n",
+    "output = {}\n",
+    "output['SDK version'] = azureml.core.VERSION\n",
+    "output['Subscription ID'] = ws.subscription_id\n",
+    "output['Workspace'] = 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",
+    "pd.DataFrame(data=output, index=['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Configure AutoML\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, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\n",
+    "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "digits = datasets.load_digits()\n",
+    "X_train = digits.data[10:,:]\n",
+    "y_train = digits.target[10:]\n",
+    "\n",
+    "automl_config = AutoMLConfig(task = 'classification',\n",
+    "                             name = experiment_name,\n",
+    "                             debug_log = 'automl_errors.log',\n",
+    "                             primary_metric = 'AUC_weighted',\n",
+    "                             iteration_timeout_minutes = 20,\n",
+    "                             iterations = 10,\n",
+    "                             n_cross_validations = 2,\n",
+    "                             verbosity = logging.INFO,\n",
+    "                             X = X_train, \n",
+    "                             y = y_train,\n",
+    "                             path = project_folder)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Train the Models\n",
+    "\n",
+    "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
+    "In this example, we specify `show_output = True` to print currently running iterations to the console."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run = experiment.submit(automl_config, show_output = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Retrieve the Best Model\n",
+    "\n",
+    "Below we select the best pipeline from our iterations. The `get_output` method on `automl_classifier` returns the best run and the fitted model for the last invocation. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_model = local_run.get_output()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Register the Fitted Model for Deployment\n",
+    "If neither `metric` nor `iteration` are specified in the `register_model` call, the iteration with the best primary metric is registered."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "description = 'AutoML Model'\n",
+    "tags = None\n",
+    "model = local_run.register_model(description = description, tags = tags)\n",
+    "local_run.model_id # This will be written to the script file later in the notebook."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create Scoring Script"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%writefile score.py\n",
+    "import pickle\n",
+    "import json\n",
+    "import numpy\n",
+    "import azureml.train.automl\n",
+    "from sklearn.externals import joblib\n",
+    "from azureml.core.model import Model\n",
+    "\n",
+    "\n",
+    "def init():\n",
+    "    global model\n",
+    "    model_path = Model.get_model_path(model_name = '<<modelid>>') # this name is model.id of model that we want to deploy\n",
+    "    # deserialize the model file back into a sklearn model\n",
+    "    model = joblib.load(model_path)\n",
+    "\n",
+    "def run(rawdata):\n",
+    "    try:\n",
+    "        data = json.loads(rawdata)['data']\n",
+    "        data = numpy.array(data)\n",
+    "        result = model.predict(data)\n",
+    "    except Exception as e:\n",
+    "        result = str(e)\n",
+    "        return json.dumps({\"error\": result})\n",
+    "    return json.dumps({\"result\":result.tolist()})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create a YAML File for the Environment"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To ensure the fit results are consistent with the training results, the SDK dependency versions need to be the same as the environment that trains the model. Details about retrieving the versions can be found in notebook [12.auto-ml-retrieve-the-training-sdk-versions](12.auto-ml-retrieve-the-training-sdk-versions.ipynb)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "experiment_name = 'automl-local-classification'\n",
+    "\n",
+    "experiment = Experiment(ws, experiment_name)\n",
+    "ml_run = AutoMLRun(experiment = experiment, run_id = local_run.id)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dependencies = ml_run.get_run_sdk_dependencies(iteration = 7)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for p in ['azureml-train-automl', 'azureml-sdk', 'azureml-core']:\n",
+    "    print('{}\\t{}'.format(p, dependencies[p]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.conda_dependencies import CondaDependencies\n",
+    "\n",
+    "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn'], pip_packages=['azureml-sdk[automl]'])\n",
+    "\n",
+    "conda_env_file_name = 'myenv.yml'\n",
+    "myenv.save_to_file('.', conda_env_file_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Substitute the actual version number in the environment file.\n",
+    "# This is not strictly needed in this notebook because the model should have been generated using the current SDK version.\n",
+    "# However, we include this in case this code is used on an experiment from a previous SDK version.\n",
+    "\n",
+    "with open(conda_env_file_name, 'r') as cefr:\n",
+    "    content = cefr.read()\n",
+    "\n",
+    "with open(conda_env_file_name, 'w') as cefw:\n",
+    "    cefw.write(content.replace(azureml.core.VERSION, dependencies['azureml-sdk']))\n",
+    "\n",
+    "# Substitute the actual model id in the script file.\n",
+    "\n",
+    "script_file_name = 'score.py'\n",
+    "\n",
+    "with open(script_file_name, 'r') as cefr:\n",
+    "    content = cefr.read()\n",
+    "\n",
+    "with open(script_file_name, 'w') as cefw:\n",
+    "    cefw.write(content.replace('<<modelid>>', local_run.model_id))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create a Container Image"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.image import Image, ContainerImage\n",
+    "\n",
+    "image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
+    "                                 execution_script = script_file_name,\n",
+    "                                 conda_file = conda_env_file_name,\n",
+    "                                 tags = {'area': \"digits\", 'type': \"automl_classification\"},\n",
+    "                                 description = \"Image for automl classification sample\")\n",
+    "\n",
+    "image = Image.create(name = \"automlsampleimage\",\n",
+    "                     # this is the model object \n",
+    "                     models = [model],\n",
+    "                     image_config = image_config, \n",
+    "                     workspace = ws)\n",
+    "\n",
+    "image.wait_for_creation(show_output = True)\n",
+    "\n",
+    "if image.creation_state == 'Failed':\n",
+    "    print(\"Image build log at: \" + image.image_build_log_uri)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Deploy the Image as a Web Service on Azure Container Instance"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.webservice import AciWebservice\n",
+    "\n",
+    "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
+    "                                               memory_gb = 1, \n",
+    "                                               tags = {'area': \"digits\", 'type': \"automl_classification\"}, \n",
+    "                                               description = 'sample service for Automl Classification')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.webservice import Webservice\n",
+    "\n",
+    "aci_service_name = 'automl-sample-01'\n",
+    "print(aci_service_name)\n",
+    "aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
+    "                                           image = image,\n",
+    "                                           name = aci_service_name,\n",
+    "                                           workspace = ws)\n",
+    "aci_service.wait_for_deployment(True)\n",
+    "print(aci_service.state)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Delete a Web Service"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#aci_service.delete()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Get Logs from a Deployed Web Service"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#aci_service.get_logs()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Test a Web Service"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Randomly select digits and test\n",
+    "digits = datasets.load_digits()\n",
+    "X_test = digits.data[:10, :]\n",
+    "y_test = digits.target[:10]\n",
+    "images = digits.images[:10]\n",
+    "\n",
+    "for index in np.random.choice(len(y_test), 3, replace = False):\n",
+    "    print(index)\n",
+    "    test_sample = json.dumps({'data':X_test[index:index + 1].tolist()})\n",
+    "    predicted = aci_service.run(input_data = test_sample)\n",
+    "    label = y_test[index]\n",
+    "    predictedDict = json.loads(predicted)\n",
+    "    title = \"Label value = %d  Predicted value = %s \" % ( label,predictedDict['result'][0])\n",
+    "    fig = plt.figure(1, figsize = (3,3))\n",
+    "    ax1 = fig.add_axes((0,0,.8,.8))\n",
+    "    ax1.set_title(title)\n",
+    "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
+    "    plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "savitam"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3.6",
+   "language": "python",
+   "name": "python36"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/10.auto-ml-multi-output-example.ipynb

@@ -0,0 +1,294 @@
+{
+ "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": [
+    "# AutoML 10: Multi-output\n",
+    "\n",
+    "This notebook shows how to use AutoML to train multi-output problems by leveraging the correlation between the outputs using indicator vectors.\n",
+    "\n",
+    "Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import logging\n",
+    "import os\n",
+    "import random\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn import datasets\n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Transformer Functions\n",
+    "The transformations of inputs `X` and `y` are happening as follows, e.g. `y = {y_1, y_2}`, then `X` becomes\n",
+    "    \n",
+    "`X 1 0`\n",
+    "     \n",
+    "`X 0 1`\n",
+    "\n",
+    "and `y` becomes,\n",
+    "\n",
+    "`y_1`\n",
+    "\n",
+    "`y_2`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from scipy import sparse\n",
+    "from scipy import linalg\n",
+    "\n",
+    "#Transformer functions\n",
+    "def multi_output_transform_x_y(X, y):\n",
+    "    X_new = multi_output_transformer_x(X, y.shape[1])\n",
+    "    y_new = multi_output_transform_y(y)\n",
+    "    return X_new, y_new\n",
+    "\n",
+    "def multi_output_transformer_x(X, number_of_columns_y):\n",
+    "    indicator_vecs = linalg.block_diag(*([np.ones((X.shape[0], 1))] * number_of_columns_y))\n",
+    "    if sparse.issparse(X):\n",
+    "        X_new = sparse.vstack(np.tile(X, number_of_columns_y))\n",
+    "        indicator_vecs = sparse.coo_matrix(indicator_vecs)\n",
+    "        X_new = sparse.hstack((X_new, indicator_vecs))\n",
+    "    else:\n",
+    "        X_new = np.tile(X, (number_of_columns_y, 1))\n",
+    "        X_new = np.hstack((X_new, indicator_vecs))\n",
+    "    return X_new\n",
+    "\n",
+    "def multi_output_transform_y(y):\n",
+    "    return y.reshape(-1, order=\"F\")\n",
+    "\n",
+    "def multi_output_inverse_transform_y(y, number_of_columns_y):\n",
+    "    return y.reshape((-1, number_of_columns_y), order = \"F\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## AutoML Experiment Setup"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# Choose a name for the experiment and specify the project folder.\n",
+    "experiment_name = 'automl-local-multi-output'\n",
+    "project_folder = './sample_projects/automl-local-multi-output'\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",
+    "pd.DataFrame(data = output, index = ['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create a Random Dataset for Test Purposes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "rng = np.random.RandomState(1)\n",
+    "X_train = np.sort(200 * rng.rand(600, 1) - 100, axis = 0)\n",
+    "y_train = np.array([np.pi * np.sin(X_train).ravel(), np.pi * np.cos(X_train).ravel()]).T\n",
+    "y_train += (0.5 - rng.rand(*y_train.shape))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Perform X and y transformation using the transformer function."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train_transformed, y_train_transformed = multi_output_transform_x_y(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Configure AutoML using the transformed results."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_config = AutoMLConfig(task = 'regression',\n",
+    "                             debug_log = 'automl_errors_multi.log',\n",
+    "                             primary_metric = 'r2_score',\n",
+    "                             iterations = 10,\n",
+    "                             n_cross_validations = 2,\n",
+    "                             verbosity = logging.INFO,\n",
+    "                             X = X_train_transformed,\n",
+    "                             y = y_train_transformed,\n",
+    "                             path = project_folder)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Fit the Transformed Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run = experiment.submit(automl_config, show_output = True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Get the best fit model.\n",
+    "best_run, fitted_model = local_run.get_output()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Generate random data set for predicting.\n",
+    "X_test = np.sort(200 * rng.rand(200, 1) - 100, axis = 0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Transform predict data.\n",
+    "X_test_transformed = multi_output_transformer_x(X_test, y_train.shape[1])\n",
+    "\n",
+    "# Predict and inverse transform the prediction.\n",
+    "y_predict = fitted_model.predict(X_test_transformed)\n",
+    "y_predict = multi_output_inverse_transform_y(y_predict, y_train.shape[1])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(y_predict)"
+   ]
+  }
+ ],
+ "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/11.auto-ml-sample-weight.ipynb

@@ -0,0 +1,251 @@
+{
+ "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": [
+    "# AutoML 11: Sample Weight\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 sample weight with AutoML. Sample weight is used where some sample values are more important than others.\n",
+    "\n",
+    "Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
+    "\n",
+    "In this notebook you will learn how to configure AutoML to use `sample_weight` and you will see the difference sample weight makes to the test results.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create an Experiment\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 random\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn import datasets\n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# Choose names for the regular and the sample weight experiments.\n",
+    "experiment_name = 'non_sample_weight_experiment'\n",
+    "sample_weight_experiment_name = 'sample_weight_experiment'\n",
+    "\n",
+    "project_folder = './sample_projects/automl-local-classification'\n",
+    "\n",
+    "experiment = Experiment(ws, experiment_name)\n",
+    "sample_weight_experiment=Experiment(ws, sample_weight_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",
+    "pd.DataFrame(data = output, index = ['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Configure AutoML\n",
+    "\n",
+    "Instantiate two `AutoMLConfig` objects. One will be used with `sample_weight` and one without."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "digits = datasets.load_digits()\n",
+    "X_train = digits.data[100:,:]\n",
+    "y_train = digits.target[100:]\n",
+    "\n",
+    "# The example makes the sample weight 0.9 for the digit 4 and 0.1 for all other digits.\n",
+    "# This makes the model more likely to classify as 4 if the image it not clear.\n",
+    "sample_weight = np.array([(0.9 if x == 4 else 0.01) for x in y_train])\n",
+    "\n",
+    "automl_classifier = AutoMLConfig(task = 'classification',\n",
+    "                                 debug_log = 'automl_errors.log',\n",
+    "                                 primary_metric = 'AUC_weighted',\n",
+    "                                 iteration_timeout_minutes = 60,\n",
+    "                                 iterations = 10,\n",
+    "                                 n_cross_validations = 2,\n",
+    "                                 verbosity = logging.INFO,\n",
+    "                                 X = X_train, \n",
+    "                                 y = y_train,\n",
+    "                                 path = project_folder)\n",
+    "\n",
+    "automl_sample_weight = AutoMLConfig(task = 'classification',\n",
+    "                                    debug_log = 'automl_errors.log',\n",
+    "                                    primary_metric = 'AUC_weighted',\n",
+    "                                    iteration_timeout_minutes = 60,\n",
+    "                                    iterations = 10,\n",
+    "                                    n_cross_validations = 2,\n",
+    "                                    verbosity = logging.INFO,\n",
+    "                                    X = X_train, \n",
+    "                                    y = y_train,\n",
+    "                                    sample_weight = sample_weight,\n",
+    "                                    path = project_folder)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Train the Models\n",
+    "\n",
+    "Call the `submit` method on the experiment objects and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
+    "In this example, we specify `show_output = True` to print currently running iterations to the console."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run = experiment.submit(automl_classifier, show_output = True)\n",
+    "sample_weight_run = sample_weight_experiment.submit(automl_sample_weight, show_output = True)\n",
+    "\n",
+    "best_run, fitted_model = local_run.get_output()\n",
+    "best_run_sample_weight, fitted_model_sample_weight = sample_weight_run.get_output()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Test the Best Fitted Model\n",
+    "\n",
+    "#### Load Test Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "digits = datasets.load_digits()\n",
+    "X_test = digits.data[:100, :]\n",
+    "y_test = digits.target[:100]\n",
+    "images = digits.images[:100]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Compare the Models\n",
+    "The prediction from the sample weight model is more likely to correctly predict 4's.  However, it is also more likely to predict 4 for some images that are not labelled as 4."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Randomly select digits and test.\n",
+    "for index in range(0,len(y_test)):\n",
+    "    predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
+    "    predicted_sample_weight = fitted_model_sample_weight.predict(X_test[index:index + 1])[0]\n",
+    "    label = y_test[index]\n",
+    "    if predicted == 4 or predicted_sample_weight == 4 or label == 4:\n",
+    "        title = \"Label value = %d  Predicted value = %d Prediced with sample weight = %d\" % (label, predicted, predicted_sample_weight)\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": "3.6.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/12.auto-ml-retrieve-the-training-sdk-versions.ipynb

@@ -0,0 +1,227 @@
+{
+ "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": [
+    "# AutoML 12: Retrieving Training SDK Versions\n",
+    "\n",
+    "This example shows how to find the SDK versions used for an experiment.\n",
+    "\n",
+    "Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import logging\n",
+    "import os\n",
+    "import random\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn import datasets\n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Train models using AutoML"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# Choose a name for the experiment and specify the project folder.\n",
+    "experiment_name = 'automl-local-classification'\n",
+    "project_folder = './sample_projects/automl-local-classification'\n",
+    "\n",
+    "experiment = Experiment(ws, experiment_name)\n",
+    "\n",
+    "output = {}\n",
+    "output['SDK version'] = azureml.core.VERSION\n",
+    "output['Subscription ID'] = ws.subscription_id\n",
+    "output['Workspace'] = 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",
+    "pd.DataFrame(data=output, index=['']).T"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "digits = datasets.load_digits()\n",
+    "X_train = digits.data[10:,:]\n",
+    "y_train = digits.target[10:]\n",
+    "\n",
+    "automl_config = AutoMLConfig(task = 'classification',\n",
+    "                             debug_log = 'automl_errors.log',\n",
+    "                             primary_metric = 'AUC_weighted',\n",
+    "                             iterations = 3,\n",
+    "                             n_cross_validations = 2,\n",
+    "                             verbosity = logging.INFO,\n",
+    "                             X = X_train, \n",
+    "                             y = y_train,\n",
+    "                             path = project_folder)\n",
+    "\n",
+    "local_run = experiment.submit(automl_config, show_output = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Retrieve the SDK versions from RunHistory"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To get the SDK versions from RunHistory, first the run id needs to be recorded. This can either be done by copying it from the output message or by retrieving it after each run."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Use a run id copied from an output message.\n",
+    "#run_id = 'AutoML_c0585b1f-a0e6-490b-84c7-3a099468b28e'\n",
+    "\n",
+    "# Retrieve the run id from a run.\n",
+    "run_id = local_run.id\n",
+    "print(run_id)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Initialize a new `AutoMLRun` object."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "experiment_name = 'automl-local-classification'\n",
+    "\n",
+    "experiment = Experiment(ws, experiment_name)\n",
+    "ml_run = AutoMLRun(experiment = experiment, run_id = run_id)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Get parent training SDK versions."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ml_run.get_run_sdk_dependencies()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Get the traning SDK versions of a specific run."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ml_run.get_run_sdk_dependencies(iteration = 2)"
+   ]
+  }
+ ],
+ "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/13a.auto-ml-dataprep.ipynb

@@ -0,0 +1,446 @@
+{
+ "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": [
+    "# AutoML 13: Prepare Data using `azureml.dataprep` for Local Execution\n",
+    "In this example we showcase how you can use the `azureml.dataprep` SDK to load and prepare data for AutoML. `azureml.dataprep` can also be used standalone; full documentation can be found [here](https://github.com/Microsoft/PendletonDocs).\n",
+    "\n",
+    "Make sure you have executed the [setup](00.configuration.ipynb) before running this notebook.\n",
+    "\n",
+    "In this notebook you will learn how to:\n",
+    "1. Define data loading and preparation steps in a `Dataflow` using `azureml.dataprep`.\n",
+    "2. Pass the `Dataflow` to AutoML for a local run.\n",
+    "3. Pass the `Dataflow` to AutoML for a remote run."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create an Experiment\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",
+    "\n",
+    "import pandas as pd\n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "import azureml.dataprep as dprep\n",
+    "from azureml.train.automl import AutoMLConfig"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    " \n",
+    "# choose a name for experiment\n",
+    "experiment_name = 'automl-dataprep-local'\n",
+    "# project folder\n",
+    "project_folder = './sample_projects/automl-dataprep-local'\n",
+    " \n",
+    "experiment = Experiment(ws, experiment_name)\n",
+    " \n",
+    "output = {}\n",
+    "output['SDK version'] = azureml.core.VERSION\n",
+    "output['Subscription ID'] = ws.subscription_id\n",
+    "output['Workspace Name'] = ws.name\n",
+    "output['Resource Group'] = ws.resource_group\n",
+    "output['Location'] = ws.location\n",
+    "output['Project Directory'] = project_folder\n",
+    "output['Experiment Name'] = experiment.name\n",
+    "pd.set_option('display.max_colwidth', -1)\n",
+    "pd.DataFrame(data = output, index = ['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Loading Data using DataPrep"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# You can use `auto_read_file` which intelligently figures out delimiters and datatypes of a file.\n",
+    "# The data referenced here was pulled from `sklearn.datasets.load_digits()`.\n",
+    "simple_example_data_root = 'https://dprepdata.blob.core.windows.net/automl-notebook-data/'\n",
+    "X = dprep.auto_read_file(simple_example_data_root + 'X.csv').skip(1)  # Remove the header row.\n",
+    "\n",
+    "# You can also use `read_csv` and `to_*` transformations to read (with overridable delimiter)\n",
+    "# and convert column types manually.\n",
+    "# Here we read a comma delimited file and convert all columns to integers.\n",
+    "y = dprep.read_csv(simple_example_data_root + 'y.csv').to_long(dprep.ColumnSelector(term='.*', use_regex = True))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Review the Data Preparation Result\n",
+    "\n",
+    "You can peek the result of a Dataflow at any range using `skip(i)` and `head(j)`. Doing so evaluates only `j` records for all the steps in the Dataflow, which makes it fast even against large datasets."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X.skip(1).head(5)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Configure AutoML\n",
+    "\n",
+    "This creates a general AutoML settings object applicable for both local and remote runs."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_settings = {\n",
+    "    \"iteration_timeout_minutes\" : 10,\n",
+    "    \"iterations\" : 2,\n",
+    "    \"primary_metric\" : 'AUC_weighted',\n",
+    "    \"preprocess\" : False,\n",
+    "    \"verbosity\" : logging.INFO,\n",
+    "    \"n_cross_validations\": 3\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Local Run"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Pass Data with `Dataflow` Objects\n",
+    "\n",
+    "The `Dataflow` objects captured above can be passed to the `submit` method for a local run. AutoML will retrieve the results from the `Dataflow` for model training."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_config = AutoMLConfig(task = 'classification',\n",
+    "                             debug_log = 'automl_errors.log',\n",
+    "                             X = X,\n",
+    "                             y = y,\n",
+    "                             **automl_settings)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run = experiment.submit(automl_config, show_output = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Explore the Results"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Widget for Monitoring Runs\n",
+    "\n",
+    "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+    "\n",
+    "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.widgets import RunDetails\n",
+    "RunDetails(local_run).show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Retrieve All Child Runs\n",
+    "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "children = list(local_run.get_children())\n",
+    "metricslist = {}\n",
+    "for run in children:\n",
+    "    properties = run.get_properties()\n",
+    "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+    "    metricslist[int(properties['iteration'])] = metrics\n",
+    "    \n",
+    "import pandas as pd\n",
+    "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+    "rundata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Retrieve the Best Model\n",
+    "\n",
+    "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_model = local_run.get_output()\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Best Model Based on Any Other Metric\n",
+    "Show the run and the model that has the smallest `log_loss` value:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lookup_metric = \"log_loss\"\n",
+    "best_run, fitted_model = local_run.get_output(metric = lookup_metric)\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Model from a Specific Iteration\n",
+    "Show the run and the model from the first iteration:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "iteration = 0\n",
+    "best_run, fitted_model = local_run.get_output(iteration = iteration)\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Test the Best Fitted Model\n",
+    "\n",
+    "#### Load Test Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn import datasets\n",
+    "\n",
+    "digits = datasets.load_digits()\n",
+    "X_test = digits.data[:10, :]\n",
+    "y_test = digits.target[:10]\n",
+    "images = digits.images[:10]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Testing Our Best Fitted Model\n",
+    "We will try to predict 2 digits and see how our model works."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Randomly select digits and test\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "import random\n",
+    "import numpy as np\n",
+    "\n",
+    "for index in np.random.choice(len(y_test), 2, replace = False):\n",
+    "    print(index)\n",
+    "    predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
+    "    label = y_test[index]\n",
+    "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
+    "    fig = plt.figure(1, figsize=(3,3))\n",
+    "    ax1 = fig.add_axes((0,0,.8,.8))\n",
+    "    ax1.set_title(title)\n",
+    "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
+    "    plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Appendix"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Capture the `Dataflow` Objects for Later Use in AutoML\n",
+    "\n",
+    "`Dataflow` objects are immutable and are composed of a list of data preparation steps. A `Dataflow` object can be branched at any point for further usage."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# sklearn.digits.data + target\n",
+    "digits_complete = dprep.auto_read_file('https://dprepdata.blob.core.windows.net/automl-notebook-data/digits-complete.csv')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "`digits_complete` (sourced from `sklearn.datasets.load_digits()`) is forked into `dflow_X` to capture all the feature columns and `dflow_y` to capture the label column."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "digits_complete.to_pandas_dataframe().shape\n",
+    "labels_column = 'Column64'\n",
+    "dflow_X = digits_complete.drop_columns(columns = [labels_column])\n",
+    "dflow_y = digits_complete.keep_columns(columns = [labels_column])"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "savitam"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3.6",
+   "language": "python",
+   "name": "python36"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/13b.auto-ml-dataprep-remote-execution.ipynb

@@ -0,0 +1,497 @@
+{
+ "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": [
+    "# AutoML 13: Prepare Data using `azureml.dataprep` for Remote Execution (DSVM)\n",
+    "In this example we showcase how you can use the `azureml.dataprep` SDK to load and prepare data for AutoML. `azureml.dataprep` can also be used standalone; full documentation can be found [here](https://github.com/Microsoft/PendletonDocs).\n",
+    "\n",
+    "Make sure you have executed the [setup](00.configuration.ipynb) before running this notebook.\n",
+    "\n",
+    "In this notebook you will learn how to:\n",
+    "1. Define data loading and preparation steps in a `Dataflow` using `azureml.dataprep`.\n",
+    "2. Pass the `Dataflow` to AutoML for a local run.\n",
+    "3. Pass the `Dataflow` to AutoML for a remote run."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create an Experiment\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",
+    "\n",
+    "import pandas as pd\n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.compute import DsvmCompute\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "import azureml.dataprep as dprep\n",
+    "from azureml.train.automl import AutoMLConfig"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    " \n",
+    "# choose a name for experiment\n",
+    "experiment_name = 'automl-dataprep-remote-dsvm'\n",
+    "# project folder\n",
+    "project_folder = './sample_projects/automl-dataprep-remote-dsvm'\n",
+    " \n",
+    "experiment = Experiment(ws, experiment_name)\n",
+    " \n",
+    "output = {}\n",
+    "output['SDK version'] = azureml.core.VERSION\n",
+    "output['Subscription ID'] = ws.subscription_id\n",
+    "output['Workspace Name'] = ws.name\n",
+    "output['Resource Group'] = ws.resource_group\n",
+    "output['Location'] = ws.location\n",
+    "output['Project Directory'] = project_folder\n",
+    "output['Experiment Name'] = experiment.name\n",
+    "pd.set_option('display.max_colwidth', -1)\n",
+    "pd.DataFrame(data = output, index = ['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Loading Data using DataPrep"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# You can use `auto_read_file` which intelligently figures out delimiters and datatypes of a file.\n",
+    "# The data referenced here was pulled from `sklearn.datasets.load_digits()`.\n",
+    "simple_example_data_root = 'https://dprepdata.blob.core.windows.net/automl-notebook-data/'\n",
+    "X = dprep.auto_read_file(simple_example_data_root + 'X.csv').skip(1)  # Remove the header row.\n",
+    "\n",
+    "# You can also use `read_csv` and `to_*` transformations to read (with overridable delimiter)\n",
+    "# and convert column types manually.\n",
+    "# Here we read a comma delimited file and convert all columns to integers.\n",
+    "y = dprep.read_csv(simple_example_data_root + 'y.csv').to_long(dprep.ColumnSelector(term='.*', use_regex = True))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Review the Data Preparation Result\n",
+    "\n",
+    "You can peek the result of a Dataflow at any range using `skip(i)` and `head(j)`. Doing so evaluates only `j` records for all the steps in the Dataflow, which makes it fast even against large datasets."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X.skip(1).head(5)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Configure AutoML\n",
+    "\n",
+    "This creates a general AutoML settings object applicable for both local and remote runs."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_settings = {\n",
+    "    \"iteration_timeout_minutes\" : 10,\n",
+    "    \"iterations\" : 2,\n",
+    "    \"primary_metric\" : 'AUC_weighted',\n",
+    "    \"preprocess\" : False,\n",
+    "    \"verbosity\" : logging.INFO,\n",
+    "    \"n_cross_validations\": 3\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Remote Run"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create or Attach a Remote Linux DSVM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dsvm_name = 'mydsvmc'\n",
+    "\n",
+    "try:\n",
+    "    while ws.compute_targets[dsvm_name].provisioning_state == 'Creating':\n",
+    "        time.sleep(1)\n",
+    "        \n",
+    "    dsvm_compute = DsvmCompute(ws, dsvm_name)\n",
+    "    print('Found existing DVSM.')\n",
+    "except:\n",
+    "    print('Creating a new DSVM.')\n",
+    "    dsvm_config = DsvmCompute.provisioning_configuration(vm_size = \"Standard_D2_v2\")\n",
+    "    dsvm_compute = DsvmCompute.create(ws, name = dsvm_name, provisioning_configuration = dsvm_config)\n",
+    "    dsvm_compute.wait_for_completion(show_output = True)\n",
+    "    print(\"Waiting one minute for ssh to be accessible\")\n",
+    "    time.sleep(60) # Wait for ssh to be accessible"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.runconfig import RunConfiguration\n",
+    "from azureml.core.conda_dependencies import CondaDependencies\n",
+    "\n",
+    "conda_run_config = RunConfiguration(framework=\"python\")\n",
+    "\n",
+    "conda_run_config.target = dsvm_compute\n",
+    "\n",
+    "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy'])\n",
+    "conda_run_config.environment.python.conda_dependencies = cd"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Pass Data with `Dataflow` Objects\n",
+    "\n",
+    "The `Dataflow` objects captured above can also be passed to the `submit` method for a remote run. AutoML will serialize the `Dataflow` object and send it to the remote compute target. The `Dataflow` will not be evaluated locally."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_config = AutoMLConfig(task = 'classification',\n",
+    "                             debug_log = 'automl_errors.log',\n",
+    "                             path = project_folder,\n",
+    "                             run_configuration=conda_run_config,\n",
+    "                             X = X,\n",
+    "                             y = y,\n",
+    "                             **automl_settings)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "remote_run = experiment.submit(automl_config, show_output = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Explore the Results"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Widget for Monitoring Runs\n",
+    "\n",
+    "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+    "\n",
+    "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.widgets import RunDetails\n",
+    "RunDetails(remote_run).show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Retrieve All Child Runs\n",
+    "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "children = list(remote_run.get_children())\n",
+    "metricslist = {}\n",
+    "for run in children:\n",
+    "    properties = run.get_properties()\n",
+    "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+    "    metricslist[int(properties['iteration'])] = metrics\n",
+    "    \n",
+    "import pandas as pd\n",
+    "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+    "rundata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Retrieve the Best Model\n",
+    "\n",
+    "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_model = remote_run.get_output()\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Best Model Based on Any Other Metric\n",
+    "Show the run and the model that has the smallest `log_loss` value:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lookup_metric = \"log_loss\"\n",
+    "best_run, fitted_model = remote_run.get_output(metric = lookup_metric)\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Model from a Specific Iteration\n",
+    "Show the run and the model from the first iteration:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "iteration = 0\n",
+    "best_run, fitted_model = remote_run.get_output(iteration = iteration)\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Test the Best Fitted Model\n",
+    "\n",
+    "#### Load Test Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn import datasets\n",
+    "\n",
+    "digits = datasets.load_digits()\n",
+    "X_test = digits.data[:10, :]\n",
+    "y_test = digits.target[:10]\n",
+    "images = digits.images[:10]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Testing Our Best Fitted Model\n",
+    "We will try to predict 2 digits and see how our model works."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Randomly select digits and test\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "import random\n",
+    "import numpy as np\n",
+    "\n",
+    "for index in np.random.choice(len(y_test), 2, replace = False):\n",
+    "    print(index)\n",
+    "    predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
+    "    label = y_test[index]\n",
+    "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
+    "    fig = plt.figure(1, figsize=(3,3))\n",
+    "    ax1 = fig.add_axes((0,0,.8,.8))\n",
+    "    ax1.set_title(title)\n",
+    "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
+    "    plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Appendix"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Capture the `Dataflow` Objects for Later Use in AutoML\n",
+    "\n",
+    "`Dataflow` objects are immutable and are composed of a list of data preparation steps. A `Dataflow` object can be branched at any point for further usage."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# sklearn.digits.data + target\n",
+    "digits_complete = dprep.auto_read_file('https://dprepdata.blob.core.windows.net/automl-notebook-data/digits-complete.csv')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "`digits_complete` (sourced from `sklearn.datasets.load_digits()`) is forked into `dflow_X` to capture all the feature columns and `dflow_y` to capture the label column."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "digits_complete.to_pandas_dataframe().shape\n",
+    "labels_column = 'Column64'\n",
+    "dflow_X = digits_complete.drop_columns(columns = [labels_column])\n",
+    "dflow_y = digits_complete.keep_columns(columns = [labels_column])"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "savitam"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3.6",
+   "language": "python",
+   "name": "python36"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/14.auto-ml-model-explanation.ipynb

@@ -0,0 +1,348 @@
+{
+ "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": [
+    "# AutoML 14: Explain classification model and visualize the explanation\n",
+    "\n",
+    "In this example we use the sklearn's [iris dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_iris.html) to showcase how you can use the AutoML Classifier for a simple classification problem.\n",
+    "\n",
+    "Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
+    "\n",
+    "In this notebook you would see\n",
+    "1. Creating an Experiment in an existing Workspace\n",
+    "2. Instantiating AutoMLConfig\n",
+    "3. Training the Model using local compute and explain the model\n",
+    "4. Visualization model's feature importance in widget\n",
+    "5. Explore best model's explanation\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create Experiment\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 random\n",
+    "\n",
+    "import pandas as pd\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# choose a name for experiment\n",
+    "experiment_name = 'automl-local-classification'\n",
+    "# project folder\n",
+    "project_folder = './sample_projects/automl-local-classification-model-explanation'\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",
+    "pd.DataFrame(data = output, index = ['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Load Iris Data Set"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn import datasets\n",
+    "\n",
+    "iris = datasets.load_iris()\n",
+    "y = iris.target\n",
+    "X = iris.data\n",
+    "\n",
+    "features = iris.feature_names\n",
+    "\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X,\n",
+    "                                                    y,\n",
+    "                                                    test_size=0.1,\n",
+    "                                                    random_state=100,\n",
+    "                                                    stratify=y)\n",
+    "\n",
+    "X_train = pd.DataFrame(X_train, columns=features)\n",
+    "X_test = pd.DataFrame(X_test, columns=features)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiate Auto ML Config\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",
+    "|**max_time_sec**|Time limit in minutes for each iterations|\n",
+    "|**iterations**|Number of iterations. In each iteration Auto ML trains the data with a specific pipeline|\n",
+    "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+    "|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification.  This should be an array of integers. |\n",
+    "|**X_valid**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+    "|**y_valid**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]|\n",
+    "|**model_explainability**|Indicate to explain each trained pipeline or not |\n",
+    "|**path**|Relative path to the project folder.  AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder. |"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_config = AutoMLConfig(task = 'classification',\n",
+    "                             debug_log = 'automl_errors.log',\n",
+    "                             primary_metric = 'AUC_weighted',\n",
+    "                             iteration_timeout_minutes = 200,\n",
+    "                             iterations = 10,\n",
+    "                             verbosity = logging.INFO,\n",
+    "                             X = X_train, \n",
+    "                             y = y_train,\n",
+    "                             X_valid = X_test,\n",
+    "                             y_valid = y_test,\n",
+    "                             model_explainability=True,\n",
+    "                             path=project_folder)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Training the Model\n",
+    "\n",
+    "You can call the submit method on the experiment object and pass the run configuration. For Local runs the execution is synchronous. Depending on the data and number of iterations this can run for while.\n",
+    "You will see the currently running iterations printing to the console."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run = experiment.submit(automl_config, show_output=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Exploring the results"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 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",
+    "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(local_run).show() "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 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 *fit* invocation. There are overloads on *get_output* that allow you to retrieve the best run and fitted model for *any* logged metric or a particular *iteration*."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_model = local_run.get_output()\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Best Model 's explanation\n",
+    "\n",
+    "Retrieve the explanation from the best_run. And explanation information includes:\n",
+    "\n",
+    "1.\tshap_values: The explanation information generated by shap lib\n",
+    "2.\texpected_values: The expected value of the model applied to set of X_train data.\n",
+    "3.\toverall_summary: The model level feature importance values sorted in descending order\n",
+    "4.\toverall_imp: The feature names sorted in the same order as in overall_summary\n",
+    "5.\tper_class_summary: The class level feature importance values sorted in descending order. Only available for the classification case\n",
+    "6.\tper_class_imp: The feature names sorted in the same order as in per_class_summary. Only available for the classification case"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.train.automl.automlexplainer import retrieve_model_explanation\n",
+    "\n",
+    "shap_values, expected_values, overall_summary, overall_imp, per_class_summary, per_class_imp = \\\n",
+    "    retrieve_model_explanation(best_run)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(overall_summary)\n",
+    "print(overall_imp)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(per_class_summary)\n",
+    "print(per_class_imp)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Beside retrieve the existed model explanation information, explain the model with different train/test data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.train.automl.automlexplainer import explain_model\n",
+    "\n",
+    "shap_values, expected_values, overall_summary, overall_imp, per_class_summary, per_class_imp = \\\n",
+    "    explain_model(fitted_model, X_train, X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(overall_summary)\n",
+    "print(overall_imp)"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "xif"
+   }
+  ],
+  "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/17.auto-ml-classification_with_tensorflow.ipynb

@@ -0,0 +1,390 @@
+{
+ "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": [
+    "# AutoML 17: Classification with Local Compute with Tesnorflow DNNClassifier and LinearClassifier using whitelist models feature.\n",
+    "\n",
+    "In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset) to showcase how you can use AutoML for a simple classification problem.\n",
+    "\n",
+    "Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
+    "This notebooks shows how can automl can be trained on a a selected list of models,see the readme.md for the models.\n",
+    "This trains the model exclusively on tensorflow based models.\n",
+    "\n",
+    "In this notebook you will learn how to:\n",
+    "1. Create an `Experiment` in an existing `Workspace`.\n",
+    "2. Configure AutoML using `AutoMLConfig`.\n",
+    "3. Train the model on a whilelisted models using local compute. \n",
+    "4. Explore the results.\n",
+    "5. Test the best fitted model.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create an Experiment\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 random\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn import datasets\n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# Choose a name for the experiment and specify the project folder.\n",
+    "experiment_name = 'automl-local-classification'\n",
+    "project_folder = './sample_projects/automl-local-classification'\n",
+    "\n",
+    "experiment = Experiment(ws, experiment_name)\n",
+    "\n",
+    "output = {}\n",
+    "output['SDK version'] = azureml.core.VERSION\n",
+    "output['Subscription ID'] = ws.subscription_id\n",
+    "output['Workspace Name'] = ws.name\n",
+    "output['Resource Group'] = ws.resource_group\n",
+    "output['Location'] = ws.location\n",
+    "output['Project Directory'] = project_folder\n",
+    "output['Experiment Name'] = experiment.name\n",
+    "pd.set_option('display.max_colwidth', -1)\n",
+    "pd.DataFrame(data = output, index = ['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Load Training Data\n",
+    "\n",
+    "This uses scikit-learn's [load_digits](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) method."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn import datasets\n",
+    "\n",
+    "digits = datasets.load_digits()\n",
+    "\n",
+    "# Exclude the first 100 rows from training so that they can be used for test.\n",
+    "X_train = digits.data[100:,:]\n",
+    "y_train = digits.target[100:]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Configure AutoML\n",
+    "\n",
+    "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
+    "\n",
+    "|Property|Description|\n",
+    "|-|-|\n",
+    "|**task**|classification or regression|\n",
+    "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i>|\n",
+    "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+    "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
+    "|**n_cross_validations**|Number of cross validation splits.|\n",
+    "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+    "|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\n",
+    "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_config = AutoMLConfig(task = 'classification',\n",
+    "                             debug_log = 'automl_errors.log',\n",
+    "                             primary_metric = 'AUC_weighted',\n",
+    "                             iteration_timeout_minutes = 60,\n",
+    "                             iterations = 10,\n",
+    "                             n_cross_validations = 3,\n",
+    "                             verbosity = logging.INFO,\n",
+    "                             X = X_train, \n",
+    "                             y = y_train,\n",
+    "                             enable_tf=True,\n",
+    "                             whitelist_models=[\"TensorFlowLinearClassifier\", \"TensorFlowDNN\"],\n",
+    "                             path = project_folder)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Train the Models\n",
+    "\n",
+    "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
+    "In this example, we specify `show_output = True` to print currently running iterations to the console."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run = experiment.submit(automl_config, show_output = True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Explore the Results"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Widget for Monitoring Runs\n",
+    "\n",
+    "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+    "\n",
+    "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.widgets import RunDetails\n",
+    "RunDetails(local_run).show() "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\n",
+    "#### Retrieve All Child Runs\n",
+    "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "children = list(local_run.get_children())\n",
+    "metricslist = {}\n",
+    "for run in children:\n",
+    "    properties = run.get_properties()\n",
+    "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+    "    metricslist[int(properties['iteration'])] = metrics\n",
+    "\n",
+    "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+    "rundata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Retrieve the Best Model\n",
+    "\n",
+    "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_model = local_run.get_output()\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Best Model Based on Any Other Metric\n",
+    "Show the run and the model that has the smallest `log_loss` value:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lookup_metric = \"log_loss\"\n",
+    "best_run, fitted_model = local_run.get_output(metric = lookup_metric)\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Model from a Specific Iteration\n",
+    "Show the run and the model from the third iteration:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "iteration = 3\n",
+    "third_run, third_model = local_run.get_output(iteration = iteration)\n",
+    "print(third_run)\n",
+    "print(third_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Test the Best Fitted Model\n",
+    "\n",
+    "#### Load Test Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "digits = datasets.load_digits()\n",
+    "X_test = digits.data[:10, :]\n",
+    "y_test = digits.target[:10]\n",
+    "images = digits.images[:10]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Testing Our Best Fitted Model\n",
+    "We will try to predict 2 digits and see how our model works."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Randomly select digits and test.\n",
+    "for index in np.random.choice(len(y_test), 2, replace = False):\n",
+    "    print(index)\n",
+    "    predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
+    "    label = y_test[index]\n",
+    "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
+    "    fig = plt.figure(1, figsize = (3,3))\n",
+    "    ax1 = fig.add_axes((0,0,.8,.8))\n",
+    "    ax1.set_title(title)\n",
+    "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
+    "    plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "savitam"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3.6",
+   "language": "python",
+   "name": "python36"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/18a.auto-ml-forecasting.ipynb

@@ -0,0 +1,397 @@
+{
+ "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": [
+    "# AutoML 18: Energy Demand Forecasting\n",
+    "\n",
+    "In this example, we show how AutoML can be used for energy demand forecasting.\n",
+    "\n",
+    "Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
+    "\n",
+    "In this notebook you would see\n",
+    "1. Creating an Experiment in an existing Workspace\n",
+    "2. Instantiating AutoMLConfig with new task type \"forecasting\" for timeseries data training, and other timeseries related settings: for this dataset we use the basic one: \"time_column_name\" \n",
+    "3. Training the Model using local compute\n",
+    "4. Exploring the results\n",
+    "5. Testing the fitted model"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create Experiment\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 azureml.core\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import os\n",
+    "import logging\n",
+    "import warnings\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",
+    "from azureml.train.automl.run import AutoMLRun\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score"
+   ]
+  },
+  {
+   "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-energydemandforecasting'\n",
+    "# project folder\n",
+    "project_folder = './sample_projects/automl-local-energydemandforecasting'\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['Run History Name'] = experiment_name\n",
+    "pd.set_option('display.max_colwidth', -1)\n",
+    "pd.DataFrame(data=output, index=['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Read Data\n",
+    "Read energy demanding data from file, and preview data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = pd.read_csv(\"nyc_energy.csv\", parse_dates=['timeStamp'])\n",
+    "data.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Split the data to train and test\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train = data[data['timeStamp'] < '2017-02-01']\n",
+    "test = data[data['timeStamp'] >= '2017-02-01']\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Prepare the test data, we will feed X_test to the fitted model and get prediction"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_test = test.pop('demand').values\n",
+    "X_test = test"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Split the train data to train and valid\n",
+    "\n",
+    "Use one month's data as valid data\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train = train[train['timeStamp'] < '2017-01-01']\n",
+    "X_valid = train[train['timeStamp'] >= '2017-01-01']\n",
+    "y_train = X_train.pop('demand').values\n",
+    "y_valid = X_valid.pop('demand').values\n",
+    "print(X_train.shape)\n",
+    "print(y_train.shape)\n",
+    "print(X_valid.shape)\n",
+    "print(y_valid.shape)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiate Auto ML Config\n",
+    "\n",
+    "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
+    "\n",
+    "|Property|Description|\n",
+    "|-|-|\n",
+    "|**task**|forecasting|\n",
+    "|**primary_metric**|This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>\n",
+    "|**iterations**|Number of iterations. In each iteration, Auto ML trains a specific pipeline on the given data|\n",
+    "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+    "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+    "|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification.  This should be an array of integers. |\n",
+    "|**X_valid**|Data used to evaluate a model in a iteration. (sparse) array-like, shape = [n_samples, n_features]|\n",
+    "|**y_valid**|Data used to evaluate a model in a iteration. (sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification.  This should be an array of integers. |\n",
+    "|**path**|Relative path to the project folder.  AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "time_column_name = 'timeStamp'\n",
+    "automl_settings = {\n",
+    "    \"time_column_name\": time_column_name,\n",
+    "}\n",
+    "\n",
+    "\n",
+    "automl_config = AutoMLConfig(task = 'forecasting',\n",
+    "                             debug_log = 'automl_nyc_energy_errors.log',\n",
+    "                             primary_metric='normalized_root_mean_squared_error',\n",
+    "                             iterations = 10,\n",
+    "                             iteration_timeout_minutes = 5,\n",
+    "                             X = X_train,\n",
+    "                             y = y_train,\n",
+    "                             X_valid = X_valid,\n",
+    "                             y_valid = y_valid,\n",
+    "                             path=project_folder,\n",
+    "                             verbosity = logging.INFO,\n",
+    "                            **automl_settings)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Training the Model\n",
+    "\n",
+    "You can call the submit method on the experiment object and pass the run configuration. For Local runs the execution is synchronous. Depending on the data and number of iterations this can run for while.\n",
+    "You will see the currently running iterations printing to the console."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run = experiment.submit(automl_config, show_output=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Retrieve the Best Model\n",
+    "Below we select the best pipeline from our iterations. The get_output method on automl_classifier returns the best run and the fitted model for the last fit invocation. There are overloads on get_output that allow you to retrieve the best run and fitted model for any logged metric or a particular iteration."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_model = local_run.get_output()\n",
+    "fitted_model.steps"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Test the Best Fitted Model\n",
+    "\n",
+    "Predict on training and test set, and calculate residual values."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = fitted_model.predict(X_test)\n",
+    "y_pred"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Define a Check Data Function\n",
+    "\n",
+    "Remove the nan values from y_test to avoid error when calculate metrics "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def _check_calc_input(y_true, y_pred, rm_na=True):\n",
+    "    \"\"\"\n",
+    "    Check that 'y_true' and 'y_pred' are non-empty and\n",
+    "    have equal length.\n",
+    "\n",
+    "    :param y_true: Vector of actual values\n",
+    "    :type y_true: array-like\n",
+    "\n",
+    "    :param y_pred: Vector of predicted values\n",
+    "    :type y_pred: array-like\n",
+    "\n",
+    "    :param rm_na:\n",
+    "        If rm_na=True, remove entries where y_true=NA and y_pred=NA.\n",
+    "    :type rm_na: boolean\n",
+    "\n",
+    "    :return:\n",
+    "        Tuple (y_true, y_pred). if rm_na=True,\n",
+    "        the returned vectors may differ from their input values.\n",
+    "    :rtype: Tuple with 2 entries\n",
+    "    \"\"\"\n",
+    "    if len(y_true) != len(y_pred):\n",
+    "        raise ValueError(\n",
+    "            'the true values and prediction values do not have equal length.')\n",
+    "    elif len(y_true) == 0:\n",
+    "        raise ValueError(\n",
+    "            'y_true and y_pred are empty.')\n",
+    "    # if there is any non-numeric element in the y_true or y_pred,\n",
+    "    # the ValueError exception will be thrown.\n",
+    "    y_true = np.array(y_true).astype(float)\n",
+    "    y_pred = np.array(y_pred).astype(float)\n",
+    "    if rm_na:\n",
+    "        # remove entries both in y_true and y_pred where at least\n",
+    "        # one element in y_true or y_pred is missing\n",
+    "        y_true_rm_na = y_true[~(np.isnan(y_true) | np.isnan(y_pred))]\n",
+    "        y_pred_rm_na = y_pred[~(np.isnan(y_true) | np.isnan(y_pred))]\n",
+    "        return (y_true_rm_na, y_pred_rm_na)\n",
+    "    else:\n",
+    "        return y_true, y_pred"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Use the Check Data Function to remove the nan values from y_test to avoid error when calculate metrics "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_test,y_pred =  _check_calc_input(y_test,y_pred)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Calculate metrics for the prediction\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(\"[Test Data] \\nRoot Mean squared error: %.2f\" % np.sqrt(mean_squared_error(y_test, y_pred)))\n",
+    "# Explained variance score: 1 is perfect prediction\n",
+    "print('mean_absolute_error score: %.2f' % mean_absolute_error(y_test, y_pred))\n",
+    "print('R2 score: %.2f' % r2_score(y_test, y_pred))\n",
+    "\n",
+    "\n",
+    "\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()"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "xiaga"
+   }
+  ],
+  "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/18b.auto-ml-forecasting.ipynb

