Keras Sample

version 1.0.10

Dockerfiles/1.0.10/Dockerfile

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

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

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

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

README.md

@@ -1,36 +1,37 @@
-# Azure Machine Learning service sample notebooks
-
----
+# Azure Machine Learning service example notebooks
 
 This repository contains example notebooks demonstrating the [Azure Machine Learning](https://azure.microsoft.com/en-us/services/machine-learning-service/) Python SDK
 which allows you to build, train, deploy and manage machine learning solutions using Azure.  The AML SDK
 allows you the choice of using local or cloud compute resources, while managing
 and maintaining the complete data science workflow from the cloud.
 
-* Read [instructions on setting up notebooks](./NBSETUP.md) to run these notebooks.
+![Azure ML workflow](https://raw.githubusercontent.com/MicrosoftDocs/azure-docs/master/articles/machine-learning/service/media/overview-what-is-azure-ml/aml.png)
 
-* 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/).
+## Quick installation
+```sh
+pip install azureml-sdk
+```
+Read more detailed instructions on [how to set up your environment](./NBSETUP.md).
 
-## Getting Started
+## 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. 
 
-These examples will provide you with an effective way to get started using AML.  Once you're familiar with
-some of the capabilities, explore the repository for specific topics.
+If you want to...
 
-- [Configuration](./configuration.ipynb) configures your notebook library to easily connect to an
-    Azure Machine Learning workspace, and sets up your workspace to be used by many of the other examples.  You should
-    always run this first when setting up a notebook library on a new machine or in a new environment
-- [Train in notebook](./how-to-use-azureml/training/train-within-notebook) shows how to create a model directly in a notebook while recording
-    metrics and deploy that model to a test service
-- [Train on remote](./how-to-use-azureml/training/train-on-remote-vm) takes the previous example and shows how to create the model on a cloud compute target
-- [Production deploy to AKS](./how-to-use-azureml/deployment/production-deploy-to-aks) shows how to create a production grade inferencing webservice
+ * ...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 AML
+## How to use Azure ML
 
-The [How to use AML](./how-to-use-azureml) folder contains specific examples demonstrating the features of the Azure Machine Learning SDK
+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
@@ -38,3 +39,20 @@ The [How to use AML](./how-to-use-azureml) folder contains specific examples dem
 - [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)
+
+
+---
+
+## Projects using Azure Machine Learning
+
+Visit following repos to see projects contributed by Azure ML users:
+
+ - [Fine tune natural language processing models using Azure Machine Learning service](https://github.com/Microsoft/AzureML-BERT)
+ - [Fashion MNIST with Azure ML SDK](https://github.com/amynic/azureml-sdk-fashion)

configuration.ipynb

@@ -96,7 +96,7 @@
       "source": [
         "import azureml.core\n",
         "\n",
-        "print(\"This notebook was created using version 1.0.6 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version 1.0.10 of the Azure ML SDK\")\n",
         "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },

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

@@ -0,0 +1,409 @@
+{
+  "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

@@ -0,0 +1,500 @@
+# 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/automated-machine-learning/README.md

@@ -35,7 +35,7 @@ Below are the three execution environments supported by AutoML.
 **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_06.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 automl-databricks-local-01.ipynb from [GitHub](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/azure-databricks) and import into the Azure databricks workspace.
 - Attach the notebook to the cluster.
 
 <a name="localconda"></a>
@@ -175,10 +175,6 @@ 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-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-whitelisting.ipynb](classification-with-whitelisting/auto-ml-classification-with-whitelisting.ipynb)
     - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
     - Simple example of using Auto ML for classification with whitelisting tensorflow models.

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

@@ -1,6 +1,7 @@
 @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"
@@ -23,15 +24,21 @@ if errorlevel 1 goto ErrorExit
 
 call python -m ipykernel install --user --name %conda_env_name% --display-name "Python (%conda_env_name%)"
 
+REM azureml.widgets is now installed as part of the pip install under the conda env.
+REM Removing the old user install so that the notebooks will use the latest widget.
+call jupyter nbextension uninstall --user --py azureml.widgets
+
 echo.
 echo.
 echo ***************************************
 echo * AutoML setup completed successfully *
 echo ***************************************
-echo.
-echo Starting jupyter notebook - please run the configuration notebook 
-echo.
-jupyter notebook --log-level=50 --notebook-dir='..\..'
+IF NOT "%options%"=="nolaunch" (
+  echo.
+  echo Starting jupyter notebook - please run the configuration notebook 
+  echo.
+  jupyter notebook --log-level=50 --notebook-dir='..\..'
+)
 
 goto End
 

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

@@ -2,6 +2,7 @@
 
 CONDA_ENV_NAME=$1
 AUTOML_ENV_FILE=$2
+OPTIONS=$3
 PIP_NO_WARN_SCRIPT_LOCATION=0
 
 if [ "$CONDA_ENV_NAME" == "" ]
@@ -22,20 +23,25 @@ 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]
+   pip install --upgrade azureml-sdk[automl,notebooks,explain] &&
+   jupyter nbextension uninstall --user --py azureml.widgets
 else
    conda env create -f $AUTOML_ENV_FILE -n $CONDA_ENV_NAME &&
    source activate $CONDA_ENV_NAME &&
    python -m ipykernel install --user --name $CONDA_ENV_NAME --display-name "Python ($CONDA_ENV_NAME)" &&
+   jupyter nbextension uninstall --user --py azureml.widgets &&
    echo "" &&
    echo "" &&
    echo "***************************************" &&
    echo "* AutoML setup completed successfully *" &&
    echo "***************************************" &&
-   echo "" &&
-   echo "Starting jupyter notebook - please run the configuration notebook" &&
-   echo "" &&
-   jupyter notebook --log-level=50 --notebook-dir '../..'
+   if [ "$OPTIONS" != "nolaunch" ]
+   then
+      echo "" &&
+      echo "Starting jupyter notebook - please run the configuration notebook" &&
+      echo "" &&
+      jupyter notebook --log-level=50 --notebook-dir '../..'
+   fi
 fi
 
 if [ $? -gt 0 ]

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

@@ -2,6 +2,7 @@
 
 CONDA_ENV_NAME=$1
 AUTOML_ENV_FILE=$2
+OPTIONS=$3
 PIP_NO_WARN_SCRIPT_LOCATION=0
 
 if [ "$CONDA_ENV_NAME" == "" ]
@@ -22,22 +23,27 @@ 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]
+   pip install --upgrade azureml-sdk[automl,notebooks,explain] &&
+   jupyter nbextension uninstall --user --py azureml.widgets
 else
    conda env create -f $AUTOML_ENV_FILE -n $CONDA_ENV_NAME &&
    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)" &&
-   pip install numpy==1.15.3
+   jupyter nbextension uninstall --user --py azureml.widgets &&
+   pip install numpy==1.15.3 &&
    echo "" &&
    echo "" &&
    echo "***************************************" &&
    echo "* AutoML setup completed successfully *" &&
    echo "***************************************" &&
-   echo "" &&
-   echo "Starting jupyter notebook - please run the configuration notebook" &&
-   echo "" &&
-   jupyter notebook --log-level=50 --notebook-dir '../..'
+   if [ "$OPTIONS" != "nolaunch" ]
+   then
+      echo "" &&
+      echo "Starting jupyter notebook - please run the configuration notebook" &&
+      echo "" &&
+      jupyter notebook --log-level=50 --notebook-dir '../..'
+   fi
 fi
 
 if [ $? -gt 0 ]

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

@@ -1,403 +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\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",
-    "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-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",
-    "pd.DataFrame(data = output, index = ['']).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": [
-    "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": [
-    "## 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"
-   }
+  "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()"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "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"
+    }
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,418 +1,413 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-    "\n",
-    "Licensed under the MIT License."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Automated Machine Learning\n",
-    "_**Classification with Local Compute**_\n",
-    "\n",
-    "## Contents\n",
-    "1. [Introduction](#Introduction)\n",
-    "1. [Setup](#Setup)\n",
-    "1. [Data](#Data)\n",
-    "1. [Train](#Train)\n",
-    "1. [Results](#Results)\n",
-    "1. [Test](#Test)\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Introduction\n",
-    "\n",
-    "In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset) to showcase how you can use AutoML for a simple classification problem.\n",
-    "\n",
-    "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
-    "\n",
-    "In this notebook you will learn how to:\n",
-    "1. Create an `Experiment` in an existing `Workspace`.\n",
-    "2. Configure AutoML using `AutoMLConfig`.\n",
-    "3. Train the model using local compute.\n",
-    "4. Explore the results.\n",
-    "5. Test the best fitted model."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup\n",
-    "\n",
-    "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import logging\n",
-    "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": [
-    "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": [
-    "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": [
-    "## Train\n",
-    "\n",
-    "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
-    "\n",
-    "|Property|Description|\n",
-    "|-|-|\n",
-    "|**task**|classification or regression|\n",
-    "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
-    "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
-    "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
-    "|**n_cross_validations**|Number of cross validation splits.|\n",
-    "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
-    "|**y**|(sparse) array-like, shape = [n_samples, ], [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": [
-    "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
-    "In this example, we specify `show_output = True` to print currently running iterations to the console."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "local_run = experiment.submit(automl_config, show_output = True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "local_run"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Optionally, you can continue an interrupted local run by calling `continue_experiment` without the `iterations` parameter, or run more iterations for a completed run by specifying the `iterations` parameter:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "local_run = local_run.continue_experiment(X = X_train, \n",
-    "                                          y = y_train, \n",
-    "                                          show_output = True,\n",
-    "                                          iterations = 5)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Results"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Widget for Monitoring Runs\n",
-    "\n",
-    "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
-    "\n",
-    "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.widgets import RunDetails\n",
-    "RunDetails(local_run).show() "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "\n",
-    "#### Retrieve All Child Runs\n",
-    "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "children = list(local_run.get_children())\n",
-    "metricslist = {}\n",
-    "for run in children:\n",
-    "    properties = run.get_properties()\n",
-    "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
-    "    metricslist[int(properties['iteration'])] = metrics\n",
-    "\n",
-    "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
-    "rundata"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Retrieve the Best Model\n",
-    "\n",
-    "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "best_run, fitted_model = local_run.get_output()\n",
-    "print(best_run)\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"
-   }
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "_**Classification with Local Compute**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Data](#Data)\n",
+        "1. [Train](#Train)\n",
+        "1. [Results](#Results)\n",
+        "1. [Test](#Test)\n",
+        "\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "\n",
+        "In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset) to showcase how you can use AutoML for a simple classification problem.\n",
+        "\n",
+        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+        "\n",
+        "In this notebook you will learn how to:\n",
+        "1. Create an `Experiment` in an existing `Workspace`.\n",
+        "2. Configure AutoML using `AutoMLConfig`.\n",
+        "3. Train the model using local compute.\n",
+        "4. Explore the results.\n",
+        "5. Test the best fitted model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup\n",
+        "\n",
+        "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import logging\n",
+        "\n",
+        "from matplotlib import pyplot as plt\n",
+        "import numpy as np\n",
+        "import pandas as pd\n",
+        "from sklearn import datasets\n",
+        "\n",
+        "import azureml.core\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "from azureml.train.automl import AutoMLConfig"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "# Choose a name for the experiment and specify the project folder.\n",
+        "experiment_name = 'automl-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",
+        "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>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": [
+        "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
+        "In this example, we specify `show_output = True` to print currently running iterations to the console."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run = experiment.submit(automl_config, show_output = True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Optionally, you can continue an interrupted local run by calling `continue_experiment` without the `iterations` parameter, or run more iterations for a completed run by specifying the `iterations` parameter:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run = local_run.continue_experiment(X = X_train, \n",
+        "                                          y = y_train, \n",
+        "                                          show_output = True,\n",
+        "                                          iterations = 5)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Results"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Widget for Monitoring Runs\n",
+        "\n",
+        "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+        "\n",
+        "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.widgets import RunDetails\n",
+        "RunDetails(local_run).show() "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "\n",
+        "#### Retrieve All Child Runs\n",
+        "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "children = list(local_run.get_children())\n",
+        "metricslist = {}\n",
+        "for run in children:\n",
+        "    properties = run.get_properties()\n",
+        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+        "    metricslist[int(properties['iteration'])] = metrics\n",
+        "\n",
+        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+        "rundata"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Retrieve the Best Model\n",
+        "\n",
+        "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run, fitted_model = local_run.get_output()\n",
+        "print(best_run)\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()"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "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"
+    }
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

how-to-use-azureml/automated-machine-learning/configuration.ipynb

@@ -1,154 +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 Configuration\n",
-        "\n",
-        "In this example you will create an Azure Machine Learning `Workspace` object and initialize your notebook directory to easily reload this object from a configuration file.  Typically you will only need to run this once per notebook directory, and all other notebooks in this directory or any sub-directories will automatically use the settings you indicate here.\n"
-      ]
-    },
-    {
-      "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 = \"<subscription_id>\"\n",
-        "resource_group = \"myrg\"\n",
-        "workspace_name = \"myws\"\n",
-        "workspace_region = \"eastus2\""
-      ]
-    },
-    {
-      "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",
-        "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()"
-      ]
-    }
-  ],
-  "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/auto-ml-dataprep.ipynb