@@ -0,0 +1,390 @@
+{
+ "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": [
+    "# AutoML 18B: Orange Juice Sales Forecasting\n",
+    "\n",
+    "In this example, we use AutoML to find and tune a time-series forecasting model.\n",
+    "\n",
+    "Make sure you have executed the [configuration notebook](00.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",
+    "## Sample Data\n",
+    "The examples in the follow code samples use the [University of Chicago's Dominick's Finer Foods dataset](https://research.chicagobooth.edu/kilts/marketing-databases/dominicks) to forecast orange juice sales. Dominick's was a grocery chain in the Chicago metropolitan area."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create Experiment\n",
+    "\n",
+    "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. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import azureml.core\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import os\n",
+    "import logging\n",
+    "\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun\n",
+    "from sklearn.metrics import mean_absolute_error, mean_squared_error"
+   ]
+  },
+  {
+   "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-ojsalesforecasting'\n",
+    "# project folder\n",
+    "project_folder = './sample_projects/automl-local-ojsalesforecasting'\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['Run History Name'] = experiment_name\n",
+    "pd.set_option('display.max_colwidth', -1)\n",
+    "pd.DataFrame(data=output, index=['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Read Data\n",
+    "You are now ready to load the historical orange juice sales data. We will load the CSV file into a plain pandas DataFrame; the time column in the CSV is called _WeekStarting_, so it will be specially parsed into the datetime type."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "time_column_name = 'WeekStarting'\n",
+    "data = pd.read_csv(\"dominicks_OJ.csv\", parse_dates=[time_column_name])\n",
+    "data.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Each row in the DataFrame holds a quantity of weekly sales for an OJ brand at a single store. The data also includes the sales price, a flag indicating if the OJ brand was advertised in the store that week, and some customer demographic information based on the store location. For historical reasons, the data also include the logarithm of the sales quantity. The Dominick's grocery data is commonly used to illustrate econometric modeling techniques where logarithms of quantities are generally preferred.    \n",
+    "\n",
+    "The task is now to build a time-series model for the _Quantity_ column. It is important to note that this dataset is comprised of many individual time-series - one for each unique combination of _Store_ and _Brand_. To distinguish the individual time-series, we thus define the **grain** - the columns whose values determine the boundaries between time-series: "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "grain_column_names = ['Store', 'Brand']\n",
+    "nseries = data.groupby(grain_column_names).ngroups\n",
+    "print('Data contains {0} individual time-series.'.format(nseries))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Data Splitting\n",
+    "For the purposes of demonstration and later forecast evaluation, we now split the data into a training and a testing set. The test set will contain the final 20 weeks of observed sales for each time-series."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ntest_periods = 20\n",
+    "\n",
+    "def split_last_n_by_grain(df, n):\n",
+    "    \"\"\"\n",
+    "    Group df by grain and split on last n rows for each group\n",
+    "    \"\"\"\n",
+    "    df_grouped = (df.sort_values(time_column_name) # Sort by ascending time\n",
+    "                  .groupby(grain_column_names, group_keys=False))\n",
+    "    df_head = df_grouped.apply(lambda dfg: dfg.iloc[:-n])\n",
+    "    df_tail = df_grouped.apply(lambda dfg: dfg.iloc[-n:])\n",
+    "    return df_head, df_tail\n",
+    "\n",
+    "X_train, X_test = split_last_n_by_grain(data, ntest_periods)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Modeling\n",
+    "\n",
+    "For forecasting tasks, AutoML uses pre-processing and estimation steps that are specific to time-series. AutoML will undertake the following pre-processing steps:\n",
+    "* Detect time-series sample frequency (e.g. hourly, daily, weekly) and create new records for absent time points to make the series regular. A regular time series has a well-defined frequency and has a value at every sample point in a contiguous time span \n",
+    "* Impute missing values in the target (via forward-fill) and feature columns (using median column values) \n",
+    "* Create grain-based features to enable fixed effects across different series\n",
+    "* Create time-based features to assist in learning seasonal patterns\n",
+    "* Encode categorical variables to numeric quantities\n",
+    "\n",
+    "AutoML will currently train a single, regression-type model across **all** time-series in a given training set. This allows the model to generalize across related series.\n",
+    "\n",
+    "You are almost ready to start an AutoML training job. We will first need to create a validation set from the existing training set (i.e. for hyper-parameter tuning): "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "nvalidation_periods = 20\n",
+    "X_train, X_validate = split_last_n_by_grain(X_train, nvalidation_periods)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We also need to separate the target column from the rest of the DataFrame: "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "target_column_name = 'Quantity'\n",
+    "y_train = X_train.pop(target_column_name).values\n",
+    "y_validate = X_validate.pop(target_column_name).values "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create an AutoMLConfig\n",
+    "\n",
+    "The AutoMLConfig object defines the settings and data for an AutoML training job. Here, we set necessary inputs like the task type, the number of AutoML iterations to try, and the training and validation data. \n",
+    "\n",
+    "For forecasting tasks, there are some additional parameters that can be set: the name of the input data column, holding the date/time and the grain column names. A time column is required for forecasting, while the grain is optional. If a grain is not given, the forecaster 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",
+    "|Property|Description|\n",
+    "|-|-|\n",
+    "|**task**|forecasting|\n",
+    "|**primary_metric**|This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>\n",
+    "|**iterations**|Number of iterations. In each iteration, Auto ML trains a specific pipeline on the given data|\n",
+    "|**X**|Training matrix of features, shape = [n_training_samples, n_features]|\n",
+    "|**y**|Target values, shape = [n_training_samples, ]|\n",
+    "|**X_valid**|Validation matrix of features, shape = [n_validation_samples, n_features]|\n",
+    "|**y_valid**|Target values for validation, shape = [n_validation_samples, ]\n",
+    "|**enable_ensembling**|Allow AutoML to create ensembles of the best performing models\n",
+    "|**debug_log**|Log file path for writing debugging information\n",
+    "|**path**|Relative path to the project folder.  AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_settings = {\n",
+    "    'time_column_name': time_column_name,\n",
+    "    'grain_column_names': grain_column_names,\n",
+    "    'drop_column_names': ['logQuantity']\n",
+    "}\n",
+    "\n",
+    "automl_config = AutoMLConfig(task='forecasting',\n",
+    "                             debug_log='automl_oj_sales_errors.log',\n",
+    "                             primary_metric='normalized_root_mean_squared_error',\n",
+    "                             iterations=10,\n",
+    "                             X=X_train,\n",
+    "                             y=y_train,\n",
+    "                             X_valid=X_validate,\n",
+    "                             y_valid=y_validate,\n",
+    "                             enable_ensembling=False,\n",
+    "                             path=project_folder,\n",
+    "                             verbosity=logging.INFO,\n",
+    "                            **automl_settings)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Training the Model\n",
+    "\n",
+    "You can now submit a new training run. For local runs, the execution is synchronous. Depending on the data and number of iterations this operation may take several minutes.\n",
+    "Information from each iteration will be printed to the console."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run = experiment.submit(automl_config, show_output=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Retrieve the Best Model\n",
+    "Each run within an Experiment stores serialized (i.e. pickled) pipelines from the AutoML iterations. We can now retrieve the pipeline with the best performance on the validation dataset:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_pipeline = local_run.get_output()\n",
+    "fitted_pipeline.steps"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Make Predictions from the Best Fitted Model\n",
+    "Now that we have retrieved the best pipeline/model, it can be used to make predictions on test data. First, we remove the target values from the test set:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_test = X_test.pop(target_column_name).values"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_test.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To produce predictions on the test set, we need to know the feature values at all dates in the test set. This requirement is somewhat reasonable for the OJ sales data since the features mainly consist of price, which is usually set in advance, and customer demographics which are approximately constant for each store over the 20 week forecast horizon in the testing data. \n",
+    "\n",
+    "The target predictions can be retrieved by calling the `predict` method on the best model:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = fitted_pipeline.predict(X_test)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Calculate evaluation metrics for the prediction\n",
+    "To evaluate the accuracy of the forecast, we'll compare against the actual sales quantities for some select metrics, included the mean absolute percentage error (MAPE)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def MAPE(actual, pred):\n",
+    "    \"\"\"\n",
+    "    Calculate mean absolute percentage error.\n",
+    "    Remove NA and values where actual is close to zero\n",
+    "    \"\"\"\n",
+    "    not_na = ~(np.isnan(actual) | np.isnan(pred))\n",
+    "    not_zero = ~np.isclose(actual, 0.0)\n",
+    "    actual_safe = actual[not_na & not_zero]\n",
+    "    pred_safe = pred[not_na & not_zero]\n",
+    "    APE = 100*np.abs((actual_safe - pred_safe)/actual_safe)\n",
+    "    return np.mean(APE)\n",
+    "\n",
+    "print(\"[Test Data] \\nRoot Mean squared error: %.2f\" % np.sqrt(mean_squared_error(y_test, y_pred)))\n",
+    "print('mean_absolute_error score: %.2f' % mean_absolute_error(y_test, y_pred))\n",
+    "print('MAPE: %.2f' % MAPE(y_test, y_pred))"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "erwright"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3.6",
+   "language": "python",
+   "name": "python36"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

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

@@ -34,8 +34,7 @@ Below are the three execution environments supported by AutoML.
 **NOTE**: Please create your Azure Databricks cluster as v4.x (high concurrency preferred) with **Python 3** (dropdown).
 **NOTE**: You should at least have contributor access to your Azure subcription to run the notebook.
 - Please remove the previous SDK version if there is any and install the latest SDK by installing **azureml-sdk[automl_databricks]** as a PyPi library in Azure Databricks workspace.
-- You can find the detail Readme instructions at [GitHub](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/azure-databricks).
-- Download the sample notebook automl-databricks-local-01.ipynb from [GitHub](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/azure-databricks) and import into the Azure databricks workspace.
+- Download the sample notebook 16a.auto-ml-classification-local-azuredatabricks from [GitHub](https://github.com/Azure/MachineLearningNotebooks) and import into the Azure databricks workspace.
 - Attach the notebook to the cluster.
 
 <a name="localconda"></a>
@@ -58,7 +57,7 @@ jupyter notebook
 ```
 
 
-### 1. Install mini-conda from [here](https://conda.io/miniconda.html), choose 64-bit Python 3.7 or higher.
+### 1. Install mini-conda from [here](https://conda.io/miniconda.html), choose Python 3.7 or higher.
 - **Note**: if you already have conda installed, you can keep using it but it should be version 4.4.10 or later (as shown by: conda -V).  If you have a previous version installed, you can update it using the command: conda update conda.
 There's no need to install mini-conda specifically.
 
@@ -69,21 +68,21 @@ There's no need to install mini-conda specifically.
 The **automl/automl_setup** script creates a new conda environment, installs the necessary packages, configures the widget and starts a jupyter notebook.
 It takes the conda environment name as an optional parameter.  The default conda environment name is azure_automl.  The exact command depends on the operating system.  See the specific sections below for Windows, Mac and Linux.  It can take about 10 minutes to execute.
 ## Windows
-Start an **Anaconda Prompt** window, cd to the **how-to-use-azureml/automated-machine-learning** folder where the sample notebooks were extracted and then run:
+Start an **Anaconda Prompt** window, cd to the **automl** folder where the sample notebooks were extracted and then run:
 ```
 automl_setup
 ```
 ## Mac
 Install "Command line developer tools" if it is not already installed (you can use the command: `xcode-select --install`).
 
-Start a Terminal windows, cd to the **how-to-use-azureml/automated-machine-learning** folder where the sample notebooks were extracted and then run:
+Start a Terminal windows, cd to the **automl** folder where the sample notebooks were extracted and then run:
 
 ```
 bash automl_setup_mac.sh
 ```
 
 ## Linux
-cd to the **how-to-use-azureml/automated-machine-learning** folder where the sample notebooks were extracted and then run:
+cd to the **automl** folder where the sample notebooks were extracted and then run:
 
 ```
 bash automl_setup_linux.sh
@@ -124,7 +123,7 @@ bash automl_setup_linux.sh
 
 - [auto-ml-remote-batchai.ipynb](remote-batchai/auto-ml-remote-batchai.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
+    - Example of using automated ML for classification using a remote Batch AI compute for training
     - Parallel execution of iterations
     - Async tracking of progress
     - Cancelling individual iterations or entire run
@@ -132,7 +131,7 @@ bash automl_setup_linux.sh
     - Specify automl settings as kwargs
 
 - [auto-ml-remote-attach.ipynb](remote-attach/auto-ml-remote-attach.ipynb)
-    - Dataset: Scikit learn's [20newsgroup](http://scikit-learn.org/stable/datasets/twenty_newsgroups.html)
+    - Dataset: [Burning Man 2016 dataset](https://innovate.burningman.org/datasets-page/)
     - handling text data with preprocess flag
     - Reading data from a blob store for remote executions
     - using pandas dataframes for reading data
@@ -155,7 +154,7 @@ bash automl_setup_linux.sh
     - 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)
+    - Dataset: scikit learn's [digit dataset](https://innovate.burningman.org/datasets-page/)
     - Download the data and store it in DataStore.
 
 - [auto-ml-classification-with-deployment.ipynb](classification-with-deployment/auto-ml-classification-with-deployment.ipynb)
@@ -175,21 +174,114 @@ bash automl_setup_linux.sh
 - [auto-ml-dataprep-remote-execution.ipynb](dataprep-remote-execution/auto-ml-dataprep-remote-execution.ipynb)
     - Using DataPrep for reading data with remote execution
 
-- [auto-ml-classification-with-whitelisting.ipynb](classification-with-whitelisting/auto-ml-classification-with-whitelisting.ipynb)
+- [auto-ml-classification-local-azuredatabricks.ipynb](classification-local-azuredatabricks/auto-ml-classification-local-azuredatabricks.ipynb)
+    - Dataset: scikit learn's [digit dataset](https://innovate.burningman.org/datasets-page/)
+    - Example of using AutoML for classification using Azure Databricks as the platform for training
+
+- [auto-ml-classification_with_tensorflow.ipynb](classification_with_tensorflow/auto-ml-classification_with_tensorflow.ipynb)
     - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
-    - Simple example of using Auto ML for classification with whitelisting tensorflow models.
+    - Simple example of using Auto ML for classification with whitelisting tensorflow models.checkout
     - Uses local compute for training
 
-- [auto-ml-forecasting-energy-demand.ipynb](forecasting-energy-demand/auto-ml-forecasting-energy-demand.ipynb)
-    - Dataset: [NYC energy demand data](forecasting-a/nyc_energy.csv)
-    - Example of using AutoML for training a forecasting model
-
-- [auto-ml-forecasting-orange-juice-sales.ipynb](forecasting-orange-juice-sales/auto-ml-forecasting-orange-juice-sales.ipynb)
-    - Dataset: [Dominick's grocery sales of orange juice](forecasting-b/dominicks_OJ.csv)
-    - Example of training an AutoML forecasting model on multiple time-series
+- [auto-ml-timeseries.ipynb](timeseries/auto-ml-timeseries.ipynb)
+    - Dataset: NYC energy demanding data
+    - Example of using AutoML for timeseries data 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.
+# Documentation
+## Table of Contents
+1. [Automated ML Settings ](#automlsettings)
+1. [Cross validation split options](#cvsplits)
+1. [Get Data Syntax](#getdata)
+1. [Data pre-processing and featurization](#preprocessing)
+
+<a name="automlsettings"></a>
+## Automated ML Settings
+
+|Property|Description|Default|
+|-|-|-|
+|**primary_metric**|This is the metric that you want to optimize.<br><br> 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><br><br> 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><br><i>normalized_root_mean_squared_log_error</i>| Classification: accuracy <br><br> Regression: spearman_correlation
+|**iteration_timeout_minutes**|Time limit in minutes for each iteration|None|
+|**iterations**|Number of iterations. In each iteration trains the data with a specific pipeline.  To get the best result, use at least 100. |100|
+|**n_cross_validations**|Number of cross validation splits|None|
+|**validation_size**|Size of validation set as percentage of all training samples|None|
+|**max_concurrent_iterations**|Max number of iterations that would be executed in parallel|1|
+|**preprocess**|*True/False* <br>Setting this to *True* enables preprocessing <br>on the input to handle missing data, and perform some common feature extraction<br>*Note: If input data is Sparse you cannot use preprocess=True*|False|
+|**max_cores_per_iteration**| Indicates how many cores on the compute target would be used to train a single pipeline.<br> You can set it to *-1* to use all cores|1|
+|**experiment_exit_score**|*double* value indicating the target for *primary_metric*. <br> Once the target is surpassed the run terminates|None|
+|**blacklist_models**|*Array* of *strings* indicating models to ignore for Auto ML from the list of models.|None|
+|**whitelist_models**|*Array* of *strings* use only models listed for Auto ML from the list of models..|None|
+ <a name="cvsplits"></a>
+## List of models for white list/blacklist
+**Classification**
+<br><i>LogisticRegression</i>
+<br><i>SGD</i>
+<br><i>MultinomialNaiveBayes</i>
+<br><i>BernoulliNaiveBayes</i>
+<br><i>SVM</i>
+<br><i>LinearSVM</i>
+<br><i>KNN</i>
+<br><i>DecisionTree</i>
+<br><i>RandomForest</i>
+<br><i>ExtremeRandomTrees</i>
+<br><i>LightGBM</i>
+<br><i>GradientBoosting</i>
+<br><i>TensorFlowDNN</i>
+<br><i>TensorFlowLinearClassifier</i>
+<br><br>**Regression**
+<br><i>ElasticNet</i>
+<br><i>GradientBoosting</i>
+<br><i>DecisionTree</i>
+<br><i>KNN</i>
+<br><i>LassoLars</i>
+<br><i>SGD</i>
+<br><i>RandomForest</i>
+<br><i>ExtremeRandomTrees</i>
+<br><i>LightGBM</i>
+<br><i>TensorFlowLinearRegressor</i>
+<br><i>TensorFlowDNN</i>
+
+## Cross validation split options
+### K-Folds Cross Validation
+Use *n_cross_validations* setting to specify the number of cross validations. The training data set will be randomly split into *n_cross_validations* folds of equal size. During each cross validation round, one of the folds will be used for validation of the model trained on the remaining folds. This process repeats for *n_cross_validations* rounds until each fold is used once as validation set. Finally, the average scores accross all *n_cross_validations* rounds will be reported, and the corresponding model will be retrained on the whole training data set.
+
+### Monte Carlo Cross Validation (a.k.a. Repeated Random Sub-Sampling)
+Use *validation_size* to specify the percentage of the training data set that should be used for validation, and use *n_cross_validations* to specify the number of cross validations. During each cross validation round, a subset of size *validation_size* will be randomly selected for validation of the model trained on the remaining data. Finally, the average scores accross all *n_cross_validations* rounds will be reported, and the corresponding model will be retrained on the whole training data set.
+
+### Custom train and validation set
+You can specify seperate train and validation set either through the get_data() or directly to the fit method.
+
+<a name="getdata"></a>
+## get_data() syntax
+The *get_data()* function can be used to return a dictionary with these values:
+
+|Key|Type|Dependency|Mutually Exclusive with|Description|
+|:-|:-|:-|:-|:-|
+|X|Pandas Dataframe or Numpy Array|y|data_train, label, columns|All features to train with|
+|y|Pandas Dataframe or Numpy Array|X|label|Label data to train with.  For classification, this should be an array of integers. |
+|X_valid|Pandas Dataframe or Numpy Array|X, y, y_valid|data_train, label|*Optional* All features to validate with.  If this is not specified, X is split between train and validate|
+|y_valid|Pandas Dataframe or Numpy Array|X, y, X_valid|data_train, label|*Optional* The label data to validate with.  If this is not specified, y is split between train and validate|
+|sample_weight|Pandas Dataframe or Numpy Array|y|data_train, label, columns|*Optional* A weight value for each label. Higher values indicate that the sample is more important.|
+|sample_weight_valid|Pandas Dataframe or Numpy Array|y_valid|data_train, label, columns|*Optional* A weight value for each validation label. Higher values indicate that the sample is more important.  If this is not specified, sample_weight is split between train and validate|
+|data_train|Pandas Dataframe|label|X, y, X_valid, y_valid|All data (features+label) to train with|
+|label|string|data_train|X, y, X_valid, y_valid|Which column in data_train represents the label|
+|columns|Array of strings|data_train||*Optional* Whitelist of columns to use for features|
+|cv_splits_indices|Array of integers|data_train||*Optional* List of indexes to split the data for cross validation|
+
+<a name="preprocessing"></a>
+## Data pre-processing and featurization
+If you use `preprocess=True`, the following data preprocessing steps are performed automatically for you:
+
+1. Dropping high cardinality or no variance features
+    - Features with no useful information are dropped from training and validation sets. These include features with all values missing, same value across all rows or with extremely high cardinality (e.g., hashes, IDs or GUIDs).
+2. Missing value imputation
+    - For numerical features, missing values are imputed with average of values in the column.
+    - For categorical features, missing values are imputed with most frequent value.
+3. Generating additional features
+    - For DateTime features: Year, Month, Day, Day of week, Day of year, Quarter, Week of the year, Hour, Minute, Second.
+    - For Text features: Term frequency based on bi-grams and tri-grams, Count vectorizer.
+4. Transformations and encodings
+    - Numeric features with very few unique values are transformed into categorical features.
 
 <a name="pythoncommand"></a>
 # Running using python command
@@ -204,58 +296,11 @@ The main code of the file must be indented so that it is under this condition.
 
 <a name="troubleshooting"></a>
 # Troubleshooting
-## automl_setup fails
-1. On windows, make sure that you are running automl_setup from an Anconda Prompt window rather than a regular cmd window.  You can launch the "Anaconda Prompt" window by hitting the Start button and typing "Anaconda Prompt".  If you don't see the application "Anaconda Prompt", you might not have conda or mini conda installed.  In that case, you can install it [here](https://conda.io/miniconda.html)
-2. Check that you have conda 64-bit installed rather than 32-bit.  You can check this with the command `conda info`.  The `platform` should be `win-64` for Windows or `osx-64` for Mac.
-3. Check that you have conda 4.4.10 or later.  You can check the version with the command `conda -V`.  If you have a previous version installed, you can update it using the command: `conda update conda`.
-4. Pass a new name as the first parameter to automl_setup so that it creates a new conda environment. You can view existing conda environments using `conda env list` and remove them with `conda env remove -n <environmentname>`. 
-
-## configuration.ipynb fails
-1) For local conda, make sure that you have susccessfully run automl_setup first.
-2) Check that the subscription_id is correct.  You can find the subscription_id in the Azure Portal by selecting All Service and then Subscriptions. The characters "<" and ">" should not be included in the subscription_id value.  For example, `subscription_id = "12345678-90ab-1234-5678-1234567890abcd"` has the valid format.
-3) Check that you have Contributor or Owner access to the Subscription.
-4) Check that the region is one of the supported regions: `eastus2`, `eastus`, `westcentralus`, `southeastasia`, `westeurope`, `australiaeast`, `westus2`, `southcentralus`
-5) Check that you have access to the region using the Azure Portal.
-
-## workspace.from_config fails
-If the call `ws = Workspace.from_config()` fails:
-1) Make sure that you have run the `configuration.ipynb` notebook successfully.
-2) If you are running a notebook from a folder that is not under the folder where you ran `configuration.ipynb`, copy the folder aml_config and the file config.json that it contains to the new folder.  Workspace.from_config reads the config.json for the notebook folder or it parent folder.
-3) If you are switching to a new subscription, resource group, workspace or region, make sure that you run the `configuration.ipynb` notebook again.  Changing config.json directly will only work if the workspace already exists in the specified resource group under the specified subscription.
-4) If you want to change the region, please change the workspace, resource group or subscription.  `Workspace.create` will not create or update a workspace if it already exists, even if the region specified is different.
-
-## Sample notebook fails
-If a sample notebook fails with an error that property, method or library does not exist:
-1) Check that you have selected correct kernel in jupyter notebook.  The kernel is displayed in the top right of the notebook page.  It can be changed using the `Kernel | Change Kernel` menu option.  For Azure Notebooks, it should be `Python 3.6`.  For local conda environments, it should be the conda envioronment name that you specified in automl_setup.  The default is azure_automl.  Note that the kernel is saved as part of the notebook.  So, if you switch to a new conda environment, you will have to select the new kernel in the notebook.
-2) Check that the notebook is for the SDK version that you are using.  You can check the SDK version by executing `azureml.core.VERSION` in a jupyter notebook cell.  You can download previous version of the sample notebooks from GitHub by clicking the `Branch` button, selecting the `Tags` tab and then selecting the version.
-
-## Remote run: DsvmCompute.create fails 
-There are several reasons why the DsvmCompute.create can fail.  The reason is usually in the error message but you have to look at the end of the error message for the detailed reason.  Some common reasons are:
-1) `Compute name is invalid, it should start with a letter, be between 2 and 16 character, and only include letters (a-zA-Z), numbers (0-9) and \'-\'.`  Note that underscore is not allowed in the name.
-2) `The requested VM size xxxxx is not available in the current region.`  You can select a different region or vm_size. 
-
-## Remote run: Unable to establish SSH connection
-AutoML uses the SSH protocol to communicate with remote DSVMs.  This defaults to port 22.  Possible causes for this error are:
-1) The DSVM is not ready for SSH connections.  When DSVM creation completes, the DSVM might still not be ready to acceept SSH connections.  The sample notebooks have a one minute delay to allow for this.
-2) Your Azure Subscription may restrict the IP address ranges that can access the DSVM on port 22.  You can check this in the Azure Portal by selecting the Virtual Machine and then clicking Networking.  The Virtual Machine name is the name that you provided in the notebook plus 10 alpha numeric characters to make the name unique.  The Inbound Port Rules define what can access the VM on specific ports.  Note that there is a priority priority order.  So, a Deny entry with a low priority number will override a Allow entry with a higher priority number.
-
-## Remote run: setup iteration fails
-This is often an issue with the `get_data` method.
-1) Check that the `get_data` method is valid by running it locally.
-2) Make sure that `get_data` isn't referring to any local files.  `get_data` is executed on the remote DSVM.  So, it doesn't have direct access to local data files.  Instead you can store the data files with DataStore.  See [auto-ml-remote-execution-with-datastore.ipynb](remote-execution-with-datastore/auto-ml-remote-execution-with-datastore.ipynb)
-3) You can get to the error log for the setup iteration by clicking the `Click here to see the run in Azure portal` link, click `Back to Experiment`, click on the highest run number and then click on Logs.
-
-## Remote run: disk full
-AutoML creates files under /tmp/azureml_runs for each iteration that it runs.  It creates a folder with the iteration id.  For example: AutoML_9a038a18-77cc-48f1-80fb-65abdbc33abe_93.  Under this, there is a azureml-logs folder, which contains logs.  If you run too many iterations on the same DSVM, these files can fill the disk.
-You can delete the files under /tmp/azureml_runs or just delete the VM and create a new one.
-If your get_data downloads files, make sure the delete them or they can use disk space as well.
-When using DataStore, it is good to specify an absolute path for the files so that they are downloaded just once.  If you specify a relative path, it will download a file for each iteration.
-
-## Remote run: Iterations fail and the log contains "MemoryError"
+## Iterations fail and the log contains "MemoryError"
 This can be caused by insufficient memory on the DSVM.  AutoML loads all training data into memory.  So, the available memory should be more than the training data size.
 If you are using a remote DSVM, memory is needed for each concurrent iteration.  The max_concurrent_iterations setting specifies the maximum concurrent iterations.  For example, if the training data size is 8Gb and max_concurrent_iterations is set to 10, the minimum memory required is at least 80Gb.
 To resolve this issue, allocate a DSVM with more memory or reduce the value specified for max_concurrent_iterations.
 
-## Remote run: Iterations show as "Not Responding" in the RunDetails widget.
+## Iterations show as "Not Responding" in the RunDetails widget.
 This can be caused by too many concurrent iterations for a remote DSVM.  Each concurrent iteration usually takes 100% of a core when it is running.  Some iterations can use multiple cores.  So, the max_concurrent_iterations setting should always be less than the number of cores of the DSVM.
 To resolve this issue, try reducing the value specified for the max_concurrent_iterations setting.

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

@@ -1,7 +1,6 @@
 @echo off
 set conda_env_name=%1
 set automl_env_file=%2
-set options=%3
 set PIP_NO_WARN_SCRIPT_LOCATION=0
 
 IF "%conda_env_name%"=="" SET conda_env_name="azure_automl"
@@ -12,8 +11,8 @@ IF NOT EXIST %automl_env_file% GOTO YmlMissing
 call conda activate %conda_env_name% 2>nul:
 
 if not errorlevel 1 (
-  echo Upgrading azureml-sdk[automl,notebooks,explain] in existing conda environment %conda_env_name%
-  call pip install --upgrade azureml-sdk[automl,notebooks,explain]
+  echo Upgrading azureml-sdk[automl] in existing conda environment %conda_env_name%
+  call pip install --upgrade azureml-sdk[automl,notebooks]
   if errorlevel 1 goto ErrorExit
 ) else (
   call conda env create -f %automl_env_file% -n %conda_env_name%
@@ -22,23 +21,25 @@ if not errorlevel 1 (
 call conda activate %conda_env_name% 2>nul:
 if errorlevel 1 goto ErrorExit
 
+call pip install psutil
+
 call python -m ipykernel install --user --name %conda_env_name% --display-name "Python (%conda_env_name%)"
 
-REM azureml.widgets is now installed as part of the pip install under the conda env.
-REM Removing the old user install so that the notebooks will use the latest widget.
-call jupyter nbextension uninstall --user --py azureml.widgets
+call jupyter nbextension install --py azureml.widgets --user
+if errorlevel 1 goto ErrorExit
+
+call jupyter nbextension enable --py azureml.widgets --user
+if errorlevel 1 goto ErrorExit
 
 echo.
 echo.
 echo ***************************************
 echo * AutoML setup completed successfully *
 echo ***************************************
-IF NOT "%options%"=="nolaunch" (
-  echo.
-  echo Starting jupyter notebook - please run the configuration notebook 
-  echo.
-  jupyter notebook --log-level=50 --notebook-dir='..\..'
-)
+echo.
+echo Starting jupyter notebook - please run notebook 00.configuration
+echo.
+jupyter notebook --log-level=50
 
 goto End
 

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

@@ -2,7 +2,6 @@
 
 CONDA_ENV_NAME=$1
 AUTOML_ENV_FILE=$2
-OPTIONS=$3
 PIP_NO_WARN_SCRIPT_LOCATION=0
 
 if [ "$CONDA_ENV_NAME" == "" ]
@@ -22,26 +21,23 @@ fi
 
 if source activate $CONDA_ENV_NAME 2> /dev/null
 then
-   echo "Upgrading azureml-sdk[automl,notebooks,explain] in existing conda environment" $CONDA_ENV_NAME
-   pip install --upgrade azureml-sdk[automl,notebooks,explain] &&
-   jupyter nbextension uninstall --user --py azureml.widgets
+   echo "Upgrading azureml-sdk[automl] in existing conda environment" $CONDA_ENV_NAME
+   pip install --upgrade azureml-sdk[automl,notebooks]
 else
    conda env create -f $AUTOML_ENV_FILE -n $CONDA_ENV_NAME &&
    source activate $CONDA_ENV_NAME &&
    python -m ipykernel install --user --name $CONDA_ENV_NAME --display-name "Python ($CONDA_ENV_NAME)" &&
-   jupyter nbextension uninstall --user --py azureml.widgets &&
+   jupyter nbextension install --py azureml.widgets --user &&
+   jupyter nbextension enable --py azureml.widgets --user &&
    echo "" &&
    echo "" &&
    echo "***************************************" &&
    echo "* AutoML setup completed successfully *" &&
    echo "***************************************" &&
-   if [ "$OPTIONS" != "nolaunch" ]
-   then
    echo "" &&
-      echo "Starting jupyter notebook - please run the configuration notebook" &&
+   echo "Starting jupyter notebook - please run notebook 00.configuration" &&
    echo "" &&
-      jupyter notebook --log-level=50 --notebook-dir '../..'
-   fi
+   jupyter notebook --log-level=50
 fi
 
 if [ $? -gt 0 ]

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

@@ -2,7 +2,6 @@
 
 CONDA_ENV_NAME=$1
 AUTOML_ENV_FILE=$2
-OPTIONS=$3
 PIP_NO_WARN_SCRIPT_LOCATION=0
 
 if [ "$CONDA_ENV_NAME" == "" ]
@@ -22,28 +21,25 @@ fi
 
 if source activate $CONDA_ENV_NAME 2> /dev/null
 then
-   echo "Upgrading azureml-sdk[automl,notebooks,explain] in existing conda environment" $CONDA_ENV_NAME
-   pip install --upgrade azureml-sdk[automl,notebooks,explain] &&
-   jupyter nbextension uninstall --user --py azureml.widgets
+   echo "Upgrading azureml-sdk[automl] in existing conda environment" $CONDA_ENV_NAME
+   pip install --upgrade azureml-sdk[automl,notebooks]
 else
    conda env create -f $AUTOML_ENV_FILE -n $CONDA_ENV_NAME &&
    source activate $CONDA_ENV_NAME &&
    conda install lightgbm -c conda-forge -y &&
    python -m ipykernel install --user --name $CONDA_ENV_NAME --display-name "Python ($CONDA_ENV_NAME)" &&
-   jupyter nbextension uninstall --user --py azureml.widgets &&
-   pip install numpy==1.15.3 &&
+   jupyter nbextension install --py azureml.widgets --user &&
+   jupyter nbextension enable --py azureml.widgets --user &&
+   pip install numpy==1.15.3
    echo "" &&
    echo "" &&
    echo "***************************************" &&
    echo "* AutoML setup completed successfully *" &&
    echo "***************************************" &&
-   if [ "$OPTIONS" != "nolaunch" ]
-   then
    echo "" &&
-      echo "Starting jupyter notebook - please run the configuration notebook" &&
+   echo "Starting jupyter notebook - please run notebook 00.configuration" &&
    echo "" &&
-      jupyter notebook --log-level=50 --notebook-dir '../..'
-   fi
+   jupyter notebook --log-level=50
 fi
 
 if [ $? -gt 0 ]

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

@@ -13,26 +13,11 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "# Automated Machine Learning\n",
-        "_**Classification with Deployment**_\n",
-        "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Train](#Train)\n",
-        "1. [Deploy](#Deploy)\n",
-        "1. [Test](#Test)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
+    "# Automated Machine Learning: Classification with Deployment\n",
     "\n",
     "In this example we use the scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) to showcase how you can use AutoML for a simple classification problem and deploy it to an Azure Container Instance (ACI).\n",
     "\n",
-        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+    "Make sure you have executed the [configuration](../configuration.ipynb) before running this notebook.\n",
     "\n",
     "In this notebook you will learn how to:\n",
     "1. Create an experiment using an existing workspace.\n",
@@ -42,14 +27,14 @@
     "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."
+    "8. Test the ACI service.\n"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Setup\n",
+    "## Create an Experiment\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."
    ]
@@ -62,8 +47,11 @@
    "source": [
     "import json\n",
     "import logging\n",
+    "import os\n",
+    "import random\n",
     "\n",
     "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
     "import numpy as np\n",
     "import pandas as pd\n",
     "from sklearn import datasets\n",
@@ -99,14 +87,15 @@
     "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"
+    "pd.DataFrame(data=output, index=['']).T"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Diagnostics\n",
+    "\n",
     "Opt-in diagnostics for better experience, quality, and security of future releases."
    ]
   },
@@ -124,7 +113,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Train\n",
+    "## Configure AutoML\n",
     "\n",
     "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
     "\n",
@@ -167,6 +156,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Train the Models\n",
+    "\n",
     "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."
    ]
@@ -180,21 +171,10 @@
     "local_run = experiment.submit(automl_config, show_output = True)"
    ]
   },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "local_run"
-      ]
-    },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Deploy\n",
-        "\n",
     "### Retrieve the Best Model\n",
     "\n",
     "Below we select the best pipeline from our iterations. The `get_output` method on `automl_classifier` returns the best run and the fitted model for the last invocation. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
@@ -226,8 +206,7 @@
     "description = 'AutoML Model'\n",
     "tags = None\n",
     "model = local_run.register_model(description = description, tags = tags)\n",
-        "\n",
-        "print(local_run.model_id) # This will be written to the script file later in the notebook."
+    "local_run.model_id # This will be written to the script file later in the notebook."
    ]
   },
   {
@@ -463,7 +442,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Test"
+    "### Test a Web Service"
    ]
   },
   {

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

@@ -1,398 +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",
-        "_**Classification using whitelist models**_\n",
-        "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Data](#Data)\n",
-        "1. [Train](#Train)\n",
-        "1. [Results](#Results)\n",
-        "1. [Test](#Test)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
-        "\n",
-        "In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset) to showcase how you can use AutoML for a simple classification problem.\n",
-        "\n",
-        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
-        "This notebooks shows how can automl can be trained on a a selected list of models,see the readme.md for the models.\n",
-        "This trains the model exclusively on tensorflow based models.\n",
-        "\n",
-        "In this notebook you will learn how to:\n",
-        "1. Create an `Experiment` in an existing `Workspace`.\n",
-        "2. Configure AutoML using `AutoMLConfig`.\n",
-        "3. Train the model on a whilelisted models using local compute. \n",
-        "4. Explore the results.\n",
-        "5. Test the best fitted model."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Setup\n",
-        "\n",
-        "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import logging\n",
-        "\n",
-        "from matplotlib import pyplot as plt\n",
-        "import numpy as np\n",
-        "import pandas as pd\n",
-        "from sklearn import datasets\n",
-        "\n",
-        "import azureml.core\n",
-        "from azureml.core.experiment import Experiment\n",
-        "from azureml.core.workspace import Workspace\n",
-        "from azureml.train.automl import AutoMLConfig"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ws = Workspace.from_config()\n",
-        "\n",
-        "# Choose a name for the experiment and specify the project folder.\n",
-        "experiment_name = 'automl-local-whitelist'\n",
-        "project_folder = './sample_projects/automl-local-whitelist'\n",
-        "\n",
-        "experiment = Experiment(ws, experiment_name)\n",
-        "\n",
-        "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
-        "output['Subscription ID'] = ws.subscription_id\n",
-        "output['Workspace Name'] = ws.name\n",
-        "output['Resource Group'] = ws.resource_group\n",
-        "output['Location'] = ws.location\n",
-        "output['Project Directory'] = project_folder\n",
-        "output['Experiment Name'] = experiment.name\n",
-        "pd.set_option('display.max_colwidth', -1)\n",
-        "outputDf = pd.DataFrame(data = output, index = [''])\n",
-        "outputDf.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Opt-in diagnostics for better experience, quality, and security of future releases."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.telemetry import set_diagnostics_collection\n",
-        "set_diagnostics_collection(send_diagnostics = True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Data\n",
-        "\n",
-        "This uses scikit-learn's [load_digits](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) method."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "digits = datasets.load_digits()\n",
-        "\n",
-        "# Exclude the first 100 rows from training so that they can be used for test.\n",
-        "X_train = digits.data[100:,:]\n",
-        "y_train = digits.target[100:]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Train\n",
-        "\n",
-        "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
-        "\n",
-        "|Property|Description|\n",
-        "|-|-|\n",
-        "|**task**|classification or regression|\n",
-        "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i>|\n",
-        "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
-        "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
-        "|**n_cross_validations**|Number of cross validation splits.|\n",
-        "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
-        "|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\n",
-        "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|\n",
-        "|**whitelist_models**|List of models that AutoML should use.  The possible values are listed [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#configure-your-experiment-settings).|"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "automl_config = AutoMLConfig(task = 'classification',\n",
-        "                             debug_log = 'automl_errors.log',\n",
-        "                             primary_metric = 'AUC_weighted',\n",
-        "                             iteration_timeout_minutes = 60,\n",
-        "                             iterations = 10,\n",
-        "                             n_cross_validations = 3,\n",
-        "                             verbosity = logging.INFO,\n",
-        "                             X = X_train, \n",
-        "                             y = y_train,\n",
-        "                             enable_tf=True,\n",
-        "                             whitelist_models=[\"TensorFlowLinearClassifier\", \"TensorFlowDNN\"],\n",
-        "                             path = project_folder)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
-        "In this example, we specify `show_output = True` to print currently running iterations to the console."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "local_run = experiment.submit(automl_config, show_output = True)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "local_run"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Results"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Widget for Monitoring Runs\n",
-        "\n",
-        "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
-        "\n",
-        "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.widgets import RunDetails\n",
-        "RunDetails(local_run).show() "
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "\n",
-        "#### Retrieve All Child Runs\n",
-        "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "children = list(local_run.get_children())\n",
-        "metricslist = {}\n",
-        "for run in children:\n",
-        "    properties = run.get_properties()\n",
-        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
-        "    metricslist[int(properties['iteration'])] = metrics\n",
-        "\n",
-        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
-        "rundata"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Retrieve the Best Model\n",
-        "\n",
-        "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "best_run, fitted_model = local_run.get_output()\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Best Model Based on Any Other Metric\n",
-        "Show the run and the model that has the smallest `log_loss` value:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "lookup_metric = \"log_loss\"\n",
-        "best_run, fitted_model = local_run.get_output(metric = lookup_metric)\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Model from a Specific Iteration\n",
-        "Show the run and the model from the third iteration:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "iteration = 3\n",
-        "third_run, third_model = local_run.get_output(iteration = iteration)\n",
-        "print(third_run)\n",
-        "print(third_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Test\n",
-        "\n",
-        "#### Load Test Data"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "digits = datasets.load_digits()\n",
-        "X_test = digits.data[:10, :]\n",
-        "y_test = digits.target[:10]\n",
-        "images = digits.images[:10]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Testing Our Best Fitted Model\n",
-        "We will try to predict 2 digits and see how our model works."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Randomly select digits and test.\n",
-        "for index in np.random.choice(len(y_test), 2, replace = False):\n",
-        "    print(index)\n",
-        "    predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
-        "    label = y_test[index]\n",
-        "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
-        "    fig = plt.figure(1, figsize = (3,3))\n",
-        "    ax1 = fig.add_axes((0,0,.8,.8))\n",
-        "    ax1.set_title(title)\n",
-        "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
-        "    plt.show()"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "savitam"
-      }
-    ],
-    "kernelspec": {
-      "display_name": "Python 3.6",
-      "language": "python",
-      "name": "python36"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.6.6"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