@@ -1,469 +1,466 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-    "\n",
-    "Licensed under the MIT License."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Automated Machine Learning\n",
-    "_**Prepare Data using `azureml.dataprep` for Local Execution**_\n",
-    "\n",
-    "## Contents\n",
-    "1. [Introduction](#Introduction)\n",
-    "1. [Setup](#Setup)\n",
-    "1. [Data](#Data)\n",
-    "1. [Train](#Train)\n",
-    "1. [Results](#Results)\n",
-    "1. [Test](#Test)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Introduction\n",
-    "In this example we showcase how you can use the `azureml.dataprep` SDK to load and prepare data for AutoML. `azureml.dataprep` can also be used standalone; full documentation can be found [here](https://github.com/Microsoft/PendletonDocs).\n",
-    "\n",
-    "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
-    "\n",
-    "In this notebook you will learn how to:\n",
-    "1. Define data loading and preparation steps in a `Dataflow` using `azureml.dataprep`.\n",
-    "2. Pass the `Dataflow` to AutoML for a local run.\n",
-    "3. Pass the `Dataflow` to AutoML for a remote run."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup\n",
-    "\n",
-    "Currently, Data Prep only supports __Ubuntu 16__ and __Red Hat Enterprise Linux 7__. We are working on supporting more linux distros."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "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": [
-    "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": [
-    "## Data"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# You can use `auto_read_file` which intelligently figures out delimiters and datatypes of a file.\n",
-    "# The data referenced here was pulled from `sklearn.datasets.load_digits()`.\n",
-    "simple_example_data_root = 'https://dprepdata.blob.core.windows.net/automl-notebook-data/'\n",
-    "X = dprep.auto_read_file(simple_example_data_root + 'X.csv').skip(1)  # Remove the header row.\n",
-    "\n",
-    "# You can also use `read_csv` and `to_*` transformations to read (with overridable delimiter)\n",
-    "# and convert column types manually.\n",
-    "# Here we read a comma delimited file and convert all columns to integers.\n",
-    "y = dprep.read_csv(simple_example_data_root + 'y.csv').to_long(dprep.ColumnSelector(term='.*', use_regex = True))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Review the Data Preparation Result\n",
-    "\n",
-    "You can peek the result of a Dataflow at any range using `skip(i)` and `head(j)`. Doing so evaluates only `j` records for all the steps in the Dataflow, which makes it fast even against large datasets."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "X.skip(1).head(5)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Train\n",
-    "\n",
-    "This creates a general AutoML settings object applicable for both local and remote runs."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "automl_settings = {\n",
-    "    \"iteration_timeout_minutes\" : 10,\n",
-    "    \"iterations\" : 2,\n",
-    "    \"primary_metric\" : 'AUC_weighted',\n",
-    "    \"preprocess\" : False,\n",
-    "    \"verbosity\" : logging.INFO,\n",
-    "    \"n_cross_validations\": 3\n",
-    "}"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Pass Data with `Dataflow` Objects\n",
-    "\n",
-    "The `Dataflow` objects captured above can be passed to the `submit` method for a local run. AutoML will retrieve the results from the `Dataflow` for model training."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "automl_config = AutoMLConfig(task = 'classification',\n",
-    "                             debug_log = 'automl_errors.log',\n",
-    "                             X = X,\n",
-    "                             y = y,\n",
-    "                             **automl_settings)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "local_run = experiment.submit(automl_config, show_output = True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "local_run"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Results"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Widget for Monitoring Runs\n",
-    "\n",
-    "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
-    "\n",
-    "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.widgets import RunDetails\n",
-    "RunDetails(local_run).show()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Retrieve All Child Runs\n",
-    "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "children = list(local_run.get_children())\n",
-    "metricslist = {}\n",
-    "for run in children:\n",
-    "    properties = run.get_properties()\n",
-    "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
-    "    metricslist[int(properties['iteration'])] = metrics\n",
-    "    \n",
-    "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\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"
-   }
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "_**Prepare Data using `azureml.dataprep` for Local Execution**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Data](#Data)\n",
+        "1. [Train](#Train)\n",
+        "1. [Results](#Results)\n",
+        "1. [Test](#Test)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "In this example we showcase how you can use the `azureml.dataprep` SDK to load and prepare data for AutoML. `azureml.dataprep` can also be used standalone; full documentation can be found [here](https://github.com/Microsoft/PendletonDocs).\n",
+        "\n",
+        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+        "\n",
+        "In this notebook you will learn how to:\n",
+        "1. Define data loading and preparation steps in a `Dataflow` using `azureml.dataprep`.\n",
+        "2. Pass the `Dataflow` to AutoML for a local run.\n",
+        "3. Pass the `Dataflow` to AutoML for a remote run."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup\n",
+        "\n",
+        "Currently, Data Prep only supports __Ubuntu 16__ and __Red Hat Enterprise Linux 7__. We are working on supporting more linux distros."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "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": [
+        "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import logging\n",
+        "\n",
+        "import pandas as pd\n",
+        "\n",
+        "import azureml.core\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "import azureml.dataprep as dprep\n",
+        "from azureml.train.automl import AutoMLConfig"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        " \n",
+        "# choose a name for experiment\n",
+        "experiment_name = 'automl-dataprep-local'\n",
+        "# project folder\n",
+        "project_folder = './sample_projects/automl-dataprep-local'\n",
+        " \n",
+        "experiment = Experiment(ws, experiment_name)\n",
+        " \n",
+        "output = {}\n",
+        "output['SDK version'] = azureml.core.VERSION\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace Name'] = ws.name\n",
+        "output['Resource Group'] = ws.resource_group\n",
+        "output['Location'] = ws.location\n",
+        "output['Project Directory'] = project_folder\n",
+        "output['Experiment Name'] = experiment.name\n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
+        "outputDf.T"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Data"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# You can use `auto_read_file` which intelligently figures out delimiters and datatypes of a file.\n",
+        "# The data referenced here was pulled from `sklearn.datasets.load_digits()`.\n",
+        "simple_example_data_root = 'https://dprepdata.blob.core.windows.net/automl-notebook-data/'\n",
+        "X = dprep.auto_read_file(simple_example_data_root + 'X.csv').skip(1)  # Remove the header row.\n",
+        "\n",
+        "# You can also use `read_csv` and `to_*` transformations to read (with overridable delimiter)\n",
+        "# and convert column types manually.\n",
+        "# Here we read a comma delimited file and convert all columns to integers.\n",
+        "y = dprep.read_csv(simple_example_data_root + 'y.csv').to_long(dprep.ColumnSelector(term='.*', use_regex = True))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Review the Data Preparation Result\n",
+        "\n",
+        "You can peek the result of a Dataflow at any range using `skip(i)` and `head(j)`. Doing so evaluates only `j` records for all the steps in the Dataflow, which makes it fast even against large datasets."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X.skip(1).head(5)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train\n",
+        "\n",
+        "This creates a general AutoML settings object applicable for both local and remote runs."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "automl_settings = {\n",
+        "    \"iteration_timeout_minutes\" : 10,\n",
+        "    \"iterations\" : 2,\n",
+        "    \"primary_metric\" : 'AUC_weighted',\n",
+        "    \"preprocess\" : False,\n",
+        "    \"verbosity\" : logging.INFO,\n",
+        "    \"n_cross_validations\": 3\n",
+        "}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Pass Data with `Dataflow` Objects\n",
+        "\n",
+        "The `Dataflow` objects captured above can be passed to the `submit` method for a local run. AutoML will retrieve the results from the `Dataflow` for model training."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "automl_config = AutoMLConfig(task = 'classification',\n",
+        "                             debug_log = 'automl_errors.log',\n",
+        "                             X = X,\n",
+        "                             y = y,\n",
+        "                             **automl_settings)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run = experiment.submit(automl_config, show_output = True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Results"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Widget for Monitoring Runs\n",
+        "\n",
+        "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+        "\n",
+        "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.widgets import RunDetails\n",
+        "RunDetails(local_run).show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Retrieve All Child Runs\n",
+        "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "children = list(local_run.get_children())\n",
+        "metricslist = {}\n",
+        "for run in children:\n",
+        "    properties = run.get_properties()\n",
+        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+        "    metricslist[int(properties['iteration'])] = metrics\n",
+        "    \n",
+        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+        "rundata"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Retrieve the Best Model\n",
+        "\n",
+        "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run, fitted_model = local_run.get_output()\n",
+        "print(best_run)\n",
+        "print(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Best Model Based on Any Other Metric\n",
+        "Show the run and the model that has the smallest `log_loss` value:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "lookup_metric = \"log_loss\"\n",
+        "best_run, fitted_model = local_run.get_output(metric = lookup_metric)\n",
+        "print(best_run)\n",
+        "print(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Model from a Specific Iteration\n",
+        "Show the run and the model from the first iteration:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "iteration = 0\n",
+        "best_run, fitted_model = local_run.get_output(iteration = iteration)\n",
+        "print(best_run)\n",
+        "print(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Test\n",
+        "\n",
+        "#### Load Test Data"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from sklearn import datasets\n",
+        "\n",
+        "digits = datasets.load_digits()\n",
+        "X_test = digits.data[:10, :]\n",
+        "y_test = digits.target[:10]\n",
+        "images = digits.images[:10]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Testing Our Best Fitted Model\n",
+        "We will try to predict 2 digits and see how our model works."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "#Randomly select digits and test\n",
+        "from matplotlib import pyplot as plt\n",
+        "import numpy as np\n",
+        "\n",
+        "for index in np.random.choice(len(y_test), 2, replace = False):\n",
+        "    print(index)\n",
+        "    predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
+        "    label = y_test[index]\n",
+        "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
+        "    fig = plt.figure(1, figsize=(3,3))\n",
+        "    ax1 = fig.add_axes((0,0,.8,.8))\n",
+        "    ax1.set_title(title)\n",
+        "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
+        "    plt.show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Appendix"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Capture the `Dataflow` Objects for Later Use in AutoML\n",
+        "\n",
+        "`Dataflow` objects are immutable and are composed of a list of data preparation steps. A `Dataflow` object can be branched at any point for further usage."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# sklearn.digits.data + target\n",
+        "digits_complete = dprep.auto_read_file('https://dprepdata.blob.core.windows.net/automl-notebook-data/digits-complete.csv')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "`digits_complete` (sourced from `sklearn.datasets.load_digits()`) is forked into `dflow_X` to capture all the feature columns and `dflow_y` to capture the label column."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(digits_complete.to_pandas_dataframe().shape)\n",
+        "labels_column = 'Column64'\n",
+        "dflow_X = digits_complete.drop_columns(columns = [labels_column])\n",
+        "dflow_y = digits_complete.keep_columns(columns = [labels_column])"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "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"
+    }
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,370 +1,359 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-    "\n",
-    "Licensed under the MIT License."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Automated Machine Learning\n",
-    "_**Exploring Previous Runs**_\n",
-    "\n",
-    "## Contents\n",
-    "1. [Introduction](#Introduction)\n",
-    "1. [Setup](#Setup)\n",
-    "1. [Explore](#Explore)\n",
-    "1. [Download](#Download)\n",
-    "1. [Register](#Register)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Introduction\n",
-    "In this example we present some examples on navigating previously executed runs. We also show how you can download a fitted model for any previous run.\n",
-    "\n",
-    "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
-    "\n",
-    "In this notebook you will learn how to:\n",
-    "1. List all experiments in a workspace.\n",
-    "2. List all AutoML runs in an experiment.\n",
-    "3. Get details for an AutoML run, including settings, run widget, and all metrics.\n",
-    "4. Download a fitted pipeline for any iteration."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import 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()"
-   ]
-  },
-  {
-   "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": [
-    "## Explore"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### List Experiments"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "experiment_list = Experiment.list(workspace=ws)\n",
-    "\n",
-    "summary_df = pd.DataFrame(index = ['No of Runs'])\n",
-    "for experiment in experiment_list:\n",
-    "    automl_runs = list(experiment.get_runs(type='automl'))\n",
-    "    summary_df[experiment.name] = [len(automl_runs)]\n",
-    "    \n",
-    "pd.set_option('display.max_colwidth', -1)\n",
-    "summary_df.T"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### List runs for an experiment\n",
-    "Set `experiment_name` to any experiment name from the result of the Experiment.list cell to load the AutoML runs."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "experiment_name = 'automl-local-classification' # Replace this with any project name from previous cell.\n",
-    "\n",
-    "proj = ws.experiments[experiment_name]\n",
-    "summary_df = pd.DataFrame(index = ['Type', 'Status', 'Primary Metric', 'Iterations', 'Compute', 'Name'])\n",
-    "automl_runs = list(proj.get_runs(type='automl'))\n",
-    "automl_runs_project = []\n",
-    "for run in automl_runs:\n",
-    "    properties = run.get_properties()\n",
-    "    tags = run.get_tags()\n",
-    "    amlsettings = 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 a run\n",
-    "\n",
-    "Copy the project name and run id from the previous cell output to find more details on a particular run."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "run_id = automl_runs_project[0]  # Replace with your own run_id from above run ids\n",
-    "assert (run_id in summary_df.keys()), \"Run id not found! Please set run id to a value from above run ids\"\n",
-    "\n",
-    "from azureml.widgets import RunDetails\n",
-    "\n",
-    "experiment = Experiment(ws, experiment_name)\n",
-    "ml_run = AutoMLRun(experiment = experiment, run_id = run_id)\n",
-    "\n",
-    "summary_df = pd.DataFrame(index = ['Type', 'Status', 'Primary Metric', 'Iterations', 'Compute', 'Name', 'Start Time', 'End Time'])\n",
-    "properties = ml_run.get_properties()\n",
-    "tags = ml_run.get_tags()\n",
-    "status = ml_run.get_details()\n",
-    "amlsettings = 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"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Download the Best Model for Any Given Metric"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "metric = 'AUC_weighted' # Replace with a metric name.\n",
-    "best_run, fitted_model = ml_run.get_output(metric = metric)\n",
-    "fitted_model"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Download the Model for Any Given Iteration"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "iteration = 1 # Replace with an iteration number.\n",
-    "best_run, fitted_model = ml_run.get_output(iteration = iteration)\n",
-    "fitted_model"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Register"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Register fitted model for deployment\n",
-    "If neither `metric` nor `iteration` are specified in the `register_model` call, the iteration with the best primary metric is registered."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "description = 'AutoML Model'\n",
-    "tags = None\n",
-    "ml_run.register_model(description = description, tags = tags)\n",
-    "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"
-   }
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "_**Exploring Previous Runs**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Explore](#Explore)\n",
+        "1. [Download](#Download)\n",
+        "1. [Register](#Register)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "In this example we present some examples on navigating previously executed runs. We also show how you can download a fitted model for any previous run.\n",
+        "\n",
+        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+        "\n",
+        "In this notebook you will learn how to:\n",
+        "1. List all experiments in a workspace.\n",
+        "2. List all AutoML runs in an experiment.\n",
+        "3. Get details for an AutoML run, including settings, run widget, and all metrics.\n",
+        "4. Download a fitted pipeline for any iteration."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import pandas as pd\n",
+        "import json\n",
+        "\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "from azureml.train.automl.run import AutoMLRun"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "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": [
+        "## Explore"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### List Experiments"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "experiment_list = Experiment.list(workspace=ws)\n",
+        "\n",
+        "summary_df = pd.DataFrame(index = ['No of Runs'])\n",
+        "for experiment in experiment_list:\n",
+        "    automl_runs = list(experiment.get_runs(type='automl'))\n",
+        "    summary_df[experiment.name] = [len(automl_runs)]\n",
+        "    \n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "summary_df.T"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### List runs for an experiment\n",
+        "Set `experiment_name` to any experiment name from the result of the Experiment.list cell to load the AutoML runs."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "experiment_name = 'automl-local-classification' # Replace this with any project name from previous cell.\n",
+        "\n",
+        "proj = ws.experiments[experiment_name]\n",
+        "summary_df = pd.DataFrame(index = ['Type', 'Status', 'Primary Metric', 'Iterations', 'Compute', 'Name'])\n",
+        "automl_runs = list(proj.get_runs(type='automl'))\n",
+        "automl_runs_project = []\n",
+        "for run in automl_runs:\n",
+        "    properties = run.get_properties()\n",
+        "    tags = run.get_tags()\n",
+        "    amlsettings = json.loads(properties['AMLSettingsJsonString'])\n",
+        "    if 'iterations' in tags:\n",
+        "        iterations = tags['iterations']\n",
+        "    else:\n",
+        "        iterations = properties['num_iterations']\n",
+        "    summary_df[run.id] = [amlsettings['task_type'], run.get_details()['status'], properties['primary_metric'], iterations, properties['target'], amlsettings['name']]\n",
+        "    if run.get_details()['status'] == 'Completed':\n",
+        "        automl_runs_project.append(run.id)\n",
+        "    \n",
+        "from IPython.display import HTML\n",
+        "projname_html = HTML(\"<h3>{}</h3>\".format(proj.name))\n",
+        "\n",
+        "from IPython.display import display\n",
+        "display(projname_html)\n",
+        "display(summary_df.T)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Get details for a run\n",
+        "\n",
+        "Copy the project name and run id from the previous cell output to find more details on a particular run."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run_id = automl_runs_project[0]  # Replace with your own run_id from above run ids\n",
+        "assert (run_id in summary_df.keys()), \"Run id not found! Please set run id to a value from above run ids\"\n",
+        "\n",
+        "from azureml.widgets import RunDetails\n",
+        "\n",
+        "experiment = Experiment(ws, experiment_name)\n",
+        "ml_run = AutoMLRun(experiment = experiment, run_id = run_id)\n",
+        "\n",
+        "summary_df = pd.DataFrame(index = ['Type', 'Status', 'Primary Metric', 'Iterations', 'Compute', 'Name', 'Start Time', 'End Time'])\n",
+        "properties = ml_run.get_properties()\n",
+        "tags = ml_run.get_tags()\n",
+        "status = ml_run.get_details()\n",
+        "amlsettings = json.loads(properties['AMLSettingsJsonString'])\n",
+        "if 'iterations' in tags:\n",
+        "    iterations = tags['iterations']\n",
+        "else:\n",
+        "    iterations = properties['num_iterations']\n",
+        "start_time = None\n",
+        "if 'startTimeUtc' in status:\n",
+        "    start_time = status['startTimeUtc']\n",
+        "end_time = None\n",
+        "if 'endTimeUtc' in status:\n",
+        "    end_time = status['endTimeUtc']\n",
+        "summary_df[ml_run.id] = [amlsettings['task_type'], status['status'], properties['primary_metric'], iterations, properties['target'], amlsettings['name'], start_time, end_time]\n",
+        "display(HTML('<h3>Runtime Details</h3>'))\n",
+        "display(summary_df)\n",
+        "\n",
+        "#settings_df = pd.DataFrame(data = amlsettings, index = [''])\n",
+        "display(HTML('<h3>AutoML Settings</h3>'))\n",
+        "display(amlsettings)\n",
+        "\n",
+        "display(HTML('<h3>Iterations</h3>'))\n",
+        "RunDetails(ml_run).show() \n",
+        "\n",
+        "children = list(ml_run.get_children())\n",
+        "metricslist = {}\n",
+        "for run in children:\n",
+        "    properties = run.get_properties()\n",
+        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+        "    metricslist[int(properties['iteration'])] = metrics\n",
+        "\n",
+        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+        "display(HTML('<h3>Metrics</h3>'))\n",
+        "display(rundata)\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Download"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Download the Best Model for Any Given Metric"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "metric = 'AUC_weighted' # Replace with a metric name.\n",
+        "best_run, fitted_model = ml_run.get_output(metric = metric)\n",
+        "fitted_model"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Download the Model for Any Given Iteration"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "iteration = 1 # Replace with an iteration number.\n",
+        "best_run, fitted_model = ml_run.get_output(iteration = iteration)\n",
+        "fitted_model"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Register"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Register fitted model for deployment\n",
+        "If neither `metric` nor `iteration` are specified in the `register_model` call, the iteration with the best primary metric is registered."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "description = 'AutoML Model'\n",
+        "tags = None\n",
+        "ml_run.register_model(description = description, tags = tags)\n",
+        "print(ml_run.model_id) # Use this id to deploy the model as a web service in Azure."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Register the Best Model for Any Given Metric"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "metric = 'AUC_weighted' # Replace with a metric name.\n",
+        "description = 'AutoML Model'\n",
+        "tags = None\n",
+        "ml_run.register_model(description = description, tags = tags, metric = metric)\n",
+        "print(ml_run.model_id) # Use this id to deploy the model as a web service in Azure."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Register the Model for Any Given Iteration"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "iteration = 1 # Replace with an iteration number.\n",
+        "description = 'AutoML Model'\n",
+        "tags = None\n",
+        "ml_run.register_model(description = description, tags = tags, iteration = iteration)\n",
+        "print(ml_run.model_id) # Use this id to deploy the model as a web service in Azure."
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "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"
+    }
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,418 +1,405 @@
 {
- "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",
-    "\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": [
-    "## 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": [
-    "### 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"
-   }
+  "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()"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "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"
+    }
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,413 +1,441 @@
 {
- "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\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": [
-    "## 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"
-   }
+  "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))"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "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"
+    }
   },
-  "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
+  "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

@@ -1,401 +1,396 @@
 {
- "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",
-    "_**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",
-    "\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"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup\n",
-    "\n",
-    "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import logging\n",
-    "import os\n",
-    "import 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": [
-    "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"
-   ]
-  },
-  {
-   "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": [
-    "## Train\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": [
-    "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()"
-   ]
-  },
-  {
-   "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": [
-    "## Test"
-   ]
-  },
-  {
-   "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"
-   }
+  "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",
+        "_**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",
+        "\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"
+      ]
+    },
+    {
+      "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.\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",
+        "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"
+      ]
+    },
+    {
+      "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",
+        "# 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": [
+        "## Train\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": [
+        "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()"
+      ]
+    },
+    {
+      "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": [
+        "## Test"
+      ]
+    },
+    {
+      "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"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "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"
+    }
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,367 +1,365 @@
 {
- "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",
-    "_**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",
-    "\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"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup\n",
-    "\n",
-    "As part of the setup you have already created a <b>Workspace</b>. For AutoML you would need to create an <b>Experiment</b>. An <b>Experiment</b> is a named object in a <b>Workspace</b>, which is used to run experiments."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import logging\n",
-    "import os\n",
-    "import 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": [
-    "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"
-   ]
-  },
-  {
-   "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": [
-    "## Train\n",
-    "\n",
-    "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
-    "\n",
-    "|Property|Description|\n",
-    "|-|-|\n",
-    "|**task**|classification or regression|\n",
-    "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
-    "|**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": [
-    "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": [
-    "## 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"
-   }
+  "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",
+        "_**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",
+        "\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"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup\n",
+        "\n",
+        "As part of the setup you have already created a <b>Workspace</b>. For AutoML you would need to create an <b>Experiment</b>. An <b>Experiment</b> is a named object in a <b>Workspace</b>, which is used to run experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import logging\n",
+        "\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"
+      ]
+    },
+    {
+      "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",
+        "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"
+      ]
+    },
+    {
+      "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": [
+        "## Train\n",
+        "\n",
+        "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
+        "\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**task**|classification or regression|\n",
+        "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
+        "|**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": [
+        "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": [
+        "## 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)"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "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"
+    }
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,424 +1,417 @@
 {
- "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",
-    "_**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",
-    "\n",
-    "In this notebook you will learn how to:\n",
-    "1. Create an `Experiment` in an existing `Workspace`.\n",
-    "2. Configure AutoML using `AutoMLConfig`.\n",
-    "3. Train the model using local compute.\n",
-    "4. Explore the results.\n",
-    "5. Test the best fitted model."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup\n",
-    "\n",
-    "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import logging\n",
-    "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": [
-    "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",
-    "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.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": [
-    "## Train\n",
-    "\n",
-    "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
-    "\n",
-    "|Property|Description|\n",
-    "|-|-|\n",
-    "|**task**|classification or regression|\n",
-    "|**primary_metric**|This is the metric that you want to optimize. Regression supports the following primary metrics: <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>|\n",
-    "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
-    "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
-    "|**n_cross_validations**|Number of cross validation splits.|\n",
-    "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
-    "|**y**|(sparse) array-like, shape = [n_samples, ], [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": [
-    "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 `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"
-   ]
-  },
-  {
-   "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"
-   }
+  "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",
+        "_**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",
+        "\n",
+        "In this notebook you will learn how to:\n",
+        "1. Create an `Experiment` in an existing `Workspace`.\n",
+        "2. Configure AutoML using `AutoMLConfig`.\n",
+        "3. Train the model using local compute.\n",
+        "4. Explore the results.\n",
+        "5. Test the best fitted model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup\n",
+        "\n",
+        "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import logging\n",
+        "\n",
+        "from matplotlib import pyplot as plt\n",
+        "import numpy as np\n",
+        "import pandas as pd\n",
+        "\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-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",
+        "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",
+        "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.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": [
+        "## Train\n",
+        "\n",
+        "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
+        "\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**task**|classification or regression|\n",
+        "|**primary_metric**|This is the metric that you want to optimize. Regression supports the following primary metrics: <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>|\n",
+        "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+        "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
+        "|**n_cross_validations**|Number of cross validation splits.|\n",
+        "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+        "|**y**|(sparse) array-like, shape = [n_samples, ], [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": [
+        "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 `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"
+      ]
+    },
+    {
+      "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",
+        "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()"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "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"
+    }
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,260 +1,257 @@
 {
- "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",
-    "_**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",
-    "\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."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup\n",
-    "\n",
-    "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import logging\n",
-    "import os\n",
-    "import 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": [
-    "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\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": [
-    "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\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"
-   }
+  "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",
+        "_**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",
+        "\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."
+      ]
+    },
+    {
+      "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 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",
+        "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": [
+        "## Train\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": [
+        "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\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()"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "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"
+    }
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,403 +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": [
-    "# Automated Machine Learning\n",
-    "_**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",
-    "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": [
-    "## Setup\n",
-    "\n",
-    "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import logging\n",
-    "import os\n",
-    "import 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": [
-    "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"
-   ]
-  },
-  {
-   "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": [
-    "## Train\n",
-    "\n",
-    "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
-    "\n",
-    "|Property|Description|\n",
-    "|-|-|\n",
-    "|**task**|classification or regression|\n",
-    "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
-    "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
-    "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
-    "|**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": [
-    "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()"
-   ]
-  },
-  {
-   "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": [
-    "## Test"
-   ]
-  },
-  {
-   "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"
-   }
+  "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",
+        "_**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",
+        "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": [
+        "## 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",
+        "import pandas as pd\n",
+        "\n",
+        "import azureml.core\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "from azureml.train.automl import AutoMLConfig"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "# choose a name for the 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",
+        "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"
+      ]
+    },
+    {
+      "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": [
+        "## Train\n",
+        "\n",
+        "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
+        "\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**task**|classification or regression|\n",
+        "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
+        "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+        "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
+        "|**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": [
+        "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()"
+      ]
+    },
+    {
+      "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": [
+        "## Test"
+      ]
+    },
+    {
+      "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()"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "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"
+    }
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,70 +1,26 @@
 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 see 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. 
+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. 
+- 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.
 
-**Create Azure Databricks Cluster:**
+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.
 
-Select New Cluster and fill in following detail:
- - Cluster name: _yourclustername_
- - Databricks Runtime: Any 4.x runtime.
- - Python version: **3**
- - Workers: 2 or higher.  
+**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.
 
-These settings are only for using Automated Machine Learning on Databricks.
- - Max. number of **concurrent iterations** in Automated ML settings is **<=** to the number of **worker nodes** in your Databricks cluster.
- - Worker node VM types: **Memory optimized VM** preferred. 
- - Uncheck _Enable Autoscaling_
+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. 
 
-
-It will take few minutes to create the cluster. Please ensure that the cluster state is running before proceeding further.
-
-**Install Azure ML SDK without Automated ML capability on your Azure Databricks cluster**
-
-- Select Import library
-
-- Source: Upload Python Egg or PyPI
-
-- PyPi Name: **azureml-sdk[databricks]**
-
-**Install Azure ML with Automated ML SDK on your Azure Databricks cluster**
-
-- Select Import library
-
-- Source: Upload Python Egg or PyPI
-
-- PyPi Name: **azureml-sdk[automl_databricks]**
-
-**For installation with or without Automated ML**
-
-- Click Install Library
-
-- Do not select _Attach automatically to all clusters_. In case you have selected earlier then you can go to your Home folder and deselect it.
-
-- Select the check box _Attach_ next to your cluster name
-
-(More details on how to attach and detach libs are here - [https://docs.databricks.com/user-guide/libraries.html#attach-a-library-to-a-cluster](https://docs.databricks.com/user-guide/libraries.html#attach-a-library-to-a-cluster) )
-
-- Ensure that there are no errors until Status changes to _Attached_. It may take a couple of minutes.
-
-**Note** - If you have the old build the please deselect it from cluster’s installed libs > move to trash. Install the new build and restart the cluster. And if still there is an issue then detach and reattach your cluster.
-
-iPython Notebooks 1-4 have to be run sequentially after making changes based on your subscription. The corresponding DBC archive contains all the notebooks and can be imported into your Databricks workspace. You can the run notebooks after importing [databricks_amlsdk](Databricks_AMLSDK_1-4_6.dbc) instead of downloading individually.
-
-Notebooks 1-4 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 details on SDK concepts, please refer to [notebooks](https://github.com/Azure/MachineLearningNotebooks).
+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.
 
-You can also use Azure Databricks as a compute target for [training models with an Azure Machine Learning pipeline](https://docs.microsoft.com/machine-learning/service/how-to-set-up-training-targets#databricks).
-
+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

@@ -1,396 +1,380 @@
 {
- "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"
-   }
+  "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\")"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
+  "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
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 1
 }

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

@@ -1,354 +1,338 @@
 {
- "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"
-   }
+  "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": []
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
+  "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
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 1
 }

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

@@ -1,182 +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"
-   }
+  "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": []
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
+  "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
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 1
 }

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

@@ -1,264 +1,179 @@
 {
- "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": [
-    "##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"
-   }
+  "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": []
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
+  "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
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 1
 }