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

@@ -13,42 +13,25 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "# Automated Machine Learning\n",
-        "_**Classification with Local Compute**_\n",
-        "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Data](#Data)\n",
-        "1. [Train](#Train)\n",
-        "1. [Results](#Results)\n",
-        "1. [Test](#Test)\n",
-        "\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
+    "# Automated Machine Learning: Classification with Local Compute\n",
     "\n",
     "In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset) to showcase how you can use AutoML for a simple classification problem.\n",
     "\n",
-        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+    "Make sure you have executed the [configuration](../configuration.ipynb) before running this notebook.\n",
     "\n",
     "In this notebook you will learn how to:\n",
     "1. Create an `Experiment` in an existing `Workspace`.\n",
     "2. Configure AutoML using `AutoMLConfig`.\n",
     "3. Train the model using local compute.\n",
     "4. Explore the results.\n",
-        "5. Test the best fitted model."
+    "5. Test the best fitted model.\n"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Setup\n",
+    "## Create an Experiment\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."
    ]
@@ -60,8 +43,11 @@
    "outputs": [],
    "source": [
     "import logging\n",
+    "import os\n",
+    "import random\n",
     "\n",
     "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
     "import numpy as np\n",
     "import pandas as pd\n",
     "from sklearn import datasets\n",
@@ -69,7 +55,8 @@
     "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\n",
+    "from azureml.train.automl.run import AutoMLRun"
    ]
   },
   {
@@ -95,14 +82,15 @@
     "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"
+    "pd.DataFrame(data = output, index = ['']).T"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Diagnostics\n",
+    "\n",
     "Opt-in diagnostics for better experience, quality, and security of future releases."
    ]
   },
@@ -120,7 +108,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Data\n",
+    "## Load Training Data\n",
     "\n",
     "This uses scikit-learn's [load_digits](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) method."
    ]
@@ -131,6 +119,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from sklearn import datasets\n",
+    "\n",
     "digits = datasets.load_digits()\n",
     "\n",
     "# Exclude the first 100 rows from training so that they can be used for test.\n",
@@ -142,7 +132,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Train\n",
+    "## Configure AutoML\n",
     "\n",
     "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
     "\n",
@@ -180,6 +170,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Train the Models\n",
+    "\n",
     "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."
    ]
@@ -221,11 +213,20 @@
     "                                          iterations = 5)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Results"
+    "## Explore the Results"
    ]
   },
   {
@@ -339,7 +340,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Test \n",
+    "### Test the Best Fitted Model\n",
     "\n",
     "#### Load Test Data"
    ]

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

@@ -0,0 +1,390 @@
+{
+ "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: Classification with Local Compute with Tesnorflow DNNClassifier and LinearClassifier using whitelist models\n",
+    "\n",
+    "In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset) to showcase how you can use AutoML for a simple classification problem.\n",
+    "\n",
+    "Make sure you have executed the [configuration](../configuration.ipynb) before running this notebook.\n",
+    "This notebooks shows how can automl can be trained on a a selected list of models,see the readme.md for the models.\n",
+    "This trains the model exclusively on tensorflow based models.\n",
+    "\n",
+    "In this notebook you will learn how to:\n",
+    "1. Create an `Experiment` in an existing `Workspace`.\n",
+    "2. Configure AutoML using `AutoMLConfig`.\n",
+    "3. Train the model on a whilelisted models using local compute. \n",
+    "4. Explore the results.\n",
+    "5. Test the best fitted model.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create an Experiment\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 random\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn import datasets\n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# Choose a name for the experiment and specify the project folder.\n",
+    "experiment_name = 'automl-local-classification'\n",
+    "project_folder = './sample_projects/automl-local-classification'\n",
+    "\n",
+    "experiment = Experiment(ws, experiment_name)\n",
+    "\n",
+    "output = {}\n",
+    "output['SDK version'] = azureml.core.VERSION\n",
+    "output['Subscription ID'] = ws.subscription_id\n",
+    "output['Workspace Name'] = ws.name\n",
+    "output['Resource Group'] = ws.resource_group\n",
+    "output['Location'] = ws.location\n",
+    "output['Project Directory'] = project_folder\n",
+    "output['Experiment Name'] = experiment.name\n",
+    "pd.set_option('display.max_colwidth', -1)\n",
+    "pd.DataFrame(data = output, index = ['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Load Training Data\n",
+    "\n",
+    "This uses scikit-learn's [load_digits](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) method."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn import datasets\n",
+    "\n",
+    "digits = datasets.load_digits()\n",
+    "\n",
+    "# Exclude the first 100 rows from training so that they can be used for test.\n",
+    "X_train = digits.data[100:,:]\n",
+    "y_train = digits.target[100:]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Configure AutoML\n",
+    "\n",
+    "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
+    "\n",
+    "|Property|Description|\n",
+    "|-|-|\n",
+    "|**task**|classification or regression|\n",
+    "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i>|\n",
+    "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+    "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
+    "|**n_cross_validations**|Number of cross validation splits.|\n",
+    "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+    "|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\n",
+    "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_config = AutoMLConfig(task = 'classification',\n",
+    "                             debug_log = 'automl_errors.log',\n",
+    "                             primary_metric = 'AUC_weighted',\n",
+    "                             iteration_timeout_minutes = 60,\n",
+    "                             iterations = 10,\n",
+    "                             n_cross_validations = 3,\n",
+    "                             verbosity = logging.INFO,\n",
+    "                             X = X_train, \n",
+    "                             y = y_train,\n",
+    "                             enable_tf=True,\n",
+    "                             whitelist_models=[\"TensorFlowLinearClassifier\", \"TensorFlowDNN\"],\n",
+    "                             path = project_folder)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Train the Models\n",
+    "\n",
+    "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
+    "In this example, we specify `show_output = True` to print currently running iterations to the console."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run = experiment.submit(automl_config, show_output = True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Explore the Results"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Widget for Monitoring Runs\n",
+    "\n",
+    "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+    "\n",
+    "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.widgets import RunDetails\n",
+    "RunDetails(local_run).show() "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\n",
+    "#### Retrieve All Child Runs\n",
+    "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "children = list(local_run.get_children())\n",
+    "metricslist = {}\n",
+    "for run in children:\n",
+    "    properties = run.get_properties()\n",
+    "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+    "    metricslist[int(properties['iteration'])] = metrics\n",
+    "\n",
+    "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+    "rundata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Retrieve the Best Model\n",
+    "\n",
+    "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_model = local_run.get_output()\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Best Model Based on Any Other Metric\n",
+    "Show the run and the model that has the smallest `log_loss` value:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lookup_metric = \"log_loss\"\n",
+    "best_run, fitted_model = local_run.get_output(metric = lookup_metric)\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Model from a Specific Iteration\n",
+    "Show the run and the model from the third iteration:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "iteration = 3\n",
+    "third_run, third_model = local_run.get_output(iteration = iteration)\n",
+    "print(third_run)\n",
+    "print(third_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Test the Best Fitted Model\n",
+    "\n",
+    "#### Load Test Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "digits = datasets.load_digits()\n",
+    "X_test = digits.data[:10, :]\n",
+    "y_test = digits.target[:10]\n",
+    "images = digits.images[:10]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Testing Our Best Fitted Model\n",
+    "We will try to predict 2 digits and see how our model works."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Randomly select digits and test.\n",
+    "for index in np.random.choice(len(y_test), 2, replace = False):\n",
+    "    print(index)\n",
+    "    predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
+    "    label = y_test[index]\n",
+    "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
+    "    fig = plt.figure(1, figsize = (3,3))\n",
+    "    ax1 = fig.add_axes((0,0,.8,.8))\n",
+    "    ax1.set_title(title)\n",
+    "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
+    "    plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "savitam"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3.6",
+   "language": "python",
+   "name": "python36"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

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

@@ -13,26 +13,10 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "# Automated Machine Learning\n",
-        "_**Prepare Data using `azureml.dataprep` for Remote Execution (DSVM)**_\n",
-        "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Data](#Data)\n",
-        "1. [Train](#Train)\n",
-        "1. [Results](#Results)\n",
-        "1. [Test](#Test)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
+    "# Automated Machine Learning: Prepare Data using `azureml.dataprep` for Remote Execution (DSVM)\n",
     "In this example we showcase how you can use the `azureml.dataprep` SDK to load and prepare data for AutoML. `azureml.dataprep` can also be used standalone; full documentation can be found [here](https://github.com/Microsoft/PendletonDocs).\n",
     "\n",
-        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+    "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",
@@ -44,15 +28,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Setup\n",
+    "## Diagnostics\n",
     "\n",
-        "Currently, Data Prep only supports __Ubuntu 16__ and __Red Hat Enterprise Linux 7__. We are working on supporting more linux distros."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
     "Opt-in diagnostics for better experience, quality, and security of future releases."
    ]
   },
@@ -70,6 +47,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Create an Experiment\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."
    ]
   },
@@ -80,6 +59,7 @@
    "outputs": [],
    "source": [
     "import logging\n",
+    "import os\n",
     "import time\n",
     "\n",
     "import pandas as pd\n",
@@ -116,15 +96,14 @@
     "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"
+    "pd.DataFrame(data = output, index = ['']).T"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Data"
+    "## Loading Data using DataPrep"
    ]
   },
   {
@@ -148,6 +127,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Review the Data Preparation Result\n",
+    "\n",
     "You can peek the result of a Dataflow at any range using `skip(i)` and `head(j)`. Doing so evaluates only `j` records for all the steps in the Dataflow, which makes it fast even against large datasets."
    ]
   },
@@ -164,7 +145,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Train\n",
+    "## Configure AutoML\n",
     "\n",
     "This creates a general AutoML settings object applicable for both local and remote runs."
    ]
@@ -185,6 +166,13 @@
     "}"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Remote Run"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -265,20 +253,11 @@
     "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"
+    "## Explore the Results"
    ]
   },
   {
@@ -323,6 +302,7 @@
     "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
     "    metricslist[int(properties['iteration'])] = metrics\n",
     "    \n",
+    "import pandas as pd\n",
     "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
     "rundata"
    ]
@@ -391,7 +371,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Test\n",
+    "### Test the Best Fitted Model\n",
     "\n",
     "#### Load Test Data"
    ]
@@ -426,6 +406,8 @@
    "source": [
     "#Randomly select digits and test\n",
     "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "import random\n",
     "import numpy as np\n",
     "\n",
     "for index in np.random.choice(len(y_test), 2, replace = False):\n",
@@ -479,7 +461,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-        "print(digits_complete.to_pandas_dataframe().shape)\n",
+    "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/dataprep/auto-ml-dataprep.ipynb

@@ -13,26 +13,10 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "# Automated Machine Learning\n",
-        "_**Prepare Data using `azureml.dataprep` for Local Execution**_\n",
-        "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Data](#Data)\n",
-        "1. [Train](#Train)\n",
-        "1. [Results](#Results)\n",
-        "1. [Test](#Test)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
+    "# Automated Machine Learning: Prepare Data using `azureml.dataprep` for Local Execution\n",
     "In this example we showcase how you can use the `azureml.dataprep` SDK to load and prepare data for AutoML. `azureml.dataprep` can also be used standalone; full documentation can be found [here](https://github.com/Microsoft/PendletonDocs).\n",
     "\n",
-        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+    "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",
@@ -44,15 +28,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Setup\n",
+    "## Diagnostics\n",
     "\n",
-        "Currently, Data Prep only supports __Ubuntu 16__ and __Red Hat Enterprise Linux 7__. We are working on supporting more linux distros."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
     "Opt-in diagnostics for better experience, quality, and security of future releases."
    ]
   },
@@ -70,6 +47,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Create an Experiment\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."
    ]
   },
@@ -80,6 +59,7 @@
    "outputs": [],
    "source": [
     "import logging\n",
+    "import os\n",
     "\n",
     "import pandas as pd\n",
     "\n",
@@ -114,15 +94,14 @@
     "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"
+    "pd.DataFrame(data = output, index = ['']).T"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Data"
+    "## Loading Data using DataPrep"
    ]
   },
   {
@@ -146,7 +125,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Review the Data Preparation Result\n",
+    "## Review the Data Preparation Result\n",
     "\n",
     "You can peek the result of a Dataflow at any range using `skip(i)` and `head(j)`. Doing so evaluates only `j` records for all the steps in the Dataflow, which makes it fast even against large datasets."
    ]
@@ -164,7 +143,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Train\n",
+    "## Configure AutoML\n",
     "\n",
     "This creates a general AutoML settings object applicable for both local and remote runs."
    ]
@@ -185,6 +164,13 @@
     "}"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Local Run"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -216,20 +202,11 @@
     "local_run = experiment.submit(automl_config, show_output = True)"
    ]
   },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "local_run"
-      ]
-    },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Results"
+    "## Explore the Results"
    ]
   },
   {
@@ -274,6 +251,7 @@
     "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
     "    metricslist[int(properties['iteration'])] = metrics\n",
     "    \n",
+    "import pandas as pd\n",
     "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
     "rundata"
    ]
@@ -342,7 +320,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Test\n",
+    "### Test the Best Fitted Model\n",
     "\n",
     "#### Load Test Data"
    ]
@@ -377,6 +355,8 @@
    "source": [
     "#Randomly select digits and test\n",
     "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "import random\n",
     "import numpy as np\n",
     "\n",
     "for index in np.random.choice(len(y_test), 2, replace = False):\n",
@@ -430,7 +410,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-        "print(digits_complete.to_pandas_dataframe().shape)\n",
+    "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/exploring-previous-runs/auto-ml-exploring-previous-runs.ipynb

@@ -13,38 +13,24 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "# Automated Machine Learning\n",
-        "_**Exploring Previous Runs**_\n",
+    "# Automated Machine Learning: Exploring Previous Runs\n",
     "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Explore](#Explore)\n",
-        "1. [Download](#Download)\n",
-        "1. [Register](#Register)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
     "In this example we present some examples on navigating previously executed runs. We also show how you can download a fitted model for any previous run.\n",
     "\n",
-        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+    "Make sure you have executed the [configuration](../configuration.ipynb) before running this notebook.\n",
     "\n",
     "In this notebook you will learn how to:\n",
     "1. List all experiments in a workspace.\n",
     "2. List all AutoML runs in an experiment.\n",
     "3. Get details for an AutoML run, including settings, run widget, and all metrics.\n",
-        "4. Download a fitted pipeline for any iteration."
+    "4. Download a fitted pipeline for any iteration.\n"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Setup"
+    "# List all AutoML Experiments in a Workspace"
    ]
   },
   {
@@ -53,11 +39,22 @@
    "metadata": {},
    "outputs": [],
    "source": [
-        "import pandas as pd\n",
-        "import json\n",
+    "import logging\n",
+    "import os\n",
+    "import random\n",
+    "import re\n",
     "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\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.run import Run\n",
     "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
     "from azureml.train.automl.run import AutoMLRun"
    ]
   },
@@ -67,13 +64,29 @@
    "metadata": {},
    "outputs": [],
    "source": [
-        "ws = Workspace.from_config()"
+    "ws = Workspace.from_config()\n",
+    "experiment_list = Experiment.list(workspace=ws)\n",
+    "\n",
+    "summary_df = pd.DataFrame(index = ['No of Runs'])\n",
+    "pattern = re.compile('^AutoML_[^_]*$')\n",
+    "for experiment in experiment_list:\n",
+    "    all_runs = list(experiment.get_runs())\n",
+    "    automl_runs = []\n",
+    "    for run in all_runs:\n",
+    "        if(pattern.match(run.id)):\n",
+    "            automl_runs.append(run)    \n",
+    "    summary_df[experiment.name] = [len(automl_runs)]\n",
+    "    \n",
+    "pd.set_option('display.max_colwidth', -1)\n",
+    "summary_df.T"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Diagnostics\n",
+    "\n",
     "Opt-in diagnostics for better experience, quality, and security of future releases."
    ]
   },
@@ -91,38 +104,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Explore"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### List Experiments"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "experiment_list = Experiment.list(workspace=ws)\n",
-        "\n",
-        "summary_df = pd.DataFrame(index = ['No of Runs'])\n",
-        "for experiment in experiment_list:\n",
-        "    automl_runs = list(experiment.get_runs(type='automl'))\n",
-        "    summary_df[experiment.name] = [len(automl_runs)]\n",
-        "    \n",
-        "pd.set_option('display.max_colwidth', -1)\n",
-        "summary_df.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### List runs for an experiment\n",
+    "# List AutoML runs for an experiment\n",
     "Set `experiment_name` to any experiment name from the result of the Experiment.list cell to load the AutoML runs."
    ]
   },
@@ -136,12 +118,14 @@
     "\n",
     "proj = ws.experiments[experiment_name]\n",
     "summary_df = pd.DataFrame(index = ['Type', 'Status', 'Primary Metric', 'Iterations', 'Compute', 'Name'])\n",
-        "automl_runs = list(proj.get_runs(type='automl'))\n",
+    "pattern = re.compile('^AutoML_[^_]*$')\n",
+    "all_runs = list(proj.get_runs(properties={'azureml.runsource': 'automl'}))\n",
     "automl_runs_project = []\n",
-        "for run in automl_runs:\n",
+    "for run in all_runs:\n",
+    "    if(pattern.match(run.id)):\n",
     "        properties = run.get_properties()\n",
     "        tags = run.get_tags()\n",
-        "    amlsettings = json.loads(properties['AMLSettingsJsonString'])\n",
+    "        amlsettings = eval(properties['RawAMLSettingsString'])\n",
     "        if 'iterations' in tags:\n",
     "            iterations = tags['iterations']\n",
     "        else:\n",
@@ -162,7 +146,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Get details for a run\n",
+    "# Get details for an AutoML run\n",
     "\n",
     "Copy the project name and run id from the previous cell output to find more details on a particular run."
    ]
@@ -185,7 +169,7 @@
     "properties = ml_run.get_properties()\n",
     "tags = ml_run.get_tags()\n",
     "status = ml_run.get_details()\n",
-        "amlsettings = json.loads(properties['AMLSettingsJsonString'])\n",
+    "amlsettings = eval(properties['RawAMLSettingsString'])\n",
     "if 'iterations' in tags:\n",
     "    iterations = tags['iterations']\n",
     "else:\n",
@@ -223,14 +207,14 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Download"
+    "# Download fitted models"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Download the Best Model for Any Given Metric"
+    "## Download the Best Model for Any Given Metric"
    ]
   },
   {
@@ -248,7 +232,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Download the Model for Any Given Iteration"
+    "## Download the Model for Any Given Iteration"
    ]
   },
   {
@@ -266,14 +250,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Register"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Register fitted model for deployment\n",
+    "# Register fitted model for deployment\n",
     "If neither `metric` nor `iteration` are specified in the `register_model` call, the iteration with the best primary metric is registered."
    ]
   },
@@ -286,14 +263,14 @@
     "description = 'AutoML Model'\n",
     "tags = None\n",
     "ml_run.register_model(description = description, tags = tags)\n",
-        "print(ml_run.model_id) # Use this id to deploy the model as a web service in Azure."
+    "ml_run.model_id # Use this id to deploy the model as a web service in Azure."
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Register the Best Model for Any Given Metric"
+    "## Register the Best Model for Any Given Metric"
    ]
   },
   {
@@ -313,7 +290,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Register the Model for Any Given Iteration"
+    "## Register the Model for Any Given Iteration"
    ]
   },
   {

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

@@ -0,0 +1,398 @@
+{
+ "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: Energy Demand Forecasting\n",
+    "\n",
+    "In this example, we show how AutoML can be used for energy demand forecasting.\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. Creating an Experiment in an existing Workspace\n",
+    "2. Instantiating AutoMLConfig with new task type \"forecasting\" for timeseries data training, and other timeseries related settings: for this dataset we use the basic one: \"time_column_name\" \n",
+    "3. Training the Model using local compute\n",
+    "4. Exploring the results\n",
+    "5. Testing the fitted model"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create Experiment\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 azureml.core\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import os\n",
+    "import logging\n",
+    "import warnings\n",
+    "# Squash warning messages for cleaner output in the notebook\n",
+    "warnings.showwarning = lambda *args, **kwargs: None\n",
+    "\n",
+    "\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
+    "from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score"
+   ]
+  },
+  {
+   "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-energydemandforecasting'\n",
+    "# project folder\n",
+    "project_folder = './sample_projects/automl-local-energydemandforecasting'\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['Run History Name'] = experiment_name\n",
+    "pd.set_option('display.max_colwidth', -1)\n",
+    "pd.DataFrame(data=output, index=['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Read Data\n",
+    "Read energy demanding data from file, and preview data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = pd.read_csv(\"nyc_energy.csv\", parse_dates=['timeStamp'])\n",
+    "data.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Split the data to train and test\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train = data[data['timeStamp'] < '2017-02-01']\n",
+    "test = data[data['timeStamp'] >= '2017-02-01']\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Prepare the test data, we will feed X_test to the fitted model and get prediction"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_test = test.pop('demand').values\n",
+    "X_test = test"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Split the train data to train and valid\n",
+    "\n",
+    "Use one month's data as valid data\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train = train[train['timeStamp'] < '2017-01-01']\n",
+    "X_valid = train[train['timeStamp'] >= '2017-01-01']\n",
+    "y_train = X_train.pop('demand').values\n",
+    "y_valid = X_valid.pop('demand').values\n",
+    "print(X_train.shape)\n",
+    "print(y_train.shape)\n",
+    "print(X_valid.shape)\n",
+    "print(y_valid.shape)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiate Auto ML Config\n",
+    "\n",
+    "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
+    "\n",
+    "|Property|Description|\n",
+    "|-|-|\n",
+    "|**task**|forecasting|\n",
+    "|**primary_metric**|This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>\n",
+    "|**iterations**|Number of iterations. In each iteration, Auto ML trains a specific pipeline on the given data|\n",
+    "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+    "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+    "|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification.  This should be an array of integers. |\n",
+    "|**X_valid**|Data used to evaluate a model in a iteration. (sparse) array-like, shape = [n_samples, n_features]|\n",
+    "|**y_valid**|Data used to evaluate a model in a iteration. (sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification.  This should be an array of integers. |\n",
+    "|**path**|Relative path to the project folder.  AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "time_column_name = 'timeStamp'\n",
+    "automl_settings = {\n",
+    "    \"time_column_name\": time_column_name,\n",
+    "}\n",
+    "\n",
+    "\n",
+    "automl_config = AutoMLConfig(task = 'forecasting',\n",
+    "                             debug_log = 'automl_nyc_energy_errors.log',\n",
+    "                             primary_metric='normalized_root_mean_squared_error',\n",
+    "                             iterations = 10,\n",
+    "                             iteration_timeout_minutes = 5,\n",
+    "                             X = X_train,\n",
+    "                             y = y_train,\n",
+    "                             X_valid = X_valid,\n",
+    "                             y_valid = y_valid,\n",
+    "                             path=project_folder,\n",
+    "                             verbosity = logging.INFO,\n",
+    "                            **automl_settings)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Training the Model\n",
+    "\n",
+    "You can call the submit method on the experiment object and pass the run configuration. For Local runs the execution is synchronous. Depending on the data and number of iterations this can run for while.\n",
+    "You will see the currently running iterations printing to the console."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run = experiment.submit(automl_config, show_output=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Retrieve the Best Model\n",
+    "Below we select the best pipeline from our iterations. The get_output method on automl_classifier returns the best run and the fitted model for the last fit invocation. There are overloads on get_output that allow you to retrieve the best run and fitted model for any logged metric or a particular iteration."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_model = local_run.get_output()\n",
+    "fitted_model.steps"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Test the Best Fitted Model\n",
+    "\n",
+    "Predict on training and test set, and calculate residual values."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = fitted_model.predict(X_test)\n",
+    "y_pred"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Define a Check Data Function\n",
+    "\n",
+    "Remove the nan values from y_test to avoid error when calculate metrics "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def _check_calc_input(y_true, y_pred, rm_na=True):\n",
+    "    \"\"\"\n",
+    "    Check that 'y_true' and 'y_pred' are non-empty and\n",
+    "    have equal length.\n",
+    "\n",
+    "    :param y_true: Vector of actual values\n",
+    "    :type y_true: array-like\n",
+    "\n",
+    "    :param y_pred: Vector of predicted values\n",
+    "    :type y_pred: array-like\n",
+    "\n",
+    "    :param rm_na:\n",
+    "        If rm_na=True, remove entries where y_true=NA and y_pred=NA.\n",
+    "    :type rm_na: boolean\n",
+    "\n",
+    "    :return:\n",
+    "        Tuple (y_true, y_pred). if rm_na=True,\n",
+    "        the returned vectors may differ from their input values.\n",
+    "    :rtype: Tuple with 2 entries\n",
+    "    \"\"\"\n",
+    "    if len(y_true) != len(y_pred):\n",
+    "        raise ValueError(\n",
+    "            'the true values and prediction values do not have equal length.')\n",
+    "    elif len(y_true) == 0:\n",
+    "        raise ValueError(\n",
+    "            'y_true and y_pred are empty.')\n",
+    "    # if there is any non-numeric element in the y_true or y_pred,\n",
+    "    # the ValueError exception will be thrown.\n",
+    "    y_true = np.array(y_true).astype(float)\n",
+    "    y_pred = np.array(y_pred).astype(float)\n",
+    "    if rm_na:\n",
+    "        # remove entries both in y_true and y_pred where at least\n",
+    "        # one element in y_true or y_pred is missing\n",
+    "        y_true_rm_na = y_true[~(np.isnan(y_true) | np.isnan(y_pred))]\n",
+    "        y_pred_rm_na = y_pred[~(np.isnan(y_true) | np.isnan(y_pred))]\n",
+    "        return (y_true_rm_na, y_pred_rm_na)\n",
+    "    else:\n",
+    "        return y_true, y_pred"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Use the Check Data Function to remove the nan values from y_test to avoid error when calculate metrics "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_test,y_pred =  _check_calc_input(y_test,y_pred)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Calculate metrics for the prediction\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(\"[Test Data] \\nRoot Mean squared error: %.2f\" % np.sqrt(mean_squared_error(y_test, y_pred)))\n",
+    "# Explained variance score: 1 is perfect prediction\n",
+    "print('mean_absolute_error score: %.2f' % mean_absolute_error(y_test, y_pred))\n",
+    "print('R2 score: %.2f' % r2_score(y_test, y_pred))\n",
+    "\n",
+    "\n",
+    "\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()"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "xiaga"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3.6",
+   "language": "python",
+   "name": "python36"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

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

@@ -0,0 +1,394 @@
+{
+ "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: Orange Juice Sales Forecasting\n",
+    "\n",
+    "In this example, we use AutoML to find and tune a time-series forecasting model.\n",
+    "\n",
+    "Make sure you have executed the [configuration notebook](../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",
+    "## Sample Data\n",
+    "The examples in the follow code samples use the [University of Chicago's Dominick's Finer Foods dataset](https://research.chicagobooth.edu/kilts/marketing-databases/dominicks) to forecast orange juice sales. Dominick's was a grocery chain in the Chicago metropolitan area."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create Experiment\n",
+    "\n",
+    "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. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import azureml.core\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import os\n",
+    "import logging\n",
+    "import warnings\n",
+    "# Squash warning messages for cleaner output in the notebook\n",
+    "warnings.showwarning = lambda *args, **kwargs: None\n",
+    "\n",
+    "\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun\n",
+    "from sklearn.metrics import mean_absolute_error, mean_squared_error"
+   ]
+  },
+  {
+   "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-ojsalesforecasting'\n",
+    "# project folder\n",
+    "project_folder = './sample_projects/automl-local-ojsalesforecasting'\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['Run History Name'] = experiment_name\n",
+    "pd.set_option('display.max_colwidth', -1)\n",
+    "pd.DataFrame(data=output, index=['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Read Data\n",
+    "You are now ready to load the historical orange juice sales data. We will load the CSV file into a plain pandas DataFrame; the time column in the CSV is called _WeekStarting_, so it will be specially parsed into the datetime type."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "time_column_name = 'WeekStarting'\n",
+    "data = pd.read_csv(\"dominicks_OJ.csv\", parse_dates=[time_column_name])\n",
+    "data.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Each row in the DataFrame holds a quantity of weekly sales for an OJ brand at a single store. The data also includes the sales price, a flag indicating if the OJ brand was advertised in the store that week, and some customer demographic information based on the store location. For historical reasons, the data also include the logarithm of the sales quantity. The Dominick's grocery data is commonly used to illustrate econometric modeling techniques where logarithms of quantities are generally preferred.    \n",
+    "\n",
+    "The task is now to build a time-series model for the _Quantity_ column. It is important to note that this dataset is comprised of many individual time-series - one for each unique combination of _Store_ and _Brand_. To distinguish the individual time-series, we thus define the **grain** - the columns whose values determine the boundaries between time-series: "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "grain_column_names = ['Store', 'Brand']\n",
+    "nseries = data.groupby(grain_column_names).ngroups\n",
+    "print('Data contains {0} individual time-series.'.format(nseries))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Data Splitting\n",
+    "For the purposes of demonstration and later forecast evaluation, we now split the data into a training and a testing set. The test set will contain the final 20 weeks of observed sales for each time-series."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ntest_periods = 20\n",
+    "\n",
+    "def split_last_n_by_grain(df, n):\n",
+    "    \"\"\"\n",
+    "    Group df by grain and split on last n rows for each group\n",
+    "    \"\"\"\n",
+    "    df_grouped = (df.sort_values(time_column_name) # Sort by ascending time\n",
+    "                  .groupby(grain_column_names, group_keys=False))\n",
+    "    df_head = df_grouped.apply(lambda dfg: dfg.iloc[:-n])\n",
+    "    df_tail = df_grouped.apply(lambda dfg: dfg.iloc[-n:])\n",
+    "    return df_head, df_tail\n",
+    "\n",
+    "X_train, X_test = split_last_n_by_grain(data, ntest_periods)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Modeling\n",
+    "\n",
+    "For forecasting tasks, AutoML uses pre-processing and estimation steps that are specific to time-series. AutoML will undertake the following pre-processing steps:\n",
+    "* Detect time-series sample frequency (e.g. hourly, daily, weekly) and create new records for absent time points to make the series regular. A regular time series has a well-defined frequency and has a value at every sample point in a contiguous time span \n",
+    "* Impute missing values in the target (via forward-fill) and feature columns (using median column values) \n",
+    "* Create grain-based features to enable fixed effects across different series\n",
+    "* Create time-based features to assist in learning seasonal patterns\n",
+    "* Encode categorical variables to numeric quantities\n",
+    "\n",
+    "AutoML will currently train a single, regression-type model across **all** time-series in a given training set. This allows the model to generalize across related series.\n",
+    "\n",
+    "You are almost ready to start an AutoML training job. We will first need to create a validation set from the existing training set (i.e. for hyper-parameter tuning): "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "nvalidation_periods = 20\n",
+    "X_train, X_validate = split_last_n_by_grain(X_train, nvalidation_periods)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We also need to separate the target column from the rest of the DataFrame: "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "target_column_name = 'Quantity'\n",
+    "y_train = X_train.pop(target_column_name).values\n",
+    "y_validate = X_validate.pop(target_column_name).values "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create an AutoMLConfig\n",
+    "\n",
+    "The AutoMLConfig object defines the settings and data for an AutoML training job. Here, we set necessary inputs like the task type, the number of AutoML iterations to try, and the training and validation data. \n",
+    "\n",
+    "For forecasting tasks, there are some additional parameters that can be set: the name of the input data column, holding the date/time and the grain column names. A time column is required for forecasting, while the grain is optional. If a grain is not given, the forecaster 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",
+    "|Property|Description|\n",
+    "|-|-|\n",
+    "|**task**|forecasting|\n",
+    "|**primary_metric**|This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>\n",
+    "|**iterations**|Number of iterations. In each iteration, Auto ML trains a specific pipeline on the given data|\n",
+    "|**X**|Training matrix of features, shape = [n_training_samples, n_features]|\n",
+    "|**y**|Target values, shape = [n_training_samples, ]|\n",
+    "|**X_valid**|Validation matrix of features, shape = [n_validation_samples, n_features]|\n",
+    "|**y_valid**|Target values for validation, shape = [n_validation_samples, ]\n",
+    "|**enable_ensembling**|Allow AutoML to create ensembles of the best performing models\n",
+    "|**debug_log**|Log file path for writing debugging information\n",
+    "|**path**|Relative path to the project folder.  AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_settings = {\n",
+    "    'time_column_name': time_column_name,\n",
+    "    'grain_column_names': grain_column_names,\n",
+    "    'drop_column_names': ['logQuantity']\n",
+    "}\n",
+    "\n",
+    "automl_config = AutoMLConfig(task='forecasting',\n",
+    "                             debug_log='automl_oj_sales_errors.log',\n",
+    "                             primary_metric='normalized_root_mean_squared_error',\n",
+    "                             iterations=10,\n",
+    "                             X=X_train,\n",
+    "                             y=y_train,\n",
+    "                             X_valid=X_validate,\n",
+    "                             y_valid=y_validate,\n",
+    "                             enable_ensembling=False,\n",
+    "                             path=project_folder,\n",
+    "                             verbosity=logging.INFO,\n",
+    "                            **automl_settings)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Training the Model\n",
+    "\n",
+    "You can now submit a new training run. For local runs, the execution is synchronous. Depending on the data and number of iterations this operation may take several minutes.\n",
+    "Information from each iteration will be printed to the console."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run = experiment.submit(automl_config, show_output=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Retrieve the Best Model\n",
+    "Each run within an Experiment stores serialized (i.e. pickled) pipelines from the AutoML iterations. We can now retrieve the pipeline with the best performance on the validation dataset:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_pipeline = local_run.get_output()\n",
+    "fitted_pipeline.steps"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Make Predictions from the Best Fitted Model\n",
+    "Now that we have retrieved the best pipeline/model, it can be used to make predictions on test data. First, we remove the target values from the test set:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_test = X_test.pop(target_column_name).values"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_test.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To produce predictions on the test set, we need to know the feature values at all dates in the test set. This requirement is somewhat reasonable for the OJ sales data since the features mainly consist of price, which is usually set in advance, and customer demographics which are approximately constant for each store over the 20 week forecast horizon in the testing data. \n",
+    "\n",
+    "The target predictions can be retrieved by calling the `predict` method on the best model:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = fitted_pipeline.predict(X_test)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Calculate evaluation metrics for the prediction\n",
+    "To evaluate the accuracy of the forecast, we'll compare against the actual sales quantities for some select metrics, included the mean absolute percentage error (MAPE)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def MAPE(actual, pred):\n",
+    "    \"\"\"\n",
+    "    Calculate mean absolute percentage error.\n",
+    "    Remove NA and values where actual is close to zero\n",
+    "    \"\"\"\n",
+    "    not_na = ~(np.isnan(actual) | np.isnan(pred))\n",
+    "    not_zero = ~np.isclose(actual, 0.0)\n",
+    "    actual_safe = actual[not_na & not_zero]\n",
+    "    pred_safe = pred[not_na & not_zero]\n",
+    "    APE = 100*np.abs((actual_safe - pred_safe)/actual_safe)\n",
+    "    return np.mean(APE)\n",
+    "\n",
+    "print(\"[Test Data] \\nRoot Mean squared error: %.2f\" % np.sqrt(mean_squared_error(y_test, y_pred)))\n",
+    "print('mean_absolute_error score: %.2f' % mean_absolute_error(y_test, y_pred))\n",
+    "print('MAPE: %.2f' % MAPE(y_test, y_pred))"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "erwright"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3.6",
+   "language": "python",
+   "name": "python36"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

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

@@ -1,405 +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",
-        "_**Energy Demand Forecasting**_\n",
-        "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Data](#Data)\n",
-        "1. [Train](#Train)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
-        "In this example, we show how AutoML can be used for energy demand forecasting.\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. Creating an Experiment in an existing Workspace\n",
-        "2. Instantiating AutoMLConfig with new task type \"forecasting\" for timeseries data training, and other timeseries related settings: for this dataset we use the basic one: \"time_column_name\" \n",
-        "3. Training the Model using local compute\n",
-        "4. Exploring the results\n",
-        "5. Testing the fitted model"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Setup\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "To use the *forecasting* task in AutoML, you need to have the **azuremlftk** package installed in your environment. The following cell tests whether this package is installed locally and, if not, gives you instructions for installing it.  "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "try:\n",
-        "    import ftk\n",
-        "    print('Using FTK version ' + ftk.__version__)\n",
-        "except ImportError:\n",
-        "    print(\"Unable to import forecasting package. This notebook does not work without this package.\\n\"\n",
-        "          + \"Please open a command prompt and run `pip install azuremlftk` to install the package. \\n\"\n",
-        "          + \"Make sure you install the package into AutoML's Python environment.\\n\\n\"\n",
-        "          + \"For instance, if AutoML is installed in a conda environment called `python36`, run:\\n\"\n",
-        "          + \"> activate python36\\n> pip install azuremlftk\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import azureml.core\n",
-        "import pandas as pd\n",
-        "import numpy as np\n",
-        "import logging\n",
-        "import warnings\n",
-        "# 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",
-        "from matplotlib import pyplot as plt\n",
-        "from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score"
-      ]
-    },
-    {
-      "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."
-      ]
-    },
-    {
-      "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-energydemandforecasting'\n",
-        "# project folder\n",
-        "project_folder = './sample_projects/automl-local-energydemandforecasting'\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['Run History Name'] = experiment_name\n",
-        "pd.set_option('display.max_colwidth', -1)\n",
-        "outputDf = pd.DataFrame(data = output, index = [''])\n",
-        "outputDf.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Data\n",
-        "Read energy demanding data from file, and preview data."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "data = pd.read_csv(\"nyc_energy.csv\", parse_dates=['timeStamp'])\n",
-        "data.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Split the data to train and test\n",
-        "\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "train = data[data['timeStamp'] < '2017-02-01']\n",
-        "test = data[data['timeStamp'] >= '2017-02-01']\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Prepare the test data, we will feed X_test to the fitted model and get prediction"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "y_test = test.pop('demand').values\n",
-        "X_test = test"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Split the train data to train and valid\n",
-        "\n",
-        "Use one month's data as valid data\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "X_train = train[train['timeStamp'] < '2017-01-01']\n",
-        "X_valid = train[train['timeStamp'] >= '2017-01-01']\n",
-        "y_train = X_train.pop('demand').values\n",
-        "y_valid = X_valid.pop('demand').values\n",
-        "print(X_train.shape)\n",
-        "print(y_train.shape)\n",
-        "print(X_valid.shape)\n",
-        "print(y_valid.shape)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Train\n",
-        "\n",
-        "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
-        "\n",
-        "|Property|Description|\n",
-        "|-|-|\n",
-        "|**task**|forecasting|\n",
-        "|**primary_metric**|This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>\n",
-        "|**iterations**|Number of iterations. In each iteration, Auto ML trains a specific pipeline on the given data|\n",
-        "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
-        "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
-        "|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification.  This should be an array of integers. |\n",
-        "|**X_valid**|Data used to evaluate a model in a iteration. (sparse) array-like, shape = [n_samples, n_features]|\n",
-        "|**y_valid**|Data used to evaluate a model in a iteration. (sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification.  This should be an array of integers. |\n",
-        "|**path**|Relative path to the project folder.  AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder. "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "time_column_name = 'timeStamp'\n",
-        "automl_settings = {\n",
-        "    \"time_column_name\": time_column_name,\n",
-        "}\n",
-        "\n",
-        "\n",
-        "automl_config = AutoMLConfig(task = 'forecasting',\n",
-        "                             debug_log = 'automl_nyc_energy_errors.log',\n",
-        "                             primary_metric='normalized_root_mean_squared_error',\n",
-        "                             iterations = 10,\n",
-        "                             iteration_timeout_minutes = 5,\n",
-        "                             X = X_train,\n",
-        "                             y = y_train,\n",
-        "                             X_valid = X_valid,\n",
-        "                             y_valid = y_valid,\n",
-        "                             path=project_folder,\n",
-        "                             verbosity = logging.INFO,\n",
-        "                            **automl_settings)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "You can call the submit method on the experiment object and pass the run configuration. For Local runs the execution is synchronous. Depending on the data and number of iterations this can run for while.\n",
-        "You will see the currently running iterations printing to the console."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "local_run = experiment.submit(automl_config, show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "local_run"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Retrieve the Best Model\n",
-        "Below we select the best pipeline from our iterations. The get_output method on automl_classifier returns the best run and the fitted model for the last fit invocation. There are overloads on get_output that allow you to retrieve the best run and fitted model for any logged metric or a particular iteration."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "best_run, fitted_model = local_run.get_output()\n",
-        "fitted_model.steps"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Test the Best Fitted Model\n",
-        "\n",
-        "Predict on training and test set, and calculate residual values."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "y_pred = fitted_model.predict(X_test)\n",
-        "y_pred"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Use the Check Data Function to remove the nan values from y_test to avoid error when calculate metrics "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "if len(y_test) != len(y_pred):\n",
-        "    raise ValueError(\n",
-        "        'the true values and prediction values do not have equal length.')\n",
-        "elif len(y_test) == 0:\n",
-        "    raise ValueError(\n",
-        "        'y_true and y_pred are empty.')\n",
-        "\n",
-        "# if there is any non-numeric element in the y_true or y_pred,\n",
-        "# the ValueError exception will be thrown.\n",
-        "y_test_f = np.array(y_test).astype(float)\n",
-        "y_pred_f = np.array(y_pred).astype(float)\n",
-        "\n",
-        "# remove entries both in y_true and y_pred where at least\n",
-        "# one element in y_true or y_pred is missing\n",
-        "y_test = y_test_f[~(np.isnan(y_test_f) | np.isnan(y_pred_f))]\n",
-        "y_pred = y_pred_f[~(np.isnan(y_test_f) | np.isnan(y_pred_f))]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Calculate metrics for the prediction\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "print(\"[Test Data] \\nRoot Mean squared error: %.2f\" % np.sqrt(mean_squared_error(y_test, y_pred)))\n",
-        "# Explained variance score: 1 is perfect prediction\n",
-        "print('mean_absolute_error score: %.2f' % mean_absolute_error(y_test, y_pred))\n",
-        "print('R2 score: %.2f' % r2_score(y_test, y_pred))\n",
-        "\n",
-        "\n",
-        "\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()"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "xiaga"
-      }
-    ],
-    "kernelspec": {
-      "display_name": "Python 3.6",
-      "language": "python",
-      "name": "python36"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.6.8"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