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

@@ -0,0 +1,704 @@
+{
+  "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

@@ -1,495 +1,491 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Enabling App Insights for Services in Production\n",
-    "With this notebook, you can learn how to enable App Insights for standard service monitoring, plus, we provide examples for doing custom logging within a scoring files in a model. \n",
-    "\n",
-    "\n",
-    "## What does Application Insights monitor?\n",
-    "It monitors request rates, response times, failure rates, etc. For more information visit [App Insights docs.](https://docs.microsoft.com/en-us/azure/application-insights/app-insights-overview)\n",
-    "\n",
-    "\n",
-    "## What is different compared to standard production deployment process?\n",
-    "If you want to enable generic App Insights for a service run:\n",
-    "```python\n",
-    "aks_service= Webservice(ws, \"aks-w-dc2\")\n",
-    "aks_service.update(enable_app_insights=True)```\n",
-    "Where \"aks-w-dc2\" is your service name. You can also do this from the Azure Portal under your Workspace--> deployments--> Select deployment--> Edit--> Advanced Settings--> Select \"Enable AppInsights diagnostics\"\n",
-    "\n",
-    "If you want to log custom traces, you will follow the standard deplyment process for AKS and you will:\n",
-    "1. Update scoring file.\n",
-    "2. Update aks configuration.\n",
-    "3. Build new image and deploy it. "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 1. Import your dependencies"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "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)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 2. Set up your configuration and create a workspace\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "ws = Workspace.from_config()\n",
-    "print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 3. Register Model\n",
-    "Register an existing trained model, add descirption and tags."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#Register the model\n",
-    "from azureml.core.model import Model\n",
-    "model = Model.register(model_path = \"sklearn_regression_model.pkl\", # this points to a local file\n",
-    "                       model_name = \"sklearn_regression_model.pkl\", # this is the name the model is registered as\n",
-    "                       tags = {'area': \"diabetes\", 'type': \"regression\"},\n",
-    "                       description = \"Ridge regression model to predict diabetes\",\n",
-    "                       workspace = ws)\n",
-    "\n",
-    "print(model.name, model.description, model.version)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 4. *Update your scoring file with custom print statements*\n",
-    "Here is an example:\n",
-    "### a. In your init function add:\n",
-    "```python\n",
-    "print (\"model initialized\" + time.strftime(\"%H:%M:%S\"))```\n",
-    "\n",
-    "### b. In your run function add:\n",
-    "```python\n",
-    "print (\"Prediction created\" + time.strftime(\"%H:%M:%S\"))```"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%writefile score.py\n",
-    "import pickle\n",
-    "import json\n",
-    "import numpy \n",
-    "from sklearn.externals import joblib\n",
-    "from sklearn.linear_model import Ridge\n",
-    "from azureml.core.model import Model\n",
-    "import time\n",
-    "\n",
-    "def init():\n",
-    "    global model\n",
-    "    #Print statement for appinsights custom traces:\n",
-    "    print (\"model initialized\" + time.strftime(\"%H:%M:%S\"))\n",
-    "    \n",
-    "    # note here \"sklearn_regression_model.pkl\" is the name of the model registered under the workspace\n",
-    "    # this call should return the path to the model.pkl file on the local disk.\n",
-    "    model_path = Model.get_model_path(model_name = 'sklearn_regression_model.pkl')\n",
-    "    \n",
-    "    # deserialize the model file back into a sklearn model\n",
-    "    model = joblib.load(model_path)\n",
-    "  \n",
-    "\n",
-    "# note you can pass in multiple rows for scoring\n",
-    "def run(raw_data):\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",
-    "        return result.tolist()\n",
-    "    except Exception as e:\n",
-    "        error = str(e)\n",
-    "        print (error + time.strftime(\"%H:%M:%S\"))\n",
-    "        return error"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 5. *Create myenv.yml file*"
-   ]
-  },
-  {
-   "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'])\n",
-    "\n",
-    "with open(\"myenv.yml\",\"w\") as f:\n",
-    "    f.write(myenv.serialize_to_string())"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 6. Create your new Image"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.image import ContainerImage\n",
-    "\n",
-    "image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
-    "                                                  runtime = \"python\",\n",
-    "                                                  conda_file = \"myenv.yml\",\n",
-    "                                                  description = \"Image with ridge regression model\",\n",
-    "                                                  tags = {'area': \"diabetes\", 'type': \"regression\"}\n",
-    "                                                 )\n",
-    "\n",
-    "image = ContainerImage.create(name = \"myimage1\",\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)"
-   ]
-  },
-  {
-   "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",
-    "import json\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": {},
-   "source": [
-    "## 7. Deploy to AKS service"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Create AKS compute if you haven't done so."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Use the default configuration (can also provide parameters to customize)\n",
-    "prov_config = AksCompute.provisioning_configuration()\n",
-    "\n",
-    "aks_name = 'my-aks-test3' \n",
-    "# Create the cluster\n",
-    "aks_target = ComputeTarget.create(workspace = ws, \n",
-    "                                  name = aks_name, \n",
-    "                                  provisioning_configuration = prov_config)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%time\n",
-    "aks_target.wait_for_completion(show_output = True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(aks_target.provisioning_state)\n",
-    "print(aks_target.provisioning_errors)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "If you already have a cluster you can attach the service to it:"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "```python \n",
-    "%%time\n",
-    "resource_id = '/subscriptions/<subscriptionid>/resourcegroups/<resourcegroupname>/providers/Microsoft.ContainerService/managedClusters/<aksservername>'\n",
-    "create_name= 'myaks4'\n",
-    "attach_config = AksCompute.attach_configuration(resource_id=resource_id)\n",
-    "aks_target = ComputeTarget.attach(workspace = ws, \n",
-    "                                  name = create_name, \n",
-    "                                  attach_configuration=attach_config)\n",
-    "## Wait for the operation to complete\n",
-    "aks_target.wait_for_provisioning(True)```"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### a. *Activate App Insights through updating AKS Webservice configuration*\n",
-    "In order to enable App Insights in your service you will need to update your AKS configuration file:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#Set the web service configuration\n",
-    "aks_config = AksWebservice.deploy_configuration(enable_app_insights=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### b. Deploy your service"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "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",
-    "                                               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.\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 8. Test your service "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "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",
-    "    [101,9,8,37,6,45,4,3,2,41]\n",
-    "]})\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\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 9. See your service telemetry in App Insights\n",
-    "1. Go to the [Azure Portal](https://portal.azure.com/)\n",
-    "2. All resources--> Select the subscription/resource group where you created your Workspace--> Select the App Insights type\n",
-    "3. Click on the AppInsights resource. You'll see a highlevel dashboard with information on Requests, Server response time and availability.\n",
-    "4. Click on the top banner \"Analytics\"\n",
-    "5. In the \"Schema\" section select \"traces\" and run your query.\n",
-    "6. Voila! All your custom traces should be there."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Disable App Insights"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "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": "marthalc"
-   }
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Enabling App Insights for Services in Production\n",
+        "With this notebook, you can learn how to enable App Insights for standard service monitoring, plus, we provide examples for doing custom logging within a scoring files in a model. \n",
+        "\n",
+        "\n",
+        "## What does Application Insights monitor?\n",
+        "It monitors request rates, response times, failure rates, etc. For more information visit [App Insights docs.](https://docs.microsoft.com/en-us/azure/application-insights/app-insights-overview)\n",
+        "\n",
+        "\n",
+        "## What is different compared to standard production deployment process?\n",
+        "If you want to enable generic App Insights for a service run:\n",
+        "```python\n",
+        "aks_service= Webservice(ws, \"aks-w-dc2\")\n",
+        "aks_service.update(enable_app_insights=True)```\n",
+        "Where \"aks-w-dc2\" is your service name. You can also do this from the Azure Portal under your Workspace--> deployments--> Select deployment--> Edit--> Advanced Settings--> Select \"Enable AppInsights diagnostics\"\n",
+        "\n",
+        "If you want to log custom traces, you will follow the standard deplyment process for AKS and you will:\n",
+        "1. Update scoring file.\n",
+        "2. Update aks configuration.\n",
+        "3. Build new image and deploy it. "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 1. Import your dependencies"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core import Workspace\n",
+        "from azureml.core.compute import AksCompute, ComputeTarget\n",
+        "from azureml.core.webservice import AksWebservice\n",
+        "import azureml.core\n",
+        "import json\n",
+        "print(azureml.core.VERSION)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 2. Set up your configuration and create a workspace\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 3. Register Model\n",
+        "Register an existing trained model, add descirption and tags."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "#Register the model\n",
+        "from azureml.core.model import Model\n",
+        "model = Model.register(model_path = \"sklearn_regression_model.pkl\", # this points to a local file\n",
+        "                       model_name = \"sklearn_regression_model.pkl\", # this is the name the model is registered as\n",
+        "                       tags = {'area': \"diabetes\", 'type': \"regression\"},\n",
+        "                       description = \"Ridge regression model to predict diabetes\",\n",
+        "                       workspace = ws)\n",
+        "\n",
+        "print(model.name, model.description, model.version)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 4. *Update your scoring file with custom print statements*\n",
+        "Here is an example:\n",
+        "### a. In your init function add:\n",
+        "```python\n",
+        "print (\"model initialized\" + time.strftime(\"%H:%M:%S\"))```\n",
+        "\n",
+        "### b. In your run function add:\n",
+        "```python\n",
+        "print (\"Prediction created\" + time.strftime(\"%H:%M:%S\"))```"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%writefile score.py\n",
+        "import pickle\n",
+        "import json\n",
+        "import numpy \n",
+        "from sklearn.externals import joblib\n",
+        "from sklearn.linear_model import Ridge\n",
+        "from azureml.core.model import Model\n",
+        "import time\n",
+        "\n",
+        "def init():\n",
+        "    global model\n",
+        "    #Print statement for appinsights custom traces:\n",
+        "    print (\"model initialized\" + time.strftime(\"%H:%M:%S\"))\n",
+        "    \n",
+        "    # note here \"sklearn_regression_model.pkl\" is the name of the model registered under the workspace\n",
+        "    # this call should return the path to the model.pkl file on the local disk.\n",
+        "    model_path = Model.get_model_path(model_name = 'sklearn_regression_model.pkl')\n",
+        "    \n",
+        "    # deserialize the model file back into a sklearn model\n",
+        "    model = joblib.load(model_path)\n",
+        "  \n",
+        "\n",
+        "# note you can pass in multiple rows for scoring\n",
+        "def run(raw_data):\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",
+        "        return result.tolist()\n",
+        "    except Exception as e:\n",
+        "        error = str(e)\n",
+        "        print (error + time.strftime(\"%H:%M:%S\"))\n",
+        "        return error"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 5. *Create myenv.yml file*"
+      ]
+    },
+    {
+      "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'])\n",
+        "\n",
+        "with open(\"myenv.yml\",\"w\") as f:\n",
+        "    f.write(myenv.serialize_to_string())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 6. Create your new Image"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.image import ContainerImage\n",
+        "\n",
+        "image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
+        "                                                  runtime = \"python\",\n",
+        "                                                  conda_file = \"myenv.yml\",\n",
+        "                                                  description = \"Image with ridge regression model\",\n",
+        "                                                  tags = {'area': \"diabetes\", 'type': \"regression\"}\n",
+        "                                                 )\n",
+        "\n",
+        "image = ContainerImage.create(name = \"myimage1\",\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)"
+      ]
+    },
+    {
+      "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": {},
+      "source": [
+        "## 7. Deploy to AKS service"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create AKS compute if you haven't done so."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Use the default configuration (can also provide parameters to customize)\n",
+        "prov_config = AksCompute.provisioning_configuration()\n",
+        "\n",
+        "aks_name = 'my-aks-test3' \n",
+        "# Create the cluster\n",
+        "aks_target = ComputeTarget.create(workspace = ws, \n",
+        "                                  name = aks_name, \n",
+        "                                  provisioning_configuration = prov_config)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%time\n",
+        "aks_target.wait_for_completion(show_output = True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(aks_target.provisioning_state)\n",
+        "print(aks_target.provisioning_errors)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "If you already have a cluster you can attach the service to it:"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "```python \n",
+        "%%time\n",
+        "resource_id = '/subscriptions/<subscriptionid>/resourcegroups/<resourcegroupname>/providers/Microsoft.ContainerService/managedClusters/<aksservername>'\n",
+        "create_name= 'myaks4'\n",
+        "attach_config = AksCompute.attach_configuration(resource_id=resource_id)\n",
+        "aks_target = ComputeTarget.attach(workspace = ws, \n",
+        "                                  name = create_name, \n",
+        "                                  attach_configuration=attach_config)\n",
+        "## Wait for the operation to complete\n",
+        "aks_target.wait_for_provisioning(True)```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### a. *Activate App Insights through updating AKS Webservice configuration*\n",
+        "In order to enable App Insights in your service you will need to update your AKS configuration file:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "#Set the web service configuration\n",
+        "aks_config = AksWebservice.deploy_configuration(enable_app_insights=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### b. Deploy your service"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "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",
+        "                                               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.\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 8. Test your service "
+      ]
+    },
+    {
+      "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')\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\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 9. See your service telemetry in App Insights\n",
+        "1. Go to the [Azure Portal](https://portal.azure.com/)\n",
+        "2. All resources--> Select the subscription/resource group where you created your Workspace--> Select the App Insights type\n",
+        "3. Click on the AppInsights resource. You'll see a highlevel dashboard with information on Requests, Server response time and availability.\n",
+        "4. Click on the top banner \"Analytics\"\n",
+        "5. In the \"Schema\" section select \"traces\" and run your query.\n",
+        "6. Voila! All your custom traces should be there."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Disable App Insights"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "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()"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python [default]",
-   "language": "python",
-   "name": "python3"
+  "metadata": {
+    "authors": [
+      {
+        "name": "jocier"
+      }
+    ],
+    "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"
+    }
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,477 +1,471 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Enabling Data Collection for Models in Production\n",
-    "With this notebook, you can learn how to collect input model data from your Azure Machine Learning service in an Azure Blob storage. Once enabled, this data collected gives you the opportunity:\n",
-    "\n",
-    "* Monitor data drifts as production data enters your model\n",
-    "* Make better decisions on when to retrain or optimize your model\n",
-    "* Retrain your model with the data collected\n",
-    "\n",
-    "## What data is collected?\n",
-    "* Model input data (voice, images, and video are not supported) from services deployed in Azure Kubernetes Cluster (AKS)\n",
-    "* Model predictions using production input data.\n",
-    "\n",
-    "**Note:** pre-aggregation or pre-calculations on this data are done by user and not included in this version of the product.\n",
-    "\n",
-    "## What is different compared to standard production deployment process?\n",
-    "1. Update scoring file.\n",
-    "2. Update yml file with new dependency.\n",
-    "3. Update aks configuration.\n",
-    "4. Build new image and deploy it. "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 1. Import your dependencies"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "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)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 2. Set up your configuration and create a workspace\n",
-    "Follow Notebook 00 instructions to do this.\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "ws = Workspace.from_config()\n",
-    "print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 3. Register Model\n",
-    "Register an existing trained model, add descirption and tags."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#Register the model\n",
-    "from azureml.core.model import Model\n",
-    "model = Model.register(model_path = \"sklearn_regression_model.pkl\", # this points to a local file\n",
-    "                       model_name = \"sklearn_regression_model.pkl\", # this is the name the model is registered as\n",
-    "                       tags = {'area': \"diabetes\", 'type': \"regression\"},\n",
-    "                       description = \"Ridge regression model to predict diabetes\",\n",
-    "                       workspace = ws)\n",
-    "\n",
-    "print(model.name, model.description, model.version)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 4. *Update your scoring file with Data Collection*\n",
-    "The file below, compared to the file used in notebook 11, has the following changes:\n",
-    "### a. Import the module\n",
-    "```python \n",
-    "from azureml.monitoring import ModelDataCollector```\n",
-    "### b. In your init function add:\n",
-    "```python \n",
-    "global inputs_dc, prediction_d\n",
-    "inputs_dc = ModelDataCollector(\"best_model\", identifier=\"inputs\", feature_names=[\"feat1\", \"feat2\", \"feat3\", \"feat4\", \"feat5\", \"Feat6\"])\n",
-    "prediction_dc = ModelDataCollector(\"best_model\", identifier=\"predictions\", feature_names=[\"prediction1\", \"prediction2\"])```\n",
-    "    \n",
-    "* Identifier: Identifier is later used for building the folder structure in your Blob, it can be used to divide \"raw\" data versus \"processed\".\n",
-    "* CorrelationId: is an optional parameter, you do not need to set it up if your model doesn't require it. Having a correlationId in place does help you for easier mapping with other data. (Examples include: LoanNumber, CustomerId, etc.)\n",
-    "* Feature Names: These need to be set up in the order of your features in order for them to have column names when the .csv is created.\n",
-    "\n",
-    "### c. In your run function add:\n",
-    "```python\n",
-    "inputs_dc.collect(data)\n",
-    "prediction_dc.collect(result)```"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%writefile score.py\n",
-    "import pickle\n",
-    "import json\n",
-    "import numpy \n",
-    "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",
-    "    global model\n",
-    "    print (\"model initialized\" + time.strftime(\"%H:%M:%S\"))\n",
-    "    # note here \"sklearn_regression_model.pkl\" is the name of the model registered under the workspace\n",
-    "    # this call should return the path to the model.pkl file on the local disk.\n",
-    "    model_path = Model.get_model_path(model_name = 'sklearn_regression_model.pkl')\n",
-    "    # deserialize the model file back into a sklearn model\n",
-    "    model = joblib.load(model_path)\n",
-    "    global inputs_dc, prediction_dc\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",
-    "    # 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 (\"saving input data\" + time.strftime(\"%H:%M:%S\"))\n",
-    "        inputs_dc.collect(data) #this call is saving our input data into our blob\n",
-    "        prediction_dc.collect(result)#this call is saving our prediction data into our blob\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",
-    "        print (error + time.strftime(\"%H:%M:%S\"))\n",
-    "        return error"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 5. *Update your myenv.yml file with the required module*"
-   ]
-  },
-  {
-   "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'])\n",
-    "myenv.add_pip_package(\"azureml-monitoring\")\n",
-    "\n",
-    "with open(\"myenv.yml\",\"w\") as f:\n",
-    "    f.write(myenv.serialize_to_string())"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 6. Create your new Image"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.image import ContainerImage\n",
-    "\n",
-    "image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
-    "                                                  runtime = \"python\",\n",
-    "                                                  conda_file = \"myenv.yml\",\n",
-    "                                                  description = \"Image with ridge regression model\",\n",
-    "                                                  tags = {'area': \"diabetes\", 'type': \"regression\"}\n",
-    "                                                 )\n",
-    "\n",
-    "image = ContainerImage.create(name = \"myimage1\",\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)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(model.name, model.description, model.version)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 7. Deploy to AKS service"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Create AKS compute if you haven't done so."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Use the default configuration (can also provide parameters to customize)\n",
-    "prov_config = AksCompute.provisioning_configuration()\n",
-    "\n",
-    "aks_name = 'my-aks-test1' \n",
-    "# Create the cluster\n",
-    "aks_target = ComputeTarget.create(workspace = ws, \n",
-    "                                  name = aks_name, \n",
-    "                                  provisioning_configuration = prov_config)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%time\n",
-    "aks_target.wait_for_completion(show_output = True)\n",
-    "print(aks_target.provisioning_state)\n",
-    "print(aks_target.provisioning_errors)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "If you already have a cluster you can attach the service to it:"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "scrolled": true
-   },
-   "source": [
-    "```python \n",
-    "    %%time\n",
-    "    resource_id = '/subscriptions/<subscriptionid>/resourcegroups/<resourcegroupname>/providers/Microsoft.ContainerService/managedClusters/<aksservername>'\n",
-    "    create_name= 'myaks4'\n",
-    "    attach_config = AksCompute.attach_configuration(resource_id=resource_id)\n",
-    "    aks_target = ComputeTarget.attach(workspace = ws, \n",
-    "                                      name = create_name, \n",
-    "                                      attach_configuration=attach_config)\n",
-    "    ## Wait for the operation to complete\n",
-    "    aks_target.wait_for_provisioning(True)```"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### a. *Activate Data Collection and App Insights through updating AKS Webservice configuration*\n",
-    "In order to enable Data Collection and App Insights in your service you will need to update your AKS configuration file:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#Set the web service configuration\n",
-    "aks_config = AksWebservice.deploy_configuration(collect_model_data=True, enable_app_insights=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### b. Deploy your service"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "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",
-    "                                               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\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 8. Test your service and send some data\n",
-    "**Note**: It will take around 15 mins for your data to appear in your blob.\n",
-    "The data will appear in your Azure Blob following this format:\n",
-    "\n",
-    "/modeldata/subscriptionid/resourcegroupname/workspacename/webservicename/modelname/modelversion/identifier/year/month/day/data.csv "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%time\n",
-    "import json\n",
-    "\n",
-    "test_sample = json.dumps({'data': [\n",
-    "    [1,2,3,4,54,6,7,8,88,10], \n",
-    "    [10,9,8,37,36,45,4,33,2,1]\n",
-    "]})\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\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 9. Validate you data and analyze it\n",
-    "You can look into your data following this path format in your Azure Blob (it takes up to 15 minutes for the data to appear):\n",
-    "\n",
-    "/modeldata/**subscriptionid>**/**resourcegroupname>**/**workspacename>**/**webservicename>**/**modelname>**/**modelversion>>**/**identifier>**/*year/month/day*/data.csv \n",
-    "\n",
-    "For doing further analysis you have multiple options:"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### a. Create DataBricks cluter and connect it to your blob\n",
-    "https://docs.microsoft.com/en-us/azure/azure-databricks/quickstart-create-databricks-workspace-portal or in your databricks workspace you can look for the template \"Azure Blob Storage Import Example Notebook\".\n",
-    "\n",
-    "\n",
-    "Here is an example for setting up the file location to extract the relevant data:\n",
-    "\n",
-    "<code> file_location = \"wasbs://mycontainer@storageaccountname.blob.core.windows.net/unknown/unknown/unknown-bigdataset-unknown/my_iterate_parking_inputs/2018/&deg;/&deg;/data.csv\" \n",
-    "file_type = \"csv\"</code>\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### b. Connect Blob to Power Bi (Small Data only)\n",
-    "1. Download and Open PowerBi Desktop\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 “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."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Disable Data Collection"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "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": "marthalc"
-   }
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Enabling Data Collection for Models in Production\n",
+        "With this notebook, you can learn how to collect input model data from your Azure Machine Learning service in an Azure Blob storage. Once enabled, this data collected gives you the opportunity:\n",
+        "\n",
+        "* Monitor data drifts as production data enters your model\n",
+        "* Make better decisions on when to retrain or optimize your model\n",
+        "* Retrain your model with the data collected\n",
+        "\n",
+        "## What data is collected?\n",
+        "* Model input data (voice, images, and video are not supported) from services deployed in Azure Kubernetes Cluster (AKS)\n",
+        "* Model predictions using production input data.\n",
+        "\n",
+        "**Note:** pre-aggregation or pre-calculations on this data are done by user and not included in this version of the product.\n",
+        "\n",
+        "## What is different compared to standard production deployment process?\n",
+        "1. Update scoring file.\n",
+        "2. Update yml file with new dependency.\n",
+        "3. Update aks configuration.\n",
+        "4. Build new image and deploy it. "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 1. Import your dependencies"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core import Workspace\n",
+        "from azureml.core.compute import AksCompute, ComputeTarget\n",
+        "from azureml.core.webservice import Webservice, AksWebservice\n",
+        "import azureml.core\n",
+        "print(azureml.core.VERSION)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 2. Set up your configuration and create a workspace"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 3. Register Model\n",
+        "Register an existing trained model, add descirption and tags."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "#Register the model\n",
+        "from azureml.core.model import Model\n",
+        "model = Model.register(model_path = \"sklearn_regression_model.pkl\", # this points to a local file\n",
+        "                       model_name = \"sklearn_regression_model.pkl\", # this is the name the model is registered as\n",
+        "                       tags = {'area': \"diabetes\", 'type': \"regression\"},\n",
+        "                       description = \"Ridge regression model to predict diabetes\",\n",
+        "                       workspace = ws)\n",
+        "\n",
+        "print(model.name, model.description, model.version)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 4. *Update your scoring file with Data Collection*\n",
+        "The file below, compared to the file used in notebook 11, has the following changes:\n",
+        "### a. Import the module\n",
+        "```python \n",
+        "from azureml.monitoring import ModelDataCollector```\n",
+        "### b. In your init function add:\n",
+        "```python \n",
+        "global inputs_dc, prediction_d\n",
+        "inputs_dc = ModelDataCollector(\"best_model\", identifier=\"inputs\", feature_names=[\"feat1\", \"feat2\", \"feat3\", \"feat4\", \"feat5\", \"Feat6\"])\n",
+        "prediction_dc = ModelDataCollector(\"best_model\", identifier=\"predictions\", feature_names=[\"prediction1\", \"prediction2\"])```\n",
+        "    \n",
+        "* Identifier: Identifier is later used for building the folder structure in your Blob, it can be used to divide \"raw\" data versus \"processed\".\n",
+        "* CorrelationId: is an optional parameter, you do not need to set it up if your model doesn't require it. Having a correlationId in place does help you for easier mapping with other data. (Examples include: LoanNumber, CustomerId, etc.)\n",
+        "* Feature Names: These need to be set up in the order of your features in order for them to have column names when the .csv is created.\n",
+        "\n",
+        "### c. In your run function add:\n",
+        "```python\n",
+        "inputs_dc.collect(data)\n",
+        "prediction_dc.collect(result)```"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%writefile score.py\n",
+        "import pickle\n",
+        "import json\n",
+        "import numpy \n",
+        "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",
+        "    global model\n",
+        "    print (\"model initialized\" + time.strftime(\"%H:%M:%S\"))\n",
+        "    # note here \"sklearn_regression_model.pkl\" is the name of the model registered under the workspace\n",
+        "    # this call should return the path to the model.pkl file on the local disk.\n",
+        "    model_path = Model.get_model_path(model_name = 'sklearn_regression_model.pkl')\n",
+        "    # deserialize the model file back into a sklearn model\n",
+        "    model = joblib.load(model_path)\n",
+        "    global inputs_dc, prediction_dc\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",
+        "    # 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 (\"saving input data\" + time.strftime(\"%H:%M:%S\"))\n",
+        "        inputs_dc.collect(data) #this call is saving our input data into our blob\n",
+        "        prediction_dc.collect(result)#this call is saving our prediction data into our blob\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",
+        "        print (error + time.strftime(\"%H:%M:%S\"))\n",
+        "        return error"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 5. *Update your myenv.yml file with the required module*"
+      ]
+    },
+    {
+      "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'])\n",
+        "myenv.add_pip_package(\"azureml-monitoring\")\n",
+        "\n",
+        "with open(\"myenv.yml\",\"w\") as f:\n",
+        "    f.write(myenv.serialize_to_string())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 6. Create your new Image"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.image import ContainerImage\n",
+        "\n",
+        "image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
+        "                                                  runtime = \"python\",\n",
+        "                                                  conda_file = \"myenv.yml\",\n",
+        "                                                  description = \"Image with ridge regression model\",\n",
+        "                                                  tags = {'area': \"diabetes\", 'type': \"regression\"}\n",
+        "                                                 )\n",
+        "\n",
+        "image = ContainerImage.create(name = \"myimage1\",\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)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(model.name, model.description, model.version)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 7. Deploy to AKS service"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create AKS compute if you haven't done so."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Use the default configuration (can also provide parameters to customize)\n",
+        "prov_config = AksCompute.provisioning_configuration()\n",
+        "\n",
+        "aks_name = 'my-aks-test1' \n",
+        "# Create the cluster\n",
+        "aks_target = ComputeTarget.create(workspace = ws, \n",
+        "                                  name = aks_name, \n",
+        "                                  provisioning_configuration = prov_config)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%time\n",
+        "aks_target.wait_for_completion(show_output = True)\n",
+        "print(aks_target.provisioning_state)\n",
+        "print(aks_target.provisioning_errors)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "If you already have a cluster you can attach the service to it:"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "```python \n",
+        "    %%time\n",
+        "    resource_id = '/subscriptions/<subscriptionid>/resourcegroups/<resourcegroupname>/providers/Microsoft.ContainerService/managedClusters/<aksservername>'\n",
+        "    create_name= 'myaks4'\n",
+        "    attach_config = AksCompute.attach_configuration(resource_id=resource_id)\n",
+        "    aks_target = ComputeTarget.attach(workspace = ws, \n",
+        "                                      name = create_name, \n",
+        "                                      attach_configuration=attach_config)\n",
+        "    ## Wait for the operation to complete\n",
+        "    aks_target.wait_for_provisioning(True)```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### a. *Activate Data Collection and App Insights through updating AKS Webservice configuration*\n",
+        "In order to enable Data Collection and App Insights in your service you will need to update your AKS configuration file:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "#Set the web service configuration\n",
+        "aks_config = AksWebservice.deploy_configuration(collect_model_data=True, enable_app_insights=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### b. Deploy your service"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "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",
+        "                                               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\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 8. Test your service and send some data\n",
+        "**Note**: It will take around 15 mins for your data to appear in your blob.\n",
+        "The data will appear in your Azure Blob following this format:\n",
+        "\n",
+        "/modeldata/subscriptionid/resourcegroupname/workspacename/webservicename/modelname/modelversion/identifier/year/month/day/data.csv "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%time\n",
+        "import json\n",
+        "\n",
+        "test_sample = json.dumps({'data': [\n",
+        "    [1,2,3,4,54,6,7,8,88,10], \n",
+        "    [10,9,8,37,36,45,4,33,2,1]\n",
+        "]})\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\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 9. Validate you data and analyze it\n",
+        "You can look into your data following this path format in your Azure Blob (it takes up to 15 minutes for the data to appear):\n",
+        "\n",
+        "/modeldata/**subscriptionid>**/**resourcegroupname>**/**workspacename>**/**webservicename>**/**modelname>**/**modelversion>>**/**identifier>**/*year/month/day*/data.csv \n",
+        "\n",
+        "For doing further analysis you have multiple options:"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### a. Create DataBricks cluter and connect it to your blob\n",
+        "https://docs.microsoft.com/en-us/azure/azure-databricks/quickstart-create-databricks-workspace-portal or in your databricks workspace you can look for the template \"Azure Blob Storage Import Example Notebook\".\n",
+        "\n",
+        "\n",
+        "Here is an example for setting up the file location to extract the relevant data:\n",
+        "\n",
+        "<code> file_location = \"wasbs://mycontainer@storageaccountname.blob.core.windows.net/unknown/unknown/unknown-bigdataset-unknown/my_iterate_parking_inputs/2018/&deg;/&deg;/data.csv\" \n",
+        "file_type = \"csv\"</code>\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "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",
+        "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",
+        "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."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Disable Data Collection"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "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()"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python [default]",
-   "language": "python",
-   "name": "python3"
+  "metadata": {
+    "authors": [
+      {
+        "name": "jocier"
+      }
+    ],
+    "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"
+    }
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -4,7 +4,7 @@ These tutorials show how to create and deploy Open Neural Network eXchange ([ONN
 