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

@@ -1,441 +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",
-        "_**Orange Juice Sales Forecasting**_\n",
-        "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Data](#Data)\n",
-        "1. [Train](#Train)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
-        "In this example, we use AutoML to find and tune a time-series forecasting model.\n",
-        "\n",
-        "Make sure you have executed the [configuration notebook](../../../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](https://research.chicagobooth.edu/kilts/marketing-databases/dominicks) to forecast orange juice sales. Dominick's was a grocery chain in the Chicago metropolitan area."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Setup"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "To use the *forecasting* task in AutoML, you need to have the **azuremlftk** package installed in your environment. The following cell tests whether this package is installed locally and, if not, gives you instructions for installing it."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "try:\n",
-        "    import ftk\n",
-        "    print('Using FTK version ' + ftk.__version__)\n",
-        "except ImportError:\n",
-        "    print(\"Unable to import forecasting package. This notebook does not work without this package.\\n\"\n",
-        "          + \"Please open a command prompt and run `pip install azuremlftk` to install the package. \\n\"\n",
-        "          + \"Make sure you install the package into AutoML's Python environment.\\n\\n\"\n",
-        "          + \"For instance, if AutoML is installed in a conda environment called `python36`, run:\\n\"\n",
-        "          + \"> activate python36\\n> pip install azuremlftk\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import azureml.core\n",
-        "import pandas as pd\n",
-        "import numpy as np\n",
-        "import logging\n",
-        "import warnings\n",
-        "# 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",
-        "from sklearn.metrics import mean_absolute_error, mean_squared_error"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "As part of the setup you have already created a <b>Workspace</b>. To run AutoML, you also need to create an <b>Experiment</b>. An Experiment 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. "
-      ]
-    },
-    {
-      "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-ojsalesforecasting'\n",
-        "# project folder\n",
-        "project_folder = './sample_projects/automl-local-ojsalesforecasting'\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['Run History Name'] = experiment_name\n",
-        "pd.set_option('display.max_colwidth', -1)\n",
-        "outputDf = pd.DataFrame(data = output, index = [''])\n",
-        "outputDf.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Data\n",
-        "You are now ready to load the historical orange juice sales data. We will load the CSV file into a plain pandas DataFrame; the time column in the CSV is called _WeekStarting_, so it will be specially parsed into the datetime type."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "time_column_name = 'WeekStarting'\n",
-        "data = pd.read_csv(\"dominicks_OJ.csv\", parse_dates=[time_column_name])\n",
-        "data.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Each row in the DataFrame holds a quantity of weekly sales for an OJ brand at a single store. The data also includes the sales price, a flag indicating if the OJ brand was advertised in the store that week, and some customer demographic information based on the store location. For historical reasons, the data also include the logarithm of the sales quantity. The Dominick's grocery data is commonly used to illustrate econometric modeling techniques where logarithms of quantities are generally preferred.    \n",
-        "\n",
-        "The task is now to build a time-series model for the _Quantity_ column. It is important to note that this dataset is comprised of many individual time-series - one for each unique combination of _Store_ and _Brand_. To distinguish the individual time-series, we thus define the **grain** - the columns whose values determine the boundaries between time-series: "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "grain_column_names = ['Store', 'Brand']\n",
-        "nseries = data.groupby(grain_column_names).ngroups\n",
-        "print('Data contains {0} individual time-series.'.format(nseries))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Data Splitting\n",
-        "For the purposes of demonstration and later forecast evaluation, we now split the data into a training and a testing set. The test set will contain the final 20 weeks of observed sales for each time-series."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ntest_periods = 20\n",
-        "\n",
-        "def split_last_n_by_grain(df, n):\n",
-        "    \"\"\"\n",
-        "    Group df by grain and split on last n rows for each group\n",
-        "    \"\"\"\n",
-        "    df_grouped = (df.sort_values(time_column_name) # Sort by ascending time\n",
-        "                  .groupby(grain_column_names, group_keys=False))\n",
-        "    df_head = df_grouped.apply(lambda dfg: dfg.iloc[:-n])\n",
-        "    df_tail = df_grouped.apply(lambda dfg: dfg.iloc[-n:])\n",
-        "    return df_head, df_tail\n",
-        "\n",
-        "X_train, X_test = split_last_n_by_grain(data, ntest_periods)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Modeling\n",
-        "\n",
-        "For forecasting tasks, AutoML uses pre-processing and estimation steps that are specific to time-series. AutoML will undertake the following pre-processing steps:\n",
-        "* Detect time-series sample frequency (e.g. hourly, daily, weekly) and create new records for absent time points to make the series regular. A regular time series has a well-defined frequency and has a value at every sample point in a contiguous time span \n",
-        "* Impute missing values in the target (via forward-fill) and feature columns (using median column values) \n",
-        "* Create grain-based features to enable fixed effects across different series\n",
-        "* Create time-based features to assist in learning seasonal patterns\n",
-        "* Encode categorical variables to numeric quantities\n",
-        "\n",
-        "AutoML will currently train a single, regression-type model across **all** time-series in a given training set. This allows the model to generalize across related series.\n",
-        "\n",
-        "You are almost ready to start an AutoML training job. We will first need to create a validation set from the existing training set (i.e. for hyper-parameter tuning): "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "nvalidation_periods = 20\n",
-        "X_train, X_validate = split_last_n_by_grain(X_train, nvalidation_periods)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "We also need to separate the target column from the rest of the DataFrame: "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "target_column_name = 'Quantity'\n",
-        "y_train = X_train.pop(target_column_name).values\n",
-        "y_validate = X_validate.pop(target_column_name).values "
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Train\n",
-        "\n",
-        "The AutoMLConfig object defines the settings and data for an AutoML training job. Here, we set necessary inputs like the task type, the number of AutoML iterations to try, and the training and validation data. \n",
-        "\n",
-        "For forecasting tasks, there are some additional parameters that can be set: the name of the column holding the date/time and the grain column names. A time column is required for forecasting, while the grain is optional. If a grain is not given, the forecaster 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",
-        "|Property|Description|\n",
-        "|-|-|\n",
-        "|**task**|forecasting|\n",
-        "|**primary_metric**|This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>\n",
-        "|**iterations**|Number of iterations. In each iteration, Auto ML trains a specific pipeline on the given data|\n",
-        "|**X**|Training matrix of features, shape = [n_training_samples, n_features]|\n",
-        "|**y**|Target values, shape = [n_training_samples, ]|\n",
-        "|**X_valid**|Validation matrix of features, shape = [n_validation_samples, n_features]|\n",
-        "|**y_valid**|Target values for validation, shape = [n_validation_samples, ]\n",
-        "|**enable_ensembling**|Allow AutoML to create ensembles of the best performing models\n",
-        "|**debug_log**|Log file path for writing debugging information\n",
-        "|**path**|Relative path to the project folder.  AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder. "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "automl_settings = {\n",
-        "    'time_column_name': time_column_name,\n",
-        "    'grain_column_names': grain_column_names,\n",
-        "    'drop_column_names': ['logQuantity']\n",
-        "}\n",
-        "\n",
-        "automl_config = AutoMLConfig(task='forecasting',\n",
-        "                             debug_log='automl_oj_sales_errors.log',\n",
-        "                             primary_metric='normalized_root_mean_squared_error',\n",
-        "                             iterations=10,\n",
-        "                             X=X_train,\n",
-        "                             y=y_train,\n",
-        "                             X_valid=X_validate,\n",
-        "                             y_valid=y_validate,\n",
-        "                             enable_ensembling=False,\n",
-        "                             path=project_folder,\n",
-        "                             verbosity=logging.INFO,\n",
-        "                            **automl_settings)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "You can now submit a new training run. For local runs, the execution is synchronous. Depending on the data and number of iterations this operation may take several minutes.\n",
-        "Information from each iteration will be printed to the console."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "local_run = experiment.submit(automl_config, show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "local_run"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Retrieve the Best Model\n",
-        "Each run within an Experiment stores serialized (i.e. pickled) pipelines from the AutoML iterations. We can now retrieve the pipeline with the best performance on the validation dataset:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "best_run, fitted_pipeline = local_run.get_output()\n",
-        "fitted_pipeline.steps"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Make Predictions from the Best Fitted Model\n",
-        "Now that we have retrieved the best pipeline/model, it can be used to make predictions on test data. First, we remove the target values from the test set:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "y_test = X_test.pop(target_column_name).values"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "X_test.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "To produce predictions on the test set, we need to know the feature values at all dates in the test set. This requirement is somewhat reasonable for the OJ sales data since the features mainly consist of price, which is usually set in advance, and customer demographics which are approximately constant for each store over the 20 week forecast horizon in the testing data. \n",
-        "\n",
-        "The target predictions can be retrieved by calling the `predict` method on the best model:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "y_pred = fitted_pipeline.predict(X_test)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Calculate evaluation metrics for the prediction\n",
-        "To evaluate the accuracy of the forecast, we'll compare against the actual sales quantities for some select metrics, included the mean absolute percentage error (MAPE)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "def MAPE(actual, pred):\n",
-        "    \"\"\"\n",
-        "    Calculate mean absolute percentage error.\n",
-        "    Remove NA and values where actual is close to zero\n",
-        "    \"\"\"\n",
-        "    not_na = ~(np.isnan(actual) | np.isnan(pred))\n",
-        "    not_zero = ~np.isclose(actual, 0.0)\n",
-        "    actual_safe = actual[not_na & not_zero]\n",
-        "    pred_safe = pred[not_na & not_zero]\n",
-        "    APE = 100*np.abs((actual_safe - pred_safe)/actual_safe)\n",
-        "    return np.mean(APE)\n",
-        "\n",
-        "print(\"[Test Data] \\nRoot Mean squared error: %.2f\" % np.sqrt(mean_squared_error(y_test, y_pred)))\n",
-        "print('mean_absolute_error score: %.2f' % mean_absolute_error(y_test, y_pred))\n",
-        "print('MAPE: %.2f' % MAPE(y_test, y_pred))"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "erwright"
-      }
-    ],
-    "kernelspec": {
-      "display_name": "Python 3.6",
-      "language": "python",
-      "name": "python36"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.6.8"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

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

@@ -13,26 +13,11 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "# Automated Machine Learning\n",
-        "_**Blacklisting Models, Early Termination, and Handling Missing Data**_\n",
+    "# Automated Machine Learning: Blacklisting Models, Early Termination, and Handling Missing Data\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 [digit dataset](http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset) to showcase how you can use AutoML for handling missing values in data. We also provide a stopping metric indicating a target for the primary metrics so that AutoML can terminate the run without necessarly going through all the iterations. Finally, if you want to avoid a certain pipeline, we allow you to specify a blacklist of algorithms that AutoML will ignore for this run.\n",
     "\n",
-        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\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",
@@ -44,14 +29,14 @@
     "In addition this notebook showcases the following features\n",
     "- **Blacklisting** certain pipelines\n",
     "- Specifying **target metrics** to indicate stopping criteria\n",
-        "- Handling **missing data** in the input"
+    "- Handling **missing data** in the input\n"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Setup\n",
+    "## Create an Experiment\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."
    ]
@@ -63,8 +48,11 @@
    "outputs": [],
    "source": [
     "import logging\n",
+    "import os\n",
+    "import random\n",
     "\n",
     "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
     "import numpy as np\n",
     "import pandas as pd\n",
     "from sklearn import datasets\n",
@@ -72,7 +60,8 @@
     "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\n",
+    "from azureml.train.automl.run import AutoMLRun"
    ]
   },
   {
@@ -98,14 +87,15 @@
     "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"
+    "pd.DataFrame(data=output, index=['']).T"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Diagnostics\n",
+    "\n",
     "Opt-in diagnostics for better experience, quality, and security of future releases."
    ]
   },
@@ -123,7 +113,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Data"
+    "### Creating missing data"
    ]
   },
   {
@@ -132,6 +122,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from scipy import sparse\n",
+    "\n",
     "digits = datasets.load_digits()\n",
     "X_train = digits.data[10:,:]\n",
     "y_train = digits.target[10:]\n",
@@ -161,7 +153,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Train\n",
+    "## Configure AutoML\n",
     "\n",
     "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.  This includes setting `experiment_exit_score`, which should cause the run to complete before the `iterations` count is reached.\n",
     "\n",
@@ -205,6 +197,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Train the Models\n",
+    "\n",
     "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."
    ]
@@ -218,20 +212,11 @@
     "local_run = experiment.submit(automl_config, show_output = True)"
    ]
   },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "local_run"
-      ]
-    },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Results"
+    "## Explore the Results"
    ]
   },
   {
@@ -339,7 +324,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Test"
+    "### Testing the best Fitted Model"
    ]
   },
   {

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

@@ -13,39 +13,25 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "# Automated Machine Learning\n",
-        "_**Explain classification model and visualize the explanation**_\n",
+    "# Automated Machine Learning: Explain classification model and visualize the explanation\n",
     "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Data](#Data)\n",
-        "1. [Train](#Train)\n",
-        "1. [Results](#Results)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
     "In this example we use the sklearn's [iris dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_iris.html) to showcase how you can use the AutoML Classifier for a simple classification problem.\n",
     "\n",
-        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+    "Make sure you have executed the [configuration](../configuration.ipynb) before running this notebook.\n",
     "\n",
     "In this notebook you would see\n",
     "1. Creating an Experiment in an existing Workspace\n",
     "2. Instantiating AutoMLConfig\n",
     "3. Training the Model using local compute and explain the model\n",
     "4. Visualization model's feature importance in widget\n",
-        "5. Explore best model's explanation"
+    "5. Explore best model's explanation\n"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Setup\n",
+    "## Create Experiment\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."
    ]
@@ -57,12 +43,15 @@
    "outputs": [],
    "source": [
     "import logging\n",
+    "import os\n",
+    "import random\n",
     "\n",
     "import pandas as pd\n",
     "import azureml.core\n",
     "from azureml.core.experiment import Experiment\n",
     "from azureml.core.workspace import Workspace\n",
-        "from azureml.train.automl import AutoMLConfig"
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
    ]
   },
   {
@@ -89,14 +78,15 @@
     "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"
+    "pd.DataFrame(data = output, index = ['']).T"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Diagnostics\n",
+    "\n",
     "Opt-in diagnostics for better experience, quality, and security of future releases"
    ]
   },
@@ -114,7 +104,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Data"
+    "## Load Iris Data Set"
    ]
   },
   {
@@ -146,7 +136,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Train\n",
+    "## Instantiate Auto ML Config\n",
     "\n",
     "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
     "\n",
@@ -188,6 +178,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Training the Model\n",
+    "\n",
     "You can call the submit method on the experiment object and pass the run configuration. For Local runs the execution is synchronous. Depending on the data and number of iterations this can run for while.\n",
     "You will see the currently running iterations printing to the console."
    ]
@@ -201,20 +193,11 @@
     "local_run = experiment.submit(automl_config, show_output=True)"
    ]
   },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "local_run"
-      ]
-    },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Results"
+    "## Exploring the results"
    ]
   },
   {

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

@@ -13,40 +13,25 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "# Automated Machine Learning\n",
-        "_**Regression with Local Compute**_\n",
+    "# AutoML: Regression with Local Compute\n",
     "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Data](#Data)\n",
-        "1. [Train](#Train)\n",
-        "1. [Results](#Results)\n",
-        "1. [Test](#Test)\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
     "In this example we use the scikit-learn's [diabetes dataset](http://scikit-learn.org/stable/datasets/index.html#diabetes-dataset) to showcase how you can use AutoML for a simple regression problem.\n",
     "\n",
-        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+    "Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
     "\n",
     "In this notebook you will learn how to:\n",
     "1. Create an `Experiment` in an existing `Workspace`.\n",
     "2. Configure AutoML using `AutoMLConfig`.\n",
     "3. Train the model using local compute.\n",
     "4. Explore the results.\n",
-        "5. Test the best fitted model."
+    "5. Test the best fitted model.\n"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Setup\n",
+    "## Create an Experiment\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."
    ]
@@ -58,15 +43,20 @@
    "outputs": [],
    "source": [
     "import logging\n",
+    "import os\n",
+    "import random\n",
     "\n",
     "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\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"
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
    ]
   },
   {
@@ -92,14 +82,15 @@
     "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"
+    "pd.DataFrame(data = output, index = ['']).T"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Diagnostics\n",
+    "\n",
     "Opt-in diagnostics for better experience, quality, and security of future releases."
    ]
   },
@@ -117,7 +108,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Data\n",
+    "### Load Training Data\n",
     "This uses scikit-learn's [load_diabetes](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_diabetes.html) method."
    ]
   },
@@ -129,6 +120,8 @@
    "source": [
     "# Load the diabetes dataset, a well-known built-in small dataset that comes with scikit-learn.\n",
     "from sklearn.datasets import load_diabetes\n",
+    "from sklearn.linear_model import Ridge\n",
+    "from sklearn.metrics import mean_squared_error\n",
     "from sklearn.model_selection import train_test_split\n",
     "\n",
     "X, y = load_diabetes(return_X_y = True)\n",
@@ -142,7 +135,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Train\n",
+    "## Configure AutoML\n",
     "\n",
     "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
     "\n",
@@ -180,6 +173,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Train the Models\n",
+    "\n",
     "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."
    ]
@@ -206,7 +201,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Results"
+    "## Explore the Results"
    ]
   },
   {
@@ -320,7 +315,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Test"
+    "### Test the Best Fitted Model"
    ]
   },
   {
@@ -350,6 +345,9 @@
    "outputs": [],
    "source": [
     "%matplotlib inline\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "from sklearn import datasets\n",
     "from sklearn.metrics import mean_squared_error, r2_score\n",
     "\n",
     "# Set up a multi-plot chart.\n",
@@ -368,8 +366,8 @@
     "a0.set_ylabel('Residual Values', fontsize = 12)\n",
     "\n",
     "# Plot a histogram.\n",
-        "a0.hist(y_residual_train, orientation = 'horizontal', color = 'b', bins = 10, histtype = 'step')\n",
-        "a0.hist(y_residual_train, orientation = 'horizontal', color = 'b', alpha = 0.2, bins = 10)\n",
+    "a0.hist(y_residual_train, orientation = 'horizontal', color = 'b', bins = 10, histtype = 'step');\n",
+    "a0.hist(y_residual_train, orientation = 'horizontal', color = 'b', alpha = 0.2, bins = 10);\n",
     "\n",
     "# Plot residual values of test set.\n",
     "a1.axis([0, 90, -200, 200])\n",

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

@@ -13,26 +13,11 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "# Automated Machine Learning\n",
-        "_**Remote Execution using attach**_\n",
+    "# Automated Machine Learning: 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",
+    "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",
@@ -48,14 +33,14 @@
     "- **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"
+    "- Handling **text** data using the `preprocess` flag\n"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Setup\n",
+    "## Create an Experiment\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."
    ]
@@ -66,15 +51,21 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "import logging\n",
     "import os\n",
+    "import random\n",
     "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\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"
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
    ]
   },
   {
@@ -86,8 +77,8 @@
     "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",
+    "experiment_name = 'automl-remote-dsvm-blobstore'\n",
+    "project_folder = './sample_projects/automl-remote-dsvm-blobstore'\n",
     "\n",
     "experiment = Experiment(ws, experiment_name)\n",
     "\n",
@@ -100,14 +91,15 @@
     "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"
+    "pd.DataFrame(data=output, index=['']).T"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Diagnostics\n",
+    "\n",
     "Opt-in diagnostics for better experience, quality, and security of future releases."
    ]
   },
@@ -125,7 +117,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Attach a Remote Linux DSVM\n",
+    "## Attach a Remote Linux DSVM\n",
     "To use a remote Docker compute target:\n",
     "1. Create a Linux DSVM in Azure, following these [quick instructions](https://docs.microsoft.com/en-us/azure/machine-learning/desktop-workbench/how-to-create-dsvm-hdi). 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",
@@ -192,7 +184,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Data\n",
+    "## 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",
     "In this example, the `get_data()` function returns a [dictionary](README.md#getdata)."
    ]
@@ -240,7 +232,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Train\n",
+    "## Configure AutoML <a class=\"anchor\" id=\"Instatiate-AutoML-Remote-DSVM\"></a>\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",
@@ -285,6 +277,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Train the Models <a class=\"anchor\" id=\"Training-the-model-Remote-DSVM\"></a>\n",
+    "\n",
     "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."
    ]
   },
@@ -297,20 +291,11 @@
     "remote_run = experiment.submit(automl_config)"
    ]
   },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run"
-      ]
-    },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Results\n",
+    "## Exploring the Results <a class=\"anchor\" id=\"Exploring-the-Results-Remote-DSVM\"></a>\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",
@@ -344,7 +329,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Pre-process cache cleanup\n",
+    "## 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"
    ]
   },
@@ -387,7 +372,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Cancelling Runs\n",
+    "## Cancelling Runs\n",
     "You can cancel ongoing remote runs using the `cancel` and `cancel_iteration` functions."
    ]
   },
@@ -463,7 +448,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Test"
+    "### Testing the Fitted Model <a class=\"anchor\" id=\"Testing-the-Fitted-Model-Remote-DSVM\"></a>\n"
    ]
   },
   {

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

@@ -13,32 +13,17 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "# Automated Machine Learning\n",
-        "_**Remote Execution using AmlCompute**_\n",
+    "# Automated Machine Learning: Remote Execution using Batch AI\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",
+    "Make sure you have executed the [configuration](../configuration.ipynb) before running this notebook.\n",
     "\n",
     "In this notebook you would see\n",
     "1. Create an `Experiment` in an existing `Workspace`.\n",
-        "2. Create or Attach existing AmlCompute to a workspace.\n",
+    "2. Attach an existing Batch AI compute to a workspace.\n",
     "3. Configure AutoML using `AutoMLConfig`.\n",
-        "4. Train the model using AmlCompute\n",
+    "4. Train the model using Batch AI.\n",
     "5. Explore the results.\n",
     "6. Test the best fitted model.\n",
     "\n",
@@ -47,14 +32,14 @@
     "- **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`"
+    "- Specifying AutoML settings as `**kwargs`\n"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Setup\n",
+    "## Create an Experiment\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."
    ]
@@ -67,8 +52,10 @@
    "source": [
     "import logging\n",
     "import os\n",
+    "import random\n",
     "\n",
     "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
     "import numpy as np\n",
     "import pandas as pd\n",
     "from sklearn import datasets\n",
@@ -76,7 +63,8 @@
     "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\n",
+    "from azureml.train.automl.run import AutoMLRun"
    ]
   },
   {
@@ -88,8 +76,8 @@
     "ws = Workspace.from_config()\n",
     "\n",
     "# Choose a name for the run history container in the workspace.\n",
-        "experiment_name = 'automl-remote-amlcompute'\n",
-        "project_folder = './sample_projects/automl-remote-amlcompute'\n",
+    "experiment_name = 'automl-remote-batchai'\n",
+    "project_folder = './sample_projects/automl-remote-batchai'\n",
     "\n",
     "experiment = Experiment(ws, experiment_name)\n",
     "\n",
@@ -102,14 +90,15 @@
     "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"
+    "pd.DataFrame(data = output, index = ['']).T"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Diagnostics\n",
+    "\n",
     "Opt-in diagnostics for better experience, quality, and security of future releases."
    ]
   },
@@ -127,12 +116,12 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Create or Attach existing AmlCompute\n",
-        "You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) for your AutoML run. In this tutorial, you create `AmlCompute` as your training compute resource.\n",
+    "## Create Batch AI Cluster\n",
+    "The cluster is created as Machine Learning Compute and will appear under your workspace.\n",
     "\n",
-        "**Creation of AmlCompute takes approximately 5 minutes.** If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
+    "**Note:** The creation of the Batch AI cluster can take over 10 minutes, please be patient.\n",
     "\n",
-        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
+    "As with other Azure services, there are limits on certain resources (e.g. Batch AI cluster size) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
    ]
   },
   {
@@ -145,15 +134,15 @@
     "from azureml.core.compute import ComputeTarget\n",
     "\n",
     "# Choose a name for your cluster.\n",
-        "amlcompute_cluster_name = \"automlcl\"\n",
+    "batchai_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",
+    "if batchai_cluster_name in cts and cts[batchai_cluster_name].type == 'BatchAI':\n",
     "    found = True\n",
     "    print('Found existing compute target.')\n",
-        "    compute_target = cts[amlcompute_cluster_name]\n",
+    "    compute_target = cts[batchai_cluster_name]\n",
     "    \n",
     "if not found:\n",
     "    print('Creating a new compute target...')\n",
@@ -162,13 +151,13 @@
     "                                                                max_nodes = 6)\n",
     "\n",
     "    # Create the cluster.\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
+    "    compute_target = ComputeTarget.create(ws, batchai_cluster_name, provisioning_config)\n",
     "    \n",
     "    # Can poll for a minimum number of nodes and for a specific timeout.\n",
     "    # If no min_node_count is provided, it will use the scale settings for the cluster.\n",
     "    compute_target.wait_for_completion(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()."
+    "     # For a more detailed view of current Batch AI cluster status, use the 'status' property."
    ]
   },
   {
@@ -183,7 +172,7 @@
     "# create a new RunConfig object\n",
     "conda_run_config = RunConfiguration(framework=\"python\")\n",
     "\n",
-        "# Set compute target to AmlCompute\n",
+    "# Set compute target to the Batch AI cluster\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",
@@ -196,7 +185,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Data\n",
+    "## 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",
     "In this example, the `get_data()` function returns data using scikit-learn's [load_digits](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) method."
    ]
@@ -236,11 +225,11 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Train\n",
+    "## Instantiate AutoML <a class=\"anchor\" id=\"Instatiate-AutoML-Remote-DSVM\"></a>\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 AmlCompute, you can't pass Numpy arrays directly to the fit method.\n",
+    "**Note:** When using Batch AI, you can't pass Numpy arrays directly to the fit method.\n",
     "\n",
     "|Property|Description|\n",
     "|-|-|\n",
@@ -280,6 +269,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Train the Models\n",
+    "\n",
     "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",
     "In this example, we specify `show_output = False` to suppress console output while the run is in progress."
    ]
@@ -293,20 +284,11 @@
     "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",
+    "## Explore the 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."
@@ -391,7 +373,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Cancelling Runs\n",
+    "## Cancelling Runs\n",
     "\n",
     "You can cancel ongoing remote runs using the `cancel` and `cancel_iteration` functions."
    ]
@@ -473,7 +455,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Test\n",
+    "### Testing the Fitted Model <a class=\"anchor\" id=\"Testing-the-Fitted-Model-Remote-DSVM\"></a>\n",
     "\n",
     "#### Load Test Data"
    ]

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

@@ -13,40 +13,26 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "# Automated Machine Learning\n",
-        "_**Remote Execution with DataStore**_\n",
+    "# Automated Machine Learning: 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",
+    "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."
+    "2. get_data returning data from DataStore.\n",
+    "\n"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Setup\n",
+    "## Create Experiment\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."
    ]
@@ -59,16 +45,21 @@
    "source": [
     "import logging\n",
     "import os\n",
+    "import random\n",
     "import time\n",
     "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
     "import numpy as np\n",
     "import pandas as pd\n",
+    "from sklearn import datasets\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"
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
    ]
   },
   {
@@ -82,7 +73,7 @@
     "# 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",
+    "project_folder = './sample_projects/automl-remote-dsvm-file'\n",
     "\n",
     "experiment=Experiment(ws, experiment_name)\n",
     "\n",
@@ -95,14 +86,15 @@
     "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"
+    "pd.DataFrame(data=output, index=['']).T"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Diagnostics\n",
+    "\n",
     "Opt-in diagnostics for better experience, quality, and security of future releases"
    ]
   },
@@ -120,7 +112,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Create a Remote Linux DSVM\n",
+    "## 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://render.githubusercontent.com/documentation/sdk/ssh-issue.md) on this."
@@ -152,9 +144,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Data\n",
-        "\n",
-        "### Copy data file to local\n",
+    "## Copy data file to local\n",
     "\n",
     "Download the data file.\n"
    ]
@@ -165,8 +155,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-        "if not os.path.isdir('data'):\n",
-        "    os.mkdir('data')    "
+    "mkdir data"
    ]
   },
   {
@@ -197,7 +186,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Upload data to the cloud"
+    "## Upload data to the cloud"
    ]
   },
   {
@@ -215,6 +204,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from azureml.core import Workspace, Datastore\n",
     "#blob_datastore = Datastore(ws, blob_datastore_name)\n",
     "ds = ws.get_default_datastore()\n",
     "print(ds.datastore_type, ds.account_name, ds.container_name)"
@@ -234,7 +224,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Configure & Run\n",
+    "## 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."
@@ -279,7 +269,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Create Get Data File\n",
+    "## 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",
@@ -318,7 +308,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Train\n",
+    "## Instantiate AutoML <a class=\"anchor\" id=\"Instatiate-AutoML-Remote-DSVM\"></a>\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",
@@ -365,6 +355,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Training the Models <a class=\"anchor\" id=\"Training-the-model-Remote-DSVM\"></a>\n",
+    "\n",
     "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."
    ]
   },
@@ -377,20 +369,11 @@
     "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",
+    "## Exploring the Results <a class=\"anchor\" id=\"Exploring-the-Results-Remote-DSVM\"></a>\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",
@@ -450,7 +433,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Canceling Runs\n",
+    "## Canceling Runs\n",
     "You can cancel ongoing remote runs using the *cancel()* and *cancel_iteration()* functions"
    ]
   },
@@ -471,7 +454,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Pre-process cache cleanup\n",
+    "## 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"
    ]
   },
@@ -540,7 +523,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Test\n"
+    "### Testing the Best Fitted Model <a class=\"anchor\" id=\"Testing-the-Fitted-Model-Remote-DSVM\"></a>\n"
    ]
   },
   {

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

@@ -13,26 +13,11 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "# Automated Machine Learning\n",
-        "_**Remote Execution using DSVM (Ubuntu)**_\n",
+    "# Automated Machine Learning: 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",
+    "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",
@@ -47,14 +32,14 @@
     "- **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`"
+    "- Specifying AutoML settings as `**kwargs`\n"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Setup\n",
+    "## Create an Experiment\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."
    ]
@@ -67,9 +52,11 @@
    "source": [
     "import logging\n",
     "import os\n",
+    "import random\n",
     "import time\n",
     "\n",
     "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
     "import numpy as np\n",
     "import pandas as pd\n",
     "from sklearn import datasets\n",
@@ -77,7 +64,8 @@
     "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\n",
+    "from azureml.train.automl.run import AutoMLRun"
    ]
   },
   {
@@ -89,8 +77,8 @@
     "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 = './sample_projects/automl-remote-dsvm'\n",
+    "experiment_name = 'automl-remote-dsvm4'\n",
+    "project_folder = './sample_projects/automl-remote-dsvm4'\n",
     "\n",
     "experiment = Experiment(ws, experiment_name)\n",
     "\n",
@@ -103,14 +91,15 @@
     "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"
+    "pd.DataFrame(data = output, index = ['']).T"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Diagnostics\n",
+    "\n",
     "Opt-in diagnostics for better experience, quality, and security of future releases."
    ]
   },
@@ -128,7 +117,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Create a Remote Linux DSVM\n",
+    "## 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"
    ]
   },
@@ -146,11 +135,11 @@
     "    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_config = DsvmCompute.provisioning_configuration(vm_size = \"Standard_D2_v2\")\n",
     "    dsvm_compute = DsvmCompute.create(ws, name = dsvm_name, provisioning_configuration = dsvm_config)\n",
     "    dsvm_compute.wait_for_completion(show_output = True)\n",
     "    print(\"Waiting one minute for ssh to be accessible\")\n",
-        "    time.sleep(90) # Wait for ssh to be accessible"
+    "    time.sleep(60) # Wait for ssh to be accessible"
    ]
   },
   {
@@ -176,7 +165,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Data\n",
+    "## 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",
     "In this example, the `get_data()` function returns data using scikit-learn's [load_digits](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) method."
    ]
@@ -216,7 +205,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Train\n",
+    "## Configure AutoML <a class=\"anchor\" id=\"Instantiate-AutoML-Remote-DSVM\"></a>\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",
@@ -267,6 +256,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Train the Models\n",
+    "\n",
     "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."
@@ -281,20 +272,11 @@
     "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",
+    "## Explore the 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."
@@ -370,7 +352,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Cancelling Runs\n",
+    "## Cancelling Runs\n",
     "\n",
     "You can cancel ongoing remote runs using the `cancel` and `cancel_iteration` functions."
    ]
@@ -452,7 +434,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Test\n",
+    "### Test the Best Fitted Model <a class=\"anchor\" id=\"Testing-the-Fitted-Model-Remote-DSVM\"></a>\n",
     "\n",
     "#### Load Test Data"
    ]

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

@@ -13,33 +13,20 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "# Automated Machine Learning\n",
-        "_**Sample Weight**_\n",
+    "# Automated Machine Learning: Sample Weight\n",
     "\n",
-        "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Train](#Train)\n",
-        "1. [Test](#Test)\n"
-      ]
-    },
-    {
-      "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 sample weight with AutoML. Sample weight is used where some sample values are more important than others.\n",
     "\n",
-        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+    "Make sure you have executed the [configuration](../configuration.ipynb) before running this notebook.\n",
     "\n",
-        "In this notebook you will learn how to configure AutoML to use `sample_weight` and you will see the difference sample weight makes to the test results."
+    "In this notebook you will learn how to configure AutoML to use `sample_weight` and you will see the difference sample weight makes to the test results.\n"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Setup\n",
+    "## Create an Experiment\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."
    ]
@@ -51,8 +38,11 @@
    "outputs": [],
    "source": [
     "import logging\n",
+    "import os\n",
+    "import random\n",
     "\n",
     "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\n",
     "import numpy as np\n",
     "import pandas as pd\n",
     "from sklearn import datasets\n",
@@ -60,7 +50,8 @@
     "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\n",
+    "from azureml.train.automl.run import AutoMLRun"
    ]
   },
   {
@@ -89,14 +80,15 @@
     "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"
+    "pd.DataFrame(data = output, index = ['']).T"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Diagnostics\n",
+    "\n",
     "Opt-in diagnostics for better experience, quality, and security of future releases."
    ]
   },
@@ -114,7 +106,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Train\n",
+    "## Configure AutoML\n",
     "\n",
     "Instantiate two `AutoMLConfig` objects. One will be used with `sample_weight` and one without."
    ]
@@ -161,6 +153,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Train the Models\n",
+    "\n",
     "Call the `submit` method on the experiment objects 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."
    ]
@@ -182,7 +176,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Test\n",
+    "### Test the Best Fitted Model\n",
     "\n",
     "#### Load Test Data"
    ]

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

@@ -13,25 +13,11 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "# Automated Machine Learning\n",
-        "_**Train Test Split and Handling Sparse Data**_\n",
+    "# Automated Machine Learning: Train Test Split and Handling Sparse Data\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 for handling sparse data and how to specify custom cross validations splits.\n",
-        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\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",
@@ -49,7 +35,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Setup\n",
+    "## Create an Experiment\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."
    ]
@@ -61,13 +47,20 @@
    "outputs": [],
    "source": [
     "import logging\n",
+    "import os\n",
+    "import random\n",
     "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\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"
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
    ]
   },
   {
@@ -94,14 +87,15 @@
     "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"
+    "pd.DataFrame(data=output, index=['']).T"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Diagnostics\n",
+    "\n",
     "Opt-in diagnostics for better experience, quality, and security of future releases."
    ]
   },
@@ -119,7 +113,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Data"
+    "## Creating Sparse Data"
    ]
   },
   {
@@ -161,7 +155,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Train\n",
+    "## Configure AutoML\n",
     "\n",
     "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
     "\n",
@@ -203,6 +197,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Train the Models\n",
+    "\n",
     "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."
    ]
@@ -216,20 +212,11 @@
     "local_run = experiment.submit(automl_config, show_output=True)"
    ]
   },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "local_run"
-      ]
-    },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Results"
+    "## Explore the Results"
    ]
   },
   {
@@ -337,7 +324,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Test"
+    "### Testing the Best Fitted Model"
    ]
   },
   {

how-to-use-azureml/azure-databricks/01.Installation_and_Configuration.ipynb

@@ -0,0 +1,264 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Azure ML & Azure Databricks notebooks by Parashar Shah.\n",
+    "\n",
+    "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+    "\n",
+    "Licensed under the MIT License."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We support installing AML SDK as library from GUI. When attaching a library follow this https://docs.databricks.com/user-guide/libraries.html and add the below string as your PyPi package. You can select the option to attach the library to all clusters or just one cluster.\n",
+    "\n",
+    "**azureml-sdk**\n",
+    "* Source: Upload Python Egg or PyPi\n",
+    "* PyPi Name: `azureml-sdk[databricks]`\n",
+    "* Select Install Library"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import azureml.core\n",
+    "\n",
+    "# Check core SDK version number - based on build number of preview/master.\n",
+    "print(\"SDK version:\", azureml.core.VERSION)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "![04ACI](files/tables/image2b.JPG)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Please specify the Azure subscription Id, resource group name, workspace name, and the region in which you want to create the Azure Machine Learning Workspace.\n",
+    "\n",
+    "You can get the value of your Azure subscription ID from the Azure Portal, and then selecting Subscriptions from the menu on the left.\n",
+    "\n",
+    "For the resource_group, use the name of the resource group that contains your Azure Databricks Workspace.\n",
+    "\n",
+    "NOTE: If you provide a resource group name that does not exist, the resource group will be automatically created. This may or may not succeed in your environment, depending on the permissions you have on your Azure Subscription."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# subscription_id = \"<your-subscription-id>\"\n",
+    "# resource_group = \"<your-existing-resource-group>\"\n",
+    "# workspace_name = \"<a-new-or-existing-workspace; it is unrelated to Databricks workspace>\"\n",
+    "# workspace_region = \"<your-resource group-region>\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##TESTONLY\n",
+    "# import auth creds from notebook parameters\n",
+    "tenant = dbutils.widgets.get('tenant_id')\n",
+    "username = dbutils.widgets.get('service_principal_id')\n",
+    "password = dbutils.widgets.get('service_principal_password')\n",
+    "\n",
+    "auth = azureml.core.authentication.ServicePrincipalAuthentication(tenant, username, password)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##TESTONLY\n",
+    "subscription_id  = dbutils.widgets.get('subscription_id')\n",
+    "resource_group = dbutils.widgets.get('resource_group')\n",
+    "workspace_name = dbutils.widgets.get('workspace_name')\n",
+    "workspace_region = dbutils.widgets.get('workspace_region')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##TESTONLY\n",
+    "# import the Workspace class and check the azureml SDK version\n",
+    "# exist_ok checks if workspace exists or not.\n",
+    "\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,\n",
+    "                      exist_ok=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##PUBLISHONLY\n",
+    "## import the Workspace class and check the azureml SDK version\n",
+    "## exist_ok checks if workspace exists or not.\n",
+    "#\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",
+    "#                      exist_ok=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#get workspace details\n",
+    "ws.get_details()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##TESTONLY\n",
+    "ws = Workspace(workspace_name = workspace_name,\n",
+    "               subscription_id = subscription_id,\n",
+    "               resource_group = resource_group,\n",
+    "               auth = auth)\n",
+    "\n",
+    "# persist the subscription id, resource group name, and workspace name in aml_config/config.json.\n",
+    "ws.write_config()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##PUBLISHONLY\n",
+    "#ws = Workspace(workspace_name = workspace_name,\n",
+    "#               subscription_id = subscription_id,\n",
+    "#               resource_group = resource_group)\n",
+    "#\n",
+    "## persist the subscription id, resource group name, and workspace name in aml_config/config.json.\n",
+    "#ws.write_config()\n",
+    "###if you need to give a different path/filename please use this\n",
+    "###write_config(path=\"/databricks/driver/aml_config/\",file_name=<alias_conf.cfg>)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "help(Workspace)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##TESTONLY\n",
+    "# import the Workspace class and check the azureml SDK version\n",
+    "from azureml.core import Workspace\n",
+    "\n",
+    "ws = Workspace.from_config(auth = auth)\n",
+    "#ws = Workspace.from_config(<full path>)\n",
+    "print('Workspace name: ' + ws.name, \n",
+    "      'Azure region: ' + ws.location, \n",
+    "      'Subscription id: ' + ws.subscription_id, \n",
+    "      'Resource group: ' + ws.resource_group, sep = '\\n')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##PUBLISHONLY\n",
+    "## import the Workspace class and check the azureml SDK version\n",
+    "#from azureml.core import Workspace\n",
+    "#\n",
+    "#ws = Workspace.from_config()\n",
+    "##ws = Workspace.from_config(<full path>)\n",
+    "#print('Workspace name: ' + ws.name, \n",
+    "#      'Azure region: ' + ws.location, \n",
+    "#      'Subscription id: ' + ws.subscription_id, \n",
+    "#      'Resource group: ' + ws.resource_group, sep = '\\n')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "pasha"
+   },
+   {
+    "name": "wamartin"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.0"
+  },
+  "name": "01.Installation_and_Configuration",
+  "notebookId": 3836944406456490
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}

how-to-use-azureml/azure-databricks/02.Ingest_data.ipynb

@@ -0,0 +1,182 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Azure ML & Azure Databricks notebooks by Parashar Shah.\n",
+    "\n",
+    "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+    "\n",
+    "Licensed under the MIT License."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "![04ACI](files/tables/image1.JPG)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#Data Ingestion"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import urllib"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Download AdultCensusIncome.csv from Azure CDN. This file has 32,561 rows.\n",
+    "basedataurl = \"https://amldockerdatasets.azureedge.net\"\n",
+    "datafile = \"AdultCensusIncome.csv\"\n",
+    "datafile_dbfs = os.path.join(\"/dbfs\", datafile)\n",
+    "\n",
+    "if os.path.isfile(datafile_dbfs):\n",
+    "    print(\"found {} at {}\".format(datafile, datafile_dbfs))\n",
+    "else:\n",
+    "    print(\"downloading {} to {}\".format(datafile, datafile_dbfs))\n",
+    "    urllib.request.urlretrieve(os.path.join(basedataurl, datafile), datafile_dbfs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a Spark dataframe out of the csv file.\n",
+    "data_all = sqlContext.read.format('csv').options(header='true', inferSchema='true', ignoreLeadingWhiteSpace='true', ignoreTrailingWhiteSpace='true').load(datafile)\n",
+    "print(\"({}, {})\".format(data_all.count(), len(data_all.columns)))\n",
+    "data_all.printSchema()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#renaming columns\n",
+    "columns_new = [col.replace(\"-\", \"_\") for col in data_all.columns]\n",
+    "data_all = data_all.toDF(*columns_new)\n",
+    "data_all.printSchema()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "display(data_all.limit(5))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#Data Preparation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Choose feature columns and the label column.\n",
+    "label = \"income\"\n",
+    "xvars = set(data_all.columns) - {label}\n",
+    "\n",
+    "print(\"label = {}\".format(label))\n",
+    "print(\"features = {}\".format(xvars))\n",
+    "\n",
+    "data = data_all.select([*xvars, label])\n",
+    "\n",
+    "# Split data into train and test.\n",
+    "train, test = data.randomSplit([0.75, 0.25], seed=123)\n",
+    "\n",
+    "print(\"train ({}, {})\".format(train.count(), len(train.columns)))\n",
+    "print(\"test ({}, {})\".format(test.count(), len(test.columns)))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#Data Persistence"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Write the train and test data sets to intermediate storage\n",
+    "train_data_path = \"AdultCensusIncomeTrain\"\n",
+    "test_data_path = \"AdultCensusIncomeTest\"\n",
+    "\n",
+    "train_data_path_dbfs = os.path.join(\"/dbfs\", \"AdultCensusIncomeTrain\")\n",
+    "test_data_path_dbfs = os.path.join(\"/dbfs\", \"AdultCensusIncomeTest\")\n",
+    "\n",
+    "train.write.mode('overwrite').parquet(train_data_path)\n",
+    "test.write.mode('overwrite').parquet(test_data_path)\n",
+    "print(\"train and test datasets saved to {} and {}\".format(train_data_path_dbfs, test_data_path_dbfs))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "pasha"
+   },
+   {
+    "name": "wamartin"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.0"
+  },
+  "name": "02.Ingest_data",
+  "notebookId": 3836944406456362
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}

how-to-use-azureml/azure-databricks/03.Build_model_runHistory.ipynb

@@ -0,0 +1,396 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Azure ML & Azure Databricks notebooks by Parashar Shah.\n",
+    "\n",
+    "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+    "\n",
+    "Licensed under the MIT License."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "![04ACI](files/tables/image2.JPG)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#Model Building"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import pprint\n",
+    "import numpy as np\n",
+    "\n",
+    "from pyspark.ml import Pipeline, PipelineModel\n",
+    "from pyspark.ml.feature import OneHotEncoder, StringIndexer, VectorAssembler\n",
+    "from pyspark.ml.classification import LogisticRegression\n",
+    "from pyspark.ml.evaluation import BinaryClassificationEvaluator\n",
+    "from pyspark.ml.tuning import CrossValidator, ParamGridBuilder"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import azureml.core\n",
+    "\n",
+    "# Check core SDK version number\n",
+    "print(\"SDK version:\", azureml.core.VERSION)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##TESTONLY\n",
+    "# import auth creds from notebook parameters\n",
+    "tenant = dbutils.widgets.get('tenant_id')\n",
+    "username = dbutils.widgets.get('service_principal_id')\n",
+    "password = dbutils.widgets.get('service_principal_password')\n",
+    "\n",
+    "auth = azureml.core.authentication.ServicePrincipalAuthentication(tenant, username, password)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# import the Workspace class and check the azureml SDK version\n",
+    "from azureml.core import Workspace\n",
+    "\n",
+    "ws = Workspace.from_config(auth = auth)\n",
+    "print('Workspace name: ' + ws.name, \n",
+    "      'Azure region: ' + ws.location, \n",
+    "      'Subscription id: ' + ws.subscription_id, \n",
+    "      'Resource group: ' + ws.resource_group, sep = '\\n')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##PUBLISHONLY\n",
+    "## import the Workspace class and check the azureml SDK version\n",
+    "#from azureml.core import Workspace\n",
+    "#\n",
+    "#ws = Workspace.from_config()\n",
+    "#print('Workspace name: ' + ws.name, \n",
+    "#      'Azure region: ' + ws.location, \n",
+    "#      'Subscription id: ' + ws.subscription_id, \n",
+    "#      'Resource group: ' + ws.resource_group, sep = '\\n')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#get the train and test datasets\n",
+    "train_data_path = \"AdultCensusIncomeTrain\"\n",
+    "test_data_path = \"AdultCensusIncomeTest\"\n",
+    "\n",
+    "train = spark.read.parquet(train_data_path)\n",
+    "test = spark.read.parquet(test_data_path)\n",
+    "\n",
+    "print(\"train: ({}, {})\".format(train.count(), len(train.columns)))\n",
+    "print(\"test: ({}, {})\".format(test.count(), len(test.columns)))\n",
+    "\n",
+    "train.printSchema()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#Define Model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "label = \"income\"\n",
+    "dtypes = dict(train.dtypes)\n",
+    "dtypes.pop(label)\n",
+    "\n",
+    "si_xvars = []\n",
+    "ohe_xvars = []\n",
+    "featureCols = []\n",
+    "for idx,key in enumerate(dtypes):\n",
+    "    if dtypes[key] == \"string\":\n",
+    "        featureCol = \"-\".join([key, \"encoded\"])\n",
+    "        featureCols.append(featureCol)\n",
+    "        \n",
+    "        tmpCol = \"-\".join([key, \"tmp\"])\n",
+    "        # string-index and one-hot encode the string column\n",
+    "        #https://spark.apache.org/docs/2.3.0/api/java/org/apache/spark/ml/feature/StringIndexer.html\n",
+    "        #handleInvalid: Param for how to handle invalid data (unseen labels or NULL values). \n",
+    "        #Options are 'skip' (filter out rows with invalid data), 'error' (throw an error), \n",
+    "        #or 'keep' (put invalid data in a special additional bucket, at index numLabels). Default: \"error\"\n",
+    "        si_xvars.append(StringIndexer(inputCol=key, outputCol=tmpCol, handleInvalid=\"skip\"))\n",
+    "        ohe_xvars.append(OneHotEncoder(inputCol=tmpCol, outputCol=featureCol))\n",
+    "    else:\n",
+    "        featureCols.append(key)\n",
+    "\n",
+    "# string-index the label column into a column named \"label\"\n",
+    "si_label = StringIndexer(inputCol=label, outputCol='label')\n",
+    "\n",
+    "# assemble the encoded feature columns in to a column named \"features\"\n",
+    "assembler = VectorAssembler(inputCols=featureCols, outputCol=\"features\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.run import Run\n",
+    "from azureml.core.experiment import Experiment\n",
+    "import numpy as np\n",
+    "import os\n",
+    "import shutil\n",
+    "\n",
+    "model_name = \"AdultCensus_runHistory.mml\"\n",
+    "model_dbfs = os.path.join(\"/dbfs\", model_name)\n",
+    "run_history_name = 'spark-ml-notebook'\n",
+    "\n",
+    "# start a training run by defining an experiment\n",
+    "myexperiment = Experiment(ws, \"Ignite_AI_Talk\")\n",
+    "root_run = myexperiment.start_logging()\n",
+    "\n",
+    "# Regularization Rates - \n",
+    "regs = [0.0001, 0.001, 0.01, 0.1]\n",
+    " \n",
+    "# try a bunch of regularization rate in a Logistic Regression model\n",
+    "for reg in regs:\n",
+    "    print(\"Regularization rate: {}\".format(reg))\n",
+    "    # create a bunch of child runs\n",
+    "    with root_run.child_run(\"reg-\" + str(reg)) as run:\n",
+    "        # create a new Logistic Regression model.\n",
+    "        lr = LogisticRegression(regParam=reg)\n",
+    "        \n",
+    "        # put together the pipeline\n",
+    "        pipe = Pipeline(stages=[*si_xvars, *ohe_xvars, si_label, assembler, lr])\n",
+    "\n",
+    "        # train the model\n",
+    "        model_p = pipe.fit(train)\n",
+    "        \n",
+    "        # make prediction\n",
+    "        pred = model_p.transform(test)\n",
+    "        \n",
+    "        # evaluate. note only 2 metrics are supported out of the box by Spark ML.\n",
+    "        bce = BinaryClassificationEvaluator(rawPredictionCol='rawPrediction')\n",
+    "        au_roc = bce.setMetricName('areaUnderROC').evaluate(pred)\n",
+    "        au_prc = bce.setMetricName('areaUnderPR').evaluate(pred)\n",
+    "\n",
+    "        print(\"Area under ROC: {}\".format(au_roc))\n",
+    "        print(\"Area Under PR: {}\".format(au_prc))\n",
+    "      \n",
+    "        # log reg, au_roc, au_prc and feature names in run history\n",
+    "        run.log(\"reg\", reg)\n",
+    "        run.log(\"au_roc\", au_roc)\n",
+    "        run.log(\"au_prc\", au_prc)\n",
+    "        run.log_list(\"columns\", train.columns)\n",
+    "\n",
+    "        # save model\n",
+    "        model_p.write().overwrite().save(model_name)\n",
+    "        \n",
+    "        # upload the serialized model into run history record\n",
+    "        mdl, ext = model_name.split(\".\")\n",
+    "        model_zip = mdl + \".zip\"\n",
+    "        shutil.make_archive(mdl, 'zip', model_dbfs)\n",
+    "        run.upload_file(\"outputs/\" + model_name, model_zip)        \n",
+    "        #run.upload_file(\"outputs/\" + model_name, path_or_stream = model_dbfs) #cannot deal with folders\n",
+    "\n",
+    "        # now delete the serialized model from local folder since it is already uploaded to run history \n",
+    "        shutil.rmtree(model_dbfs)\n",
+    "        os.remove(model_zip)\n",
+    "        \n",
+    "# Declare run completed\n",
+    "root_run.complete()\n",
+    "root_run_id = root_run.id\n",
+    "print (\"run id:\", root_run.id)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "metrics = root_run.get_metrics(recursive=True)\n",
+    "best_run_id = max(metrics, key = lambda k: metrics[k]['au_roc'])\n",
+    "print(best_run_id, metrics[best_run_id]['au_roc'], metrics[best_run_id]['reg'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Get the best run\n",
+    "child_runs = {}\n",
+    "\n",
+    "for r in root_run.get_children():\n",
+    "    child_runs[r.id] = r\n",
+    "   \n",
+    "best_run = child_runs[best_run_id]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Download the model from the best run to a local folder\n",
+    "best_model_file_name = \"best_model.zip\"\n",
+    "best_run.download_file(name = 'outputs/' + model_name, output_file_path = best_model_file_name)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#Model Evaluation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##unzip the model to dbfs (as load() seems to require that) and load it.\n",
+    "if os.path.isfile(model_dbfs) or os.path.isdir(model_dbfs):\n",
+    "    shutil.rmtree(model_dbfs)\n",
+    "shutil.unpack_archive(best_model_file_name, model_dbfs)\n",
+    "\n",
+    "model_p_best = PipelineModel.load(model_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# make prediction\n",
+    "pred = model_p_best.transform(test)\n",
+    "output = pred[['hours_per_week','age','workclass','marital_status','income','prediction']]\n",
+    "display(output.limit(5))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# evaluate. note only 2 metrics are supported out of the box by Spark ML.\n",
+    "bce = BinaryClassificationEvaluator(rawPredictionCol='rawPrediction')\n",
+    "au_roc = bce.setMetricName('areaUnderROC').evaluate(pred)\n",
+    "au_prc = bce.setMetricName('areaUnderPR').evaluate(pred)\n",
+    "\n",
+    "print(\"Area under ROC: {}\".format(au_roc))\n",
+    "print(\"Area Under PR: {}\".format(au_prc))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#Model Persistence"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##NOTE: by default the model is saved to and loaded from /dbfs/ instead of cwd!\n",
+    "model_p_best.write().overwrite().save(model_name)\n",
+    "print(\"saved model to {}\".format(model_dbfs))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%sh\n",
+    "\n",
+    "ls -la /dbfs/AdultCensus_runHistory.mml/*"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dbutils.notebook.exit(\"success\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "pasha"
+   },
+   {
+    "name": "wamartin"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.0"
+  },
+  "name": "03.Build_model_runHistory",
+  "notebookId": 3836944406456339
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}