 ## Tutorials
 
-0. [Configure your Azure Machine Learning Workspace](https://github.com/Azure/MachineLearningNotebooks/blob/master/configuration.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)

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

@@ -1,435 +1,435 @@
 {
- "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": [
-    "# YOLO Real-time Object Detection using ONNX on AzureML\n",
-    "\n",
-    "This example shows how to convert the TinyYOLO model from CoreML to ONNX and operationalize it as a web service using Azure Machine Learning services and the ONNX Runtime.\n",
-    "\n",
-    "## What is ONNX\n",
-    "ONNX is an open format for representing machine learning and deep learning models. ONNX enables open and interoperable AI by enabling data scientists and developers to use the tools of their choice without worrying about lock-in and flexibility to deploy to a variety of platforms. ONNX is developed and supported by a community of partners including Microsoft, Facebook, and Amazon. For more information, explore the [ONNX website](http://onnx.ai).\n",
-    "\n",
-    "## YOLO Details\n",
-    "You Only Look Once (YOLO) is a state-of-the-art, real-time object detection system. For more information about YOLO, please visit the [YOLO website](https://pjreddie.com/darknet/yolo/)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Prerequisites\n",
-    "\n",
-    "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 [00.configuration.ipynb](../00.configuration.ipynb) notebook 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": [
-    "#### Install necessary packages\n",
-    "\n",
-    "You'll need to run the following commands to use this tutorial:\n",
-    "\n",
-    "```sh\n",
-    "pip install onnxmltools\n",
-    "pip install coremltools  # use this on Linux and Mac\n",
-    "pip install git+https://github.com/apple/coremltools  # use this on Windows\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Convert model to ONNX\n",
-    "\n",
-    "First we download the CoreML model. We use the CoreML model listed at https://coreml.store/tinyyolo. This may take a few minutes."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import urllib.request\n",
-    "\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"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Then we use ONNXMLTools to convert the model."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import onnxmltools\n",
-    "import coremltools\n",
-    "\n",
-    "# Load a CoreML model\n",
-    "coreml_model = coremltools.utils.load_spec('TinyYOLO.mlmodel')\n",
-    "\n",
-    "# Convert from CoreML into ONNX\n",
-    "onnx_model = onnxmltools.convert_coreml(coreml_model, 'TinyYOLOv2')\n",
-    "\n",
-    "# Save ONNX model\n",
-    "onnxmltools.utils.save_model(onnx_model, 'tinyyolov2.onnx')\n",
-    "\n",
-    "import os\n",
-    "print(os.path.getsize('tinyyolov2.onnx'))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Deploying as a web service with Azure ML\n",
-    "\n",
-    "### Load Azure ML workspace\n",
-    "\n",
-    "We begin by instantiating a workspace object from the existing workspace created earlier in the configuration notebook."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core import Workspace\n",
-    "\n",
-    "ws = Workspace.from_config()\n",
-    "print(ws.name, ws.location, ws.resource_group, sep = '\\n')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Registering your model with Azure ML\n",
-    "\n",
-    "Now we upload the model and register it in the workspace."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.model import Model\n",
-    "\n",
-    "model = Model.register(model_path = \"tinyyolov2.onnx\",\n",
-    "                       model_name = \"tinyyolov2\",\n",
-    "                       tags = {\"onnx\": \"demo\"},\n",
-    "                       description = \"TinyYOLO\",\n",
-    "                       workspace = ws)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Displaying your registered models\n",
-    "\n",
-    "You can optionally list out all the models that you have registered in this workspace."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "models = ws.models\n",
-    "for name, m in models.items():\n",
-    "    print(\"Name:\", name,\"\\tVersion:\", m.version, \"\\tDescription:\", m.description, m.tags)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Write scoring file\n",
-    "\n",
-    "We are now going to deploy our ONNX model on Azure ML using the ONNX Runtime. We begin by writing a score.py file that will be invoked by the web service call. The `init()` function is called once when the container is started so we load the model using the ONNX Runtime into a global session object."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%writefile score.py\n",
-    "import json\n",
-    "import time\n",
-    "import sys\n",
-    "import os\n",
-    "from azureml.core.model import Model\n",
-    "import numpy as np    # we're going to use numpy to process input and output data\n",
-    "import onnxruntime    # to inference ONNX models, we use the ONNX Runtime\n",
-    "\n",
-    "def init():\n",
-    "    global session\n",
-    "    model = Model.get_model_path(model_name = 'tinyyolov2')\n",
-    "    session = onnxruntime.InferenceSession(model)\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",
-    "    return np.array(result).tolist()\n",
-    "\n",
-    "def run(input_data_json):\n",
-    "    try:\n",
-    "        start = time.time()   # start timer\n",
-    "        input_data = preprocess(input_data_json)\n",
-    "        input_name = session.get_inputs()[0].name  # get the id of the first input of the model   \n",
-    "        result = session.run([], {input_name: input_data})\n",
-    "        end = time.time()     # stop timer\n",
-    "        return {\"result\": postprocess(result),\n",
-    "                \"time\": end - start}\n",
-    "    except Exception as e:\n",
-    "        result = str(e)\n",
-    "        return {\"error\": result}"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Create container image\n",
-    "First we create a YAML file that specifies which dependencies we would like to see in our container."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.conda_dependencies import CondaDependencies \n",
-    "\n",
-    "myenv = CondaDependencies.create(pip_packages=[\"numpy\",\"onnxruntime\",\"azureml-core\"])\n",
-    "\n",
-    "with open(\"myenv.yml\",\"w\") as f:\n",
-    "    f.write(myenv.serialize_to_string())"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Then we have Azure ML create the container. This step will likely take a few minutes."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.image import ContainerImage\n",
-    "\n",
-    "image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
-    "                                                  runtime = \"python\",\n",
-    "                                                  conda_file = \"myenv.yml\",\n",
-    "                                                  description = \"TinyYOLO ONNX Demo\",\n",
-    "                                                  tags = {\"demo\": \"onnx\"}\n",
-    "                                                 )\n",
-    "\n",
-    "\n",
-    "image = ContainerImage.create(name = \"onnxyolo\",\n",
-    "                              models = [model],\n",
-    "                              image_config = image_config,\n",
-    "                              workspace = ws)\n",
-    "\n",
-    "image.wait_for_creation(show_output = True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "In case you need to debug your code, the next line of code accesses the log file."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(image.image_build_log_uri)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We're all set! Let's get our model chugging.\n",
-    "\n",
-    "### Deploy the container image"
-   ]
-  },
-  {
-   "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 = {'demo': 'onnx'}, \n",
-    "                                               description = 'web service for TinyYOLO ONNX model')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The following cell will likely take a few minutes to run as well."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.webservice import Webservice\n",
-    "from random import randint\n",
-    "\n",
-    "aci_service_name = 'onnx-tinyyolo'+str(randint(0,100))\n",
-    "print(\"Service\", aci_service_name)\n",
-    "\n",
-    "aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
-    "                                           image = image,\n",
-    "                                           name = aci_service_name,\n",
-    "                                           workspace = ws)\n",
-    "\n",
-    "aci_service.wait_for_deployment(True)\n",
-    "print(aci_service.state)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "In case the deployment fails, you can check the logs. Make sure to delete your aci_service before trying again."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "if aci_service.state != 'Healthy':\n",
-    "    # run this command for debugging.\n",
-    "    print(aci_service.get_logs())\n",
-    "    aci_service.delete()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Success!\n",
-    "\n",
-    "If you've made it this far, you've deployed a working web service that does object detection using an ONNX model. You can get the URL for the webservice with the code below."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(aci_service.scoring_uri)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "When you are eventually done using the web service, remember to delete it."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#aci_service.delete()"
-   ]
-  }
- ],
- "metadata": {
-  "authors": [
-   {
-    "name": "onnx"
-   }
+  "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": [
+        "# YOLO Real-time Object Detection using ONNX on AzureML\n",
+        "\n",
+        "This example shows how to convert the TinyYOLO model from CoreML to ONNX and operationalize it as a web service using Azure Machine Learning services and the ONNX Runtime.\n",
+        "\n",
+        "## What is ONNX\n",
+        "ONNX is an open format for representing machine learning and deep learning models. ONNX enables open and interoperable AI by enabling data scientists and developers to use the tools of their choice without worrying about lock-in and flexibility to deploy to a variety of platforms. ONNX is developed and supported by a community of partners including Microsoft, Facebook, and Amazon. For more information, explore the [ONNX website](http://onnx.ai).\n",
+        "\n",
+        "## YOLO Details\n",
+        "You Only Look Once (YOLO) is a state-of-the-art, real-time object detection system. For more information about YOLO, please visit the [YOLO website](https://pjreddie.com/darknet/yolo/)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Prerequisites\n",
+        "\n",
+        "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",
+        "    * 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": [
+        "#### Install necessary packages\n",
+        "\n",
+        "You'll need to run the following commands to use this tutorial:\n",
+        "\n",
+        "```sh\n",
+        "pip install onnxmltools\n",
+        "pip install coremltools  # use this on Linux and Mac\n",
+        "pip install git+https://github.com/apple/coremltools  # use this on Windows\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "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."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "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"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Then we use ONNXMLTools to convert the model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import onnxmltools\n",
+        "import coremltools\n",
+        "\n",
+        "# Load a CoreML model\n",
+        "coreml_model = coremltools.utils.load_spec('TinyYOLO.mlmodel')\n",
+        "\n",
+        "# Convert from CoreML into ONNX\n",
+        "onnx_model = onnxmltools.convert_coreml(coreml_model, 'TinyYOLOv2')\n",
+        "\n",
+        "# Save ONNX model\n",
+        "onnxmltools.utils.save_model(onnx_model, 'tinyyolov2.onnx')\n",
+        "\n",
+        "import os\n",
+        "print(os.path.getsize('tinyyolov2.onnx'))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Deploying as a web service with Azure ML\n",
+        "\n",
+        "### Load Azure ML workspace\n",
+        "\n",
+        "We begin by instantiating a workspace object from the existing workspace created earlier in the configuration notebook."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core import Workspace\n",
+        "\n",
+        "ws = Workspace.from_config()\n",
+        "print(ws.name, ws.location, ws.resource_group, sep = '\\n')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Registering your model with Azure ML\n",
+        "\n",
+        "Now we upload the model and register it in the workspace."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.model import Model\n",
+        "\n",
+        "model = Model.register(model_path = \"tinyyolov2.onnx\",\n",
+        "                       model_name = \"tinyyolov2\",\n",
+        "                       tags = {\"onnx\": \"demo\"},\n",
+        "                       description = \"TinyYOLO\",\n",
+        "                       workspace = ws)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Displaying your registered models\n",
+        "\n",
+        "You can optionally list out all the models that you have registered in this workspace."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "models = ws.models\n",
+        "for name, m in models.items():\n",
+        "    print(\"Name:\", name,\"\\tVersion:\", m.version, \"\\tDescription:\", m.description, m.tags)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Write scoring file\n",
+        "\n",
+        "We are now going to deploy our ONNX model on Azure ML using the ONNX Runtime. We begin by writing a score.py file that will be invoked by the web service call. The `init()` function is called once when the container is started so we load the model using the ONNX Runtime into a global session object."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%writefile score.py\n",
+        "import json\n",
+        "import time\n",
+        "import sys\n",
+        "import os\n",
+        "from azureml.core.model import Model\n",
+        "import numpy as np    # we're going to use numpy to process input and output data\n",
+        "import onnxruntime    # to inference ONNX models, we use the ONNX Runtime\n",
+        "\n",
+        "def init():\n",
+        "    global session\n",
+        "    model = Model.get_model_path(model_name = 'tinyyolov2')\n",
+        "    session = onnxruntime.InferenceSession(model)\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",
+        "    return np.array(result).tolist()\n",
+        "\n",
+        "def run(input_data_json):\n",
+        "    try:\n",
+        "        start = time.time()   # start timer\n",
+        "        input_data = preprocess(input_data_json)\n",
+        "        input_name = session.get_inputs()[0].name  # get the id of the first input of the model   \n",
+        "        result = session.run([], {input_name: input_data})\n",
+        "        end = time.time()     # stop timer\n",
+        "        return {\"result\": postprocess(result),\n",
+        "                \"time\": end - start}\n",
+        "    except Exception as e:\n",
+        "        result = str(e)\n",
+        "        return {\"error\": result}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create container image\n",
+        "First we create a YAML file that specifies which dependencies we would like to see in our container."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.conda_dependencies import CondaDependencies \n",
+        "\n",
+        "myenv = CondaDependencies.create(pip_packages=[\"numpy\",\"onnxruntime\",\"azureml-core\"])\n",
+        "\n",
+        "with open(\"myenv.yml\",\"w\") as f:\n",
+        "    f.write(myenv.serialize_to_string())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Then we have Azure ML create the container. This step will likely take a few minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.image import ContainerImage\n",
+        "\n",
+        "image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
+        "                                                  runtime = \"python\",\n",
+        "                                                  conda_file = \"myenv.yml\",\n",
+        "                                                  description = \"TinyYOLO ONNX Demo\",\n",
+        "                                                  tags = {\"demo\": \"onnx\"}\n",
+        "                                                 )\n",
+        "\n",
+        "\n",
+        "image = ContainerImage.create(name = \"onnxyolo\",\n",
+        "                              models = [model],\n",
+        "                              image_config = image_config,\n",
+        "                              workspace = ws)\n",
+        "\n",
+        "image.wait_for_creation(show_output = True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "In case you need to debug your code, the next line of code accesses the log file."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(image.image_build_log_uri)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We're all set! Let's get our model chugging.\n",
+        "\n",
+        "### Deploy the container image"
+      ]
+    },
+    {
+      "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 = {'demo': 'onnx'}, \n",
+        "                                               description = 'web service for TinyYOLO ONNX model')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "The following cell will likely take a few minutes to run as well."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.webservice import Webservice\n",
+        "from random import randint\n",
+        "\n",
+        "aci_service_name = 'onnx-tinyyolo'+str(randint(0,100))\n",
+        "print(\"Service\", aci_service_name)\n",
+        "\n",
+        "aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
+        "                                           image = image,\n",
+        "                                           name = aci_service_name,\n",
+        "                                           workspace = ws)\n",
+        "\n",
+        "aci_service.wait_for_deployment(True)\n",
+        "print(aci_service.state)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "In case the deployment fails, you can check the logs. Make sure to delete your aci_service before trying again."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "if aci_service.state != 'Healthy':\n",
+        "    # run this command for debugging.\n",
+        "    print(aci_service.get_logs())\n",
+        "    aci_service.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Success!\n",
+        "\n",
+        "If you've made it this far, you've deployed a working web service that does object detection using an ONNX model. You can get the URL for the webservice with the code below."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(aci_service.scoring_uri)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "When you are eventually done using the web service, remember to delete it."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "#aci_service.delete()"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "metadata": {
+    "authors": [
+      {
+        "name": "viswamy"
+      }
+    ],
+    "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"
+    }
   },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.5.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,419 +1,419 @@
 {
- "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": [
-    "# ResNet50 Image Classification using ONNX and AzureML\n",
-    "\n",
-    "This example shows how to deploy the ResNet50 ONNX model as a web service using Azure Machine Learning services and the ONNX Runtime.\n",
-    "\n",
-    "## What is ONNX\n",
-    "ONNX is an open format for representing machine learning and deep learning models. ONNX enables open and interoperable AI by enabling data scientists and developers to use the tools of their choice without worrying about lock-in and flexibility to deploy to a variety of platforms. ONNX is developed and supported by a community of partners including Microsoft, Facebook, and Amazon. For more information, explore the [ONNX website](http://onnx.ai).\n",
-    "\n",
-    "## ResNet50 Details\n",
-    "ResNet classifies the major object in an input image into a set of 1000 pre-defined classes. For more information about the ResNet50 model and how it was created can be found on the [ONNX Model Zoo github](https://github.com/onnx/models/tree/master/models/image_classification/resnet). "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Prerequisites\n",
-    "\n",
-    "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 [00.configuration.ipynb](../00.configuration.ipynb) notebook 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": [
-    "#### Download pre-trained ONNX model from ONNX Model Zoo.\n",
-    "\n",
-    "Download the [ResNet50v2 model and test data](https://s3.amazonaws.com/onnx-model-zoo/resnet/resnet50v2/resnet50v2.tar.gz) and extract it in the same folder as this tutorial notebook.\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import urllib.request\n",
-    "\n",
-    "onnx_model_url = \"https://s3.amazonaws.com/onnx-model-zoo/resnet/resnet50v2/resnet50v2.tar.gz\"\n",
-    "urllib.request.urlretrieve(onnx_model_url, filename=\"resnet50v2.tar.gz\")\n",
-    "\n",
-    "!tar xvzf resnet50v2.tar.gz"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Deploying as a web service with Azure ML"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Load your Azure ML workspace\n",
-    "\n",
-    "We begin by instantiating a workspace object from the existing workspace created earlier in the configuration notebook."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core import Workspace\n",
-    "\n",
-    "ws = Workspace.from_config()\n",
-    "print(ws.name, ws.location, ws.resource_group, sep = '\\n')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Register your model with Azure ML\n",
-    "\n",
-    "Now we upload the model and register it in the workspace."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.model import Model\n",
-    "\n",
-    "model = Model.register(model_path = \"resnet50v2/resnet50v2.onnx\",\n",
-    "                       model_name = \"resnet50v2\",\n",
-    "                       tags = {\"onnx\": \"demo\"},\n",
-    "                       description = \"ResNet50v2 from ONNX Model Zoo\",\n",
-    "                       workspace = ws)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Displaying your registered models\n",
-    "\n",
-    "You can optionally list out all the models that you have registered in this workspace."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "models = ws.models\n",
-    "for name, m in models.items():\n",
-    "    print(\"Name:\", name,\"\\tVersion:\", m.version, \"\\tDescription:\", m.description, m.tags)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Write scoring file\n",
-    "\n",
-    "We are now going to deploy our ONNX model on Azure ML using the ONNX Runtime. We begin by writing a score.py file that will be invoked by the web service call. The `init()` function is called once when the container is started so we load the model using the ONNX Runtime into a global session object."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%writefile score.py\n",
-    "import json\n",
-    "import time\n",
-    "import sys\n",
-    "import os\n",
-    "from azureml.core.model import Model\n",
-    "import numpy as np    # we're going to use numpy to process input and output data\n",
-    "import onnxruntime    # to inference ONNX models, we use the ONNX Runtime\n",
-    "\n",
-    "def softmax(x):\n",
-    "    x = x.reshape(-1)\n",
-    "    e_x = np.exp(x - np.max(x))\n",
-    "    return e_x / e_x.sum(axis=0)\n",
-    "\n",
-    "def init():\n",
-    "    global session\n",
-    "    model = Model.get_model_path(model_name = 'resnet50v2')\n",
-    "    session = onnxruntime.InferenceSession(model, None)\n",
-    "\n",
-    "def preprocess(input_data_json):\n",
-    "    # convert the JSON data into the tensor input\n",
-    "    img_data = np.array(json.loads(input_data_json)['data']).astype('float32')\n",
-    "    \n",
-    "    #normalize\n",
-    "    mean_vec = np.array([0.485, 0.456, 0.406])\n",
-    "    stddev_vec = np.array([0.229, 0.224, 0.225])\n",
-    "    norm_img_data = np.zeros(img_data.shape).astype('float32')\n",
-    "    for i in range(img_data.shape[0]):\n",
-    "        norm_img_data[i,:,:] = (img_data[i,:,:]/255 - mean_vec[i]) / stddev_vec[i]\n",
-    "\n",
-    "    return norm_img_data\n",
-    "\n",
-    "def postprocess(result):\n",
-    "    return softmax(np.array(result)).tolist()\n",
-    "\n",
-    "def run(input_data_json):\n",
-    "    try:\n",
-    "        start = time.time()\n",
-    "        # load in our data which is expected as NCHW 224x224 image\n",
-    "        input_data = preprocess(input_data_json)\n",
-    "        input_name = session.get_inputs()[0].name  # get the id of the first input of the model   \n",
-    "        result = session.run([], {input_name: input_data})\n",
-    "        end = time.time()     # stop timer\n",
-    "        return {\"result\": postprocess(result),\n",
-    "                \"time\": end - start}\n",
-    "    except Exception as e:\n",
-    "        result = str(e)\n",
-    "        return {\"error\": result}"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Create container image"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "First we create a YAML file that specifies which dependencies we would like to see in our container."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.conda_dependencies import CondaDependencies \n",
-    "\n",
-    "myenv = CondaDependencies.create(pip_packages=[\"numpy\",\"onnxruntime\",\"azureml-core\"])\n",
-    "\n",
-    "with open(\"myenv.yml\",\"w\") as f:\n",
-    "    f.write(myenv.serialize_to_string())"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Then we have Azure ML create the container. This step will likely take a few minutes."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.image import ContainerImage\n",
-    "\n",
-    "image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
-    "                                                  runtime = \"python\",\n",
-    "                                                  conda_file = \"myenv.yml\",\n",
-    "                                                  description = \"ONNX ResNet50 Demo\",\n",
-    "                                                  tags = {\"demo\": \"onnx\"}\n",
-    "                                                 )\n",
-    "\n",
-    "\n",
-    "image = ContainerImage.create(name = \"onnxresnet50v2\",\n",
-    "                              models = [model],\n",
-    "                              image_config = image_config,\n",
-    "                              workspace = ws)\n",
-    "\n",
-    "image.wait_for_creation(show_output = True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "In case you need to debug your code, the next line of code accesses the log file."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(image.image_build_log_uri)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We're all set! Let's get our model chugging.\n",
-    "\n",
-    "### Deploy the container image"
-   ]
-  },
-  {
-   "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 = {'demo': 'onnx'}, \n",
-    "                                               description = 'web service for ResNet50 ONNX model')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The following cell will likely take a few minutes to run as well."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.webservice import Webservice\n",
-    "from random import randint\n",
-    "\n",
-    "aci_service_name = 'onnx-demo-resnet50'+str(randint(0,100))\n",
-    "print(\"Service\", aci_service_name)\n",
-    "\n",
-    "aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
-    "                                           image = image,\n",
-    "                                           name = aci_service_name,\n",
-    "                                           workspace = ws)\n",
-    "\n",
-    "aci_service.wait_for_deployment(True)\n",
-    "print(aci_service.state)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "In case the deployment fails, you can check the logs. Make sure to delete your aci_service before trying again."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "if aci_service.state != 'Healthy':\n",
-    "    # run this command for debugging.\n",
-    "    print(aci_service.get_logs())\n",
-    "    aci_service.delete()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Success!\n",
-    "\n",
-    "If you've made it this far, you've deployed a working web service that does image classification using an ONNX model. You can get the URL for the webservice with the code below."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(aci_service.scoring_uri)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "When you are eventually done using the web service, remember to delete it."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#aci_service.delete()"
-   ]
-  }
- ],
- "metadata": {
-  "authors": [
-   {
-    "name": "onnx"
-   }
+  "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": [
+        "# ResNet50 Image Classification using ONNX and AzureML\n",
+        "\n",
+        "This example shows how to deploy the ResNet50 ONNX model as a web service using Azure Machine Learning services and the ONNX Runtime.\n",
+        "\n",
+        "## What is ONNX\n",
+        "ONNX is an open format for representing machine learning and deep learning models. ONNX enables open and interoperable AI by enabling data scientists and developers to use the tools of their choice without worrying about lock-in and flexibility to deploy to a variety of platforms. ONNX is developed and supported by a community of partners including Microsoft, Facebook, and Amazon. For more information, explore the [ONNX website](http://onnx.ai).\n",
+        "\n",
+        "## ResNet50 Details\n",
+        "ResNet classifies the major object in an input image into a set of 1000 pre-defined classes. For more information about the ResNet50 model and how it was created can be found on the [ONNX Model Zoo github](https://github.com/onnx/models/tree/master/models/image_classification/resnet). "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Prerequisites\n",
+        "\n",
+        "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",
+        "    * 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": [
+        "#### Download pre-trained ONNX model from ONNX Model Zoo.\n",
+        "\n",
+        "Download the [ResNet50v2 model and test data](https://s3.amazonaws.com/onnx-model-zoo/resnet/resnet50v2/resnet50v2.tar.gz) and extract it in the same folder as this tutorial notebook.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import urllib.request\n",
+        "\n",
+        "onnx_model_url = \"https://s3.amazonaws.com/onnx-model-zoo/resnet/resnet50v2/resnet50v2.tar.gz\"\n",
+        "urllib.request.urlretrieve(onnx_model_url, filename=\"resnet50v2.tar.gz\")\n",
+        "\n",
+        "!tar xvzf resnet50v2.tar.gz"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Deploying as a web service with Azure ML"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Load your Azure ML workspace\n",
+        "\n",
+        "We begin by instantiating a workspace object from the existing workspace created earlier in the configuration notebook."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core import Workspace\n",
+        "\n",
+        "ws = Workspace.from_config()\n",
+        "print(ws.name, ws.location, ws.resource_group, sep = '\\n')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Register your model with Azure ML\n",
+        "\n",
+        "Now we upload the model and register it in the workspace."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.model import Model\n",
+        "\n",
+        "model = Model.register(model_path = \"resnet50v2/resnet50v2.onnx\",\n",
+        "                       model_name = \"resnet50v2\",\n",
+        "                       tags = {\"onnx\": \"demo\"},\n",
+        "                       description = \"ResNet50v2 from ONNX Model Zoo\",\n",
+        "                       workspace = ws)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Displaying your registered models\n",
+        "\n",
+        "You can optionally list out all the models that you have registered in this workspace."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "models = ws.models\n",
+        "for name, m in models.items():\n",
+        "    print(\"Name:\", name,\"\\tVersion:\", m.version, \"\\tDescription:\", m.description, m.tags)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Write scoring file\n",
+        "\n",
+        "We are now going to deploy our ONNX model on Azure ML using the ONNX Runtime. We begin by writing a score.py file that will be invoked by the web service call. The `init()` function is called once when the container is started so we load the model using the ONNX Runtime into a global session object."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%writefile score.py\n",
+        "import json\n",
+        "import time\n",
+        "import sys\n",
+        "import os\n",
+        "from azureml.core.model import Model\n",
+        "import numpy as np    # we're going to use numpy to process input and output data\n",
+        "import onnxruntime    # to inference ONNX models, we use the ONNX Runtime\n",
+        "\n",
+        "def softmax(x):\n",
+        "    x = x.reshape(-1)\n",
+        "    e_x = np.exp(x - np.max(x))\n",
+        "    return e_x / e_x.sum(axis=0)\n",
+        "\n",
+        "def init():\n",
+        "    global session\n",
+        "    model = Model.get_model_path(model_name = 'resnet50v2')\n",
+        "    session = onnxruntime.InferenceSession(model, None)\n",
+        "\n",
+        "def preprocess(input_data_json):\n",
+        "    # convert the JSON data into the tensor input\n",
+        "    img_data = np.array(json.loads(input_data_json)['data']).astype('float32')\n",
+        "    \n",
+        "    #normalize\n",
+        "    mean_vec = np.array([0.485, 0.456, 0.406])\n",
+        "    stddev_vec = np.array([0.229, 0.224, 0.225])\n",
+        "    norm_img_data = np.zeros(img_data.shape).astype('float32')\n",
+        "    for i in range(img_data.shape[0]):\n",
+        "        norm_img_data[i,:,:] = (img_data[i,:,:]/255 - mean_vec[i]) / stddev_vec[i]\n",
+        "\n",
+        "    return norm_img_data\n",
+        "\n",
+        "def postprocess(result):\n",
+        "    return softmax(np.array(result)).tolist()\n",
+        "\n",
+        "def run(input_data_json):\n",
+        "    try:\n",
+        "        start = time.time()\n",
+        "        # load in our data which is expected as NCHW 224x224 image\n",
+        "        input_data = preprocess(input_data_json)\n",
+        "        input_name = session.get_inputs()[0].name  # get the id of the first input of the model   \n",
+        "        result = session.run([], {input_name: input_data})\n",
+        "        end = time.time()     # stop timer\n",
+        "        return {\"result\": postprocess(result),\n",
+        "                \"time\": end - start}\n",
+        "    except Exception as e:\n",
+        "        result = str(e)\n",
+        "        return {\"error\": result}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create container image"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "First we create a YAML file that specifies which dependencies we would like to see in our container."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.conda_dependencies import CondaDependencies \n",
+        "\n",
+        "myenv = CondaDependencies.create(pip_packages=[\"numpy\",\"onnxruntime\",\"azureml-core\"])\n",
+        "\n",
+        "with open(\"myenv.yml\",\"w\") as f:\n",
+        "    f.write(myenv.serialize_to_string())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Then we have Azure ML create the container. This step will likely take a few minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.image import ContainerImage\n",
+        "\n",
+        "image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
+        "                                                  runtime = \"python\",\n",
+        "                                                  conda_file = \"myenv.yml\",\n",
+        "                                                  description = \"ONNX ResNet50 Demo\",\n",
+        "                                                  tags = {\"demo\": \"onnx\"}\n",
+        "                                                 )\n",
+        "\n",
+        "\n",
+        "image = ContainerImage.create(name = \"onnxresnet50v2\",\n",
+        "                              models = [model],\n",
+        "                              image_config = image_config,\n",
+        "                              workspace = ws)\n",
+        "\n",
+        "image.wait_for_creation(show_output = True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "In case you need to debug your code, the next line of code accesses the log file."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(image.image_build_log_uri)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We're all set! Let's get our model chugging.\n",
+        "\n",
+        "### Deploy the container image"
+      ]
+    },
+    {
+      "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 = {'demo': 'onnx'}, \n",
+        "                                               description = 'web service for ResNet50 ONNX model')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "The following cell will likely take a few minutes to run as well."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.webservice import Webservice\n",
+        "from random import randint\n",
+        "\n",
+        "aci_service_name = 'onnx-demo-resnet50'+str(randint(0,100))\n",
+        "print(\"Service\", aci_service_name)\n",
+        "\n",
+        "aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
+        "                                           image = image,\n",
+        "                                           name = aci_service_name,\n",
+        "                                           workspace = ws)\n",
+        "\n",
+        "aci_service.wait_for_deployment(True)\n",
+        "print(aci_service.state)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "In case the deployment fails, you can check the logs. Make sure to delete your aci_service before trying again."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "if aci_service.state != 'Healthy':\n",
+        "    # run this command for debugging.\n",
+        "    print(aci_service.get_logs())\n",
+        "    aci_service.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Success!\n",
+        "\n",
+        "If you've made it this far, you've deployed a working web service that does image classification using an ONNX model. You can get the URL for the webservice with the code below."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(aci_service.scoring_uri)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "When you are eventually done using the web service, remember to delete it."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "#aci_service.delete()"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "metadata": {
+    "authors": [
+      {
+        "name": "viswamy"
+      }
+    ],
+    "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"
+    }
   },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.5.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

how-to-use-azureml/deployment/production-deploy-to-aks/production-deploy-to-aks.ipynb

@@ -1,343 +1,343 @@
 {
- "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": [
-    "# Deploying a web service to Azure Kubernetes Service (AKS)\n",
-    "This notebook shows the steps for deploying a service: registering a model, creating an image, provisioning a cluster (one time action), and deploying a service to it. \n",
-    "We then test and delete the service, image and model."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core import Workspace\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"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import azureml.core\n",
-    "print(azureml.core.VERSION)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Get workspace\n",
-    "Load existing workspace from the config file info."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.workspace import Workspace\n",
-    "\n",
-    "ws = Workspace.from_config()\n",
-    "print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Register the model\n",
-    "Register an existing trained model, add descirption and tags."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#Register the model\n",
-    "from azureml.core.model import Model\n",
-    "model = Model.register(model_path = \"sklearn_regression_model.pkl\", # this points to a local file\n",
-    "                       model_name = \"sklearn_regression_model.pkl\", # this is the name the model is registered as\n",
-    "                       tags = {'area': \"diabetes\", 'type': \"regression\"},\n",
-    "                       description = \"Ridge regression model to predict diabetes\",\n",
-    "                       workspace = ws)\n",
-    "\n",
-    "print(model.name, model.description, model.version)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Create an image\n",
-    "Create an image using the registered model the script that will load and run the model."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%writefile score.py\n",
-    "import pickle\n",
-    "import json\n",
-    "import numpy\n",
-    "from sklearn.externals import joblib\n",
-    "from sklearn.linear_model import Ridge\n",
-    "from azureml.core.model import Model\n",
-    "\n",
-    "def init():\n",
-    "    global model\n",
-    "    # note here \"sklearn_regression_model.pkl\" is the name of the model registered under\n",
-    "    # this is a different behavior than before when the code is run locally, even though the code is the same.\n",
-    "    model_path = Model.get_model_path('sklearn_regression_model.pkl')\n",
-    "    # deserialize the model file back into a sklearn model\n",
-    "    model = joblib.load(model_path)\n",
-    "\n",
-    "# note you can pass in multiple rows for scoring\n",
-    "def run(raw_data):\n",
-    "    try:\n",
-    "        data = json.loads(raw_data)['data']\n",
-    "        data = numpy.array(data)\n",
-    "        result = model.predict(data)\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",
-    "        return error"
-   ]
-  },
-  {
-   "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'])\n",
-    "\n",
-    "with open(\"myenv.yml\",\"w\") as f:\n",
-    "    f.write(myenv.serialize_to_string())"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.image import ContainerImage\n",
-    "\n",
-    "image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
-    "                                                  runtime = \"python\",\n",
-    "                                                  conda_file = \"myenv.yml\",\n",
-    "                                                  description = \"Image with ridge regression model\",\n",
-    "                                                  tags = {'area': \"diabetes\", 'type': \"regression\"}\n",
-    "                                                 )\n",
-    "\n",
-    "image = ContainerImage.create(name = \"myimage1\",\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)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Provision the AKS Cluster\n",
-    "This is a one time setup. You can reuse this cluster for multiple deployments after it has been created. If you delete the cluster or the resource group that contains it, then you would have to recreate it."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Use the default configuration (can also provide parameters to customize)\n",
-    "prov_config = AksCompute.provisioning_configuration()\n",
-    "\n",
-    "aks_name = 'my-aks-9' \n",
-    "# Create the cluster\n",
-    "aks_target = ComputeTarget.create(workspace = ws, \n",
-    "                                  name = aks_name, \n",
-    "                                  provisioning_configuration = prov_config)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%time\n",
-    "aks_target.wait_for_completion(show_output = True)\n",
-    "print(aks_target.provisioning_state)\n",
-    "print(aks_target.provisioning_errors)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Optional step: Attach existing AKS cluster\n",
-    "\n",
-    "If you have existing AKS cluster in your Azure subscription, you can attach it to the Workspace."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "'''\n",
-    "# Use the default configuration (can also provide parameters to customize)\n",
-    "resource_id = '/subscriptions/92c76a2f-0e1c-4216-b65e-abf7a3f34c1e/resourcegroups/raymondsdk0604/providers/Microsoft.ContainerService/managedClusters/my-aks-0605d37425356b7d01'\n",
-    "\n",
-    "create_name='my-existing-aks' \n",
-    "# Create the cluster\n",
-    "attach_config = AksCompute.attach_configuration(resource_id=resource_id)\n",
-    "aks_target = ComputeTarget.attach(workspace=ws, name=create_name, attach_configuration=attach_config)\n",
-    "# Wait for the operation to complete\n",
-    "aks_target.wait_for_completion(True)\n",
-    "'''"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Deploy web service to AKS"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#Set the web service configuration (using default here)\n",
-    "aks_config = AksWebservice.deploy_configuration()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%time\n",
-    "aks_service_name ='aks-service-1'\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",
-    "aks_service.wait_for_deployment(show_output = True)\n",
-    "print(aks_service.state)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Test the web service\n",
-    "We test the web sevice by passing data."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%time\n",
-    "import json\n",
-    "\n",
-    "test_sample = json.dumps({'data': [\n",
-    "    [1,2,3,4,5,6,7,8,9,10], \n",
-    "    [10,9,8,7,6,5,4,3,2,1]\n",
-    "]})\n",
-    "test_sample = bytes(test_sample,encoding = 'utf8')\n",
-    "\n",
-    "prediction = aks_service.run(input_data = test_sample)\n",
-    "print(prediction)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Clean up\n",
-    "Delete the service, image and model."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%time\n",
-    "aks_service.delete()\n",
-    "image.delete()\n",
-    "model.delete()"
-   ]
-  }
- ],
- "metadata": {
-  "authors": [
-   {
-    "name": "raymondl"
-   }
+  "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": [
+        "# Deploying a web service to Azure Kubernetes Service (AKS)\n",
+        "This notebook shows the steps for deploying a service: registering a model, creating an image, provisioning a cluster (one time action), and deploying a service to it. \n",
+        "We then test and delete the service, image and model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core import Workspace\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"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import azureml.core\n",
+        "print(azureml.core.VERSION)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Get workspace\n",
+        "Load existing workspace from the config file info."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.workspace import Workspace\n",
+        "\n",
+        "ws = Workspace.from_config()\n",
+        "print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Register the model\n",
+        "Register an existing trained model, add descirption and tags."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "#Register the model\n",
+        "from azureml.core.model import Model\n",
+        "model = Model.register(model_path = \"sklearn_regression_model.pkl\", # this points to a local file\n",
+        "                       model_name = \"sklearn_regression_model.pkl\", # this is the name the model is registered as\n",
+        "                       tags = {'area': \"diabetes\", 'type': \"regression\"},\n",
+        "                       description = \"Ridge regression model to predict diabetes\",\n",
+        "                       workspace = ws)\n",
+        "\n",
+        "print(model.name, model.description, model.version)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Create an image\n",
+        "Create an image using the registered model the script that will load and run the model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%writefile score.py\n",
+        "import pickle\n",
+        "import json\n",
+        "import numpy\n",
+        "from sklearn.externals import joblib\n",
+        "from sklearn.linear_model import Ridge\n",
+        "from azureml.core.model import Model\n",
+        "\n",
+        "def init():\n",
+        "    global model\n",
+        "    # note here \"sklearn_regression_model.pkl\" is the name of the model registered under\n",
+        "    # this is a different behavior than before when the code is run locally, even though the code is the same.\n",
+        "    model_path = Model.get_model_path('sklearn_regression_model.pkl')\n",
+        "    # deserialize the model file back into a sklearn model\n",
+        "    model = joblib.load(model_path)\n",
+        "\n",
+        "# note you can pass in multiple rows for scoring\n",
+        "def run(raw_data):\n",
+        "    try:\n",
+        "        data = json.loads(raw_data)['data']\n",
+        "        data = numpy.array(data)\n",
+        "        result = model.predict(data)\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",
+        "        return error"
+      ]
+    },
+    {
+      "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'])\n",
+        "\n",
+        "with open(\"myenv.yml\",\"w\") as f:\n",
+        "    f.write(myenv.serialize_to_string())"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.image import ContainerImage\n",
+        "\n",
+        "image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
+        "                                                  runtime = \"python\",\n",
+        "                                                  conda_file = \"myenv.yml\",\n",
+        "                                                  description = \"Image with ridge regression model\",\n",
+        "                                                  tags = {'area': \"diabetes\", 'type': \"regression\"}\n",
+        "                                                 )\n",
+        "\n",
+        "image = ContainerImage.create(name = \"myimage1\",\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)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Provision the AKS Cluster\n",
+        "This is a one time setup. You can reuse this cluster for multiple deployments after it has been created. If you delete the cluster or the resource group that contains it, then you would have to recreate it."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Use the default configuration (can also provide parameters to customize)\n",
+        "prov_config = AksCompute.provisioning_configuration()\n",
+        "\n",
+        "aks_name = 'my-aks-9' \n",
+        "# Create the cluster\n",
+        "aks_target = ComputeTarget.create(workspace = ws, \n",
+        "                                  name = aks_name, \n",
+        "                                  provisioning_configuration = prov_config)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%time\n",
+        "aks_target.wait_for_completion(show_output = True)\n",
+        "print(aks_target.provisioning_state)\n",
+        "print(aks_target.provisioning_errors)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Optional step: Attach existing AKS cluster\n",
+        "\n",
+        "If you have existing AKS cluster in your Azure subscription, you can attach it to the Workspace."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "'''\n",
+        "# Use the default configuration (can also provide parameters to customize)\n",
+        "resource_id = '/subscriptions/92c76a2f-0e1c-4216-b65e-abf7a3f34c1e/resourcegroups/raymondsdk0604/providers/Microsoft.ContainerService/managedClusters/my-aks-0605d37425356b7d01'\n",
+        "\n",
+        "create_name='my-existing-aks' \n",
+        "# Create the cluster\n",
+        "attach_config = AksCompute.attach_configuration(resource_id=resource_id)\n",
+        "aks_target = ComputeTarget.attach(workspace=ws, name=create_name, attach_configuration=attach_config)\n",
+        "# Wait for the operation to complete\n",
+        "aks_target.wait_for_completion(True)\n",
+        "'''"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Deploy web service to AKS"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "#Set the web service configuration (using default here)\n",
+        "aks_config = AksWebservice.deploy_configuration()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%time\n",
+        "aks_service_name ='aks-service-1'\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",
+        "aks_service.wait_for_deployment(show_output = True)\n",
+        "print(aks_service.state)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Test the web service\n",
+        "We test the web sevice by passing data."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%time\n",
+        "import json\n",
+        "\n",
+        "test_sample = json.dumps({'data': [\n",
+        "    [1,2,3,4,5,6,7,8,9,10], \n",
+        "    [10,9,8,7,6,5,4,3,2,1]\n",
+        "]})\n",
+        "test_sample = bytes(test_sample,encoding = 'utf8')\n",
+        "\n",
+        "prediction = aks_service.run(input_data = test_sample)\n",
+        "print(prediction)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Clean up\n",
+        "Delete the service, image and model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%time\n",
+        "aks_service.delete()\n",
+        "image.delete()\n",
+        "model.delete()"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "metadata": {
+    "authors": [
+      {
+        "name": "raymondl"
+      }
+    ],
+    "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"
+    }
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,420 +1,421 @@
 {
- "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": [
-    "## 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",
-    " 1. Register model\n",
-    " 2. Query versions of models and select one to deploy\n",
-    " 3. Create Docker image\n",
-    " 4. Query versions of images\n",
-    " 5. Deploy the image as web service\n",
-    " \n",
-    "**IMPORTANT**:\n",
-    " * This notebook requires you to first complete \"01.SDK-101-Train-and-Deploy-to-ACI.ipynb\" Notebook\n",
-    " \n",
-    "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.  "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Prerequisites\n",
-    "Make sure you go through the [00. Installation and Configuration](00.configuration.ipynb) Notebook first if you haven't."
-   ]
-  },
-  {
-   "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": [
-    "## Initialize Workspace\n",
-    "\n",
-    "Initialize a workspace object from persisted configuration."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "create workspace"
-    ]
-   },
-   "outputs": [],
-   "source": [
-    "from azureml.core import Workspace\n",
-    "\n",
-    "ws = Workspace.from_config()\n",
-    "print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Register Model"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can add tags and descriptions to your models. Note you need to have a `sklearn_linreg_model.pkl` file in the current directory. This file is generated by the 01 notebook. The below call registers that file as a model with the same name `sklearn_linreg_model.pkl` in the workspace.\n",
-    "\n",
-    "Using tags, you can track useful information such as the name and version of the machine learning library used to train the model. Note that tags must be alphanumeric."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "register model from file"
-    ]
-   },
-   "outputs": [],
-   "source": [
-    "from azureml.core.model import Model\n",
-    "import sklearn\n",
-    "\n",
-    "library_version = \"sklearn\"+sklearn.__version__.replace(\".\",\"x\")\n",
-    "\n",
-    "model = Model.register(model_path = \"sklearn_regression_model.pkl\",\n",
-    "                       model_name = \"sklearn_regression_model.pkl\",\n",
-    "                       tags = {'area': \"diabetes\", 'type': \"regression\", 'version': library_version},\n",
-    "                       description = \"Ridge regression model to predict diabetes\",\n",
-    "                       workspace = ws)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can explore the registered models within your workspace and query by tag. Models are versioned. If you call the register_model command many times with same model name, you will get multiple versions of the model with increasing version numbers."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "register model from file"
-    ]
-   },
-   "outputs": [],
-   "source": [
-    "regression_models = Model.list(workspace=ws, tags=['area'])\n",
-    "for m in regression_models:\n",
-    "    print(\"Name:\", m.name,\"\\tVersion:\", m.version, \"\\tDescription:\", m.description, m.tags)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can pick a specific model to deploy"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(model.name, model.description, model.version, sep = '\\t')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Create Docker Image"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Show `score.py`. Note that the `sklearn_regression_model.pkl` in the `get_model_path` call is referring to a model named `sklearn_linreg_model.pkl` registered under the workspace. It is NOT referenceing the local file."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%writefile score.py\n",
-    "import pickle\n",
-    "import json\n",
-    "import numpy\n",
-    "from sklearn.externals import joblib\n",
-    "from sklearn.linear_model import Ridge\n",
-    "from azureml.core.model import Model\n",
-    "\n",
-    "def init():\n",
-    "    global model\n",
-    "    # note here \"sklearn_regression_model.pkl\" is the name of the model registered under\n",
-    "    # this is a different behavior than before when the code is run locally, even though the code is the same.\n",
-    "    model_path = Model.get_model_path('sklearn_regression_model.pkl')\n",
-    "    # deserialize the model file back into a sklearn model\n",
-    "    model = joblib.load(model_path)\n",
-    "\n",
-    "# note you can pass in multiple rows for scoring\n",
-    "def run(raw_data):\n",
-    "    try:\n",
-    "        data = json.loads(raw_data)['data']\n",
-    "        data = numpy.array(data)\n",
-    "        result = model.predict(data)\n",
-    "        # you can return any datatype as long as it is JSON-serializable\n",
-    "        return result.tolist()\n",
-    "    except Exception as e:\n",
-    "        error = str(e)\n",
-    "        return error"
-   ]
-  },
-  {
-   "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'])\n",
-    "\n",
-    "with open(\"myenv.yml\",\"w\") as f:\n",
-    "    f.write(myenv.serialize_to_string())"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Note that following command can take few minutes. \n",
-    "\n",
-    "You can add tags and descriptions to images. Also, an image can contain multiple models."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "create image"
-    ]
-   },
-   "outputs": [],
-   "source": [
-    "from azureml.core.image import Image, ContainerImage\n",
-    "\n",
-    "image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
-    "                                 execution_script=\"score.py\",\n",
-    "                                 conda_file=\"myenv.yml\",\n",
-    "                                 tags = {'area': \"diabetes\", 'type': \"regression\"},\n",
-    "                                 description = \"Image with ridge regression model\")\n",
-    "\n",
-    "image = Image.create(name = \"myimage1\",\n",
-    "                     # this is the model object \n",
-    "                     models = [model],\n",
-    "                     image_config = image_config, \n",
-    "                     workspace = ws)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "create image"
-    ]
-   },
-   "outputs": [],
-   "source": [
-    "image.wait_for_creation(show_output = True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "List images by tag and find out the detailed build log for debugging."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "create image"
-    ]
-   },
-   "outputs": [],
-   "source": [
-    "for i in Image.list(workspace = ws,tags = [\"area\"]):\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": "markdown",
-   "metadata": {},
-   "source": [
-    "### Deploy image as web service on Azure Container Instance\n",
-    "\n",
-    "Note that the service creation can take few minutes."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "deploy service",
-     "aci"
-    ]
-   },
-   "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')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "deploy service",
-     "aci"
-    ]
-   },
-   "outputs": [],
-   "source": [
-    "from azureml.core.webservice import Webservice\n",
-    "\n",
-    "aci_service_name = 'my-aci-service-2'\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": [
-    "### Test web service"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Call the web service with some dummy input data to get a prediction."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "deploy service",
-     "aci"
-    ]
-   },
-   "outputs": [],
-   "source": [
-    "import json\n",
-    "\n",
-    "test_sample = json.dumps({'data': [\n",
-    "    [1,2,3,4,5,6,7,8,9,10], \n",
-    "    [10,9,8,7,6,5,4,3,2,1]\n",
-    "]})\n",
-    "test_sample = bytes(test_sample,encoding = 'utf8')\n",
-    "\n",
-    "prediction = aci_service.run(input_data=test_sample)\n",
-    "print(prediction)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Delete ACI to clean up"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "deploy service",
-     "aci"
-    ]
-   },
-   "outputs": [],
-   "source": [
-    "aci_service.delete()"
-   ]
-  }
- ],
- "metadata": {
-  "authors": [
-   {
-    "name": "raymondl"
-   }
+  "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": [
+        "## 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",
+        " 1. Register model\n",
+        " 2. Query versions of models and select one to deploy\n",
+        " 3. Create Docker image\n",
+        " 4. Query versions of images\n",
+        " 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",
+        " \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.  "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Prerequisites\n",
+        "Make sure you go through the [configuration](../../../configuration.ipynb) Notebook first if you haven't."
+      ]
+    },
+    {
+      "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": [
+        "## Initialize Workspace\n",
+        "\n",
+        "Initialize a workspace object from persisted configuration."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "create workspace"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "from azureml.core import Workspace\n",
+        "\n",
+        "ws = Workspace.from_config()\n",
+        "print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Register Model"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can add tags and descriptions to your models. Note you need to have a `sklearn_linreg_model.pkl` file in the current directory. This file is generated by the 01 notebook. The below call registers that file as a model with the same name `sklearn_linreg_model.pkl` in the workspace.\n",
+        "\n",