how-to-use-azureml/azure-databricks/04.Deploy_to_ACI.ipynb

@@ -0,0 +1,354 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Azure ML & Azure Databricks notebooks by Parashar Shah.\n",
+    "\n",
+    "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+    "\n",
+    "Licensed under the MIT License."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Please ensure you have run all previous notebooks in sequence before running this.\n",
+    "\n",
+    "Please Register Azure Container Instance(ACI) using Azure Portal: https://docs.microsoft.com/en-us/azure/azure-resource-manager/resource-manager-supported-services#portal in your subscription before using the SDK to deploy your ML model to ACI."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "![04ACI](files/tables/image3.JPG)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import azureml.core\n",
+    "\n",
+    "# Check core SDK version number\n",
+    "print(\"SDK version:\", azureml.core.VERSION)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##TESTONLY\n",
+    "# import auth creds from notebook parameters\n",
+    "tenant = dbutils.widgets.get('tenant_id')\n",
+    "username = dbutils.widgets.get('service_principal_id')\n",
+    "password = dbutils.widgets.get('service_principal_password')\n",
+    "\n",
+    "auth = azureml.core.authentication.ServicePrincipalAuthentication(tenant, username, password)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core import Workspace\n",
+    "\n",
+    "#'''\n",
+    "ws = Workspace.from_config(auth = auth)\n",
+    "print('Workspace name: ' + ws.name, \n",
+    "      'Azure region: ' + ws.location, \n",
+    "      'Subscription id: ' + ws.subscription_id, \n",
+    "      'Resource group: ' + ws.resource_group, sep = '\\n')\n",
+    "#'''"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##PUBLISHONLY\n",
+    "#from azureml.core import Workspace\n",
+    "#import azureml.core\n",
+    "#\n",
+    "## Check core SDK version number\n",
+    "#print(\"SDK version:\", azureml.core.VERSION)\n",
+    "#\n",
+    "##'''\n",
+    "#ws = Workspace.from_config()\n",
+    "#print('Workspace name: ' + ws.name, \n",
+    "#      'Azure region: ' + ws.location, \n",
+    "#      'Subscription id: ' + ws.subscription_id, \n",
+    "#      'Resource group: ' + ws.resource_group, sep = '\\n')\n",
+    "##'''"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##NOTE: service deployment always gets the model from the current working dir.\n",
+    "import os\n",
+    "\n",
+    "model_name = \"AdultCensus_runHistory.mml\" # \n",
+    "model_name_dbfs = os.path.join(\"/dbfs\", model_name)\n",
+    "\n",
+    "print(\"copy model from dbfs to local\")\n",
+    "model_local = \"file:\" + os.getcwd() + \"/\" + model_name\n",
+    "dbutils.fs.cp(model_name, model_local, True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Register the model\n",
+    "from azureml.core.model import Model\n",
+    "mymodel = Model.register(model_path = model_name, # this points to a local file\n",
+    "                       model_name = model_name, # this is the name the model is registered as, am using same name for both path and name.                 \n",
+    "                       description = \"ADB trained model by Parashar\",\n",
+    "                       workspace = ws)\n",
+    "\n",
+    "print(mymodel.name, mymodel.description, mymodel.version)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#%%writefile score_sparkml.py\n",
+    "score_sparkml = \"\"\"\n",
+    " \n",
+    "import json\n",
+    " \n",
+    "def init():\n",
+    "    # One-time initialization of PySpark and predictive model\n",
+    "    import pyspark\n",
+    "    from azureml.core.model import Model\n",
+    "    from pyspark.ml import PipelineModel\n",
+    " \n",
+    "    global trainedModel\n",
+    "    global spark\n",
+    " \n",
+    "    spark = pyspark.sql.SparkSession.builder.appName(\"ADB and AML notebook by Parashar\").getOrCreate()\n",
+    "    model_name = \"{model_name}\" #interpolated\n",
+    "    model_path = Model.get_model_path(model_name)\n",
+    "    trainedModel = PipelineModel.load(model_path)\n",
+    "    \n",
+    "def run(input_json):\n",
+    "    if isinstance(trainedModel, Exception):\n",
+    "        return json.dumps({{\"trainedModel\":str(trainedModel)}})\n",
+    "      \n",
+    "    try:\n",
+    "        sc = spark.sparkContext\n",
+    "        input_list = json.loads(input_json)\n",
+    "        input_rdd = sc.parallelize(input_list)\n",
+    "        input_df = spark.read.json(input_rdd)\n",
+    "    \n",
+    "        # Compute prediction\n",
+    "        prediction = trainedModel.transform(input_df)\n",
+    "        #result = prediction.first().prediction\n",
+    "        predictions = prediction.collect()\n",
+    " \n",
+    "        #Get each scored result\n",
+    "        preds = [str(x['prediction']) for x in predictions]\n",
+    "        result = \",\".join(preds)\n",
+    "        # you can return any data type as long as it is JSON-serializable\n",
+    "        return result.tolist()\n",
+    "    except Exception as e:\n",
+    "        result = str(e)\n",
+    "        return result\n",
+    "    \n",
+    "\"\"\".format(model_name=model_name)\n",
+    " \n",
+    "exec(score_sparkml)\n",
+    " \n",
+    "with open(\"score_sparkml.py\", \"w\") as file:\n",
+    "    file.write(score_sparkml)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.conda_dependencies import CondaDependencies \n",
+    "\n",
+    "myacienv = CondaDependencies.create(conda_packages=['scikit-learn','numpy','pandas']) #showing how to add libs as an eg. - not needed for this model.\n",
+    "\n",
+    "with open(\"mydeployenv.yml\",\"w\") as f:\n",
+    "    f.write(myacienv.serialize_to_string())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#deploy to ACI\n",
+    "from azureml.core.webservice import AciWebservice, Webservice\n",
+    "\n",
+    "myaci_config = AciWebservice.deploy_configuration(\n",
+    "    cpu_cores = 2, \n",
+    "    memory_gb = 2, \n",
+    "    tags = {'name':'Databricks Azure ML ACI'}, \n",
+    "    description = 'This is for ADB and AML example. Azure Databricks & Azure ML SDK demo with ACI by Parashar.')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# this will take 10-15 minutes to finish\n",
+    "\n",
+    "service_name = \"aciws\"\n",
+    "runtime = \"spark-py\" \n",
+    "driver_file = \"score_sparkml.py\"\n",
+    "my_conda_file = \"mydeployenv.yml\"\n",
+    "\n",
+    "# image creation\n",
+    "from azureml.core.image import ContainerImage\n",
+    "myimage_config = ContainerImage.image_configuration(execution_script = driver_file, \n",
+    "                                    runtime = runtime, \n",
+    "                                    conda_file = my_conda_file)\n",
+    "\n",
+    "# Webservice creation\n",
+    "myservice = Webservice.deploy_from_model(\n",
+    "  workspace=ws, \n",
+    "  name=service_name,\n",
+    "  deployment_config = myaci_config,\n",
+    "  models = [mymodel],\n",
+    "  image_config = myimage_config\n",
+    "    )\n",
+    "\n",
+    "myservice.wait_for_deployment(show_output=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "help(Webservice)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# List images by ws\n",
+    "\n",
+    "for i in ContainerImage.list(workspace = ws):\n",
+    "    print('{}(v.{} [{}]) stored at {} with build log {}'.format(i.name, i.version, i.creation_state, i.image_location, i.image_build_log_uri))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#for using the Web HTTP API \n",
+    "print(myservice.scoring_uri)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "\n",
+    "#get the some sample data\n",
+    "test_data_path = \"AdultCensusIncomeTest\"\n",
+    "test = spark.read.parquet(test_data_path).limit(5)\n",
+    "\n",
+    "test_json = json.dumps(test.toJSON().collect())\n",
+    "\n",
+    "print(test_json)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#using data defined above predict if income is >50K (1) or <=50K (0)\n",
+    "myservice.run(input_data=test_json)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#comment to not delete the web service\n",
+    "#myservice.delete()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "pasha"
+   },
+   {
+    "name": "wamartin"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.0"
+  },
+  "name": "04.DeploytoACI",
+  "notebookId": 3836944406456376
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}

how-to-use-azureml/azure-databricks/06.AutoML_Databricks_local.ipynb

@@ -0,0 +1,634 @@
+{
+ "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": [
+    "# AutoML : Classification with Local Compute on Azure DataBricks\n",
+    "\n",
+    "In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset) to showcase how you can use AutoML for a simple classification problem.\n",
+    "\n",
+    "In this notebook you will learn how to:\n",
+    "1. Create Azure Machine Learning Workspace object and initialize your notebook directory to easily reload this object from a configuration file.\n",
+    "2. Create an `Experiment` in an existing `Workspace`.\n",
+    "3. Configure AutoML using `AutoMLConfig`.\n",
+    "4. Train the model using AzureDataBricks.\n",
+    "5. Explore the results.\n",
+    "6. Test the best fitted model.\n",
+    "\n",
+    "Prerequisites:\n",
+    "Before running this notebook, please follow the readme for installing necessary libraries to your cluster."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Register Machine Learning Services Resource Provider\n",
+    "Microsoft.MachineLearningServices only needs to be registed once in the subscription. To register it:\n",
+    "Start the Azure portal.\n",
+    "Select your All services and then Subscription.\n",
+    "Select the subscription that you want to use.\n",
+    "Click on Resource providers\n",
+    "Click the Register link next to Microsoft.MachineLearningServices"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Check the Azure ML Core SDK Version to Validate Your Installation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import azureml.core\n",
+    "\n",
+    "print(\"SDK Version:\", azureml.core.VERSION)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Initialize an Azure ML Workspace\n",
+    "### What is an Azure ML Workspace and Why Do I Need One?\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, operationalization, and the monitoring of operationalized models.\n",
+    "\n",
+    "\n",
+    "### What do I Need?\n",
+    "\n",
+    "To create or access an Azure ML workspace, you will need to import the Azure ML library and specify following information:\n",
+    "* A name for your workspace. You can choose one.\n",
+    "* Your subscription id. Use the `id` value from the `az account show` command output above.\n",
+    "* The resource group name. The resource group organizes Azure resources and provides a default region for the resources in the group. The resource group will be created if it doesn't exist. Resource groups can be created and viewed in the [Azure portal](https://portal.azure.com)\n",
+    "* Supported regions include `eastus2`, `eastus`,`westcentralus`, `southeastasia`, `westeurope`, `australiaeast`, `westus2`, `southcentralus`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##PUBLISHONLY\n",
+    "#subscription_id = \"<Your SubscriptionId>\"\n",
+    "#resource_group = \"<Resource group - new or existing>\"\n",
+    "#workspace_name = \"<workspace to be created>\"\n",
+    "#workspace_region = \"<azureregion>\" #eg. eastus2, westcentralus, westeurope"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Creating a Workspace\n",
+    "If you already have access to an Azure ML workspace you want to use, you can skip this cell.  Otherwise, this cell will create an Azure ML workspace for you in the specified subscription, provided you have the correct permissions for the given `subscription_id`.\n",
+    "\n",
+    "This will fail when:\n",
+    "1. The workspace already exists.\n",
+    "2. You do not have permission to create a workspace in the resource group.\n",
+    "3. You are not a subscription owner or contributor and no Azure ML workspaces have ever been created in this subscription.\n",
+    "\n",
+    "If workspace creation fails for any reason other than already existing, please work with your IT administrator to provide you with the appropriate permissions or to provision the required resources.\n",
+    "\n",
+    "**Note:** Creation of a new workspace can take several minutes."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##TESTONLY\n",
+    "# import auth creds from notebook parameters\n",
+    "tenant = dbutils.widgets.get('tenant_id')\n",
+    "username = dbutils.widgets.get('service_principal_id')\n",
+    "password = dbutils.widgets.get('service_principal_password')\n",
+    "\n",
+    "auth = azureml.core.authentication.ServicePrincipalAuthentication(tenant, username, password)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##TESTONLY\n",
+    "subscription_id  = dbutils.widgets.get('subscription_id')\n",
+    "resource_group = dbutils.widgets.get('resource_group')\n",
+    "workspace_name = dbutils.widgets.get('workspace_name')\n",
+    "workspace_region = dbutils.widgets.get('workspace_region')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 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,\n",
+    "                      exist_ok=True)\n",
+    "ws.get_details()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##PUBLISHONLY\n",
+    "#from azureml.core import Workspace\n",
+    "#import azureml.core\n",
+    "#\n",
+    "## Check core SDK version number\n",
+    "#print(\"SDK version:\", azureml.core.VERSION)\n",
+    "#\n",
+    "##'''\n",
+    "#ws = Workspace.from_config()\n",
+    "#print('Workspace name: ' + ws.name, \n",
+    "#      'Azure region: ' + ws.location, \n",
+    "#      'Subscription id: ' + ws.subscription_id, \n",
+    "#      'Resource group: ' + ws.resource_group, sep = '\\n')\n",
+    "##'''"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Configuring Your Local Environment\n",
+    "You can validate that you have access to the specified workspace and write a configuration file to the default configuration location, `./aml_config/config.json`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##TESTONLY\n",
+    "from azureml.core import Workspace\n",
+    "\n",
+    "ws = Workspace(workspace_name = workspace_name,\n",
+    "               subscription_id = subscription_id,\n",
+    "               resource_group = resource_group,\n",
+    "               auth = auth)\n",
+    "\n",
+    "# Persist the subscription id, resource group name, and workspace name in aml_config/config.json.\n",
+    "ws.write_config()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##PUBLISHONLY\n",
+    "#from azureml.core import Workspace\n",
+    "#\n",
+    "#ws = Workspace(workspace_name = workspace_name,\n",
+    "#               subscription_id = subscription_id,\n",
+    "#               resource_group = resource_group)\n",
+    "#\n",
+    "## Persist the subscription id, resource group name, and workspace name in aml_config/config.json.\n",
+    "#ws.write_config()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create a Folder to Host Sample Projects\n",
+    "Finally, create a folder where all the sample projects will be hosted."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "sample_projects_folder = './sample_projects'\n",
+    "\n",
+    "if not os.path.isdir(sample_projects_folder):\n",
+    "    os.mkdir(sample_projects_folder)\n",
+    "    \n",
+    "print('Sample projects will be created in {}.'.format(sample_projects_folder))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create an Experiment\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 random\n",
+    "import time\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib.pyplot import imshow\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\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##TESTONLY\n",
+    "ws = Workspace.from_config(auth = auth)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##PUBLISHONLY\n",
+    "#ws = Workspace.from_config(auth = auth)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Choose a name for the experiment and specify the project folder.\n",
+    "experiment_name = 'automl-local-classification'\n",
+    "project_folder = './sample_projects/automl-local-classification'\n",
+    "\n",
+    "experiment = Experiment(ws, experiment_name)\n",
+    "\n",
+    "output = {}\n",
+    "output['SDK version'] = azureml.core.VERSION\n",
+    "output['Subscription ID'] = ws.subscription_id\n",
+    "output['Workspace Name'] = ws.name\n",
+    "output['Resource Group'] = ws.resource_group\n",
+    "output['Location'] = ws.location\n",
+    "output['Project Directory'] = project_folder\n",
+    "output['Experiment Name'] = experiment.name\n",
+    "pd.set_option('display.max_colwidth', -1)\n",
+    "pd.DataFrame(data = output, index = ['']).T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Diagnostics\n",
+    "\n",
+    "Opt-in diagnostics for better experience, quality, and security of future releases."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.telemetry import set_diagnostics_collection\n",
+    "set_diagnostics_collection(send_diagnostics = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Load Training Data Using DataPrep"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import azureml.dataprep as dprep\n",
+    "# You can use `auto_read_file` which intelligently figures out delimiters and datatypes of a file.\n",
+    "# The data referenced here was pulled from `sklearn.datasets.load_digits()`.\n",
+    "simple_example_data_root = 'https://dprepdata.blob.core.windows.net/automl-notebook-data/'\n",
+    "X_train = dprep.auto_read_file(simple_example_data_root + 'X.csv').skip(1)  # Remove the header row.\n",
+    "\n",
+    "# You can also use `read_csv` and `to_*` transformations to read (with overridable delimiter)\n",
+    "# and convert column types manually.\n",
+    "# Here we read a comma delimited file and convert all columns to integers.\n",
+    "y_train = 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",
+    "You can peek the result of a Dataflow at any range using skip(i) and head(j). Doing so evaluates only j records for all the steps in the Dataflow, which makes it fast even against large datasets."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train.skip(1).head(5)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Configure AutoML\n",
+    "\n",
+    "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
+    "\n",
+    "|Property|Description|\n",
+    "|-|-|\n",
+    "|**task**|classification or regression|\n",
+    "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
+    "|**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",
+    "|**spark_context**|Spark Context object. for Databricks, use spark_context=sc|\n",
+    "|**max_cuncurrent_iterations**|Maximum number of iterations to execute in parallel. This should be less than the number of cores on the ADB..|\n",
+    "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+    "|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\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",
+    "|**concurrent_iterations**|number of concurrent runs <= total cores in all worker nodes in your Databricks cluster|\n",
+    "|**exit_score**|Target score for experiment. It is associated with the metric. eg. exit_score=0.995 will exit experiment after that|"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_config = AutoMLConfig(task = 'classification',\n",
+    "                             debug_log = 'automl_errors.log',\n",
+    "                             primary_metric = 'AUC_weighted',\n",
+    "                             iteration_timeout_minutes = 10,\n",
+    "                             iterations = 30,\n",
+    "                             n_cross_validations = 10,\n",
+    "                             max_concurrent_iterations = 8, #change it based on number of cores in worker nodes\n",
+    "                             verbosity = logging.INFO,\n",
+    "                             spark_context=sc, #databricks/spark related\n",
+    "                             X = X_train, \n",
+    "                             y = y_train,\n",
+    "                             enable_cache=False,\n",
+    "                             path = project_folder)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Train the Models\n",
+    "\n",
+    "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
+    "In this example, we specify `show_output = True` to print currently running iterations to the console."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_run = experiment.submit(automl_config, show_output = True) # for higher runs please use show_output=False and use the below"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Explore the Results"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Portal URL for Monitoring Runs\n",
+    "\n",
+    "The following will provide a link to the web interface to explore individual run details and status. In the future we might support output displayed in the notebook."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(local_run.get_portal_url())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The following will show the child runs and waits for the parent run to complete."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Retrieve All Child Runs after the experiment is completed (in portal)\n",
+    "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "children = list(local_run.get_children())\n",
+    "metricslist = {}\n",
+    "for run in children:\n",
+    "    properties = run.get_properties()\n",
+    "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}    \n",
+    "    metricslist[int(properties['iteration'])] = metrics\n",
+    "\n",
+    "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+    "rundata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Retrieve the Best Model after the above run is complete \n",
+    "\n",
+    "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_model = local_run.get_output()\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Best Model Based on Any Other Metric after the above run is complete based on the child run\n",
+    "Show the run and the model that has the smallest `log_loss` value:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lookup_metric = \"log_loss\"\n",
+    "best_run, fitted_model = local_run.get_output(metric = lookup_metric)\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Test the Best Fitted Model\n",
+    "\n",
+    "#### Load Test Data - you can split the dataset beforehand & pass Train dataset to AutoML and use Test dataset to evaluate the best model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn import datasets\n",
+    "digits = datasets.load_digits()\n",
+    "X_test = digits.data[:10, :]\n",
+    "y_test = digits.target[:10]\n",
+    "images = digits.images[:10]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Testing Our Best Fitted Model\n",
+    "We will try to predict digits and see how our model works. This is just an example to show you."
+   ]
+  },
+  {
+   "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",
+    "    display(fig)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "savitam"
+   },
+   {
+    "name": "wamartin"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.0"
+  },
+  "name": "auto-ml-classification-local-adb",
+  "notebookId": 3836944406456411
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}

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

@@ -1,26 +0,0 @@
-Azure Databricks is a managed Spark offering on Azure and customers already use it for advanced analytics. It provides a collaborative Notebook based environment with CPU or GPU based compute cluster. 
-
-In this section, you will find sample notebooks on how to use Azure Machine Learning SDK with Azure Databricks. You can train a model using Spark MLlib and then deploy the model to ACI/AKS from within Azure Databricks. You can also use Automated ML capability (**public preview**) of Azure ML SDK with Azure Databricks. 
-
-- Customers who use Azure Databricks for advanced analytics can now use the same cluster to run experiments with or without automated machine learning. 
-- You can keep the data within the same cluster. 
-- You can leverage the local worker nodes with autoscale and auto termination capabilities. 
-- You can use multiple cores of your Azure Databricks cluster to perform simultenous training. 
-- You can further tune the model generated by automated machine learning if you chose to. 
-- Every run (including the best run) is available as a pipeline, which you can tune further if needed. 
-- The model trained using Azure Databricks can be registered in Azure ML SDK workspace and then deployed to Azure managed compute (ACI or AKS) using the Azure Machine learning SDK.
-
-Please follow our [Azure doc](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-environment#azure-databricks) to install the sdk in your Azure Databricks cluster before trying any of the sample notebooks.
-
-**Single file** - 
-The following archive contains all the sample notebooks. You can the run notebooks after importing [DBC](Databricks_AMLSDK_1-4_6.dbc) in your Databricks workspace instead of downloading individually.
-
-Notebooks 1-4 have to be run sequentially & are related to Income prediction experiment based on this [dataset](https://archive.ics.uci.edu/ml/datasets/adult) and demonstrate how to data prep, train and operationalize a Spark ML model with Azure ML Python SDK from within Azure Databricks. 
-
-Notebook 6 is an Automated ML sample notebook for Classification.
-
-Learn more about [how to use Azure Databricks as a development environment](https://docs.microsoft.com/azure/machine-learning/service/how-to-configure-environment#azure-databricks) for Azure Machine Learning service.
-
-For more on SDK concepts, please refer to [notebooks](https://github.com/Azure/MachineLearningNotebooks).
-
-**Please let us know your feedback.**

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

@@ -1,380 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Azure ML & Azure Databricks notebooks by Parashar Shah.\n",
-        "\n",
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![04ACI](files/tables/image2.JPG)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#Model Building"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "import pprint\n",
-        "import numpy as np\n",
-        "\n",
-        "from pyspark.ml import Pipeline, PipelineModel\n",
-        "from pyspark.ml.feature import OneHotEncoder, StringIndexer, VectorAssembler\n",
-        "from pyspark.ml.classification import LogisticRegression\n",
-        "from pyspark.ml.evaluation import BinaryClassificationEvaluator\n",
-        "from pyspark.ml.tuning import CrossValidator, ParamGridBuilder"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import azureml.core\n",
-        "\n",
-        "# Check core SDK version number\n",
-        "print(\"SDK version:\", azureml.core.VERSION)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# import the Workspace class and check the azureml SDK version\n",
-        "from azureml.core import Workspace\n",
-        "\n",
-        "ws = Workspace.from_config(auth = auth)\n",
-        "print('Workspace name: ' + ws.name, \n",
-        "      'Azure region: ' + ws.location, \n",
-        "      'Subscription id: ' + ws.subscription_id, \n",
-        "      'Resource group: ' + ws.resource_group, sep = '\\n')"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# import the Workspace class and check the azureml SDK version\n",
-        "from azureml.core import Workspace\n",
-        "\n",
-        "ws = Workspace.from_config()\n",
-        "print('Workspace name: ' + ws.name, \n",
-        "      'Azure region: ' + ws.location, \n",
-        "      'Subscription id: ' + ws.subscription_id, \n",
-        "      'Resource group: ' + ws.resource_group, sep = '\\n')"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#get the train and test datasets\n",
-        "train_data_path = \"AdultCensusIncomeTrain\"\n",
-        "test_data_path = \"AdultCensusIncomeTest\"\n",
-        "\n",
-        "train = spark.read.parquet(train_data_path)\n",
-        "test = spark.read.parquet(test_data_path)\n",
-        "\n",
-        "print(\"train: ({}, {})\".format(train.count(), len(train.columns)))\n",
-        "print(\"test: ({}, {})\".format(test.count(), len(test.columns)))\n",
-        "\n",
-        "train.printSchema()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#Define Model"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "label = \"income\"\n",
-        "dtypes = dict(train.dtypes)\n",
-        "dtypes.pop(label)\n",
-        "\n",
-        "si_xvars = []\n",
-        "ohe_xvars = []\n",
-        "featureCols = []\n",
-        "for idx,key in enumerate(dtypes):\n",
-        "    if dtypes[key] == \"string\":\n",
-        "        featureCol = \"-\".join([key, \"encoded\"])\n",
-        "        featureCols.append(featureCol)\n",
-        "        \n",
-        "        tmpCol = \"-\".join([key, \"tmp\"])\n",
-        "        # string-index and one-hot encode the string column\n",
-        "        #https://spark.apache.org/docs/2.3.0/api/java/org/apache/spark/ml/feature/StringIndexer.html\n",
-        "        #handleInvalid: Param for how to handle invalid data (unseen labels or NULL values). \n",
-        "        #Options are 'skip' (filter out rows with invalid data), 'error' (throw an error), \n",
-        "        #or 'keep' (put invalid data in a special additional bucket, at index numLabels). Default: \"error\"\n",
-        "        si_xvars.append(StringIndexer(inputCol=key, outputCol=tmpCol, handleInvalid=\"skip\"))\n",
-        "        ohe_xvars.append(OneHotEncoder(inputCol=tmpCol, outputCol=featureCol))\n",
-        "    else:\n",
-        "        featureCols.append(key)\n",
-        "\n",
-        "# string-index the label column into a column named \"label\"\n",
-        "si_label = StringIndexer(inputCol=label, outputCol='label')\n",
-        "\n",
-        "# assemble the encoded feature columns in to a column named \"features\"\n",
-        "assembler = VectorAssembler(inputCols=featureCols, outputCol=\"features\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.run import Run\n",
-        "from azureml.core.experiment import Experiment\n",
-        "import numpy as np\n",
-        "import os\n",
-        "import shutil\n",
-        "\n",
-        "model_name = \"AdultCensus_runHistory.mml\"\n",
-        "model_dbfs = os.path.join(\"/dbfs\", model_name)\n",
-        "run_history_name = 'spark-ml-notebook'\n",
-        "\n",
-        "# start a training run by defining an experiment\n",
-        "myexperiment = Experiment(ws, \"Ignite_AI_Talk\")\n",
-        "root_run = myexperiment.start_logging()\n",
-        "\n",
-        "# Regularization Rates - \n",
-        "regs = [0.0001, 0.001, 0.01, 0.1]\n",
-        " \n",
-        "# try a bunch of regularization rate in a Logistic Regression model\n",
-        "for reg in regs:\n",
-        "    print(\"Regularization rate: {}\".format(reg))\n",
-        "    # create a bunch of child runs\n",
-        "    with root_run.child_run(\"reg-\" + str(reg)) as run:\n",
-        "        # create a new Logistic Regression model.\n",
-        "        lr = LogisticRegression(regParam=reg)\n",
-        "        \n",
-        "        # put together the pipeline\n",
-        "        pipe = Pipeline(stages=[*si_xvars, *ohe_xvars, si_label, assembler, lr])\n",
-        "\n",
-        "        # train the model\n",
-        "        model_p = pipe.fit(train)\n",
-        "        \n",
-        "        # make prediction\n",
-        "        pred = model_p.transform(test)\n",
-        "        \n",
-        "        # evaluate. note only 2 metrics are supported out of the box by Spark ML.\n",
-        "        bce = BinaryClassificationEvaluator(rawPredictionCol='rawPrediction')\n",
-        "        au_roc = bce.setMetricName('areaUnderROC').evaluate(pred)\n",
-        "        au_prc = bce.setMetricName('areaUnderPR').evaluate(pred)\n",
-        "\n",
-        "        print(\"Area under ROC: {}\".format(au_roc))\n",
-        "        print(\"Area Under PR: {}\".format(au_prc))\n",
-        "      \n",
-        "        # log reg, au_roc, au_prc and feature names in run history\n",
-        "        run.log(\"reg\", reg)\n",
-        "        run.log(\"au_roc\", au_roc)\n",
-        "        run.log(\"au_prc\", au_prc)\n",
-        "        run.log_list(\"columns\", train.columns)\n",
-        "\n",
-        "        # save model\n",
-        "        model_p.write().overwrite().save(model_name)\n",
-        "        \n",
-        "        # upload the serialized model into run history record\n",
-        "        mdl, ext = model_name.split(\".\")\n",
-        "        model_zip = mdl + \".zip\"\n",
-        "        shutil.make_archive(mdl, 'zip', model_dbfs)\n",
-        "        run.upload_file(\"outputs/\" + model_name, model_zip)        \n",
-        "        #run.upload_file(\"outputs/\" + model_name, path_or_stream = model_dbfs) #cannot deal with folders\n",
-        "\n",
-        "        # now delete the serialized model from local folder since it is already uploaded to run history \n",
-        "        shutil.rmtree(model_dbfs)\n",
-        "        os.remove(model_zip)\n",
-        "        \n",
-        "# Declare run completed\n",
-        "root_run.complete()\n",
-        "root_run_id = root_run.id\n",
-        "print (\"run id:\", root_run.id)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "metrics = root_run.get_metrics(recursive=True)\n",
-        "best_run_id = max(metrics, key = lambda k: metrics[k]['au_roc'])\n",
-        "print(best_run_id, metrics[best_run_id]['au_roc'], metrics[best_run_id]['reg'])"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#Get the best run\n",
-        "child_runs = {}\n",
-        "\n",
-        "for r in root_run.get_children():\n",
-        "    child_runs[r.id] = r\n",
-        "   \n",
-        "best_run = child_runs[best_run_id]"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#Download the model from the best run to a local folder\n",
-        "best_model_file_name = \"best_model.zip\"\n",
-        "best_run.download_file(name = 'outputs/' + model_name, output_file_path = best_model_file_name)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#Model Evaluation"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "##unzip the model to dbfs (as load() seems to require that) and load it.\n",
-        "if os.path.isfile(model_dbfs) or os.path.isdir(model_dbfs):\n",
-        "    shutil.rmtree(model_dbfs)\n",
-        "shutil.unpack_archive(best_model_file_name, model_dbfs)\n",
-        "\n",
-        "model_p_best = PipelineModel.load(model_name)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# make prediction\n",
-        "pred = model_p_best.transform(test)\n",
-        "output = pred[['hours_per_week','age','workclass','marital_status','income','prediction']]\n",
-        "display(output.limit(5))"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# evaluate. note only 2 metrics are supported out of the box by Spark ML.\n",
-        "bce = BinaryClassificationEvaluator(rawPredictionCol='rawPrediction')\n",
-        "au_roc = bce.setMetricName('areaUnderROC').evaluate(pred)\n",
-        "au_prc = bce.setMetricName('areaUnderPR').evaluate(pred)\n",
-        "\n",
-        "print(\"Area under ROC: {}\".format(au_roc))\n",
-        "print(\"Area Under PR: {}\".format(au_prc))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#Model Persistence"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "##NOTE: by default the model is saved to and loaded from /dbfs/ instead of cwd!\n",
-        "model_p_best.write().overwrite().save(model_name)\n",
-        "print(\"saved model to {}\".format(model_dbfs))"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "%sh\n",
-        "\n",
-        "ls -la /dbfs/AdultCensus_runHistory.mml/*"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "dbutils.notebook.exit(\"success\")"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "pasha"
-      },
-      {
-        "name": "wamartin"
-      }
-    ],
-    "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": "3.7.0"
-    },
-    "name": "03.Build_model_runHistory",
-    "notebookId": 3836944406456339
-  },
-  "nbformat": 4,
-  "nbformat_minor": 1
-}

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

@@ -1,338 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Azure ML & Azure Databricks notebooks by Parashar Shah.\n",
-        "\n",
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Please ensure you have run all previous notebooks in sequence before running this.\n",
-        "\n",
-        "Please Register Azure Container Instance(ACI) using Azure Portal: https://docs.microsoft.com/en-us/azure/azure-resource-manager/resource-manager-supported-services#portal in your subscription before using the SDK to deploy your ML model to ACI."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![04ACI](files/tables/image3.JPG)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import azureml.core\n",
-        "\n",
-        "# Check core SDK version number\n",
-        "print(\"SDK version:\", azureml.core.VERSION)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core import Workspace\n",
-        "\n",
-        "#'''\n",
-        "ws = Workspace.from_config(auth = auth)\n",
-        "print('Workspace name: ' + ws.name, \n",
-        "      'Azure region: ' + ws.location, \n",
-        "      'Subscription id: ' + ws.subscription_id, \n",
-        "      'Resource group: ' + ws.resource_group, sep = '\\n')\n",
-        "#'''"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core import Workspace\n",
-        "import azureml.core\n",
-        "\n",
-        "# Check core SDK version number\n",
-        "print(\"SDK version:\", azureml.core.VERSION)\n",
-        "\n",
-        "#'''\n",
-        "ws = Workspace.from_config()\n",
-        "print('Workspace name: ' + ws.name, \n",
-        "      'Azure region: ' + ws.location, \n",
-        "      'Subscription id: ' + ws.subscription_id, \n",
-        "      'Resource group: ' + ws.resource_group, sep = '\\n')\n",
-        "#'''"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "##NOTE: service deployment always gets the model from the current working dir.\n",
-        "import os\n",
-        "\n",
-        "model_name = \"AdultCensus_runHistory.mml\" # \n",
-        "model_name_dbfs = os.path.join(\"/dbfs\", model_name)\n",
-        "\n",
-        "print(\"copy model from dbfs to local\")\n",
-        "model_local = \"file:\" + os.getcwd() + \"/\" + model_name\n",
-        "dbutils.fs.cp(model_name, model_local, True)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#Register the model\n",
-        "from azureml.core.model import Model\n",
-        "mymodel = Model.register(model_path = model_name, # this points to a local file\n",
-        "                       model_name = model_name, # this is the name the model is registered as, am using same name for both path and name.                 \n",
-        "                       description = \"ADB trained model by Parashar\",\n",
-        "                       workspace = ws)\n",
-        "\n",
-        "print(mymodel.name, mymodel.description, mymodel.version)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#%%writefile score_sparkml.py\n",
-        "score_sparkml = \"\"\"\n",
-        " \n",
-        "import json\n",
-        " \n",
-        "def init():\n",
-        "    # One-time initialization of PySpark and predictive model\n",
-        "    import pyspark\n",
-        "    from azureml.core.model import Model\n",
-        "    from pyspark.ml import PipelineModel\n",
-        " \n",
-        "    global trainedModel\n",
-        "    global spark\n",
-        " \n",
-        "    spark = pyspark.sql.SparkSession.builder.appName(\"ADB and AML notebook by Parashar\").getOrCreate()\n",
-        "    model_name = \"{model_name}\" #interpolated\n",
-        "    model_path = Model.get_model_path(model_name)\n",
-        "    trainedModel = PipelineModel.load(model_path)\n",
-        "    \n",
-        "def run(input_json):\n",
-        "    if isinstance(trainedModel, Exception):\n",
-        "        return json.dumps({{\"trainedModel\":str(trainedModel)}})\n",
-        "      \n",
-        "    try:\n",
-        "        sc = spark.sparkContext\n",
-        "        input_list = json.loads(input_json)\n",
-        "        input_rdd = sc.parallelize(input_list)\n",
-        "        input_df = spark.read.json(input_rdd)\n",
-        "    \n",
-        "        # Compute prediction\n",
-        "        prediction = trainedModel.transform(input_df)\n",
-        "        #result = prediction.first().prediction\n",
-        "        predictions = prediction.collect()\n",
-        " \n",
-        "        #Get each scored result\n",
-        "        preds = [str(x['prediction']) for x in predictions]\n",
-        "        result = \",\".join(preds)\n",
-        "        # you can return any data type as long as it is JSON-serializable\n",
-        "        return result.tolist()\n",
-        "    except Exception as e:\n",
-        "        result = str(e)\n",
-        "        return result\n",
-        "    \n",
-        "\"\"\".format(model_name=model_name)\n",
-        " \n",
-        "exec(score_sparkml)\n",
-        " \n",
-        "with open(\"score_sparkml.py\", \"w\") as file:\n",
-        "    file.write(score_sparkml)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.conda_dependencies import CondaDependencies \n",
-        "\n",
-        "myacienv = CondaDependencies.create(conda_packages=['scikit-learn','numpy','pandas']) #showing how to add libs as an eg. - not needed for this model.\n",
-        "\n",
-        "with open(\"mydeployenv.yml\",\"w\") as f:\n",
-        "    f.write(myacienv.serialize_to_string())"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#deploy to ACI\n",
-        "from azureml.core.webservice import AciWebservice, Webservice\n",
-        "\n",
-        "myaci_config = AciWebservice.deploy_configuration(\n",
-        "    cpu_cores = 2, \n",
-        "    memory_gb = 2, \n",
-        "    tags = {'name':'Databricks Azure ML ACI'}, \n",
-        "    description = 'This is for ADB and AML example. Azure Databricks & Azure ML SDK demo with ACI by Parashar.')"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# this will take 10-15 minutes to finish\n",
-        "\n",
-        "service_name = \"aciws\"\n",
-        "runtime = \"spark-py\" \n",
-        "driver_file = \"score_sparkml.py\"\n",
-        "my_conda_file = \"mydeployenv.yml\"\n",
-        "\n",
-        "# image creation\n",
-        "from azureml.core.image import ContainerImage\n",
-        "myimage_config = ContainerImage.image_configuration(execution_script = driver_file, \n",
-        "                                    runtime = runtime, \n",
-        "                                    conda_file = my_conda_file)\n",
-        "\n",
-        "# Webservice creation\n",
-        "myservice = Webservice.deploy_from_model(\n",
-        "  workspace=ws, \n",
-        "  name=service_name,\n",
-        "  deployment_config = myaci_config,\n",
-        "  models = [mymodel],\n",
-        "  image_config = myimage_config\n",
-        "    )\n",
-        "\n",
-        "myservice.wait_for_deployment(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "help(Webservice)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# List images by ws\n",
-        "\n",
-        "for i in ContainerImage.list(workspace = ws):\n",
-        "    print('{}(v.{} [{}]) stored at {} with build log {}'.format(i.name, i.version, i.creation_state, i.image_location, i.image_build_log_uri))"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#for using the Web HTTP API \n",
-        "print(myservice.scoring_uri)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import json\n",
-        "\n",
-        "#get the some sample data\n",
-        "test_data_path = \"AdultCensusIncomeTest\"\n",
-        "test = spark.read.parquet(test_data_path).limit(5)\n",
-        "\n",
-        "test_json = json.dumps(test.toJSON().collect())\n",
-        "\n",
-        "print(test_json)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#using data defined above predict if income is >50K (1) or <=50K (0)\n",
-        "myservice.run(input_data=test_json)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#comment to not delete the web service\n",
-        "#myservice.delete()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": []
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "pasha"
-      },
-      {
-        "name": "wamartin"
-      }
-    ],
-    "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": "3.7.0"
-    },
-    "name": "04.DeploytoACI",
-    "notebookId": 3836944406456376
-  },
-  "nbformat": 4,
-  "nbformat_minor": 1
-}

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

@@ -1,182 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Azure ML & Azure Databricks notebooks by Parashar Shah.\n",
-        "\n",
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![04ACI](files/tables/image1.JPG)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#Data Ingestion"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "import urllib"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Download AdultCensusIncome.csv from Azure CDN. This file has 32,561 rows.\n",
-        "basedataurl = \"https://amldockerdatasets.azureedge.net\"\n",
-        "datafile = \"AdultCensusIncome.csv\"\n",
-        "datafile_dbfs = os.path.join(\"/dbfs\", datafile)\n",
-        "\n",
-        "if os.path.isfile(datafile_dbfs):\n",
-        "    print(\"found {} at {}\".format(datafile, datafile_dbfs))\n",
-        "else:\n",
-        "    print(\"downloading {} to {}\".format(datafile, datafile_dbfs))\n",
-        "    urllib.request.urlretrieve(os.path.join(basedataurl, datafile), datafile_dbfs)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Create a Spark dataframe out of the csv file.\n",
-        "data_all = sqlContext.read.format('csv').options(header='true', inferSchema='true', ignoreLeadingWhiteSpace='true', ignoreTrailingWhiteSpace='true').load(datafile)\n",
-        "print(\"({}, {})\".format(data_all.count(), len(data_all.columns)))\n",
-        "data_all.printSchema()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#renaming columns\n",
-        "columns_new = [col.replace(\"-\", \"_\") for col in data_all.columns]\n",
-        "data_all = data_all.toDF(*columns_new)\n",
-        "data_all.printSchema()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "display(data_all.limit(5))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#Data Preparation"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Choose feature columns and the label column.\n",
-        "label = \"income\"\n",
-        "xvars = set(data_all.columns) - {label}\n",
-        "\n",
-        "print(\"label = {}\".format(label))\n",
-        "print(\"features = {}\".format(xvars))\n",
-        "\n",
-        "data = data_all.select([*xvars, label])\n",
-        "\n",
-        "# Split data into train and test.\n",
-        "train, test = data.randomSplit([0.75, 0.25], seed=123)\n",
-        "\n",
-        "print(\"train ({}, {})\".format(train.count(), len(train.columns)))\n",
-        "print(\"test ({}, {})\".format(test.count(), len(test.columns)))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#Data Persistence"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Write the train and test data sets to intermediate storage\n",
-        "train_data_path = \"AdultCensusIncomeTrain\"\n",
-        "test_data_path = \"AdultCensusIncomeTest\"\n",
-        "\n",
-        "train_data_path_dbfs = os.path.join(\"/dbfs\", \"AdultCensusIncomeTrain\")\n",
-        "test_data_path_dbfs = os.path.join(\"/dbfs\", \"AdultCensusIncomeTest\")\n",
-        "\n",
-        "train.write.mode('overwrite').parquet(train_data_path)\n",
-        "test.write.mode('overwrite').parquet(test_data_path)\n",
-        "print(\"train and test datasets saved to {} and {}\".format(train_data_path_dbfs, test_data_path_dbfs))"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": []
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "pasha"
-      },
-      {
-        "name": "wamartin"
-      }
-    ],
-    "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": "3.7.0"
-    },
-    "name": "02.Ingest_data",
-    "notebookId": 3836944406456362
-  },
-  "nbformat": 4,
-  "nbformat_minor": 1
-}

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

@@ -1,179 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Azure ML & Azure Databricks notebooks by Parashar Shah.\n",
-        "\n",
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "We support installing AML SDK as library from GUI. When attaching a library follow this https://docs.databricks.com/user-guide/libraries.html and add the below string as your PyPi package. You can select the option to attach the library to all clusters or just one cluster.\n",
-        "\n",
-        "**install azureml-sdk**\n",
-        "* Source: Upload Python Egg or PyPi\n",
-        "* PyPi Name: `azureml-sdk[databricks]`\n",
-        "* Select Install Library"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import azureml.core\n",
-        "\n",
-        "# Check core SDK version number - based on build number of preview/master.\n",
-        "print(\"SDK version:\", azureml.core.VERSION)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![04ACI](files/tables/image2b.JPG)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Please specify the Azure subscription Id, resource group name, workspace name, and the region in which you want to create the Azure Machine Learning Workspace.\n",
-        "\n",
-        "You can get the value of your Azure subscription ID from the Azure Portal, and then selecting Subscriptions from the menu on the left.\n",
-        "\n",
-        "For the resource_group, use the name of the resource group that contains your Azure Databricks Workspace.\n",
-        "\n",
-        "NOTE: If you provide a resource group name that does not exist, the resource group will be automatically created. This may or may not succeed in your environment, depending on the permissions you have on your Azure Subscription."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# subscription_id = \"<your-subscription-id>\"\n",
-        "# resource_group = \"<your-existing-resource-group>\"\n",
-        "# workspace_name = \"<a-new-or-existing-workspace; it is unrelated to Databricks workspace>\"\n",
-        "# workspace_region = \"<your-resource group-region>\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# import the Workspace class and check the azureml SDK version\n",
-        "# exist_ok checks if workspace exists or not.\n",
-        "\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",
-        "                      exist_ok=True)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#get workspace details\n",
-        "ws.get_details()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ws = Workspace(workspace_name = workspace_name,\n",
-        "               subscription_id = subscription_id,\n",
-        "               resource_group = resource_group)\n",
-        "\n",
-        "# persist the subscription id, resource group name, and workspace name in aml_config/config.json.\n",
-        "ws.write_config()\n",
-        "##if you need to give a different path/filename please use this\n",
-        "##write_config(path=\"/databricks/driver/aml_config/\",file_name=<alias_conf.cfg>)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "help(Workspace)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# import the Workspace class and check the azureml SDK version\n",
-        "from azureml.core import Workspace\n",
-        "\n",
-        "ws = Workspace.from_config()\n",
-        "#ws = Workspace.from_config(<full path>)\n",
-        "print('Workspace name: ' + ws.name, \n",
-        "      'Azure region: ' + ws.location, \n",
-        "      'Subscription id: ' + ws.subscription_id, \n",
-        "      'Resource group: ' + ws.resource_group, sep = '\\n')"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": []
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "pasha"
-      },
-      {
-        "name": "wamartin"
-      }
-    ],
-    "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": "3.7.0"
-    },
-    "name": "01.Installation_and_Configuration",
-    "notebookId": 3836944406456490
-  },
-  "nbformat": 4,
-  "nbformat_minor": 1
-}

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

@@ -1,559 +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 ML on Azure Databricks\n",
-        "\n",
-        "In this example we use the scikit-learn's <a href=\"http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset\" target=\"_blank\">digit dataset</a> to showcase how you can use AutoML for a simple classification problem.\n",
-        "\n",
-        "In this notebook you will learn how to:\n",
-        "1. Create Azure Machine Learning Workspace object and initialize your notebook directory to easily reload this object from a configuration file.\n",
-        "2. Create an `Experiment` in an existing `Workspace`.\n",
-        "3. Configure Automated ML using `AutoMLConfig`.\n",
-        "4. Train the model using Azure Databricks.\n",
-        "5. Explore the results.\n",
-        "6. Test the best fitted model.\n",
-        "\n",
-        "Before running this notebook, please follow the <a href=\"https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/azure-databricks\" target=\"_blank\">readme for using Automated ML on Azure Databricks</a> for installing necessary libraries to your cluster."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "We support installing AML SDK with Automated ML as library from GUI. When attaching a library follow <a href=\"https://docs.databricks.com/user-guide/libraries.html\" target=\"_blank\">this link</a> and add the below string as your PyPi package. You can select the option to attach the library to all clusters or just one cluster.\n",
-        "\n",
-        "**azureml-sdk with automated ml**\n",
-        "* Source: Upload Python Egg or PyPi\n",
-        "* PyPi Name: `azureml-sdk[automl_databricks]`\n",
-        "* Select Install Library"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Check the Azure ML Core SDK Version to Validate Your Installation"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import azureml.core\n",
-        "\n",
-        "print(\"SDK Version:\", azureml.core.VERSION)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Initialize an Azure ML Workspace\n",
-        "### What is an Azure ML Workspace and Why Do I Need One?\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, operationalization, and the monitoring of operationalized models.\n",
-        "\n",
-        "\n",
-        "### What do I Need?\n",
-        "\n",
-        "To create or access an Azure ML workspace, you will need to import the Azure ML library and specify following information:\n",
-        "* A name for your workspace. You can choose one.\n",
-        "* Your subscription id. Use the `id` value from the `az account show` command output above.\n",
-        "* The resource group name. The resource group organizes Azure resources and provides a default region for the resources in the group. The resource group will be created if it doesn't exist. Resource groups can be created and viewed in the [Azure portal](https://portal.azure.com)\n",
-        "* Supported regions include `eastus2`, `eastus`,`westcentralus`, `southeastasia`, `westeurope`, `australiaeast`, `westus2`, `southcentralus`."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "subscription_id = \"<Your SubscriptionId>\" #you should be owner or contributor\n",
-        "resource_group = \"<Resource group - new or existing>\" #you should be owner or contributor\n",
-        "workspace_name = \"<workspace to be created>\" #your workspace name\n",
-        "workspace_region = \"<azureregion>\" #your region"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Creating a Workspace\n",
-        "If you already have access to an Azure ML workspace you want to use, you can skip this cell.  Otherwise, this cell will create an Azure ML workspace for you in the specified subscription, provided you have the correct permissions for the given `subscription_id`.\n",
-        "\n",
-        "This will fail when:\n",
-        "1. The workspace already exists.\n",
-        "2. You do not have permission to create a workspace in the resource group.\n",
-        "3. You are not a subscription owner or contributor and no Azure ML workspaces have ever been created in this subscription.\n",
-        "\n",
-        "If workspace creation fails for any reason other than already existing, please work with your IT administrator to provide you with the appropriate permissions or to provision the required resources.\n",
-        "\n",
-        "**Note:** Creation of a new workspace can take several minutes."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# 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",
-        "                      exist_ok=True)\n",
-        "ws.get_details()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": []
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Configuring Your Local Environment\n",
-        "You can validate that you have access to the specified workspace and write a configuration file to the default configuration location, `./aml_config/config.json`."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core import Workspace\n",
-        "\n",
-        "ws = Workspace(workspace_name = workspace_name,\n",
-        "               subscription_id = subscription_id,\n",
-        "               resource_group = resource_group)\n",
-        "\n",
-        "# Persist the subscription id, resource group name, and workspace name in aml_config/config.json.\n",
-        "ws.write_config()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Create a Folder to Host Sample Projects\n",
-        "Finally, create a folder where all the sample projects will be hosted."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "\n",
-        "sample_projects_folder = './sample_projects'\n",
-        "\n",
-        "if not os.path.isdir(sample_projects_folder):\n",
-        "    os.mkdir(sample_projects_folder)\n",
-        "    \n",
-        "print('Sample projects will be created in {}.'.format(sample_projects_folder))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Create an Experiment\n",
-        "\n",
-        "As part of the setup you have already created an Azure ML `Workspace` object. For Automated ML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import logging\n",
-        "import os\n",
-        "import random\n",
-        "import time\n",
-        "\n",
-        "from matplotlib import pyplot as plt\n",
-        "from matplotlib.pyplot import imshow\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\n",
-        "from azureml.train.automl.run import AutoMLRun"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Choose a name for the experiment and specify the project folder.\n",
-        "experiment_name = 'automl-local-classification'\n",
-        "project_folder = './sample_projects/automl-local-classification'\n",
-        "\n",
-        "experiment = Experiment(ws, experiment_name)\n",
-        "\n",
-        "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
-        "output['Subscription ID'] = ws.subscription_id\n",
-        "output['Workspace Name'] = ws.name\n",
-        "output['Resource Group'] = ws.resource_group\n",
-        "output['Location'] = ws.location\n",
-        "output['Project Directory'] = project_folder\n",
-        "output['Experiment Name'] = experiment.name\n",
-        "pd.set_option('display.max_colwidth', -1)\n",
-        "pd.DataFrame(data = output, index = ['']).T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Diagnostics\n",
-        "\n",
-        "Opt-in diagnostics for better experience, quality, and security of future releases."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.telemetry import set_diagnostics_collection\n",
-        "set_diagnostics_collection(send_diagnostics = True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Load Training Data Using DataPrep"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#Automated ML requires a dataflow, which is different from dataframe.\n",
-        "#If your data is in a dataframe, please use read_pandas_dataframe to convert a dataframe to dataflow before usind dprep.\n",
-        "\n",
-        "import azureml.dataprep as dprep\n",
-        "# You can use `auto_read_file` which intelligently figures out delimiters and datatypes of a file.\n",
-        "# The data referenced here was pulled from `sklearn.datasets.load_digits()`.\n",
-        "simple_example_data_root = 'https://dprepdata.blob.core.windows.net/automl-notebook-data/'\n",
-        "X_train = dprep.auto_read_file(simple_example_data_root + 'X.csv').skip(1)  # Remove the header row.\n",
-        "\n",
-        "# You can also use `read_csv` and `to_*` transformations to read (with overridable delimiter)\n",
-        "# and convert column types manually.\n",
-        "# Here we read a comma delimited file and convert all columns to integers.\n",
-        "y_train = 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",
-        "You can peek the result of a Dataflow at any range using skip(i) and head(j). Doing so evaluates only j records for all the steps in the Dataflow, which makes it fast even against large datasets."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "X_train.skip(1).head(5)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Configure AutoML\n",
-        "\n",
-        "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
-        "\n",
-        "|Property|Description|\n",
-        "|-|-|\n",
-        "|**task**|classification or regression|\n",
-        "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
-        "|**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",
-        "|**spark_context**|Spark Context object. for Databricks, use spark_context=sc|\n",
-        "|**max_concurrent_iterations**|Maximum number of iterations to execute in parallel. This should be <= number of worker nodes in your Azure Databricks cluster.|\n",
-        "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
-        "|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\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",
-        "|**preprocess**|set this to True to enable pre-processing of data eg. string to numeric using one-hot encoding|\n",
-        "|**exit_score**|Target score for experiment. It is associated with the metric. eg. exit_score=0.995 will exit experiment after that|"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "automl_config = AutoMLConfig(task = 'classification',\n",
-        "                             debug_log = 'automl_errors.log',\n",
-        "                             primary_metric = 'AUC_weighted',\n",
-        "                             iteration_timeout_minutes = 10,\n",
-        "                             iterations = 30,\n",
-        "                             n_cross_validations = 10,\n",
-        "                             max_concurrent_iterations = 2, #change it based on number of worker nodes\n",
-        "                             verbosity = logging.INFO,\n",
-        "                             spark_context=sc, #databricks/spark related\n",
-        "                             X = X_train, \n",
-        "                             y = y_train,\n",
-        "                             path = project_folder)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Train the Models\n",
-        "\n",
-        "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
-        "In this example, we specify `show_output = True` to print currently running iterations to the console."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "local_run = experiment.submit(automl_config, show_output = True) # for higher runs please use show_output=False and use the below"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Explore the Results"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Portal URL for Monitoring Runs\n",
-        "\n",
-        "The following will provide a link to the web interface to explore individual run details and status. In the future we might support output displayed in the notebook."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "displayHTML(\"<a href={} target='_blank'>Your experiment in Azure Portal: {}</a>\".format(local_run.get_portal_url(), local_run.id))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "The following will show the child runs and waits for the parent run to complete."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Retrieve All Child Runs after the experiment is completed (in portal)\n",
-        "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "children = list(local_run.get_children())\n",
-        "metricslist = {}\n",
-        "for run in children:\n",
-        "    properties = run.get_properties()\n",
-        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}    \n",
-        "    metricslist[int(properties['iteration'])] = metrics\n",
-        "\n",
-        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
-        "rundata"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Retrieve the Best Model after the above run is complete \n",
-        "\n",
-        "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "best_run, fitted_model = local_run.get_output()\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Best Model Based on Any Other Metric after the above run is complete based on the child run\n",
-        "Show the run and the model that has the smallest `log_loss` value:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "lookup_metric = \"log_loss\"\n",
-        "best_run, fitted_model = local_run.get_output(metric = lookup_metric)\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Test the Best Fitted Model\n",
-        "\n",
-        "#### Load Test Data - you can split the dataset beforehand & pass Train dataset to AutoML and use Test dataset to evaluate the best model."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from sklearn import datasets\n",
-        "digits = datasets.load_digits()\n",
-        "X_test = digits.data[:10, :]\n",
-        "y_test = digits.target[:10]\n",
-        "images = digits.images[:10]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Testing Our Best Fitted Model\n",
-        "We will try to predict digits and see how our model works. This is just an example to show you."
-      ]
-    },
-    {
-      "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",
-        "    display(fig)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "When deploying an automated ML trained model, please specify _pippackages=['azureml-sdk[automl]']_ in your CondaDependencies.\n",
-        "\n",
-        "Please refer to only the **Deploy** section in this notebook - <a href=\"https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/automated-machine-learning/classification-with-deployment\" target=\"_blank\">Deployment of Automated ML trained model</a>"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": []
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "savitam"
-      },
-      {
-        "name": "wamartin"
-      }
-    ],
-    "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": "3.7.0"
-    },
-    "name": "auto-ml-classification-local-adb",
-    "notebookId": 817220787969977
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}

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

@@ -1,704 +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": [
-        "We support installing AML SDK as library from GUI. When attaching a library follow this https://docs.databricks.com/user-guide/libraries.html and add the below string as your PyPi package. You can select the option to attach the library to all clusters or just one cluster.\n",
-        "\n",
-        "**install azureml-sdk with Automated ML**\n",
-        "* Source: Upload Python Egg or PyPi\n",
-        "* PyPi Name: `azureml-sdk[automl_databricks]`\n",
-        "* Select Install Library"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# AutoML : Classification with Local Compute on Azure DataBricks with deployment to ACI\n",
-        "\n",
-        "In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset) to showcase how you can use AutoML for a simple classification problem.\n",
-        "\n",
-        "In this notebook you will learn how to:\n",
-        "1. Create Azure Machine Learning Workspace object and initialize your notebook directory to easily reload this object from a configuration file.\n",
-        "2. Create an `Experiment` in an existing `Workspace`.\n",
-        "3. Configure AutoML using `AutoMLConfig`.\n",
-        "4. Train the model using AzureDataBricks.\n",
-        "5. Explore the results.\n",
-        "6. Register the model.\n",
-        "7. Deploy the model.\n",
-        "8. Test the best fitted model.\n",
-        "\n",
-        "Prerequisites:\n",
-        "Before running this notebook, please follow the readme for installing necessary libraries to your cluster."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Register Machine Learning Services Resource Provider\n",
-        "Microsoft.MachineLearningServices only needs to be registed once in the subscription. To register it:\n",
-        "Start the Azure portal.\n",
-        "Select your All services and then Subscription.\n",
-        "Select the subscription that you want to use.\n",
-        "Click on Resource providers\n",
-        "Click the Register link next to Microsoft.MachineLearningServices"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Check the Azure ML Core SDK Version to Validate Your Installation"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import azureml.core\n",
-        "\n",
-        "print(\"SDK Version:\", azureml.core.VERSION)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Initialize an Azure ML Workspace\n",
-        "### What is an Azure ML Workspace and Why Do I Need One?\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, operationalization, and the monitoring of operationalized models.\n",
-        "\n",
-        "\n",
-        "### What do I Need?\n",
-        "\n",
-        "To create or access an Azure ML workspace, you will need to import the Azure ML library and specify following information:\n",
-        "* A name for your workspace. You can choose one.\n",
-        "* Your subscription id. Use the `id` value from the `az account show` command output above.\n",
-        "* The resource group name. The resource group organizes Azure resources and provides a default region for the resources in the group. The resource group will be created if it doesn't exist. Resource groups can be created and viewed in the [Azure portal](https://portal.azure.com)\n",
-        "* Supported regions include `eastus2`, `eastus`,`westcentralus`, `southeastasia`, `westeurope`, `australiaeast`, `westus2`, `southcentralus`."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "subscription_id = \"<Your SubscriptionId>\"\n",
-        "resource_group = \"<Resource group - new or existing>\"\n",
-        "workspace_name = \"<workspace to be created>\"\n",
-        "workspace_region = \"<azureregion>\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Creating a Workspace\n",
-        "If you already have access to an Azure ML workspace you want to use, you can skip this cell.  Otherwise, this cell will create an Azure ML workspace for you in the specified subscription, provided you have the correct permissions for the given `subscription_id`.\n",
-        "\n",
-        "This will fail when:\n",
-        "1. The workspace already exists.\n",
-        "2. You do not have permission to create a workspace in the resource group.\n",
-        "3. You are not a subscription owner or contributor and no Azure ML workspaces have ever been created in this subscription.\n",
-        "\n",
-        "If workspace creation fails for any reason other than already existing, please work with your IT administrator to provide you with the appropriate permissions or to provision the required resources.\n",
-        "\n",
-        "**Note:** Creation of a new workspace can take several minutes."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# 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",
-        "                      exist_ok=True)\n",
-        "ws.get_details()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Configuring Your Local Environment\n",
-        "You can validate that you have access to the specified workspace and write a configuration file to the default configuration location, `./aml_config/config.json`."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core import Workspace\n",
-        "\n",
-        "ws = Workspace(workspace_name = workspace_name,\n",
-        "               subscription_id = subscription_id,\n",
-        "               resource_group = resource_group)\n",
-        "\n",
-        "# Persist the subscription id, resource group name, and workspace name in aml_config/config.json.\n",
-        "ws.write_config()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Create a Folder to Host Sample Projects\n",
-        "Finally, create a folder where all the sample projects will be hosted."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "\n",
-        "sample_projects_folder = './sample_projects'\n",
-        "\n",
-        "if not os.path.isdir(sample_projects_folder):\n",
-        "    os.mkdir(sample_projects_folder)\n",
-        "    \n",
-        "print('Sample projects will be created in {}.'.format(sample_projects_folder))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Create an Experiment\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 random\n",
-        "import time\n",
-        "\n",
-        "from matplotlib import pyplot as plt\n",
-        "from matplotlib.pyplot import imshow\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\n",
-        "from azureml.train.automl.run import AutoMLRun"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Choose a name for the experiment and specify the project folder.\n",
-        "experiment_name = 'automl-local-classification'\n",
-        "project_folder = './sample_projects/automl-local-classification'\n",
-        "\n",
-        "experiment = Experiment(ws, experiment_name)\n",
-        "\n",
-        "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
-        "output['Subscription ID'] = ws.subscription_id\n",
-        "output['Workspace Name'] = ws.name\n",
-        "output['Resource Group'] = ws.resource_group\n",
-        "output['Location'] = ws.location\n",
-        "output['Project Directory'] = project_folder\n",
-        "output['Experiment Name'] = experiment.name\n",
-        "pd.set_option('display.max_colwidth', -1)\n",
-        "pd.DataFrame(data = output, index = ['']).T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Diagnostics\n",
-        "\n",
-        "Opt-in diagnostics for better experience, quality, and security of future releases."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.telemetry import set_diagnostics_collection\n",
-        "set_diagnostics_collection(send_diagnostics = True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Load Training Data Using DataPrep"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import azureml.dataprep as dprep\n",
-        "# You can use `auto_read_file` which intelligently figures out delimiters and datatypes of a file.\n",
-        "# The data referenced here was pulled from `sklearn.datasets.load_digits()`.\n",
-        "simple_example_data_root = 'https://dprepdata.blob.core.windows.net/automl-notebook-data/'\n",
-        "X_train = dprep.auto_read_file(simple_example_data_root + 'X.csv').skip(1)  # Remove the header row.\n",
-        "\n",
-        "# You can also use `read_csv` and `to_*` transformations to read (with overridable delimiter)\n",
-        "# and convert column types manually.\n",
-        "# Here we read a comma delimited file and convert all columns to integers.\n",
-        "y_train = 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",
-        "You can peek the result of a Dataflow at any range using skip(i) and head(j). Doing so evaluates only j records for all the steps in the Dataflow, which makes it fast even against large datasets."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "X_train.skip(1).head(5)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Configure AutoML\n",
-        "\n",
-        "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
-        "\n",
-        "|Property|Description|\n",
-        "|-|-|\n",
-        "|**task**|classification or regression|\n",
-        "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
-        "|**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",
-        "|**spark_context**|Spark Context object. for Databricks, use spark_context=sc|\n",
-        "|**max_concurrent_iterations**|Maximum number of iterations to execute in parallel. This should be <= number of worker nodes in your Azure Databricks cluster.|\n",
-        "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
-        "|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\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",
-        "|**preprocess**|set this to True to enable pre-processing of data eg. string to numeric using one-hot encoding|\n",
-        "|**exit_score**|Target score for experiment. It is associated with the metric. eg. exit_score=0.995 will exit experiment after that|"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "automl_config = AutoMLConfig(task = 'classification',\n",
-        "                             debug_log = 'automl_errors.log',\n",
-        "                             primary_metric = 'AUC_weighted',\n",
-        "                             iteration_timeout_minutes = 10,\n",
-        "                             iterations = 5,\n",
-        "                             n_cross_validations = 2,\n",
-        "                             max_concurrent_iterations = 4, #change it based on number of worker nodes\n",
-        "                             verbosity = logging.INFO,\n",
-        "                             spark_context=sc, #databricks/spark related\n",
-        "                             X = X_train, \n",
-        "                             y = y_train,\n",
-        "                             enable_cache=False,\n",
-        "                             path = project_folder)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Train the Models\n",
-        "\n",
-        "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
-        "In this example, we specify `show_output = True` to print currently running iterations to the console."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "local_run = experiment.submit(automl_config, show_output = True) # for higher runs please use show_output=False and use the below"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Explore the Results"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Portal URL for Monitoring Runs\n",
-        "\n",
-        "The following will provide a link to the web interface to explore individual run details and status. In the future we might support output displayed in the notebook."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "displayHTML(\"<a href={} target='_blank'>Azure Portal: {}</a>\".format(local_run.get_portal_url(), local_run.id))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "The following will show the child runs and waits for the parent run to complete."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Retrieve All Child Runs after the experiment is completed (in portal)\n",
-        "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "children = list(local_run.get_children())\n",
-        "metricslist = {}\n",
-        "for run in children:\n",
-        "    properties = run.get_properties()\n",
-        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}    \n",
-        "    metricslist[int(properties['iteration'])] = metrics\n",
-        "\n",
-        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
-        "rundata"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Retrieve the Best Model after the above run is complete \n",
-        "\n",
-        "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "best_run, fitted_model = local_run.get_output()\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Best Model Based on Any Other Metric after the above run is complete based on the child run\n",
-        "Show the run and the model that has the smallest `log_loss` value:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "lookup_metric = \"log_loss\"\n",
-        "best_run, fitted_model = local_run.get_output(metric = lookup_metric)\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Register the Fitted Model for Deployment\n",
-        "If neither metric nor iteration are specified in the register_model call, the iteration with the best primary metric is registered."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "description = 'AutoML Model'\n",
-        "tags = None\n",
-        "model = local_run.register_model(description = description, tags = tags)\n",
-        "local_run.model_id # This will be written to the scoring script file later in the notebook."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Create Scoring Script\n",
-        "Replace model_id with name of model from output of above register cell"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "%%writefile score.py\n",
-        "import pickle\n",
-        "import json\n",
-        "import numpy\n",
-        "import azureml.train.automl\n",
-        "from sklearn.externals import joblib\n",
-        "from azureml.core.model import Model\n",
-        "\n",
-        "\n",
-        "def init():\n",
-        "    global model\n",
-        "    model_path = Model.get_model_path(model_name = '<<modelid>>') # this name is model.id of model that we want to deploy\n",
-        "    # deserialize the model file back into a sklearn model\n",
-        "    model = joblib.load(model_path)\n",
-        "\n",
-        "def run(rawdata):\n",
-        "    try:\n",
-        "        data = json.loads(rawdata)['data']\n",
-        "        data = numpy.array(data)\n",
-        "        result = model.predict(data)\n",
-        "    except Exception as e:\n",
-        "        result = str(e)\n",
-        "        return json.dumps({\"error\": result})\n",
-        "    return json.dumps({\"result\":result.tolist()})"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Create a YAML File for the Environment"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.conda_dependencies import CondaDependencies\n",
-        "\n",
-        "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn'], pip_packages=['azureml-sdk[automl]'])\n",
-        "\n",
-        "conda_env_file_name = 'mydeployenv.yml'\n",
-        "myenv.save_to_file('.', conda_env_file_name)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Create ACI config"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#deploy to ACI\n",
-        "from azureml.core.webservice import AciWebservice, Webservice\n",
-        "\n",
-        "myaci_config = AciWebservice.deploy_configuration(\n",
-        "    cpu_cores = 2, \n",
-        "    memory_gb = 2, \n",
-        "    tags = {'name':'Databricks Azure ML ACI'}, \n",
-        "    description = 'This is for ADB and AutoML example.')"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Deploy the Image as a Web Service on Azure Container Instance\n",
-        "Replace servicename with any meaningful name of service"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "\n",
-        "# this will take 10-15 minutes to finish\n",
-        "\n",
-        "service_name = \"<<servicename>>\"\n",
-        "runtime = \"spark-py\" \n",
-        "driver_file = \"score.py\"\n",
-        "my_conda_file = \"mydeployenv.yml\"\n",
-        "\n",
-        "# image creation\n",
-        "from azureml.core.image import ContainerImage\n",
-        "myimage_config = ContainerImage.image_configuration(execution_script = driver_file, \n",
-        "                                    runtime = runtime, \n",
-        "                                    conda_file = 'mydeployenv.yml')\n",
-        "\n",
-        "# Webservice creation\n",
-        "myservice = Webservice.deploy_from_model(\n",
-        "  workspace=ws, \n",
-        "  name=service_name,\n",
-        "  deployment_config = myaci_config,\n",
-        "  models = [model],\n",
-        "  image_config = myimage_config\n",
-        "    )\n",
-        "\n",
-        "myservice.wait_for_deployment(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#for using the Web HTTP API \n",
-        "print(myservice.scoring_uri)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Test the Best Fitted Model\n",
-        "\n",
-        "#### Load Test Data - you can split the dataset beforehand & pass Train dataset to AutoML and use Test dataset to evaluate the best model."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from sklearn import datasets\n",
-        "digits = datasets.load_digits()\n",
-        "X_test = digits.data[:10, :]\n",
-        "y_test = digits.target[:10]\n",
-        "images = digits.images[:10]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Testing Our Best Fitted Model\n",
-        "We will try to predict digits and see how our model works. This is just an example to show you."
-      ]
-    },
-    {
-      "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",
-        "    display(fig)"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "savitam"
-      },
-      {
-        "name": "wamartin"
-      }
-    ],
-    "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": "3.7.0"
-    },
-    "name": "auto-ml-classification-local-adb",
-    "notebookId": 3888835968049288
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}

how-to-use-azureml/deployment/enable-app-insights-in-production-service/enable-app-insights-in-production-service.ipynb

@@ -38,11 +38,13 @@
    "metadata": {},
    "outputs": [],
    "source": [
-        "from azureml.core import Workspace\n",
+    "from azureml.core import Workspace, Run\n",
     "from azureml.core.compute import AksCompute, ComputeTarget\n",
-        "from azureml.core.webservice import AksWebservice\n",
+    "from azureml.core.webservice import Webservice, AksWebservice\n",
+    "from azureml.core.image import Image\n",
+    "from azureml.core.model import Model\n",
+    "\n",
     "import azureml.core\n",
-        "import json\n",
     "print(azureml.core.VERSION)"
    ]
   },
@@ -50,7 +52,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## 2. Set up your configuration and create a workspace\n"
+    "## 2. Set up your configuration and create a workspace\n",
+    "Follow Notebook 00 instructions to do this.\n"
    ]
   },
   {
@@ -100,7 +103,8 @@
     "\n",
     "### b. In your run function add:\n",
     "```python\n",
-        "print (\"Prediction created\" + time.strftime(\"%H:%M:%S\"))```"
+    "print (\"saving input data\" + time.strftime(\"%H:%M:%S\"))\n",
+    "print (\"saving prediction data\" + time.strftime(\"%H:%M:%S\"))```"
    ]
   },
   {
@@ -116,6 +120,7 @@
     "from sklearn.externals import joblib\n",
     "from sklearn.linear_model import Ridge\n",
     "from azureml.core.model import Model\n",
+    "from azureml.monitoring import ModelDataCollector\n",
     "import time\n",
     "\n",
     "def init():\n",
@@ -130,15 +135,33 @@
     "    # deserialize the model file back into a sklearn model\n",
     "    model = joblib.load(model_path)\n",
     "    \n",
-        "\n",
+    "    global inputs_dc, prediction_dc\n",
+    "    \n",
+    "    # this setup will help us save our inputs under the \"inputs\" path in our Azure Blob\n",
+    "    inputs_dc = ModelDataCollector(model_name=\"sklearn_regression_model\", identifier=\"inputs\", feature_names=[\"feat1\", \"feat2\"]) \n",
+    "    \n",
+    "    # this setup will help us save our ipredictions under the \"predictions\" path in our Azure Blob\n",
+    "    prediction_dc = ModelDataCollector(\"sklearn_regression_model\", identifier=\"predictions\", feature_names=[\"prediction1\", \"prediction2\"]) \n",
+    "  \n",
     "# note you can pass in multiple rows for scoring\n",
     "def run(raw_data):\n",
+    "    global inputs_dc, prediction_dc\n",
     "    try:\n",
     "        data = json.loads(raw_data)['data']\n",
     "        data = numpy.array(data)\n",
     "        result = model.predict(data)\n",
-        "        print (\"Prediction created\" + time.strftime(\"%H:%M:%S\"))\n",
-        "        # you can return any datatype as long as it is JSON-serializable\n",
+    "        \n",
+    "        #Print statement for appinsights custom traces:\n",
+    "        print (\"saving input data\" + time.strftime(\"%H:%M:%S\"))\n",
+    "        \n",
+    "        #this call is saving our input data into our blob\n",
+    "        inputs_dc.collect(data) \n",
+    "        #this call is saving our prediction data into our blob\n",
+    "        prediction_dc.collect(result)\n",
+    "        \n",
+    "        #Print statement for appinsights custom traces:\n",
+    "        print (\"saving prediction data\" + time.strftime(\"%H:%M:%S\"))\n",
+    "        # you can return any data type as long as it is JSON-serializable\n",
     "        return result.tolist()\n",
     "    except Exception as e:\n",
     "        error = str(e)\n",
@@ -198,74 +221,6 @@
     "image.wait_for_creation(show_output = True)"
    ]
   },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Deploy to ACI (Optional)"
-      ]
-    },
-    {
-      "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': \"diabetes\", 'type': \"regression\"}, \n",
-        "                                               description = 'Predict diabetes using regression model',\n",
-        "                                               enable_app_insights = True)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.webservice import Webservice\n",
-        "\n",
-        "aci_service_name = 'my-aci-service-4'\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": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "%%time\n",
-        "\n",
-        "test_sample = json.dumps({'data': [\n",
-        "    [1,28,13,45,54,6,57,8,8,10], \n",
-        "    [101,9,8,37,6,45,4,3,2,41]\n",
-        "]})\n",
-        "test_sample = bytes(test_sample,encoding='utf8')"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "if aci_service.state == \"Healthy\":\n",
-        "    prediction = aci_service.run(input_data=test_sample)\n",
-        "    print(prediction)\n",
-        "else:\n",
-        "    raise ValueError(\"Service deployment isn't healthy, can't call the service\")"
-      ]
-    },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -277,7 +232,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Create AKS compute if you haven't done so."
+    "### Create AKS compute if you haven't done so (Notebook 11)"
    ]
   },
   {
@@ -289,7 +244,7 @@
     "# Use the default configuration (can also provide parameters to customize)\n",
     "prov_config = AksCompute.provisioning_configuration()\n",
     "\n",
-        "aks_name = 'my-aks-test3' \n",
+    "aks_name = 'my-aks-test2' \n",
     "# Create the cluster\n",
     "aks_target = ComputeTarget.create(workspace = ws, \n",
     "                                  name = aks_name, \n",
@@ -303,15 +258,7 @@
    "outputs": [],
    "source": [
     "%%time\n",
-        "aks_target.wait_for_completion(show_output = True)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
+    "aks_target.wait_for_completion(show_output = True)\n",
     "print(aks_target.provisioning_state)\n",
     "print(aks_target.provisioning_errors)"
    ]
@@ -370,18 +317,17 @@
    "metadata": {},
    "outputs": [],
    "source": [
-        "if aks_target.provisioning_state== \"Succeeded\": \n",
-        "    aks_service_name ='aks-w-dc5'\n",
-        "    aks_service = Webservice.deploy_from_image(workspace = ws, \n",
+    "%%time\n",
+    "aks_service_name ='aks-w-dc3'\n",
+    "\n",
+    "aks_service = Webservice.deploy_from_image(workspace = ws, \n",
     "                                           name = aks_service_name,\n",
     "                                           image = image,\n",
     "                                           deployment_config = aks_config,\n",
     "                                           deployment_target = aks_target\n",
     "                                           )\n",
-        "    aks_service.wait_for_deployment(show_output = True)\n",
-        "    print(aks_service.state)\n",
-        "else:\n",
-        "    raise ValueError(\"AKS provisioning failed.\")"
+    "aks_service.wait_for_deployment(show_output = True)\n",
+    "print(aks_service.state)"
    ]
   },
   {
@@ -398,6 +344,7 @@
    "outputs": [],
    "source": [
     "%%time\n",
+    "import json\n",
     "\n",
     "test_sample = json.dumps({'data': [\n",
     "    [1,28,13,45,54,6,57,8,8,10], \n",
@@ -405,11 +352,8 @@
     "]})\n",
     "test_sample = bytes(test_sample,encoding='utf8')\n",
     "\n",
-        "if aks_service.state == \"Healthy\":\n",
-        "    prediction = aks_service.run(input_data=test_sample)\n",
-        "    print(prediction)\n",
-        "else:\n",
-        "    raise ValueError(\"Service deployment isn't healthy, can't call the service\")"
+    "prediction = aks_service.run(input_data=test_sample)\n",
+    "print(prediction)"
    ]
   },
   {
@@ -440,32 +384,12 @@
    "source": [
     "aks_service.update(enable_app_insights=False)"
    ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Clean up"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "%%time\n",
-        "aks_service.delete()\n",
-        "aci_service.delete()\n",
-        "image.delete()\n",
-        "model.delete()"
-      ]
   }
  ],
  "metadata": {
   "authors": [
    {
-        "name": "jocier"
+    "name": "marthalc"
    }
   ],
   "kernelspec": {
@@ -483,7 +407,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-      "version": "3.6.3"
+   "version": "3.6.6"
   }
  },
  "nbformat": 4,

how-to-use-azureml/deployment/enable-data-collection-for-models-in-aks/enable-data-collection-for-models-in-aks.ipynb

@@ -37,9 +37,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-        "from azureml.core import Workspace\n",
+    "from azureml.core import Workspace, Run\n",
     "from azureml.core.compute import AksCompute, ComputeTarget\n",
     "from azureml.core.webservice import Webservice, AksWebservice\n",
+    "from azureml.core.image import Image\n",
+    "from azureml.core.model import Model\n",
+    "\n",
     "import azureml.core\n",
     "print(azureml.core.VERSION)"
    ]
@@ -48,7 +51,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## 2. Set up your configuration and create a workspace"
+    "## 2. Set up your configuration and create a workspace\n",
+    "Follow Notebook 00 instructions to do this.\n"
    ]
   },
   {
@@ -233,7 +237,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Create AKS compute if you haven't done so."
+    "### Create AKS compute if you haven't done so (Notebook 11)"
    ]
   },
   {
@@ -273,7 +277,9 @@
   },
   {
    "cell_type": "markdown",
-      "metadata": {},
+   "metadata": {
+    "scrolled": true
+   },
    "source": [
     "```python \n",
     "    %%time\n",
@@ -318,18 +324,17 @@
    "metadata": {},
    "outputs": [],
    "source": [
-        "if aks_target.provisioning_state== \"Succeeded\": \n",
-        "    aks_service_name ='aks-w-dc0'\n",
-        "    aks_service = Webservice.deploy_from_image(workspace = ws, \n",
+    "%%time\n",
+    "aks_service_name ='aks-w-dc2'\n",
+    "\n",
+    "aks_service = Webservice.deploy_from_image(workspace = ws, \n",
     "                                           name = aks_service_name,\n",
     "                                           image = image,\n",
     "                                           deployment_config = aks_config,\n",
     "                                           deployment_target = aks_target\n",
     "                                           )\n",
-        "    aks_service.wait_for_deployment(show_output = True)\n",
-        "    print(aks_service.state)\n",
-        "else: \n",
-        "    raise ValueError(\"aks provisioning failed, can't deploy service\")"
+    "aks_service.wait_for_deployment(show_output = True)\n",
+    "print(aks_service.state)"
    ]
   },
   {
@@ -358,11 +363,8 @@
     "]})\n",
     "test_sample = bytes(test_sample,encoding = 'utf8')\n",
     "\n",
-        "if aks_service.state == \"Healthy\":\n",
-        "    prediction = aks_service.run(input_data=test_sample)\n",
-        "    print(prediction)\n",
-        "else:\n",
-        "    raise ValueError(\"Service deployment isn't healthy, can't call the service\")"
+    "prediction = aks_service.run(input_data = test_sample)\n",
+    "print(prediction)"
    ]
   },
   {
@@ -397,11 +399,11 @@
    "source": [
     "### b. Connect Blob to Power Bi (Small Data only)\n",
     "1. Download and Open PowerBi Desktop\n",
-        "2. Select \u201cGet Data\u201d and click on \u201cAzure Blob Storage\u201d >> Connect\n",
+    "2. Select “Get Data” and click on “Azure Blob Storage” >> Connect\n",
     "3. Add your storage account and enter your storage key.\n",
     "4. Select the container where your Data Collection is stored and click on Edit. \n",
-        "5. In the query editor, click under \u201cName\u201d column and add your Storage account Model path into the filter. Note: if you want to only look into files from a specific year or month, just expand the filter path. For example, just look into March data: /modeldata/subscriptionid>/resourcegroupname>/workspacename>/webservicename>/modelname>/modelversion>/identifier>/year>/3\n",
-        "6. Click on the double arrow aside the \u201cContent\u201d column to combine the files. \n",
+    "5. In the query editor, click under “Name” column and add your Storage account Model path into the filter. Note: if you want to only look into files from a specific year or month, just expand the filter path. For example, just look into March data: /modeldata/subscriptionid>/resourcegroupname>/workspacename>/webservicename>/modelname>/modelversion>/identifier>/year>/3\n",
+    "6. Click on the double arrow aside the “Content” column to combine the files. \n",
     "7. Click OK and the data will preload.\n",
     "8. You can now click Close and Apply and start building your custom reports on your Model Input data."
    ]
@@ -421,31 +423,12 @@
    "source": [
     "aks_service.update(collect_model_data=False)"
    ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Clean up"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "%%time\n",
-        "aks_service.delete()\n",
-        "image.delete()\n",
-        "model.delete()"
-      ]
   }
  ],
  "metadata": {
   "authors": [
    {
-        "name": "jocier"
+    "name": "marthalc"
    }
   ],
   "kernelspec": {
@@ -463,7 +446,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-      "version": "3.6.3"
+   "version": "3.6.6"
   }
  },
  "nbformat": 4,

how-to-use-azureml/deployment/onnx/README.md

@@ -1,20 +1,14 @@
-# ONNX on Azure Machine Learning
+# ONNX on Azure Machine Learning
 
-These tutorials show how to create and deploy Open Neural Network eXchange ([ONNX](http://onnx.ai)) models in Azure Machine Learning environments using [ONNX Runtime](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-build-deploy-onnx) for inference. Once deployed as a web service, you can ping the model with your own set of images to be analyzed!
+These tutorials show how to create and deploy [ONNX](http://onnx.ai) models in Azure Machine Learning environments using [ONNX Runtime](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-build-deploy-onnx) for inference. Once deployed as a web service, you can ping the model with your own set of images to be analyzed!
 
 ## Tutorials
+- [Obtain ONNX model from ONNX Model Zoo and deploy with ONNX Runtime inference - Handwritten Digit Classification (MNIST)](https://github.com/Azure/MachineLearningNotebooks/blob/master/onnx/onnx-inference-mnist-deploy.ipynb)
+- [Obtain ONNX model from ONNX Model Zoo and deploy with ONNX Runtime inference - Facial Expression Recognition (Emotion FER+)](https://github.com/Azure/MachineLearningNotebooks/blob/master/onnx/onnx-inference-facial-emotion-recognition-deploy.ipynb)
+- [Obtain ONNX model from ONNX Model Zoo and deploy with ONNX Runtime inference - Image Recognition (ResNet50)](https://github.com/Azure/MachineLearningNotebooks/blob/master/onnx/onnx-modelzoo-aml-deploy-resnet50.ipynb)
+- [Convert ONNX model from CoreML and deploy - TinyYOLO](https://github.com/Azure/MachineLearningNotebooks/blob/master/onnx/onnx-convert-aml-deploy-tinyyolo.ipynb)
+- [Train ONNX model in PyTorch and deploy - MNIST](https://github.com/Azure/MachineLearningNotebooks/blob/master/onnx/onnx-train-pytorch-aml-deploy-mnist.ipynb)
 
-0. [Configure your Azure Machine Learning Workspace](../../../configuration.ipynb)
-
-#### Obtain models from the [ONNX Model Zoo](https://github.com/onnx/models) and deploy with ONNX Runtime Inference
-1. [Handwritten Digit Classification (MNIST)](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-inference-mnist-deploy.ipynb)
-2. [Facial Expression Recognition (Emotion FER+)](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-inference-facial-expression-recognition-deploy.ipynb)
-
-#### Demo Notebooks from Microsoft Ignite 2018
-Note that the following notebooks do not have evaluation sections for the models since they were deployed as part of a live demo. You can find the respective pre-processing and post-processing code linked from the ONNX Model Zoo Github pages ([ResNet](https://github.com/onnx/models/tree/master/models/image_classification/resnet), [TinyYoloV2](https://github.com/onnx/models/tree/master/tiny_yolov2)), or experiment with the ONNX models by [running them in the browser](https://microsoft.github.io/onnxjs-demo/#/).
-
-3. [Image Recognition (ResNet50)](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-modelzoo-aml-deploy-resnet50.ipynb)
-4. [Convert Core ML Model to ONNX and deploy - Real Time Object Detection (TinyYOLO)](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-convert-aml-deploy-tinyyolo.ipynb) 
 
 ## Documentation
 - [ONNX Runtime Python API Documentation](http://aka.ms/onnxruntime-python)
@@ -25,6 +19,7 @@ Note that the following notebooks do not have evaluation sections for the models
 - [Azure AI – Making AI Real for Business](https://aka.ms/aml-blog-overview) 
 - [What’s new in Azure Machine Learning](https://aka.ms/aml-blog-whats-new)
 
+
 ## License
 Copyright (c) Microsoft Corporation. All rights reserved.  
 Licensed under the MIT License.

how-to-use-azureml/deployment/onnx/onnx-convert-aml-deploy-tinyyolo.ipynb

@@ -33,7 +33,7 @@
     "To make the best use of your time, make sure you have done the following:\n",
     "\n",
     "* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning\n",
-        "* Go through the [configuration](../../../configuration.ipynb) notebook to:\n",
+    "* Go through the [00.configuration.ipynb](../00.configuration.ipynb) notebook to:\n",
     "    * install the AML SDK\n",
     "    * create a workspace and its configuration file (config.json)"
    ]
@@ -71,7 +71,7 @@
    "source": [
     "## Convert model to ONNX\n",
     "\n",
-        "First we download the CoreML model. We use the CoreML model from [Matthijs Hollemans's tutorial](https://github.com/hollance/YOLO-CoreML-MPSNNGraph). This may take a few minutes."
+    "First we download the CoreML model. We use the CoreML model listed at https://coreml.store/tinyyolo. This may take a few minutes."
    ]
   },
   {
@@ -82,8 +82,8 @@
    "source": [
     "import urllib.request\n",
     "\n",
-        "coreml_model_url = \"https://github.com/hollance/YOLO-CoreML-MPSNNGraph/raw/master/TinyYOLO-CoreML/TinyYOLO-CoreML/TinyYOLO.mlmodel\"\n",
-        "urllib.request.urlretrieve(coreml_model_url, filename=\"TinyYOLO.mlmodel\")\n"
+    "onnx_model_url = \"https://s3-us-west-2.amazonaws.com/coreml-models/TinyYOLO.mlmodel\"\n",
+    "urllib.request.urlretrieve(onnx_model_url, filename=\"TinyYOLO.mlmodel\")\n"
    ]
   },
   {
@@ -409,7 +409,7 @@
  "metadata": {
   "authors": [
    {
-        "name": "viswamy"
+    "name": "onnx"
    }
   ],
   "kernelspec": {
@@ -427,7 +427,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-      "version": "3.6.5"
+   "version": "3.5.6"
   }
  },
  "nbformat": 4,

how-to-use-azureml/deployment/onnx/onnx-inference-facial-expression-recognition-deploy.ipynb

@@ -34,7 +34,7 @@
     "## Prerequisites\n",
     "\n",
     "### 1. Install Azure ML SDK and create a new workspace\n",
-        "Please follow [Azure ML configuration notebook](../../../configuration.ipynb) to set up your environment.\n",
+    "Please follow [Azure ML configuration notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/00.configuration.ipynb) to set up your environment.\n",
     "\n",
     "### 2. Install additional packages needed for this Notebook\n",
     "You need to install the popular plotting library `matplotlib`, the image manipulation library `opencv`, and the `onnx` library in the conda environment where Azure Maching Learning SDK is installed.\n",
@@ -197,6 +197,7 @@
    "source": [
     "# for images and plots in this notebook\n",
     "import matplotlib.pyplot as plt  \n",
+    "from IPython.display import Image\n",
     "\n",
     "# display images inline\n",
     "%matplotlib inline"
@@ -480,8 +481,8 @@
     "    \n",
     "    emotion_keys = list(emotion_table.keys())\n",
     "    emotions = []\n",
-        "    for c in range(N):\n",
-        "        emotions.append(emotion_keys[classes[c]])\n",
+    "    for i in range(N):\n",
+    "        emotions.append(emotion_keys[classes[i]])\n",
     "    return emotions\n",
     "\n",
     "def softmax(x):\n",
@@ -533,9 +534,9 @@
     "# read in 3 testing images from .pb files\n",
     "test_data_size = 3\n",
     "\n",
-        "for num in np.arange(test_data_size):\n",
-        "    input_test_data = os.path.join(model_dir, 'test_data_set_{0}'.format(num), 'input_0.pb')\n",
-        "    output_test_data = os.path.join(model_dir, 'test_data_set_{0}'.format(num), 'output_0.pb')\n",
+    "for i in np.arange(test_data_size):\n",
+    "    input_test_data = os.path.join(model_dir, 'test_data_set_{0}'.format(i), 'input_0.pb')\n",
+    "    output_test_data = os.path.join(model_dir, 'test_data_set_{0}'.format(i), 'output_0.pb')\n",
     "    \n",
     "    # convert protobuf tensors to np arrays using the TensorProto reader from ONNX\n",
     "    tensor = onnx.TensorProto()\n",
@@ -670,19 +671,19 @@
     "    \"\"\"Convert the input image into grayscale\"\"\"\n",
     "    return np.dot(rgb[...,:3], [0.299, 0.587, 0.114])\n",
     "\n",
-        "def resize_img(img_to_resize):\n",
-        "    \"\"\"Resize image to FER+ model input dimensions\"\"\"\n",
-        "    r_img = cv2.resize(img_to_resize, dsize=(64, 64), interpolation=cv2.INTER_AREA)\n",
-        "    r_img.resize((1, 1, 64, 64))\n",
-        "    return r_img\n",
+    "def resize_img(img):\n",
+    "    \"\"\"Resize image to MNIST model input dimensions\"\"\"\n",
+    "    img = cv2.resize(img, dsize=(64, 64), interpolation=cv2.INTER_AREA)\n",
+    "    img.resize((1, 1, 64, 64))\n",
+    "    return img\n",
     "\n",
-        "def preprocess(img_to_preprocess):\n",
+    "def preprocess(img):\n",
     "    \"\"\"Resize input images and convert them to grayscale.\"\"\"\n",
-        "    if img_to_preprocess.shape == (64, 64):\n",
-        "        img_to_preprocess.resize((1, 1, 64, 64))\n",
-        "        return img_to_preprocess\n",
+    "    if img.shape == (64, 64):\n",
+    "        img.resize((1, 1, 64, 64))\n",
+    "        return img\n",
     "    \n",
-        "    grayscale = rgb2gray(img_to_preprocess)\n",
+    "    grayscale = rgb2gray(img)\n",
     "    processed_img = resize_img(grayscale)\n",
     "    return processed_img"
    ]
@@ -731,7 +732,7 @@
     "        r = json.loads(aci_service.run(input_data))\n",
     "        result = r['result'][0]\n",
     "        time_ms = np.round(r['time_in_sec'][0] * 1000, 2)\n",
-        "    except KeyError as e:\n",
+    "    except Exception as e:\n",
     "        print(str(e))\n",
     "\n",
     "    plt.figure(figsize = (16, 6))\n",
@@ -799,7 +800,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-      "version": "3.6.5"
+   "version": "3.6.6"
   },
   "msauthor": "vinitra.swamy"
  },

how-to-use-azureml/deployment/onnx/onnx-inference-mnist-deploy.ipynb

@@ -34,7 +34,7 @@
     "## Prerequisites\n",
     "\n",
     "### 1. Install Azure ML SDK and create a new workspace\n",
-        "Please follow [Azure ML configuration notebook](../../../configuration.ipynb) to set up your environment.\n",
+    "Please follow [Azure ML configuration notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/00.configuration.ipynb) to set up your environment.\n",
     "\n",
     "### 2. Install additional packages needed for this tutorial notebook\n",
     "You need to install the popular plotting library `matplotlib`, the image manipulation library `opencv`, and the `onnx` library in the conda environment where Azure Maching Learning SDK is installed. \n",
@@ -255,36 +255,25 @@
     "    input_name = session.get_inputs()[0].name\n",
     "    output_name = session.get_outputs()[0].name \n",
     "    \n",
-        "\n",
-        "def preprocess(input_data_json):\n",
-        "    # convert the JSON data into the tensor input\n",
-        "    return np.array(json.loads(input_data_json)['data']).astype('float32')\n",
-        "\n",
-        "def postprocess(result):\n",
-        "    # We use argmax to pick the highest confidence label\n",
-        "    return int(np.argmax(np.array(result).squeeze(), axis=0))\n",
-        "    \n",
     "def run(input_data):\n",
+    "    '''Purpose: evaluate test input in Azure Cloud using onnxruntime.\n",
+    "        We will call the run function later from our Jupyter Notebook \n",
+    "        so our azure service can evaluate our model input in the cloud. '''\n",
     "\n",
     "    try:\n",
     "        # load in our data, convert to readable format\n",
-        "        data = preprocess(input_data)\n",
-        "        \n",
-        "        # start timer\n",
+    "        data = np.array(json.loads(input_data)['data']).astype('float32')\n",
+    "\n",
     "        start = time.time()\n",
-        "        \n",
-        "        r = session.run([output_name], {input_name: data})\n",
-        "        \n",
-        "        #end timer\n",
+    "        r = session.run([output_name], {input_name: data})[0]\n",
     "        end = time.time()\n",
-        "        \n",
-        "        result = postprocess(r)\n",
-        "        result_dict = {\"result\": result,\n",
-        "                      \"time_in_sec\": end - start}\n",
+    "        result = choose_class(r[0])\n",
+    "        result_dict = {\"result\": [result],\n",
+    "                      \"time_in_sec\": [end - start]}\n",
     "    except Exception as e:\n",
     "        result_dict = {\"error\": str(e)}\n",
     "    \n",
-        "    return result_dict\n",
+    "    return json.dumps(result_dict)\n",
     "\n",
     "def choose_class(result_prob):\n",
     "    \"\"\"We use argmax to determine the right label to choose from our output\"\"\"\n",
@@ -434,16 +423,7 @@
     "\n",
     "If you've made it this far, you've deployed a working VM with a handwritten digit classifier running in the cloud using Azure ML. Congratulations!\n",
     "\n",
-        "You can get the URL for the webservice with the code below. Let's now see how well our model deals with our test images."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "print(aci_service.scoring_uri)"
+    "Let's see how well our model deals with our test images."
    ]
   },
   {
@@ -564,14 +544,14 @@
     "    input_data = json.dumps({'data': test_inputs[i].tolist()})\n",
     "    \n",
     "    # predict using the deployed model\n",
-        "    r = aci_service.run(input_data)\n",
+    "    r = json.loads(aci_service.run(input_data))\n",
     "    \n",
     "    if \"error\" in r:\n",
     "        print(r['error'])\n",
     "        break\n",
     "        \n",
-        "    result = r['result']\n",
-        "    time_ms = np.round(r['time_in_sec'] * 1000, 2)\n",
+    "    result = r['result'][0]\n",
+    "    time_ms = np.round(r['time_in_sec'][0] * 1000, 2)\n",
     "    \n",
     "    ground_truth = int(np.argmax(test_outputs[i]))\n",
     "    \n",
@@ -621,19 +601,19 @@
     "    \"\"\"Convert the input image into grayscale\"\"\"\n",
     "    return np.dot(rgb[...,:3], [0.299, 0.587, 0.114])\n",
     "\n",
-        "def resize_img(img_to_resize):\n",
+    "def resize_img(img):\n",
     "    \"\"\"Resize image to MNIST model input dimensions\"\"\"\n",
-        "    r_img = cv2.resize(img_to_resize, dsize=(28, 28), interpolation=cv2.INTER_AREA)\n",
-        "    r_img.resize((1, 1, 28, 28))\n",
-        "    return r_img\n",
+    "    img = cv2.resize(img, dsize=(28, 28), interpolation=cv2.INTER_AREA)\n",
+    "    img.resize((1, 1, 28, 28))\n",
+    "    return img\n",
     "\n",
-        "def preprocess(img_to_preprocess):\n",
+    "def preprocess(img):\n",
     "    \"\"\"Resize input images and convert them to grayscale.\"\"\"\n",
-        "    if img_to_preprocess.shape == (28, 28):\n",
-        "        img_to_preprocess.resize((1, 1, 28, 28))\n",
-        "        return img_to_preprocess\n",
+    "    if img.shape == (28, 28):\n",
+    "        img.resize((1, 1, 28, 28))\n",
+    "        return img\n",
     "    \n",
-        "    grayscale = rgb2gray(img_to_preprocess)\n",
+    "    grayscale = rgb2gray(img)\n",
     "    processed_img = resize_img(grayscale)\n",
     "    return processed_img"
    ]
@@ -678,10 +658,10 @@
     "    input_data = json.dumps({'data': img.tolist()})\n",
     "\n",
     "    try:\n",
-        "        r = aci_service.run(input_data)\n",
-        "        result = r['result']\n",
-        "        time_ms = np.round(r['time_in_sec'] * 1000, 2)\n",
-        "    except KeyError as e:\n",
+    "        r = json.loads(aci_service.run(input_data))\n",
+    "        result = r['result'][0]\n",
+    "        time_ms = np.round(r['time_in_sec'][0] * 1000, 2)\n",
+    "    except Exception as e:\n",
     "        print(str(e))\n",
     "\n",
     "    plt.figure(figsize = (16, 6))\n",
@@ -803,7 +783,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-      "version": "3.6.5"
+   "version": "3.6.6"
   },
   "msauthor": "vinitra.swamy"
  },

how-to-use-azureml/deployment/onnx/onnx-modelzoo-aml-deploy-resnet50.ipynb

@@ -33,7 +33,7 @@
     "To make the best use of your time, make sure you have done the following:\n",
     "\n",
     "* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning\n",
-        "* Go through the [configuration notebook](../../../configuration.ipynb) to:\n",
+    "* Go through the [00.configuration.ipynb](../00.configuration.ipynb) notebook to:\n",
     "    * install the AML SDK\n",
     "    * create a workspace and its configuration file (config.json)"
    ]
@@ -393,7 +393,7 @@
  "metadata": {
   "authors": [
    {
-        "name": "viswamy"
+    "name": "onnx"
    }
   ],
   "kernelspec": {
@@ -411,7 +411,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-      "version": "3.6.5"
+   "version": "3.5.6"
   }
  },
  "nbformat": 4,

how-to-use-azureml/deployment/register-model-create-image-deploy-service/register-model-create-image-deploy-service.ipynb

@@ -13,7 +13,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Register Model, Create Image and Deploy Service\n",
+    "## 10. Register Model, Create Image and Deploy Service\n",
     "\n",
     "This example shows how to deploy a web service in step-by-step fashion:\n",
     "\n",
@@ -24,9 +24,9 @@
     " 5. Deploy the image as web service\n",
     " \n",
     "**IMPORTANT**:\n",
-        " * This notebook requires you to first complete [train-within-notebook](../../training/train-within-notebook/train-within-notebook.ipynb) example\n",
+    " * This notebook requires you to first complete \"01.SDK-101-Train-and-Deploy-to-ACI.ipynb\" Notebook\n",
     " \n",
-        "The train-within-notebook example taught you how to deploy a web service directly from model in one step. This Notebook shows a more advanced approach that gives you more control over model versions and Docker image versions.  "
+    "The 101 Notebook taught you how to deploy a web service directly from model in one step. This Notebook shows a more advanced approach that gives you more control over model versions and Docker image versions.  "
    ]
   },
   {
@@ -34,7 +34,7 @@
    "metadata": {},
    "source": [
     "## Prerequisites\n",
-        "Make sure you go through the [configuration](../../../configuration.ipynb) Notebook first if you haven't."
+    "Make sure you go through the [00. Installation and Configuration](00.configuration.ipynb) Notebook first if you haven't."
    ]
   },
   {
@@ -241,8 +241,7 @@
     "                                 description = \"Image with ridge regression model\")\n",
     "\n",
     "image = Image.create(name = \"myimage1\",\n",
-        "                     # this is the model object. note you can pass in 0-n models via this list-type parameter\n",
-        "                     # in case you need to reference multiple models, or none at all, in your scoring script.\n",
+    "                     # this is the model object \n",
     "                     models = [model],\n",
     "                     image_config = image_config, \n",
     "                     workspace = ws)"

how-to-use-azureml/machine-learning-pipelines/00.pipeline-setup.ipynb

@@ -0,0 +1,81 @@
+{
+ "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": [
+    "# Packages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install pandas\n",
+    "!pip install requests"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Widgets\n",
+    "Install the following widgets to see the status of each run"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!jupyter nbextension install --py --user azureml.widgets\n",
+    "!jupyter nbextension enable --py --user azureml.widgets"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "hichando"
+   }
+  ],
+  "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": "3.6.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

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

@@ -8,8 +8,6 @@ The Python-based Azure Machine Learning Pipeline SDK provides interfaces to work
 
 Data management and reuse across pipelines and pipeline runs is simplified using named and strictly versioned data sources and named inputs and outputs for processing tasks. Pipelines enable collaboration across teams of data scientists by recording all intermediate tasks and data.
 
-Learn more about how to [create your first machine learning pipeline](https://docs.microsoft.com/azure/machine-learning/service/how-to-create-your-first-pipeline).
-
 ### Why build pipelines?
 
 With pipelines, you can optimize your workflow with simplicity, speed, portability, and reuse. When building pipelines with Azure Machine Learning, you can focus on what you know best — machine learning — rather than infrastructure.
@@ -36,16 +34,15 @@ Azure Machine Learning Pipelines optimize for simplicity, speed, and efficiency.
 
 In this directory, there are two types of notebooks: 
 
-* The first type of notebooks will introduce you to core Azure Machine Learning Pipelines features. These notebooks below belong in this category, and are designed to go in sequence; they're all located in the "intro-to-pipelines" folder:
+* The first type of notebooks will introduce you to core Azure Machine Learning Pipelines features. The notebooks below belong in this category, and are designed to go in sequence:
 
-1. [aml-pipelines-getting-started.ipynb](https://aka.ms/pl-get-started)
-2. [aml-pipelines-with-data-dependency-steps.ipynb](https://aka.ms/pl-data-dep)
-3. [aml-pipelines-publish-and-run-using-rest-endpoint.ipynb](https://aka.ms/pl-pub-rep)
-4. [aml-pipelines-data-transfer.ipynb](https://aka.ms/pl-data-trans)
-5. [aml-pipelines-use-databricks-as-compute-target.ipynb](https://aka.ms/pl-databricks)
-6. [aml-pipelines-use-adla-as-compute-target.ipynb](https://aka.ms/pl-adla)
+1. aml-pipelines-getting-started.ipynb
+2. aml-pipelines-with-data-dependency-steps.ipynb
+3. aml-pipelines-publish-and-run-using-rest-endpoint.ipynb
+4. aml-pipelines-data-transfer.ipynb
+5. aml-pipelines-use-databricks-as-compute-target.ipynb
+6. aml-pipelines-use-adla-as-compute-target.ipynb
 
 * The second type of notebooks illustrate more sophisticated scenarios, and are independent of each other. These notebooks include:
-
-1. [pipeline-batch-scoring.ipynb](https://aka.ms/pl-batch-score)
-2. [pipeline-style-transfer.ipynb](https://aka.ms/pl-style-trans)
+  - pipeline-batch-scoring.ipynb
+  - pipeline-style-transfer.ipynb

how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-data-transfer.ipynb

@@ -35,12 +35,16 @@
    "source": [
     "import os\n",
     "import azureml.core\n",
-        "from azureml.core.compute import ComputeTarget, DataFactoryCompute\n",
+    "from azureml.core.compute import ComputeTarget, DatabricksCompute, DataFactoryCompute\n",
     "from azureml.exceptions import ComputeTargetException\n",
-        "from azureml.core import Workspace, Experiment\n",
-        "from azureml.pipeline.core import Pipeline\n",
+    "from azureml.core import Workspace, Run, Experiment\n",
+    "from azureml.pipeline.core import Pipeline, PipelineData\n",
+    "from azureml.pipeline.steps import AdlaStep\n",
     "from azureml.core.datastore import Datastore\n",
     "from azureml.data.data_reference import DataReference\n",
+    "from azureml.data.sql_data_reference import SqlDataReference\n",
+    "from azureml.core import attach_legacy_compute_target\n",
+    "from azureml.data.stored_procedure_parameter import StoredProcedureParameter, StoredProcedureParameterType\n",
     "from azureml.pipeline.steps import DataTransferStep\n",
     "\n",
     "# Check core SDK version number\n",
@@ -94,12 +98,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-        "from msrest.exceptions import HttpOperationError\n",
     "\n",
+    "workspace = ws.name\n",
     "datastore_name='MyAdlsDatastore'\n",
-        "subscription_id=os.getenv(\"ADL_SUBSCRIPTION_62\", \"<my-subscription-id>\") # subscription id of ADLS account\n",
-        "resource_group=os.getenv(\"ADL_RESOURCE_GROUP_62\", \"<my-resource-group>\") # resource group of ADLS account\n",
-        "store_name=os.getenv(\"ADL_STORENAME_62\", \"<my-datastore-name>\") # ADLS account name\n",
+    "subscription_id=os.getenv(\"ADL_SUBSCRIPTION_62\" \"<my-subscription-id>\"), # subscription id of ADLS account\n",
+    "resource_group=os.getenv(\"ADL_RESOURCE_GROUP_62\" \"<my-resource-group>\"), # resource group of ADLS account\n",
+    "store_name=os.getenv(\"ADL_STORENAME_62\", \"<my-datastore-name>\"), # ADLS account name\n",
     "tenant_id=os.getenv(\"ADL_TENANT_62\", \"<my-tenant-id>\") # tenant id of service principal\n",
     "client_id=os.getenv(\"ADL_CLIENTID_62\", \"<my-client-id>\") # client id of service principal\n",
     "client_secret=os.getenv(\"ADL_CLIENT_SECRET_62\", \"<my-client-secret>\") # the secret of service principal\n",
@@ -107,7 +111,7 @@
     "try:\n",
     "    adls_datastore = Datastore.get(ws, datastore_name)\n",
     "    print(\"found datastore with name: %s\" % datastore_name)\n",
-        "except HttpOperationError:\n",
+    "except:\n",
     "    adls_datastore = Datastore.register_azure_data_lake(\n",
     "        workspace=ws,\n",
     "        datastore_name=datastore_name,\n",
@@ -129,7 +133,7 @@
     "try:\n",
     "    blob_datastore = Datastore.get(ws, blob_datastore_name)\n",
     "    print(\"found blob datastore with name: %s\" % blob_datastore_name)\n",
-        "except HttpOperationError:\n",
+    "except:\n",
     "    blob_datastore = Datastore.register_azure_blob_container(\n",
     "        workspace=ws,\n",
     "        datastore_name=blob_datastore_name,\n",
@@ -197,7 +201,7 @@
     "            print('Data factory not found, creating...')\n",
     "            provisioning_config = DataFactoryCompute.provisioning_configuration()\n",
     "            data_factory = ComputeTarget.create(workspace, factory_name, provisioning_config)\n",
-        "            data_factory.wait_for_completion()\n",
+    "            data_factory.wait_for_provisioning()\n",
     "            return data_factory\n",
     "        else:\n",
     "            raise e\n",

how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-getting-started.ipynb

@@ -46,9 +46,10 @@
    "outputs": [],
    "source": [
     "import azureml.core\n",
-        "from azureml.core import Workspace, Experiment, Datastore\n",
+    "from azureml.core import Workspace, Run, Experiment, Datastore\n",
     "from azureml.core.compute import AmlCompute\n",
     "from azureml.core.compute import ComputeTarget\n",
+    "from azureml.core.compute import DataFactoryCompute\n",
     "from azureml.widgets import RunDetails\n",
     "\n",
     "# Check core SDK version number\n",
@@ -70,8 +71,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-        "from azureml.pipeline.core import Pipeline\n",
+    "from azureml.data.data_reference import DataReference\n",
+    "from azureml.pipeline.core import Pipeline, PipelineData, StepSequence\n",
     "from azureml.pipeline.steps import PythonScriptStep\n",
+    "from azureml.pipeline.steps import DataTransferStep\n",
+    "from azureml.pipeline.core import PublishedPipeline\n",
+    "from azureml.pipeline.core.graph import PipelineParameter\n",
     "\n",
     "print(\"Pipeline SDK-specific imports completed\")"
    ]
@@ -232,13 +237,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-        "from azureml.core.compute_target import ComputeTargetException\n",
     "\n",
     "aml_compute_target = \"aml-compute\"\n",
     "try:\n",
     "    aml_compute = AmlCompute(ws, aml_compute_target)\n",
     "    print(\"found existing compute target.\")\n",
-        "except ComputeTargetException:\n",
+    "except:\n",
     "    print(\"creating new compute target\")\n",
     "    \n",
     "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\",\n",
@@ -247,18 +251,9 @@
     "    aml_compute = ComputeTarget.create(ws, aml_compute_target, provisioning_config)\n",
     "    aml_compute.wait_for_completion(show_output=True, min_node_count=None, timeout_in_minutes=20)\n",
     "    \n",
-        "print(\"Azure Machine Learning Compute attached\")\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# For a more detailed view of current Azure Machine Learning Compute status, use get_status()\n",
-        "# example: un-comment the following line.\n",
-        "# print(aml_compute.get_status().serialize())"
+    "print(\"Azure Machine Learning Compute attached\")\n",
+    "# For a more detailed view of current Azure Machine Learning Compute status, use the 'status' property    \n",
+    "print(aml_compute.status.serialize())"
    ]
   },
   {

how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-publish-and-run-using-rest-endpoint.ipynb

@@ -33,16 +33,20 @@
    "outputs": [],
    "source": [
     "import azureml.core\n",
-        "from azureml.core import Workspace, Datastore\n",
+    "from azureml.core import Workspace, Run, Experiment, Datastore\n",
     "from azureml.core.compute import AmlCompute\n",
     "from azureml.core.compute import ComputeTarget\n",
+    "from azureml.core.compute import DataFactoryCompute\n",
+    "from azureml.widgets import RunDetails\n",
     "\n",
     "# Check core SDK version number\n",
     "print(\"SDK version:\", azureml.core.VERSION)\n",
     "\n",
     "from azureml.data.data_reference import DataReference\n",
-        "from azureml.pipeline.core import Pipeline, PipelineData\n",
+    "from azureml.pipeline.core import Pipeline, PipelineData, StepSequence\n",
     "from azureml.pipeline.steps import PythonScriptStep\n",
+    "from azureml.pipeline.steps import DataTransferStep\n",
+    "from azureml.pipeline.core import PublishedPipeline\n",
     "from azureml.pipeline.core.graph import PipelineParameter\n",
     "\n",
     "print(\"Pipeline SDK-specific imports completed\")\n",
@@ -75,31 +79,21 @@
    "metadata": {},
    "outputs": [],
    "source": [
-        "from azureml.core.compute_target import ComputeTargetException\n",
     "\n",
     "aml_compute_target = \"aml-compute\"\n",
     "try:\n",
     "    aml_compute = AmlCompute(ws, aml_compute_target)\n",
     "    print(\"found existing compute target.\")\n",
-        "except ComputeTargetException:\n",
+    "except:\n",
     "    print(\"creating new compute target\")\n",
     "    \n",
     "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\",\n",
     "                                                                min_nodes = 1, \n",
     "                                                                max_nodes = 4)    \n",
     "    aml_compute = ComputeTarget.create(ws, aml_compute_target, provisioning_config)\n",
-        "    aml_compute.wait_for_completion(show_output=True, min_node_count=None, timeout_in_minutes=20)\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# For a more detailed view of current Azure Machine Learning Compute status, use get_status()\n",
-        "# example: un-comment the following line.\n",
-        "# print(aml_compute.get_status().serialize())"
+    "    aml_compute.wait_for_completion(show_output=True, min_node_count=None, timeout_in_minutes=20)\n",
+    "    \n",
+    "print(aml_compute.status.serialize())\n"
    ]
   },
   {

how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-use-adla-as-compute-target.ipynb

@@ -31,12 +31,14 @@
    "source": [
     "import os\n",
     "import azureml.core\n",
+    "from azureml.core.compute import ComputeTarget, DatabricksCompute\n",
     "from azureml.exceptions import ComputeTargetException\n",
-        "from azureml.core import Workspace, Experiment\n",
+    "from azureml.core import Workspace, Run, Experiment\n",
     "from azureml.pipeline.core import Pipeline, PipelineData\n",
     "from azureml.pipeline.steps import AdlaStep\n",
     "from azureml.core.datastore import Datastore\n",
     "from azureml.data.data_reference import DataReference\n",
+    "from azureml.core import attach_legacy_compute_target\n",
     "\n",
     "# Check core SDK version number\n",
     "print(\"SDK version:\", azureml.core.VERSION)"
@@ -89,12 +91,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-        "from msrest.exceptions import HttpOperationError\n",
     "\n",
+    "workspace = ws.name\n",
     "datastore_name='MyAdlsDatastore'\n",
-        "subscription_id=os.getenv(\"ADL_SUBSCRIPTION_62\", \"<my-subscription-id>\") # subscription id of ADLS account\n",
-        "resource_group=os.getenv(\"ADL_RESOURCE_GROUP_62\", \"<my-resource-group>\") # resource group of ADLS account\n",
-        "store_name=os.getenv(\"ADL_STORENAME_62\", \"<my-datastore-name>\") # ADLS account name\n",
+    "subscription_id=os.getenv(\"ADL_SUBSCRIPTION_62\" \"<my-subscription-id>\"), # subscription id of ADLS account\n",
+    "resource_group=os.getenv(\"ADL_RESOURCE_GROUP_62\" \"<my-resource-group>\"), # resource group of ADLS account\n",
+    "store_name=os.getenv(\"ADL_STORENAME_62\", \"<my-datastore-name>\"), # ADLS account name\n",
     "tenant_id=os.getenv(\"ADL_TENANT_62\", \"<my-tenant-id>\") # tenant id of service principal\n",
     "client_id=os.getenv(\"ADL_CLIENTID_62\", \"<my-client-id>\") # client id of service principal\n",
     "client_secret=os.getenv(\"ADL_CLIENT_62_SECRET\", \"<my-client-secret>\") # the secret of service principal\n",
@@ -102,7 +104,7 @@
     "try:\n",
     "    adls_datastore = Datastore.get(ws, datastore_name)\n",
     "    print(\"found datastore with name: %s\" % datastore_name)\n",
-        "except HttpOperationError:\n",
+    "except:\n",
     "    adls_datastore = Datastore.register_azure_data_lake(\n",
     "        workspace=ws,\n",
     "        datastore_name=datastore_name,\n",
@@ -169,9 +171,9 @@
     "        if 'ComputeTargetNotFound' in e.message:\n",
     "            print('adla compute not found, creating...')\n",
     "            provisioning_config = AdlaCompute.provisioning_configuration()\n",
-        "            new_adla_compute = ComputeTarget.create(workspace, compute_name, provisioning_config)\n",
-        "            new_adla_compute.wait_for_completion()\n",
-        "            return new_adla_compute\n",
+    "            adla_compute = ComputeTarget.create(workspace, compute_name, provisioning_config)\n",
+    "            adla_compute.wait_for_completion()\n",
+    "            return adla_compute\n",
     "        else:\n",
     "            raise e\n",
     "            \n",
@@ -227,10 +229,12 @@
     "\n",
     "### Remarks\n",
     "\n",
-        "You can use `@@name@@` syntax in your script to refer to inputs, outputs, and params.\n",
+    "You can use `@@name@@` syntax in your script to refer to inputs, outputs, resources, and params.\n",
     "\n",
     "* if `name` is the name of an input or output port binding, any occurences of `@@name@@` in the script\n",
     "are replaced with actual data path of corresponding port binding.\n",
+    "* if `name` is the name of a resource input port binding, any occurences of `@@name@@` in the script\n",
+    "are replaced with local path of resource after it's downloaded to script directory on a worker node.\n",
     "* if `name` matches any key in `params` dict, any occurences of `@@name@@` will be replaced with\n",
     "corresponding value in dict.\n",
     "\n",
@@ -282,7 +286,7 @@
     "    steps=[adla_step],\n",
     "    default_source_directory=script_folder)\n",
     "\n",
-        "pipeline_run = Experiment(ws, experiment_name).submit(pipeline)\n",
+    "pipeline_run = Experiment(workspace, experiment_name).submit(pipeline)\n",
     "pipeline_run.wait_for_completion()"
    ]
   },
@@ -358,7 +362,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-      "version": "3.6.6"
+   "version": "3.6.7"
   }
  },
  "nbformat": 4,

how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-use-databricks-as-compute-target.ipynb

@@ -89,7 +89,7 @@
     "from azureml.core.runconfig import JarLibrary\n",
     "from azureml.core.compute import ComputeTarget, DatabricksCompute\n",
     "from azureml.exceptions import ComputeTargetException\n",
-        "from azureml.core import Workspace, Experiment\n",
+    "from azureml.core import Workspace, Run, Experiment\n",
     "from azureml.pipeline.core import Pipeline, PipelineData\n",
     "from azureml.pipeline.steps import DatabricksStep\n",
     "from azureml.core.datastore import Datastore\n",
@@ -127,9 +127,7 @@
     "\n",
     "- **Resource Group** - The resource group name of your Azure Machine Learning workspace\n",
     "- **Databricks Workspace Name** - The workspace name of your Azure Databricks workspace\n",
-        "- **Databricks Access Token** - The access token you created in ADB\n",
-        "\n",
-        "**The Databricks workspace need to be present in the same subscription as your AML workspace**"
+    "- **Databricks Access Token** - The access token you created in ADB"
    ]
   },
   {
@@ -146,7 +144,7 @@
     "db_access_token=os.getenv(\"DATABRICKS_ACCESS_TOKEN\", \"<my-access-token>\") # Databricks access token\n",
     " \n",
     "try:\n",
-        "    databricks_compute = DatabricksCompute(workspace=ws, name=db_compute_name)\n",
+    "    databricks_compute = ComputeTarget(workspace=ws, name=db_compute_name)\n",
     "    print('Compute target {} already exists'.format(db_compute_name))\n",
     "except ComputeTargetException:\n",
     "    print('Compute not found, will use below parameters to attach new one')\n",
@@ -297,7 +295,7 @@
     "print('Datastore {} will be used'.format(def_blob_store.name))\n",
     "\n",
     "# We are uploading a sample file in the local directory to be used as a datasource\n",
-        "def_blob_store.upload_files(files=[\"./testdata.txt\"], target_path=\"dbtest\", overwrite=False)\n",
+    "def_blob_store.upload_files([\"./testdata.txt\"], target_path=\"dbtest\", overwrite=False)\n",
     "\n",
     "step_1_input = DataReference(datastore=def_blob_store, path_on_datastore=\"dbtest\",\n",
     "                                     data_reference_name=\"input\")\n",
@@ -314,74 +312,33 @@
     "- ***name:** Name of the Module\n",
     "- **inputs:** List of input connections for data consumed by this step. Fetch this inside the notebook using dbutils.widgets.get(\"input\")\n",
     "- **outputs:** List of output port definitions for outputs produced by this step. Fetch this inside the notebook using dbutils.widgets.get(\"output\")\n",
-        "- **existing_cluster_id:** Cluster ID of an existing Interactive cluster on the Databricks workspace. If you are providing this, do not provide any of the parameters below that are used to create a new cluster such as spark_version, node_type, etc.\n",
     "- **spark_version:** Version of spark for the databricks run cluster. default value: 4.0.x-scala2.11\n",
     "- **node_type:** Azure vm node types for the databricks run cluster. default value: Standard_D3_v2\n",
-        "- **num_workers:** Specifies a static number of workers for the databricks run cluster\n",
-        "- **min_workers:** Specifies a min number of workers to use for auto-scaling the databricks run cluster\n",
-        "- **max_workers:** Specifies a max number of workers to use for auto-scaling the databricks run cluster\n",
+    "- **num_workers:** Number of workers for the databricks run cluster\n",
+    "- **autoscale:** The autoscale configuration for the databricks run cluster\n",
     "- **spark_env_variables:** Spark environment variables for the databricks run cluster (dictionary of {str:str}). default value: {'PYSPARK_PYTHON': '/databricks/python3/bin/python3'}\n",
-        "- **notebook_path:** Path to the notebook in the databricks instance. If you are providing this, do not provide python script related paramaters or JAR related parameters.\n",
+    "- ***notebook_path:** Path to the notebook in the databricks instance.\n",
     "- **notebook_params:** Parameters  for the databricks notebook (dictionary of {str:str}). Fetch this inside the notebook using dbutils.widgets.get(\"myparam\")\n",
-        "- **python_script_path:** The path to the python script in the DBFS or S3. If you are providing this, do not provide python_script_name which is used for uploading script from local machine.\n",
-        "- **python_script_params:** Parameters for the python script (list of str)\n",
-        "- **main_class_name:** The name of the entry point in a JAR module. If you are providing this, do not provide any python script or notebook related parameters.\n",
-        "- **jar_params:** Parameters for the JAR module (list of str)\n",
-        "- **python_script_name:** name of a python script on your local machine (relative to source_directory). If you are providing this do not provide python_script_path which is used to execute a remote python script; or any of the JAR or notebook related parameters.\n",
-        "- **source_directory:** folder that contains the script and other files\n",
-        "- **hash_paths:** list of paths to hash to detect a change in source_directory (script file is always hashed)\n",
     "- **run_name:** Name in databricks for this run\n",
     "- **timeout_seconds:** Timeout for the databricks run\n",
-        "- **runconfig:** Runconfig to use. Either pass runconfig or each library type as a separate parameter but do not mix the two\n",
     "- **maven_libraries:** maven libraries for the databricks run\n",
     "- **pypi_libraries:** pypi libraries for the databricks run\n",
     "- **egg_libraries:** egg libraries for the databricks run\n",
     "- **jar_libraries:** jar libraries for the databricks run\n",
     "- **rcran_libraries:** rcran libraries for the databricks run\n",
-        "- **compute_target:** Azure Databricks compute\n",
-        "- **allow_reuse:** Whether the step should reuse previous results when run with the same settings/inputs\n",
-        "- **version:** Optional version tag to denote a change in functionality for the step\n",
+    "- **databricks_compute:** Azure Databricks compute\n",
+    "- **databricks_compute_name:** Name of Azure Databricks compute\n",
     "\n",
     "\\* *denotes required fields*  \n",
-        "*You must provide exactly one of num_workers or min_workers and max_workers paramaters*  \n",
-        "*You must provide exactly one of databricks_compute or databricks_compute_name parameters*\n",
-        "\n",
-        "## Use runconfig to specify library dependencies\n",
-        "You can use a runconfig to specify the library dependencies for your cluster in Databricks. The runconfig will contain a databricks section as follows:\n",
-        "```yaml\n",
-        "environment:\n",
-        "# Databricks details\n",
-        "  databricks:\n",
-        "# List of maven libraries.\n",
-        "    mavenLibraries:\n",
-        "    - coordinates: org.jsoup:jsoup:1.7.1\n",
-        "      repo: ''\n",
-        "      exclusions:\n",
-        "      - slf4j:slf4j\n",
-        "      - '*:hadoop-client'\n",
-        "# List of PyPi libraries\n",
-        "    pypiLibraries:\n",
-        "    - package: beautifulsoup4\n",
-        "      repo: ''\n",
-        "# List of RCran libraries\n",
-        "    rcranLibraries:\n",
-        "    - package: ada\n",
-        "      repo: http://cran.us.r-project.org\n",
-        "# List of JAR libraries\n",
-        "    jarLibraries:\n",
-        "    - library: dbfs:/mnt/libraries/library.jar\n",
-        "# List of Egg libraries\n",
-        "    eggLibraries:\n",
-        "    - library: dbfs:/mnt/libraries/library.egg\n",
-        "```\n",
-        "\n",
-        "You can then create a RunConfiguration object using this file and pass it as the runconfig parameter to DatabricksStep.\n",
-        "```python\n",
-        "from azureml.core.runconfig import RunConfiguration\n",
-        "\n",
-        "runconfig = RunConfiguration()\n",
-        "runconfig.load(path='<directory_where_runconfig_is_stored>', name='<runconfig_file_name>')\n",
-        "```"
+    "*You must provide exactly one of num_workers or autoscale paramaters*  \n",
+    "*You must provide exactly one of databricks_compute or databricks_compute_name parameters*"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<a id='notebook_howto'></a>"
    ]
   },
   {
@@ -389,7 +346,7 @@
    "metadata": {},
    "source": [
     "### 1. Running the demo notebook already added to the Databricks workspace\n",
-        "Create a notebook in the Azure Databricks workspace, and provide the path to that notebook as the value associated with the environment variable \"DATABRICKS_NOTEBOOK_PATH\". This will then set the variable\u00c2\u00a0notebook_path\u00c2\u00a0when you run the code cell below:"
+    "Create a notebook in the Azure Databricks workspace, and provide the path to that notebook as the value associated with the environment variable \"DATABRICKS_NOTEBOOK_PATH\". This will then set the variable notebook_path when you run the code cell below:"
    ]
   },
   {
@@ -690,7 +647,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-      "version": "3.6.2"
+   "version": "3.6.7"
   }
  },
  "nbformat": 4,

how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-data-dependency-steps.ipynb

@@ -33,17 +33,22 @@
    "outputs": [],
    "source": [
     "import azureml.core\n",
-        "from azureml.core import Workspace, Experiment, Datastore\n",
+    "from azureml.core import Workspace, Run, Experiment, Datastore\n",
     "from azureml.core.compute import AmlCompute\n",
     "from azureml.core.compute import ComputeTarget\n",
+    "from azureml.core.compute import DataFactoryCompute\n",
     "from azureml.widgets import RunDetails\n",
     "\n",
     "# Check core SDK version number\n",
     "print(\"SDK version:\", azureml.core.VERSION)\n",
     "\n",
     "from azureml.data.data_reference import DataReference\n",
-        "from azureml.pipeline.core import Pipeline, PipelineData\n",
+    "from azureml.pipeline.core import Pipeline, PipelineData, StepSequence\n",
     "from azureml.pipeline.steps import PythonScriptStep\n",
+    "from azureml.pipeline.steps import DataTransferStep\n",
+    "from azureml.pipeline.core import PublishedPipeline\n",
+    "from azureml.pipeline.core.graph import PipelineParameter\n",
+    "\n",
     "print(\"Pipeline SDK-specific imports completed\")"
    ]
   },
@@ -130,13 +135,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-        "from azureml.core.compute_target import ComputeTargetException\n",
     "\n",
     "aml_compute_target = \"aml-compute\"\n",
     "try:\n",
     "    aml_compute = AmlCompute(ws, aml_compute_target)\n",
     "    print(\"found existing compute target.\")\n",
-        "except ComputeTargetException:\n",
+    "except:\n",
     "    print(\"creating new compute target\")\n",
     "    \n",
     "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\",\n",
@@ -145,18 +149,9 @@
     "    aml_compute = ComputeTarget.create(ws, aml_compute_target, provisioning_config)\n",
     "    aml_compute.wait_for_completion(show_output=True, min_node_count=None, timeout_in_minutes=20)\n",
     "    \n",
-        "print(\"Aml Compute attached\")\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# For a more detailed view of current Azure Machine Learning Compute status, use get_status()\n",
-        "# example: un-comment the following line.\n",
-        "# print(aml_compute.get_status().serialize())"
+    "print(\"Aml Compute attached\")\n",
+    "# For a more detailed view of current AmlCompute status, use the 'status' property    \n",
+    "print(aml_compute.status.serialize())"
    ]
   },
   {

how-to-use-azureml/machine-learning-pipelines/pipeline-batch-scoring/batch_scoring.py

@@ -1,119 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-# Licensed under the MIT license.
-
-import os
-import argparse
-import datetime
-import time
-import tensorflow as tf
-from math import ceil
-import numpy as np
-import shutil
-from tensorflow.contrib.slim.python.slim.nets import inception_v3
-from azureml.core.model import Model
-
-slim = tf.contrib.slim
-
-parser = argparse.ArgumentParser(description="Start a tensorflow model serving")
-parser.add_argument('--model_name', dest="model_name", required=True)
-parser.add_argument('--label_dir', dest="label_dir", required=True)
-parser.add_argument('--dataset_path', dest="dataset_path", required=True)
-parser.add_argument('--output_dir', dest="output_dir", required=True)
-parser.add_argument('--batch_size', dest="batch_size", type=int, required=True)
-
-args = parser.parse_args()
-
-image_size = 299
-num_channel = 3
-
-# create output directory if it does not exist
-os.makedirs(args.output_dir, exist_ok=True)
-
-
-def get_class_label_dict(label_file):
-    label = []
-    proto_as_ascii_lines = tf.gfile.GFile(label_file).readlines()
-    for l in proto_as_ascii_lines:
-        label.append(l.rstrip())
-    return label
-
-
-class DataIterator:
-    def __init__(self, data_dir):
-        self.file_paths = []
-        image_list = os.listdir(data_dir)
-        # total_size = len(image_list)
-        self.file_paths = [data_dir + '/' + file_name.rstrip() for file_name in image_list]
-
-        self.labels = [1 for file_name in self.file_paths]
-
-    @property
-    def size(self):
-        return len(self.labels)
-
-    def input_pipeline(self, batch_size):
-        images_tensor = tf.convert_to_tensor(self.file_paths, dtype=tf.string)
-        labels_tensor = tf.convert_to_tensor(self.labels, dtype=tf.int64)
-        input_queue = tf.train.slice_input_producer([images_tensor, labels_tensor], shuffle=False)
-        labels = input_queue[1]
-        images_content = tf.read_file(input_queue[0])
-
-        image_reader = tf.image.decode_jpeg(images_content, channels=num_channel, name="jpeg_reader")
-        float_caster = tf.cast(image_reader, tf.float32)
-        new_size = tf.constant([image_size, image_size], dtype=tf.int32)
-        images = tf.image.resize_images(float_caster, new_size)
-        images = tf.divide(tf.subtract(images, [0]), [255])
-
-        image_batch, label_batch = tf.train.batch([images, labels], batch_size=batch_size, capacity=5 * batch_size)
-        return image_batch
-
-
-def main(_):
-    # start_time = datetime.datetime.now()
-    label_file_name = os.path.join(args.label_dir, "labels.txt")
-    label_dict = get_class_label_dict(label_file_name)
-    classes_num = len(label_dict)
-    test_feeder = DataIterator(data_dir=args.dataset_path)
-    total_size = len(test_feeder.labels)
-    count = 0
-    # get model from model registry
-    model_path = Model.get_model_path(args.model_name)
-    with tf.Session() as sess:
-        test_images = test_feeder.input_pipeline(batch_size=args.batch_size)
-        with slim.arg_scope(inception_v3.inception_v3_arg_scope()):
-            input_images = tf.placeholder(tf.float32, [args.batch_size, image_size, image_size, num_channel])
-            logits, _ = inception_v3.inception_v3(input_images,
-                                                  num_classes=classes_num,
-                                                  is_training=False)
-            probabilities = tf.argmax(logits, 1)
-
-        sess.run(tf.global_variables_initializer())
-        sess.run(tf.local_variables_initializer())
-        coord = tf.train.Coordinator()
-        threads = tf.train.start_queue_runners(sess=sess, coord=coord)
-        saver = tf.train.Saver()
-        saver.restore(sess, model_path)
-        out_filename = os.path.join(args.output_dir, "result-labels.txt")
-        with open(out_filename, "w") as result_file:
-            i = 0
-            while count < total_size and not coord.should_stop():
-                test_images_batch = sess.run(test_images)
-                file_names_batch = test_feeder.file_paths[i * args.batch_size:
-                                                          min(test_feeder.size, (i + 1) * args.batch_size)]
-                results = sess.run(probabilities, feed_dict={input_images: test_images_batch})
-                new_add = min(args.batch_size, total_size - count)
-                count += new_add
-                i += 1
-                for j in range(new_add):
-                    result_file.write(os.path.basename(file_names_batch[j]) + ": " + label_dict[results[j]] + "\n")
-                result_file.flush()
-            coord.request_stop()
-            coord.join(threads)
-
-        # copy the file to artifacts
-        shutil.copy(out_filename, "./outputs/")
-        # Move the processed data out of the blob so that the next run can process the data.
-
-
-if __name__ == "__main__":
-    tf.app.run()

how-to-use-azureml/machine-learning-pipelines/pipeline-batch-scoring/pipeline-batch-scoring.ipynb

@@ -37,8 +37,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from azureml.core import Datastore\n",
     "from azureml.core import Experiment\n",
     "from azureml.core.compute import AmlCompute, ComputeTarget\n",
+    "from azureml.core.conda_dependencies import CondaDependencies\n",
     "from azureml.core.datastore import Datastore\n",
     "from azureml.core.runconfig import CondaDependencies, RunConfiguration\n",
     "from azureml.data.data_reference import DataReference\n",
@@ -53,7 +55,7 @@
    "outputs": [],
    "source": [
     "import os\n",
-        "from azureml.core import Workspace\n",
+    "from azureml.core import Workspace, Run, Experiment\n",
     "\n",
     "ws = Workspace.from_config()\n",
     "print('Workspace name: ' + ws.name, \n",
@@ -74,7 +76,7 @@
    "metadata": {},
    "source": [
     "### Set up datastores\n",
-        "First, let\u00e2\u20ac\u2122s access the datastore that has the model, labels, and images. \n",
+    "First, let’s access the datastore that has the model, labels, and images. \n",
     "\n",
     "### Create a datastore that points to a blob container containing sample images\n",
     "\n",
@@ -104,7 +106,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "Next, let\u00e2\u20ac\u2122s specify the default datastore for the outputs."
+    "Next, let’s specify the default datastore for the outputs."
    ]
   },
   {
@@ -164,6 +166,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "import os\n",
+    "\n",
     "# choose a name for your cluster\n",
     "aml_compute_name = os.environ.get(\"AML_COMPUTE_NAME\", \"gpu-cluster\")\n",
     "cluster_min_nodes = os.environ.get(\"AML_COMPUTE_MIN_NODES\", 0)\n",
@@ -189,8 +193,8 @@
     "    # 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 Azure Machine Learning Compute  status, use get_status()\n",
-        "    print(compute_target.get_status().serialize())"
+    "     # For a more detailed view of current Azure Machine Learning Compute  status, use the 'status' property    \n",
+    "    print(compute_target.status.serialize())"
    ]
   },
   {
@@ -291,7 +295,7 @@
    "metadata": {},
    "source": [
     "## Build and run the batch scoring pipeline\n",
-        "You have everything you need to build the pipeline. Let\u00e2\u20ac\u2122s put all these together."
+    "You have everything you need to build the pipeline. Let’s put all these together."
    ]
   },
   {
@@ -509,6 +513,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from azureml.pipeline.core import PublishedPipeline\n",
+    "\n",
     "rest_endpoint = published_pipeline.endpoint\n",
     "# specify batch size when running the pipeline\n",
     "response = requests.post(rest_endpoint, \n",

how-to-use-azureml/machine-learning-pipelines/pipeline-style-transfer/neural_style_mpi.py

@@ -1,207 +0,0 @@
-# Original source: https://github.com/pytorch/examples/blob/master/fast_neural_style/neural_style/neural_style.py
-import argparse
-import os
-import sys
-import re
-
-from PIL import Image
-import torch
-from torchvision import transforms
-
-from mpi4py import MPI
-
-
-def load_image(filename, size=None, scale=None):
-    img = Image.open(filename)
-    if size is not None:
-        img = img.resize((size, size), Image.ANTIALIAS)
-    elif scale is not None:
-        img = img.resize((int(img.size[0] / scale), int(img.size[1] / scale)), Image.ANTIALIAS)
-    return img
-
-
-def save_image(filename, data):
-    img = data.clone().clamp(0, 255).numpy()
-    img = img.transpose(1, 2, 0).astype("uint8")
-    img = Image.fromarray(img)
-    img.save(filename)
-
-
-class TransformerNet(torch.nn.Module):
-    def __init__(self):
-        super(TransformerNet, self).__init__()
-        # Initial convolution layers
-        self.conv1 = ConvLayer(3, 32, kernel_size=9, stride=1)
-        self.in1 = torch.nn.InstanceNorm2d(32, affine=True)
-        self.conv2 = ConvLayer(32, 64, kernel_size=3, stride=2)
-        self.in2 = torch.nn.InstanceNorm2d(64, affine=True)
-        self.conv3 = ConvLayer(64, 128, kernel_size=3, stride=2)
-        self.in3 = torch.nn.InstanceNorm2d(128, affine=True)
-        # Residual layers
-        self.res1 = ResidualBlock(128)
-        self.res2 = ResidualBlock(128)
-        self.res3 = ResidualBlock(128)
-        self.res4 = ResidualBlock(128)
-        self.res5 = ResidualBlock(128)
-        # Upsampling Layers
-        self.deconv1 = UpsampleConvLayer(128, 64, kernel_size=3, stride=1, upsample=2)
-        self.in4 = torch.nn.InstanceNorm2d(64, affine=True)
-        self.deconv2 = UpsampleConvLayer(64, 32, kernel_size=3, stride=1, upsample=2)
-        self.in5 = torch.nn.InstanceNorm2d(32, affine=True)
-        self.deconv3 = ConvLayer(32, 3, kernel_size=9, stride=1)
-        # Non-linearities
-        self.relu = torch.nn.ReLU()
-
-    def forward(self, X):
-        y = self.relu(self.in1(self.conv1(X)))
-        y = self.relu(self.in2(self.conv2(y)))
-        y = self.relu(self.in3(self.conv3(y)))
-        y = self.res1(y)
-        y = self.res2(y)
-        y = self.res3(y)
-        y = self.res4(y)
-        y = self.res5(y)
-        y = self.relu(self.in4(self.deconv1(y)))
-        y = self.relu(self.in5(self.deconv2(y)))
-        y = self.deconv3(y)
-        return y
-
-
-class ConvLayer(torch.nn.Module):
-    def __init__(self, in_channels, out_channels, kernel_size, stride):
-        super(ConvLayer, self).__init__()
-        reflection_padding = kernel_size // 2
-        self.reflection_pad = torch.nn.ReflectionPad2d(reflection_padding)
-        self.conv2d = torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride)
-
-    def forward(self, x):
-        out = self.reflection_pad(x)
-        out = self.conv2d(out)
-        return out
-
-
-class ResidualBlock(torch.nn.Module):
-    """ResidualBlock
-    introduced in: https://arxiv.org/abs/1512.03385
-    recommended architecture: http://torch.ch/blog/2016/02/04/resnets.html
-    """
-
-    def __init__(self, channels):
-        super(ResidualBlock, self).__init__()
-        self.conv1 = ConvLayer(channels, channels, kernel_size=3, stride=1)
-        self.in1 = torch.nn.InstanceNorm2d(channels, affine=True)
-        self.conv2 = ConvLayer(channels, channels, kernel_size=3, stride=1)
-        self.in2 = torch.nn.InstanceNorm2d(channels, affine=True)
-        self.relu = torch.nn.ReLU()
-
-    def forward(self, x):
-        residual = x
-        out = self.relu(self.in1(self.conv1(x)))
-        out = self.in2(self.conv2(out))
-        out = out + residual
-        return out
-
-
-class UpsampleConvLayer(torch.nn.Module):
-    """UpsampleConvLayer
-    Upsamples the input and then does a convolution. This method gives better results
-    compared to ConvTranspose2d.
-    ref: http://distill.pub/2016/deconv-checkerboard/
-    """
-
-    def __init__(self, in_channels, out_channels, kernel_size, stride, upsample=None):
-        super(UpsampleConvLayer, self).__init__()
-        self.upsample = upsample
-        if upsample:
-            self.upsample_layer = torch.nn.Upsample(mode='nearest', scale_factor=upsample)
-        reflection_padding = kernel_size // 2
-        self.reflection_pad = torch.nn.ReflectionPad2d(reflection_padding)
-        self.conv2d = torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride)
-
-    def forward(self, x):
-        x_in = x
-        if self.upsample:
-            x_in = self.upsample_layer(x_in)
-        out = self.reflection_pad(x_in)
-        out = self.conv2d(out)
-        return out
-
-
-def stylize(args, comm):
-
-    rank = comm.Get_rank()
-    size = comm.Get_size()
-
-    device = torch.device("cuda" if args.cuda else "cpu")
-    with torch.no_grad():
-        style_model = TransformerNet()
-        state_dict = torch.load(os.path.join(args.model_dir, args.style + ".pth"))
-        # remove saved deprecated running_* keys in InstanceNorm from the checkpoint
-        for k in list(state_dict.keys()):
-            if re.search(r'in\d+\.running_(mean|var)$', k):
-                del state_dict[k]
-        style_model.load_state_dict(state_dict)
-        style_model.to(device)
-
-        filenames = os.listdir(args.content_dir)
-        filenames = sorted(filenames)
-        partition_size = len(filenames) // size
-        partitioned_filenames = filenames[rank * partition_size: (rank + 1) * partition_size]
-        print("RANK {} - is processing {} images out of the total {}".format(rank, len(partitioned_filenames),
-                                                                             len(filenames)))
-
-        output_paths = []
-        for filename in partitioned_filenames:
-            # print("Processing {}".format(filename))
-            full_path = os.path.join(args.content_dir, filename)
-            content_image = load_image(full_path, scale=args.content_scale)
-            content_transform = transforms.Compose([
-                transforms.ToTensor(),
-                transforms.Lambda(lambda x: x.mul(255))
-            ])
-            content_image = content_transform(content_image)
-            content_image = content_image.unsqueeze(0).to(device)
-
-            output = style_model(content_image).cpu()
-
-            output_path = os.path.join(args.output_dir, filename)
-            save_image(output_path, output[0])
-
-            output_paths.append(output_path)
-
-        print("RANK {} - number of pre-aggregated output files {}".format(rank, len(output_paths)))
-
-        output_paths_list = comm.gather(output_paths, root=0)
-
-        if rank == 0:
-            print("RANK {} - number of aggregated output files {}".format(rank, len(output_paths_list)))
-            print("RANK {} - end".format(rank))
-
-
-def main():
-    arg_parser = argparse.ArgumentParser(description="parser for fast-neural-style")
-
-    arg_parser.add_argument("--content-scale", type=float, default=None,
-                            help="factor for scaling down the content image")
-    arg_parser.add_argument("--model-dir", type=str, required=True,
-                            help="saved model to be used for stylizing the image.")
-    arg_parser.add_argument("--cuda", type=int, required=True,
-                            help="set it to 1 for running on GPU, 0 for CPU")
-    arg_parser.add_argument("--style", type=str, help="style name")
-    arg_parser.add_argument("--content-dir", type=str, required=True,
-                            help="directory holding the images")
-    arg_parser.add_argument("--output-dir", type=str, required=True,
-                            help="directory holding the output images")
-    args = arg_parser.parse_args()
-
-    comm = MPI.COMM_WORLD
-
-    if args.cuda and not torch.cuda.is_available():
-        print("ERROR: cuda is not available, try running on CPU")
-        sys.exit(1)
-    os.makedirs(args.output_dir, exist_ok=True)
-    stylize(args, comm)
-
-
-if __name__ == "__main__":
-    main()

how-to-use-azureml/machine-learning-pipelines/pipeline-style-transfer/pipeline-style-transfer.ipynb

@@ -44,7 +44,7 @@
    "outputs": [],
    "source": [
     "import os\n",
-        "from azureml.core import Workspace, Experiment\n",
+    "from azureml.core import Workspace, Run, Experiment\n",
     "\n",
     "ws = Workspace.from_config()\n",
     "print('Workspace name: ' + ws.name, \n",
@@ -69,8 +69,7 @@
     "from azureml.data.data_reference import DataReference\n",
     "from azureml.pipeline.core import Pipeline, PipelineData\n",
     "from azureml.pipeline.steps import PythonScriptStep, MpiStep\n",
-        "from azureml.core.runconfig import CondaDependencies, RunConfiguration\n",
-        "from azureml.core.compute_target import ComputeTargetException"
+    "from azureml.core.runconfig import CondaDependencies, RunConfiguration"
    ]
   },
   {
@@ -91,7 +90,7 @@
     "try:\n",
     "    cpu_cluster = AmlCompute(ws, cpu_cluster_name)\n",
     "    print(\"found existing cluster.\")\n",
-        "except ComputeTargetException:\n",
+    "except:\n",
     "    print(\"creating new cluster\")\n",
     "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_v2\",\n",
     "                                                                    max_nodes = 1)\n",
@@ -105,7 +104,7 @@
     "try:\n",
     "    gpu_cluster = AmlCompute(ws, gpu_cluster_name)\n",
     "    print(\"found existing cluster.\")\n",
-        "except ComputeTargetException:\n",
+    "except:\n",
     "    print(\"creating new cluster\")\n",
     "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_NC6\",\n",
     "                                                                    max_nodes = 3)\n",
@@ -527,6 +526,7 @@
     "                               \"ParameterAssignments\": {\"style\": \"rain_princess\", \"nodecount\": 3}})    \n",
     "run_id = response.json()[\"Id\"]\n",
     "\n",
+    "from azureml.pipeline.core.run import PipelineRun\n",
     "published_pipeline_run_rain = PipelineRun(ws.experiments[\"style_transfer\"], run_id)\n",
     "\n",
     "RunDetails(published_pipeline_run_rain).show()"
@@ -545,6 +545,7 @@
     "                               \"ParameterAssignments\": {\"style\": \"udnie\", \"nodecount\": 4}})   \n",
     "run_id = response.json()[\"Id\"]\n",
     "\n",
+    "from azureml.pipeline.core.run import PipelineRun\n",
     "published_pipeline_run_udnie = PipelineRun(ws.experiments[\"style_transfer\"], run_id)\n",
     "\n",
     "RunDetails(published_pipeline_run_udnie).show()"

how-to-use-azureml/training-with-deep-learning/README.md

@@ -1,16 +1,6 @@
 ## Azure Machine Learning service training examples
 
 These examples show you:
-
-1. [How to use the Estimator pattern in Azure ML](how-to-use-estimator)
-2. [Train using TensorFlow Estimator and tune hyperparameters using Hyperdrive](train-hyperparameter-tune-deploy-with-tensorflow)
-3. [Train using Keras and tune hyperparameters using Hyperdrive](train-hyperparameter-tune-deploy-with-keras)
-4. [Train using Pytorch Estimator and tune hyperparameters using Hyperdrive](train-hyperparameter-tune-deploy-with-pytorch)
-5. [Distributed training using TensorFlow and Parameter Server](distributed-tensorflow-with-parameter-server)
-6. [Distributed training using TensorFlow and Horovod](distributed-tensorflow-with-horovod)
-7. [Distributed training using Pytorch and Horovod](distributed-pytorch-with-horovod)
-8. [Distributed training using CNTK and custom Docker image](distributed-cntk-with-custom-docker)
-9. [Export run history records to Tensorboard](export-run-history-to-tensorboard)
-10. [Use TensorBoard to monitor training execution](tensorboard)
-
-Learn more about how to use `Estimator` class to  [train deep neural networks with Azure Machine Learning](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-ml-models).
+ * Distributed training of models on Machine Learning Compute cluster
+ * Hyperparameter tuning at scale
+ * Using Tensorboard with Azure ML Python SDK.

how-to-use-azureml/training-with-deep-learning/distributed-cntk-with-custom-docker/cntk_distr_mnist.py

@@ -1,117 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-# Licensed under the MIT license.
-# Adapted from:
-# https://github.com/Microsoft/CNTK/blob/master/Examples/Image/Classification/ConvNet/Python/ConvNet_MNIST.py
-# ====================================================================
-"""Train a CNN model on the MNIST dataset via distributed training."""
-
-from __future__ import print_function
-import numpy as np
-import os
-import cntk as C
-import argparse
-from cntk.train.training_session import CheckpointConfig, TestConfig
-
-
-def create_reader(path, is_training, input_dim, label_dim, total_number_of_samples):
-    """Define the reader for both training and evaluation action."""
-    return C.io.MinibatchSource(C.io.CTFDeserializer(path, C.io.StreamDefs(
-        features=C.io.StreamDef(field='features', shape=input_dim),
-        labels=C.io.StreamDef(field='labels', shape=label_dim)
-    )), randomize=is_training, max_samples=total_number_of_samples)
-
-
-def convnet_mnist(max_epochs, output_dir, data_dir, debug_output=False, epoch_size=60000, minibatch_size=64):
-    """Creates and trains a feedforward classification model for MNIST images."""
-    image_height = 28
-    image_width = 28
-    num_channels = 1
-    input_dim = image_height * image_width * num_channels
-    num_output_classes = 10
-
-    # Input variables denoting the features and label data
-    input_var = C.ops.input_variable((num_channels, image_height, image_width), np.float32)
-    label_var = C.ops.input_variable(num_output_classes, np.float32)
-
-    # Instantiate the feedforward classification model
-    scaled_input = C.ops.element_times(C.ops.constant(0.00390625), input_var)
-
-    with C.layers.default_options(activation=C.ops.relu, pad=False):
-        conv1 = C.layers.Convolution2D((5, 5), 32, pad=True)(scaled_input)
-        pool1 = C.layers.MaxPooling((3, 3), (2, 2))(conv1)
-        conv2 = C.layers.Convolution2D((3, 3), 48)(pool1)
-        pool2 = C.layers.MaxPooling((3, 3), (2, 2))(conv2)
-        conv3 = C.layers.Convolution2D((3, 3), 64)(pool2)
-        f4 = C.layers.Dense(96)(conv3)
-        drop4 = C.layers.Dropout(0.5)(f4)
-        z = C.layers.Dense(num_output_classes, activation=None)(drop4)
-
-    ce = C.losses.cross_entropy_with_softmax(z, label_var)
-    pe = C.metrics.classification_error(z, label_var)
-
-    # Load train data
-    reader_train = create_reader(os.path.join(data_dir, 'Train-28x28_cntk_text.txt'), True,
-                                 input_dim, num_output_classes, max_epochs * epoch_size)
-    # Load test data
-    reader_test = create_reader(os.path.join(data_dir, 'Test-28x28_cntk_text.txt'), False,
-                                input_dim, num_output_classes, C.io.FULL_DATA_SWEEP)
-
-    # Set learning parameters
-    lr_per_sample = [0.001] * 10 + [0.0005] * 10 + [0.0001]
-    lr_schedule = C.learning_parameter_schedule_per_sample(lr_per_sample, epoch_size=epoch_size)
-    mms = [0] * 5 + [0.9990239141819757]
-    mm_schedule = C.learners.momentum_schedule_per_sample(mms, epoch_size=epoch_size)
-
-    # Instantiate the trainer object to drive the model training
-    local_learner = C.learners.momentum_sgd(z.parameters, lr_schedule, mm_schedule)
-    progress_printer = C.logging.ProgressPrinter(
-        tag='Training',
-        rank=C.train.distributed.Communicator.rank(),
-        num_epochs=max_epochs,
-    )
-
-    learner = C.train.distributed.data_parallel_distributed_learner(local_learner)
-    trainer = C.Trainer(z, (ce, pe), learner, progress_printer)
-
-    # define mapping from reader streams to network inputs
-    input_map_train = {
-        input_var: reader_train.streams.features,
-        label_var: reader_train.streams.labels
-    }
-
-    input_map_test = {
-        input_var: reader_test.streams.features,
-        label_var: reader_test.streams.labels
-    }
-
-    C.logging.log_number_of_parameters(z)
-    print()
-
-    C.train.training_session(
-        trainer=trainer,
-        mb_source=reader_train,
-        model_inputs_to_streams=input_map_train,
-        mb_size=minibatch_size,
-        progress_frequency=epoch_size,
-        checkpoint_config=CheckpointConfig(frequency=epoch_size,
-                                           filename=os.path.join(output_dir, "ConvNet_MNIST")),
-        test_config=TestConfig(reader_test, minibatch_size=minibatch_size,
-                               model_inputs_to_streams=input_map_test)
-    ).train()
-
-    return
-
-
-if __name__ == '__main__':
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--num_epochs', help='Total number of epochs to train', type=int, default='40')
-    parser.add_argument('--output_dir', help='Output directory', required=False, default='outputs')
-    parser.add_argument('--data_dir', help='Directory with training data')
-    args = parser.parse_args()
-
-    os.makedirs(args.output_dir, exist_ok=True)
-
-    convnet_mnist(args.num_epochs, args.output_dir, args.data_dir)
-
-    # Must call MPI finalize when process exit without exceptions
-    C.train.distributed.Communicator.finalize()

how-to-use-azureml/training-with-deep-learning/distributed-cntk-with-custom-docker/distributed-cntk-with-custom-docker.ipynb

@@ -1,394 +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": [
-        "# Distributed CNTK using custom docker images\n",
-        "In this tutorial, you will train a CNTK model on the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset using a custom docker image and distributed training."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Prerequisites\n",
-        "* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning\n",
-        "* Go through the [configuration notebook](../../../configuration.ipynb) to:\n",
-        "    * install the AML SDK\n",
-        "    * create a workspace and its configuration file (`config.json`)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Check core SDK version number\n",
-        "import azureml.core\n",
-        "\n",
-        "print(\"SDK version:\", azureml.core.VERSION)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Diagnostics\n",
-        "Opt-in diagnostics for better experience, quality, and security of future releases."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "tags": [
-          "Diagnostics"
-        ]
-      },
-      "outputs": [],
-      "source": [
-        "from azureml.telemetry import set_diagnostics_collection\n",
-        "\n",
-        "set_diagnostics_collection(send_diagnostics=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Initialize workspace\n",
-        "\n",
-        "Initialize a [Workspace](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#workspace) object from the existing workspace you created in the Prerequisites step. `Workspace.from_config()` creates a workspace object from the details stored in `config.json`."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.workspace import Workspace\n",
-        "\n",
-        "ws = Workspace.from_config()\n",
-        "print('Workspace name: ' + ws.name,\n",
-        "      'Azure region: ' + ws.location, \n",
-        "      'Subscription id: ' + ws.subscription_id, \n",
-        "      'Resource group: ' + ws.resource_group, sep='\\n')"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Create or Attach existing AmlCompute\n",
-        "You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) for training your model. In this tutorial, you create `AmlCompute` as your training compute resource.\n",
-        "\n",
-        "**Creation of AmlCompute takes approximately 5 minutes.** If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
-        "\n",
-        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
-        "from azureml.core.compute_target import ComputeTargetException\n",
-        "\n",
-        "# choose a name for your cluster\n",
-        "cluster_name = \"gpucluster\"\n",
-        "\n",
-        "try:\n",
-        "    compute_target = ComputeTarget(workspace=ws, name=cluster_name)\n",
-        "    print('Found existing compute target.')\n",
-        "except ComputeTargetException:\n",
-        "    print('Creating a new compute target...')\n",
-        "    compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_NC6',\n",
-        "                                                           max_nodes=4)\n",
-        "\n",
-        "    # create the cluster\n",
-        "    compute_target = ComputeTarget.create(ws, cluster_name, compute_config)\n",
-        "\n",
-        "    compute_target.wait_for_completion(show_output=True)\n",
-        "\n",
-        "# use get_status() to get a detailed status for the current AmlCompute\n",
-        "print(compute_target.get_status().serialize())"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Upload training data\n",
-        "For this tutorial, we will be using the MNIST dataset.\n",
-        "\n",
-        "First, let's download the dataset. We've included the `install_mnist.py` script to download the data and convert it to a CNTK-supported format. Our data files will get written to a directory named `'mnist'`."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import install_mnist\n",
-        "\n",
-        "install_mnist.main('mnist')"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "To make the data accessible for remote training, you will need to upload the data from your local machine to the cloud. AML provides a convenient way to do so via a [Datastore](https://docs.microsoft.com/azure/machine-learning/service/how-to-access-data). The datastore provides a mechanism for you to upload/download data, and interact with it from your remote compute targets. \n",
-        "\n",
-        "Each workspace is associated with a default datastore. In this tutorial, we will upload the training data to this default datastore, which we will then mount on the remote compute for training in the next section."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ds = ws.get_default_datastore()\n",
-        "print(ds.datastore_type, ds.account_name, ds.container_name)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "The following code will upload the training data to the path `./mnist` on the default datastore."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ds.upload(src_dir='./mnist', target_path='./mnist')"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Now let's get a reference to the path on the datastore with the training data. We can do so using the `path` method. In the next section, we can then pass this reference to our training script's `--data_dir` argument. "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "path_on_datastore = 'mnist'\n",
-        "ds_data = ds.path(path_on_datastore)\n",
-        "print(ds_data)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Train model on the remote compute\n",
-        "Now that we have the cluster ready to go, let's run our distributed training job."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Create a project directory\n",
-        "Create a directory that will contain all the necessary code from your local machine that you will need access to on the remote resource. This includes the training script, and any additional files your training script depends on."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "\n",
-        "project_folder = './cntk-distr'\n",
-        "os.makedirs(project_folder, exist_ok=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copy the training script `cntk_distr_mnist.py` into this project directory."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import shutil\n",
-        "\n",
-        "shutil.copy('cntk_distr_mnist.py', project_folder)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Create an experiment\n",
-        "Create an [experiment](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#experiment) to track all the runs in your workspace for this distributed CNTK tutorial. "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core import Experiment\n",
-        "\n",
-        "experiment_name = 'cntk-distr'\n",
-        "experiment = Experiment(ws, name=experiment_name)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Create an Estimator\n",
-        "The AML SDK's base Estimator enables you to easily submit custom scripts for both single-node and distributed runs. You should this generic estimator for training code using frameworks such as sklearn or CNTK that don't have corresponding custom estimators. For more information on using the generic estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-ml-models)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.train.estimator import Estimator\n",
-        "\n",
-        "script_params = {\n",
-        "    '--num_epochs': 20,\n",
-        "    '--data_dir': ds_data.as_mount(),\n",
-        "    '--output_dir': './outputs'\n",
-        "}\n",
-        "\n",
-        "estimator = Estimator(source_directory=project_folder,\n",
-        "                      compute_target=compute_target,\n",
-        "                      entry_script='cntk_distr_mnist.py',\n",
-        "                      script_params=script_params,\n",
-        "                      node_count=2,\n",
-        "                      process_count_per_node=1,\n",
-        "                      distributed_backend='mpi',\n",
-        "                      pip_packages=['cntk-gpu==2.6'],\n",
-        "                      custom_docker_base_image='microsoft/mmlspark:gpu-0.12',\n",
-        "                      use_gpu=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "We would like to train our model using a [pre-built Docker container](https://hub.docker.com/r/microsoft/mmlspark/). To do so, specify the name of the docker image to the argument `custom_docker_base_image`. You can only provide images available in public docker repositories such as Docker Hub using this argument. To use an image from a private docker repository, use the constructor's `environment_definition` parameter instead. Finally, we provide the `cntk` package to `pip_packages` to install CNTK 2.6 on our custom image.\n",
-        "\n",
-        "The above code specifies that we will run our training script on `2` nodes, with one worker per node. In order to run distributed CNTK, which uses MPI, you must provide the argument `distributed_backend='mpi'`."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Submit job\n",
-        "Run your experiment by submitting your estimator object. Note that this call is asynchronous."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "run = experiment.submit(estimator)\n",
-        "print(run)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Monitor your run\n",
-        "You can monitor the progress of the run with a Jupyter widget. Like the run submission, the widget is asynchronous and provides live updates every 10-15 seconds until the job completes."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.widgets import RunDetails\n",
-        "\n",
-        "RunDetails(run).show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Alternatively, you can block until the script has completed training before running more code."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "run.wait_for_completion(show_output=True)"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "minxia"
-      }
-    ],
-    "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/training-with-deep-learning/distributed-cntk-with-custom-docker/install_mnist.py

@@ -1,96 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-# Licensed under the MIT license.
-# Script from:
-# https://github.com/Microsoft/CNTK/blob/master/Examples/Image/DataSets/MNIST/install_mnist.py
-
-from __future__ import print_function
-try:
-    from urllib.request import urlretrieve
-except ImportError:
-    from urllib import urlretrieve
-import gzip
-import os
-import struct
-import numpy as np
-
-
-def loadData(src, cimg):
-    print('Downloading ' + src)
-    gzfname, h = urlretrieve(src, './delete.me')
-    print('Done.')
-    try:
-        with gzip.open(gzfname) as gz:
-            n = struct.unpack('I', gz.read(4))
-            # Read magic number.
-            if n[0] != 0x3080000:
-                raise Exception('Invalid file: unexpected magic number.')
-            # Read number of entries.
-            n = struct.unpack('>I', gz.read(4))[0]
-            if n != cimg:
-                raise Exception('Invalid file: expected {0} entries.'.format(cimg))
-            crow = struct.unpack('>I', gz.read(4))[0]
-            ccol = struct.unpack('>I', gz.read(4))[0]
-            if crow != 28 or ccol != 28:
-                raise Exception('Invalid file: expected 28 rows/cols per image.')
-            # Read data.
-            res = np.fromstring(gz.read(cimg * crow * ccol), dtype=np.uint8)
-    finally:
-        os.remove(gzfname)
-    return res.reshape((cimg, crow * ccol))
-
-
-def loadLabels(src, cimg):
-    print('Downloading ' + src)
-    gzfname, h = urlretrieve(src, './delete.me')
-    print('Done.')
-    try:
-        with gzip.open(gzfname) as gz:
-            n = struct.unpack('I', gz.read(4))
-            # Read magic number.
-            if n[0] != 0x1080000:
-                raise Exception('Invalid file: unexpected magic number.')
-            # Read number of entries.
-            n = struct.unpack('>I', gz.read(4))
-            if n[0] != cimg:
-                raise Exception('Invalid file: expected {0} rows.'.format(cimg))
-            # Read labels.
-            res = np.fromstring(gz.read(cimg), dtype=np.uint8)
-    finally:
-        os.remove(gzfname)
-    return res.reshape((cimg, 1))
-
-
-def load(dataSrc, labelsSrc, cimg):
-    data = loadData(dataSrc, cimg)
-    labels = loadLabels(labelsSrc, cimg)
-    return np.hstack((data, labels))
-
-
-def savetxt(filename, ndarray):
-    with open(filename, 'w') as f:
-        labels = list(map(' '.join, np.eye(10, dtype=np.uint).astype(str)))
-        for row in ndarray:
-            row_str = row.astype(str)
-            label_str = labels[row[-1]]
-            feature_str = ' '.join(row_str[:-1])
-            f.write('|labels {} |features {}\n'.format(label_str, feature_str))
-
-
-def main(data_dir):
-    os.makedirs(data_dir, exist_ok=True)
-    train = load('http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz',
-                 'http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz', 60000)
-    print('Writing train text file...')
-    train_txt = os.path.join(data_dir, 'Train-28x28_cntk_text.txt')
-    savetxt(train_txt, train)
-    print('Done.')
-    test = load('http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz',
-                'http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz', 10000)
-    print('Writing test text file...')
-    test_txt = os.path.join(data_dir, 'Test-28x28_cntk_text.txt')
-    savetxt(test_txt, test)
-    print('Done.')
-
-
-if __name__ == "__main__":
-    main('mnist')

how-to-use-azureml/training-with-deep-learning/distributed-pytorch-with-horovod/distributed-pytorch-with-horovod.ipynb

@@ -14,7 +14,7 @@
    "metadata": {},
    "source": [
     "# Distributed PyTorch with Horovod\n",
-        "In this tutorial, you will train a PyTorch model on the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset using distributed training via [Horovod](https://github.com/uber/horovod) across a GPU cluster."
+    "In this tutorial, you will train a PyTorch model on the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset using distributed training via [Horovod](https://github.com/uber/horovod)."
    ]
   },
   {
@@ -22,8 +22,11 @@
    "metadata": {},
    "source": [
     "## Prerequisites\n",
-        "* Go through the [Configuration](../../../configuration.ipynb) notebook to install the Azure Machine Learning Python SDK and create an Azure ML `Workspace`\n",
-        "* Review the [tutorial](../train-hyperparameter-tune-deploy-with-pytorch/train-hyperparameter-tune-deploy-with-pytorch.ipynb) on single-node PyTorch training using Azure Machine Learning"
+    "* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning (AML)\n",
+    "* Go through the [00.configuration.ipynb](https://github.com/Azure/MachineLearningNotebooks/blob/master/00.configuration.ipynb) notebook to:\n",
+    "    * install the AML SDK\n",
+    "    * create a workspace and its configuration file (`config.json`)\n",
+    "* Review the [tutorial](https://aka.ms/aml-notebook-pytorch) on single-node PyTorch training using the SDK"
    ]
   },
   {
@@ -82,19 +85,17 @@
     "print('Workspace name: ' + ws.name, \n",
     "      'Azure region: ' + ws.location, \n",
     "      'Subscription id: ' + ws.subscription_id, \n",
-        "      'Resource group: ' + ws.resource_group, sep='\\n')"
+    "      'Resource group: ' + ws.resource_group, sep = '\\n')"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Create or attach existing AmlCompute\n",
-        "You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) for training your model. In this tutorial, we use Azure ML managed compute ([AmlCompute](https://docs.microsoft.com/azure/machine-learning/service/how-to-set-up-training-targets#amlcompute)) for our remote training compute resource. Specifically, the below code creates an `STANDARD_NC6` GPU cluster that autoscales from `0` to `4` nodes.\n",
+    "## Create a remote compute target\n",
+    "You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) to execute your training script on. In this tutorial, you create an `AmlCompute` cluster as your training compute resource. This code creates a cluster for you if it does not already exist in your workspace.\n",
     "\n",
-        "**Creation of AmlCompute takes approximately 5 minutes.** If the AmlCompute with that name is already in your workspace, this code will skip the creation process.\n",
-        "\n",
-        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
+    "**Creation of the cluster takes approximately 5 minutes.** If the cluster is already in your workspace this code will skip the cluster creation process."
    ]
   },
   {
@@ -114,7 +115,7 @@
     "    print('Found existing compute target.')\n",
     "except ComputeTargetException:\n",
     "    print('Creating a new compute target...')\n",
-        "    compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_NC6',\n",
+    "    compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_NC6', \n",
     "                                                           max_nodes=4)\n",
     "\n",
     "    # create the cluster\n",
@@ -122,15 +123,15 @@
     "\n",
     "    compute_target.wait_for_completion(show_output=True)\n",
     "\n",
-        "# use get_status() to get a detailed status for the current AmlCompute. \n",
-        "print(compute_target.get_status().serialize())"
+    "# Use the 'status' property to get a detailed status for the current cluster. \n",
+    "print(compute_target.status.serialize())"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "The above code creates GPU compute. If you instead want to create CPU compute, provide a different VM size to the `vm_size` parameter, such as `STANDARD_D2_V2`."
+    "The above code creates a GPU cluster. If you instead want to create a CPU cluster, provide a different VM size to the `vm_size` parameter, such as `STANDARD_D2_V2`."
    ]
   },
   {
@@ -138,7 +139,7 @@
    "metadata": {},
    "source": [
     "## Train model on the remote compute\n",
-        "Now that we have the AmlCompute ready to go, let's run our distributed training job."
+    "Now that we have the cluster ready to go, let's run our distributed training job."
    ]
   },
   {
@@ -165,27 +166,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "### Prepare training script\n",
-        "Now you will need to create your training script. In this tutorial, the script for distributed training of MNIST is already provided for you at `pytorch_horovod_mnist.py`. In practice, you should be able to take any custom PyTorch training script as is and run it with Azure ML without having to modify your code.\n",
-        "\n",
-        "However, if you would like to use Azure ML's [metric logging](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#logging) capabilities, you will have to add a small amount of Azure ML logic inside your training script. In this example, at each logging interval, we will log the loss for that minibatch to our Azure ML run.\n",
-        "\n",
-        "To do so, in `pytorch_horovod_mnist.py`, we will first access the Azure ML `Run` object within the script:\n",
-        "```Python\n",
-        "from azureml.core.run import Run\n",
-        "run = Run.get_context()\n",
-        "```\n",
-        "Later within the script, we log the loss metric to our run:\n",
-        "```Python\n",
-        "run.log('loss', loss.item())\n",
-        "```"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Once your script is ready, copy the training script `pytorch_horovod_mnist.py` into the project directory."
+    "Copy the training script `pytorch_horovod_mnist.py` into this project directory."
    ]
   },
   {
@@ -224,7 +205,7 @@
    "metadata": {},
    "source": [
     "### Create a PyTorch estimator\n",
-        "The Azure ML SDK's PyTorch estimator enables you to easily submit PyTorch training jobs for both single-node and distributed runs. For more information on the PyTorch estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-pytorch)."
+    "The AML SDK's PyTorch estimator enables you to easily submit PyTorch training jobs for both single-node and distributed runs. For more information on the PyTorch estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-pytorch)."
    ]
   },
   {
@@ -274,7 +255,7 @@
    "metadata": {},
    "source": [
     "### Monitor your run\n",
-        "You can monitor the progress of the run with a Jupyter widget. Like the run submission, the widget is asynchronous and provides live updates every 10-15 seconds until the job completes. You can see that the widget automatically plots and visualizes the loss metric that we logged to the Azure ML run."
+    "You can monitor the progress of the run with a Jupyter widget. Like the run submission, the widget is asynchronous and provides live updates every 10-15 seconds until the job completes."
    ]
   },
   {

how-to-use-azureml/training-with-deep-learning/distributed-pytorch-with-horovod/pytorch_horovod_mnist.py

@@ -1,7 +1,6 @@
-# Copyright (c) 2017, PyTorch contributors
-# Modifications copyright (C) Microsoft Corporation
-# Licensed under the BSD license
-# Adapted from https://github.com/uber/horovod/blob/master/examples/pytorch_mnist.py
+# Copyright 2017 Uber Technologies, Inc.
+# Licensed under the Apache License, Version 2.0
+# Script from horovod/examples: https://github.com/uber/horovod/blob/master/examples/pytorch_mnist.py
 
 from __future__ import print_function
 import argparse
@@ -9,15 +8,10 @@ import torch.nn as nn
 import torch.nn.functional as F
 import torch.optim as optim
 from torchvision import datasets, transforms
+from torch.autograd import Variable
 import torch.utils.data.distributed
 import horovod.torch as hvd
 
-from azureml.core.run import Run
-# get the Azure ML run object
-run = Run.get_context()
-
-print("Torch version:", torch.__version__)
-
 # Training settings
 parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
 parser.add_argument('--batch-size', type=int, default=64, metavar='N',
@@ -36,8 +30,6 @@ parser.add_argument('--seed', type=int, default=42, metavar='S',
                     help='random seed (default: 42)')
 parser.add_argument('--log-interval', type=int, default=10, metavar='N',
                     help='how many batches to wait before logging training status')
-parser.add_argument('--fp16-allreduce', action='store_true', default=False,
-                    help='use fp16 compression during allreduce')
 args = parser.parse_args()
 args.cuda = not args.no_cuda and torch.cuda.is_available()
 
@@ -50,7 +42,7 @@ if args.cuda:
     torch.cuda.manual_seed(args.seed)
 
 
-kwargs = {}
+kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
 train_dataset = \
     datasets.MNIST('data-%d' % hvd.rank(), train=True, download=True,
                    transform=transforms.Compose([
@@ -105,13 +97,9 @@ hvd.broadcast_parameters(model.state_dict(), root_rank=0)
 optimizer = optim.SGD(model.parameters(), lr=args.lr * hvd.size(),
                       momentum=args.momentum)
 
-# Horovod: (optional) compression algorithm.
-compression = hvd.Compression.fp16 if args.fp16_allreduce else hvd.Compression.none
-
 # Horovod: wrap optimizer with DistributedOptimizer.
-optimizer = hvd.DistributedOptimizer(optimizer,
-                                     named_parameters=model.named_parameters(),
-                                     compression=compression)
+optimizer = hvd.DistributedOptimizer(
+    optimizer, named_parameters=model.named_parameters())
 
 
 def train(epoch):
@@ -120,6 +108,7 @@ def train(epoch):
     for batch_idx, (data, target) in enumerate(train_loader):
         if args.cuda:
             data, target = data.cuda(), target.cuda()
+        data, target = Variable(data), Variable(target)
         optimizer.zero_grad()
         output = model(data)
         loss = F.nll_loss(output, target)
@@ -128,16 +117,13 @@ def train(epoch):
         if batch_idx % args.log_interval == 0:
             print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                 epoch, batch_idx * len(data), len(train_sampler),
-                100. * batch_idx / len(train_loader), loss.item()))
-
-            # log the loss to the Azure ML run
-            run.log('loss', loss.item())
+                100. * batch_idx / len(train_loader), loss.data[0]))
 
 
 def metric_average(val, name):
-    tensor = torch.tensor(val)
+    tensor = torch.FloatTensor([val])
     avg_tensor = hvd.allreduce(tensor, name=name)
-    return avg_tensor.item()
+    return avg_tensor[0]
 
 
 def test():
@@ -147,9 +133,10 @@ def test():
     for data, target in test_loader:
         if args.cuda:
             data, target = data.cuda(), target.cuda()
+        data, target = Variable(data, volatile=True), Variable(target)
         output = model(data)
         # sum up batch loss
-        test_loss += F.nll_loss(output, target, size_average=False).item()
+        test_loss += F.nll_loss(output, target, size_average=False).data[0]
         # get the index of the max log-probability
         pred = output.data.max(1, keepdim=True)[1]
         test_accuracy += pred.eq(target.data.view_as(pred)).cpu().float().sum()

how-to-use-azureml/training-with-deep-learning/distributed-tensorflow-with-horovod/distributed-tensorflow-with-horovod.ipynb

@@ -23,10 +23,10 @@
    "source": [
     "## Prerequisites\n",
     "* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning (AML)\n",
-        "* Go through the [configuration notebook](../../../configuration.ipynb) to:\n",
+    "* Go through the [00.configuration.ipynb](https://github.com/Azure/MachineLearningNotebooks/blob/master/00.configuration.ipynb) notebook to:\n",
     "    * install the AML SDK\n",
     "    * create a workspace and its configuration file (`config.json`)\n",
-        "* Review the [tutorial](../train-hyperparameter-tune-deploy-with-tensorflow/train-hyperparameter-tune-deploy-with-tensorflow.ipynb) on single-node TensorFlow training using the SDK"
+    "* Review the [tutorial](https://aka.ms/aml-notebook-hyperdrive) on single-node TensorFlow training using the SDK"
    ]
   },
   {
@@ -84,19 +84,17 @@
     "print('Workspace name: ' + ws.name, \n",
     "      'Azure region: ' + ws.location, \n",
     "      'Subscription id: ' + ws.subscription_id, \n",
-        "      'Resource group: ' + ws.resource_group, sep='\\n')"
+    "      'Resource group: ' + ws.resource_group, sep = '\\n')"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Create or Attach existing AmlCompute\n",
-        "You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) for training your model. In this tutorial, you create `AmlCompute` as your training compute resource.\n",
+    "## Create a remote compute target\n",
+    "You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) to execute your training script on. In this tutorial, you create an `AmlCompute` cluster as your training compute resource. This code creates a cluster for you if it does not already exist in your workspace.\n",
     "\n",
-        "**Creation of AmlCompute takes approximately 5 minutes.** If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
-        "\n",
-        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
+    "**Creation of the cluster takes approximately 5 minutes.** If the cluster is already in your workspace this code will skip the cluster creation process."
    ]
   },
   {
@@ -124,8 +122,8 @@
     "\n",
     "    compute_target.wait_for_completion(show_output=True)\n",
     "\n",
-        "# use get_status() to get a detailed status for the current cluster. \n",
-        "print(compute_target.get_status().serialize())"
+    "# Use the 'status' property to get a detailed status for the current cluster. \n",
+    "print(compute_target.status.serialize())"
    ]
   },
   {
@@ -238,6 +236,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "import os\n",
+    "\n",
     "project_folder = './tf-distr-hvd'\n",
     "os.makedirs(project_folder, exist_ok=True)"
    ]

how-to-use-azureml/training-with-deep-learning/distributed-tensorflow-with-parameter-server/distributed-tensorflow-with-parameter-server.ipynb

@@ -23,7 +23,7 @@
    "source": [
     "## Prerequisites\n",
     "* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning (AML)\n",
-        "* Go through the [configuration notebook](../../../configuration.ipynb) to:\n",
+    "* Go through the [00.configuration.ipynb](https://github.com/Azure/MachineLearningNotebooks/blob/master/00.configuration.ipynb) notebook to:\n",
     "    * install the AML SDK\n",
     "    * create a workspace and its configuration file (`config.json`)\n",
     "* Review the [tutorial](https://aka.ms/aml-notebook-hyperdrive) on single-node TensorFlow training using the SDK"
@@ -91,12 +91,10 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-        "## Create or Attach existing AmlCompute\n",
-        "You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) for training your model. In this tutorial, you create `AmlCompute` as your training compute resource.\n",
+    "## Create a remote compute target\n",
+    "You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) to execute your training script on. In this tutorial, you create an `AmlCompute` cluster as your training compute resource. This code creates a cluster for you if it does not already exist in your workspace.\n",
     "\n",
-        "**Creation of AmlCompute takes approximately 5 minutes.** If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
-        "\n",
-        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
+    "**Creation of the cluster takes approximately 5 minutes.** If the cluster is already in your workspace this code will skip the cluster creation process."
    ]
   },
   {
@@ -124,8 +122,8 @@
     "\n",
     "    compute_target.wait_for_completion(show_output=True)\n",
     "\n",
-        "# use get_status() to get a detailed status for the current cluster. \n",
-        "print(compute_target.get_status().serialize())"
+    "# Use the 'status' property to get a detailed status for the current cluster. \n",
+    "print(compute_target.status.serialize())"
    ]
   },
   {

how-to-use-azureml/training-with-deep-learning/export-run-history-to-tensorboard/export-run-history-to-tensorboard.ipynb

@@ -26,7 +26,7 @@
    "source": [
     "## Prerequisites\n",
     "* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning\n",
-        "* Go through the [configuration notebook](../../../configuration.ipynb) notebook to:\n",
+    "* Go through the [00.configuration.ipynb](https://github.com/Azure/MachineLearningNotebooks/blob/master/00.configuration.ipynb) notebook to:\n",
     "    * install the AML SDK\n",
     "    * create a workspace and its configuration file (`config.json`)"
    ]
@@ -74,13 +74,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-        "from azureml.core import Workspace, Experiment\n",
+    "from azureml.core import Workspace, Run, Experiment\n",
+    "\n",
     "\n",
     "ws = Workspace.from_config()\n",
     "print('Workspace name: ' + ws.name, \n",
     "      'Azure region: ' + ws.location, \n",
     "      'Subscription id: ' + ws.subscription_id, \n",
-        "      'Resource group: ' + ws.resource_group, sep='\\n')"
+    "      'Resource group: ' + ws.resource_group, sep = '\\n')"
    ]
   },
   {
@@ -142,7 +143,7 @@
     "        # More data science stuff\n",
     "        reg = Ridge(alpha=alpha)\n",
     "        reg.fit(data[\"train\"][\"x\"], data[\"train\"][\"y\"])\n",
-        "        \n",
+    "        # TODO save model\n",
     "        preds = reg.predict(data[\"test\"][\"x\"])\n",
     "        mse = mean_squared_error(preds, data[\"test\"][\"y\"])\n",
     "        # End train and eval\n",
@@ -168,6 +169,7 @@
     "# Export Run History to Tensorboard logs\n",
     "from azureml.contrib.tensorboard.export import export_to_tensorboard\n",
     "import os\n",
+    "import tensorflow as tf\n",
     "\n",
     "logdir = 'exportedTBlogs'\n",
     "log_path = os.path.join(os.getcwd(), logdir)\n",