+        "Using tags, you can track useful information such as the name and version of the machine learning library used to train the model. Note that tags must be alphanumeric."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "register model from file"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "from azureml.core.model import Model\n",
+        "import sklearn\n",
+        "\n",
+        "library_version = \"sklearn\"+sklearn.__version__.replace(\".\",\"x\")\n",
+        "\n",
+        "model = Model.register(model_path = \"sklearn_regression_model.pkl\",\n",
+        "                       model_name = \"sklearn_regression_model.pkl\",\n",
+        "                       tags = {'area': \"diabetes\", 'type': \"regression\", 'version': library_version},\n",
+        "                       description = \"Ridge regression model to predict diabetes\",\n",
+        "                       workspace = ws)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can explore the registered models within your workspace and query by tag. Models are versioned. If you call the register_model command many times with same model name, you will get multiple versions of the model with increasing version numbers."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "register model from file"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "regression_models = Model.list(workspace=ws, tags=['area'])\n",
+        "for m in regression_models:\n",
+        "    print(\"Name:\", m.name,\"\\tVersion:\", m.version, \"\\tDescription:\", m.description, m.tags)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can pick a specific model to deploy"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(model.name, model.description, model.version, sep = '\\t')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create Docker Image"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Show `score.py`. Note that the `sklearn_regression_model.pkl` in the `get_model_path` call is referring to a model named `sklearn_linreg_model.pkl` registered under the workspace. It is NOT referenceing the local file."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%writefile score.py\n",
+        "import pickle\n",
+        "import json\n",
+        "import numpy\n",
+        "from sklearn.externals import joblib\n",
+        "from sklearn.linear_model import Ridge\n",
+        "from azureml.core.model import Model\n",
+        "\n",
+        "def init():\n",
+        "    global model\n",
+        "    # note here \"sklearn_regression_model.pkl\" is the name of the model registered under\n",
+        "    # this is a different behavior than before when the code is run locally, even though the code is the same.\n",
+        "    model_path = Model.get_model_path('sklearn_regression_model.pkl')\n",
+        "    # deserialize the model file back into a sklearn model\n",
+        "    model = joblib.load(model_path)\n",
+        "\n",
+        "# note you can pass in multiple rows for scoring\n",
+        "def run(raw_data):\n",
+        "    try:\n",
+        "        data = json.loads(raw_data)['data']\n",
+        "        data = numpy.array(data)\n",
+        "        result = model.predict(data)\n",
+        "        # you can return any datatype as long as it is JSON-serializable\n",
+        "        return result.tolist()\n",
+        "    except Exception as e:\n",
+        "        error = str(e)\n",
+        "        return error"
+      ]
+    },
+    {
+      "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'])\n",
+        "\n",
+        "with open(\"myenv.yml\",\"w\") as f:\n",
+        "    f.write(myenv.serialize_to_string())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Note that following command can take few minutes. \n",
+        "\n",
+        "You can add tags and descriptions to images. Also, an image can contain multiple models."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "create image"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "from azureml.core.image import Image, ContainerImage\n",
+        "\n",
+        "image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
+        "                                 execution_script=\"score.py\",\n",
+        "                                 conda_file=\"myenv.yml\",\n",
+        "                                 tags = {'area': \"diabetes\", 'type': \"regression\"},\n",
+        "                                 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",
+        "                     models = [model],\n",
+        "                     image_config = image_config, \n",
+        "                     workspace = ws)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "create image"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "image.wait_for_creation(show_output = True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "List images by tag and find out the detailed build log for debugging."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "create image"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "for i in Image.list(workspace = ws,tags = [\"area\"]):\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": "markdown",
+      "metadata": {},
+      "source": [
+        "### Deploy image as web service on Azure Container Instance\n",
+        "\n",
+        "Note that the service creation can take few minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "deploy service",
+          "aci"
+        ]
+      },
+      "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')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "deploy service",
+          "aci"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "from azureml.core.webservice import Webservice\n",
+        "\n",
+        "aci_service_name = 'my-aci-service-2'\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": [
+        "### Test web service"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Call the web service with some dummy input data to get a prediction."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "deploy service",
+          "aci"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "import json\n",
+        "\n",
+        "test_sample = json.dumps({'data': [\n",
+        "    [1,2,3,4,5,6,7,8,9,10], \n",
+        "    [10,9,8,7,6,5,4,3,2,1]\n",
+        "]})\n",
+        "test_sample = bytes(test_sample,encoding = 'utf8')\n",
+        "\n",
+        "prediction = aci_service.run(input_data=test_sample)\n",
+        "print(prediction)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Delete ACI to clean up"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "deploy service",
+          "aci"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "aci_service.delete()"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "metadata": {
+    "authors": [
+      {
+        "name": "raymondl"
+      }
+    ],
+    "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"
+    }
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,332 +1,328 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Copyright (c) Microsoft Corporation. All rights reserved.  \n",
-    "Licensed under the MIT License."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Azure Machine Learning Pipeline with DataTranferStep\n",
-    "This notebook is used to demonstrate the use of DataTranferStep in Azure Machine Learning Pipeline.\n",
-    "\n",
-    "In certain cases, you will need to transfer data from one data location to another. For example, your data may be in Files storage and you may want to move it to Blob storage. Or, if your data is in an ADLS account and you want to make it available in the Blob storage. The built-in **DataTransferStep** class helps you transfer data in these situations.\n",
-    "\n",
-    "The below example shows how to move data in an ADLS account to Blob storage."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Azure Machine Learning and Pipeline SDK-specific imports"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "import azureml.core\n",
-    "from azureml.core.compute import ComputeTarget, DatabricksCompute, DataFactoryCompute\n",
-    "from azureml.exceptions import ComputeTargetException\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",
-    "print(\"SDK version:\", azureml.core.VERSION)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Initialize Workspace\n",
-    "\n",
-    "Initialize a workspace object from persisted configuration. Make sure the config file is present at .\\config.json\n",
-    "\n",
-    "If you don't have a config.json file, please go through the configuration Notebook located here:\n",
-    "https://github.com/Azure/MachineLearningNotebooks. \n",
-    "\n",
-    "This sets you up with a working config file that has information on your workspace, subscription id, etc. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "create workspace"
-    ]
-   },
-   "outputs": [],
-   "source": [
-    "ws = Workspace.from_config()\n",
-    "print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Register Datastores\n",
-    "\n",
-    "In the code cell below, you will need to fill in the appropriate values for the workspace name, datastore name, subscription id, resource group, store name, tenant id, client id, and client secret that are associated with your ADLS datastore. \n",
-    "\n",
-    "For background on registering your data store, consult this article:\n",
-    "\n",
-    "https://docs.microsoft.com/en-us/azure/data-lake-store/data-lake-store-service-to-service-authenticate-using-active-directory"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\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",
-    "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",
-    "\n",
-    "try:\n",
-    "    adls_datastore = Datastore.get(ws, datastore_name)\n",
-    "    print(\"found datastore with name: %s\" % datastore_name)\n",
-    "except:\n",
-    "    adls_datastore = Datastore.register_azure_data_lake(\n",
-    "        workspace=ws,\n",
-    "        datastore_name=datastore_name,\n",
-    "        subscription_id=subscription_id, # subscription id of ADLS account\n",
-    "        resource_group=resource_group, # resource group of ADLS account\n",
-    "        store_name=store_name, # ADLS account name\n",
-    "        tenant_id=tenant_id, # tenant id of service principal\n",
-    "        client_id=client_id, # client id of service principal\n",
-    "        client_secret=client_secret) # the secret of service principal\n",
-    "    print(\"registered datastore with name: %s\" % datastore_name)\n",
-    "\n",
-    "\n",
-    "\n",
-    "blob_datastore_name='MyBlobDatastore'\n",
-    "account_name=os.getenv(\"BLOB_ACCOUNTNAME_62\", \"<my-account-name>\") # Storage account name\n",
-    "container_name=os.getenv(\"BLOB_CONTAINER_62\", \"<my-container-name>\") # Name of Azure blob container\n",
-    "account_key=os.getenv(\"BLOB_ACCOUNT_KEY_62\", \"<my-account-key>\") # Storage account key\n",
-    "\n",
-    "try:\n",
-    "    blob_datastore = Datastore.get(ws, blob_datastore_name)\n",
-    "    print(\"found blob datastore with name: %s\" % blob_datastore_name)\n",
-    "except:\n",
-    "    blob_datastore = Datastore.register_azure_blob_container(\n",
-    "        workspace=ws,\n",
-    "        datastore_name=blob_datastore_name,\n",
-    "        account_name=account_name, # Storage account name\n",
-    "        container_name=container_name, # Name of Azure blob container\n",
-    "        account_key=account_key) # Storage account key\"\n",
-    "    print(\"registered blob datastore with name: %s\" % blob_datastore_name)\n",
-    "\n",
-    "# CLI:\n",
-    "# az ml datastore register-blob -n <datastore-name> -a <account-name> -c <container-name> -k <account-key> [-t <sas-token>]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Create DataReferences"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "adls_datastore = Datastore(workspace=ws, name=\"MyAdlsDatastore\")\n",
-    "\n",
-    "# adls\n",
-    "adls_data_ref = DataReference(\n",
-    "    datastore=adls_datastore,\n",
-    "    data_reference_name=\"adls_test_data\",\n",
-    "    path_on_datastore=\"testdata\")\n",
-    "\n",
-    "blob_datastore = Datastore(workspace=ws, name=\"MyBlobDatastore\")\n",
-    "\n",
-    "# blob data\n",
-    "blob_data_ref = DataReference(\n",
-    "    datastore=blob_datastore,\n",
-    "    data_reference_name=\"blob_test_data\",\n",
-    "    path_on_datastore=\"testdata\")\n",
-    "\n",
-    "print(\"obtained adls, blob data references\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup Data Factory Account"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data_factory_name = 'adftest'\n",
-    "\n",
-    "def get_or_create_data_factory(workspace, factory_name):\n",
-    "    try:\n",
-    "        return DataFactoryCompute(workspace, factory_name)\n",
-    "    except ComputeTargetException as e:\n",
-    "        if 'ComputeTargetNotFound' in e.message:\n",
-    "            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",
-    "            return data_factory\n",
-    "        else:\n",
-    "            raise e\n",
-    "            \n",
-    "data_factory_compute = get_or_create_data_factory(ws, data_factory_name)\n",
-    "\n",
-    "print(\"setup data factory account complete\")\n",
-    "\n",
-    "# CLI:\n",
-    "# Create: az ml computetarget setup datafactory -n <name>\n",
-    "# BYOC: az ml computetarget attach datafactory -n <name> -i <resource-id>"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Create a DataTransferStep"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "**DataTransferStep** is used to transfer data between Azure Blob, Azure Data Lake Store, and Azure SQL database.\n",
-    "\n",
-    "- **name:** Name of module\n",
-    "- **source_data_reference:** Input connection that serves as source of data transfer operation.\n",
-    "- **destination_data_reference:** Input connection that serves as destination of data transfer operation.\n",
-    "- **compute_target:** Azure Data Factory to use for transferring data.\n",
-    "- **allow_reuse:** Whether the step should reuse results of previous DataTransferStep when run with same inputs. Set as False to force data to be transferred again.\n",
-    "\n",
-    "Optional arguments to explicitly specify whether a path corresponds to a file or a directory. These are useful when storage contains both file and directory with the same name or when creating a new destination path.\n",
-    "\n",
-    "- **source_reference_type:** An optional string specifying the type of source_data_reference. Possible values include: 'file', 'directory'. When not specified, we use the type of existing path or directory if it's a new path.\n",
-    "- **destination_reference_type:** An optional string specifying the type of destination_data_reference. Possible values include: 'file', 'directory'. When not specified, we use the type of existing path or directory if it's a new path."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "transfer_adls_to_blob = DataTransferStep(\n",
-    "    name=\"transfer_adls_to_blob\",\n",
-    "    source_data_reference=adls_data_ref,\n",
-    "    destination_data_reference=blob_data_ref,\n",
-    "    compute_target=data_factory_compute)\n",
-    "\n",
-    "print(\"data transfer step created\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Build and Submit the Experiment"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "pipeline = Pipeline(\n",
-    "    description=\"data_transfer_101\",\n",
-    "    workspace=ws,\n",
-    "    steps=[transfer_adls_to_blob])\n",
-    "\n",
-    "pipeline_run = Experiment(ws, \"Data_Transfer_example\").submit(pipeline)\n",
-    "pipeline_run.wait_for_completion()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### View Run Details"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.widgets import RunDetails\n",
-    "RunDetails(pipeline_run).show()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Next: Databricks as a Compute Target\n",
-    "To use Databricks as a compute target from Azure Machine Learning Pipeline, a DatabricksStep is used. This [notebook](./aml-pipelines-use-databricks-as-compute-target.ipynb) demonstrates the use of a DatabricksStep in an Azure Machine Learning Pipeline."
-   ]
-  }
- ],
- "metadata": {
-  "authors": [
-   {
-    "name": "diray"
-   }
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.  \n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Azure Machine Learning Pipeline with DataTranferStep\n",
+        "This notebook is used to demonstrate the use of DataTranferStep in Azure Machine Learning Pipeline.\n",
+        "\n",
+        "In certain cases, you will need to transfer data from one data location to another. For example, your data may be in Files storage and you may want to move it to Blob storage. Or, if your data is in an ADLS account and you want to make it available in the Blob storage. The built-in **DataTransferStep** class helps you transfer data in these situations.\n",
+        "\n",
+        "The below example shows how to move data in an ADLS account to Blob storage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Azure Machine Learning and Pipeline SDK-specific imports"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "import azureml.core\n",
+        "from azureml.core.compute import ComputeTarget, 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.datastore import Datastore\n",
+        "from azureml.data.data_reference import DataReference\n",
+        "from azureml.pipeline.steps import DataTransferStep\n",
+        "\n",
+        "# Check core SDK version number\n",
+        "print(\"SDK version:\", azureml.core.VERSION)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Initialize Workspace\n",
+        "\n",
+        "Initialize a workspace object from persisted configuration. Make sure the config file is present at .\\config.json\n",
+        "\n",
+        "If you don't have a config.json file, please go through the configuration Notebook located here:\n",
+        "https://github.com/Azure/MachineLearningNotebooks. \n",
+        "\n",
+        "This sets you up with a working config file that has information on your workspace, subscription id, etc. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "create workspace"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Register Datastores\n",
+        "\n",
+        "In the code cell below, you will need to fill in the appropriate values for the workspace name, datastore name, subscription id, resource group, store name, tenant id, client id, and client secret that are associated with your ADLS datastore. \n",
+        "\n",
+        "For background on registering your data store, consult this article:\n",
+        "\n",
+        "https://docs.microsoft.com/en-us/azure/data-lake-store/data-lake-store-service-to-service-authenticate-using-active-directory"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from msrest.exceptions import HttpOperationError\n",
+        "\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",
+        "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",
+        "\n",
+        "try:\n",
+        "    adls_datastore = Datastore.get(ws, datastore_name)\n",
+        "    print(\"found datastore with name: %s\" % datastore_name)\n",
+        "except HttpOperationError:\n",
+        "    adls_datastore = Datastore.register_azure_data_lake(\n",
+        "        workspace=ws,\n",
+        "        datastore_name=datastore_name,\n",
+        "        subscription_id=subscription_id, # subscription id of ADLS account\n",
+        "        resource_group=resource_group, # resource group of ADLS account\n",
+        "        store_name=store_name, # ADLS account name\n",
+        "        tenant_id=tenant_id, # tenant id of service principal\n",
+        "        client_id=client_id, # client id of service principal\n",
+        "        client_secret=client_secret) # the secret of service principal\n",
+        "    print(\"registered datastore with name: %s\" % datastore_name)\n",
+        "\n",
+        "\n",
+        "\n",
+        "blob_datastore_name='MyBlobDatastore'\n",
+        "account_name=os.getenv(\"BLOB_ACCOUNTNAME_62\", \"<my-account-name>\") # Storage account name\n",
+        "container_name=os.getenv(\"BLOB_CONTAINER_62\", \"<my-container-name>\") # Name of Azure blob container\n",
+        "account_key=os.getenv(\"BLOB_ACCOUNT_KEY_62\", \"<my-account-key>\") # Storage account key\n",
+        "\n",
+        "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",
+        "    blob_datastore = Datastore.register_azure_blob_container(\n",
+        "        workspace=ws,\n",
+        "        datastore_name=blob_datastore_name,\n",
+        "        account_name=account_name, # Storage account name\n",
+        "        container_name=container_name, # Name of Azure blob container\n",
+        "        account_key=account_key) # Storage account key\"\n",
+        "    print(\"registered blob datastore with name: %s\" % blob_datastore_name)\n",
+        "\n",
+        "# CLI:\n",
+        "# az ml datastore register-blob -n <datastore-name> -a <account-name> -c <container-name> -k <account-key> [-t <sas-token>]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Create DataReferences"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "adls_datastore = Datastore(workspace=ws, name=\"MyAdlsDatastore\")\n",
+        "\n",
+        "# adls\n",
+        "adls_data_ref = DataReference(\n",
+        "    datastore=adls_datastore,\n",
+        "    data_reference_name=\"adls_test_data\",\n",
+        "    path_on_datastore=\"testdata\")\n",
+        "\n",
+        "blob_datastore = Datastore(workspace=ws, name=\"MyBlobDatastore\")\n",
+        "\n",
+        "# blob data\n",
+        "blob_data_ref = DataReference(\n",
+        "    datastore=blob_datastore,\n",
+        "    data_reference_name=\"blob_test_data\",\n",
+        "    path_on_datastore=\"testdata\")\n",
+        "\n",
+        "print(\"obtained adls, blob data references\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup Data Factory Account"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "data_factory_name = 'adftest'\n",
+        "\n",
+        "def get_or_create_data_factory(workspace, factory_name):\n",
+        "    try:\n",
+        "        return DataFactoryCompute(workspace, factory_name)\n",
+        "    except ComputeTargetException as e:\n",
+        "        if 'ComputeTargetNotFound' in e.message:\n",
+        "            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",
+        "            return data_factory\n",
+        "        else:\n",
+        "            raise e\n",
+        "            \n",
+        "data_factory_compute = get_or_create_data_factory(ws, data_factory_name)\n",
+        "\n",
+        "print(\"setup data factory account complete\")\n",
+        "\n",
+        "# CLI:\n",
+        "# Create: az ml computetarget setup datafactory -n <name>\n",
+        "# BYOC: az ml computetarget attach datafactory -n <name> -i <resource-id>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Create a DataTransferStep"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "**DataTransferStep** is used to transfer data between Azure Blob, Azure Data Lake Store, and Azure SQL database.\n",
+        "\n",
+        "- **name:** Name of module\n",
+        "- **source_data_reference:** Input connection that serves as source of data transfer operation.\n",
+        "- **destination_data_reference:** Input connection that serves as destination of data transfer operation.\n",
+        "- **compute_target:** Azure Data Factory to use for transferring data.\n",
+        "- **allow_reuse:** Whether the step should reuse results of previous DataTransferStep when run with same inputs. Set as False to force data to be transferred again.\n",
+        "\n",
+        "Optional arguments to explicitly specify whether a path corresponds to a file or a directory. These are useful when storage contains both file and directory with the same name or when creating a new destination path.\n",
+        "\n",
+        "- **source_reference_type:** An optional string specifying the type of source_data_reference. Possible values include: 'file', 'directory'. When not specified, we use the type of existing path or directory if it's a new path.\n",
+        "- **destination_reference_type:** An optional string specifying the type of destination_data_reference. Possible values include: 'file', 'directory'. When not specified, we use the type of existing path or directory if it's a new path."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "transfer_adls_to_blob = DataTransferStep(\n",
+        "    name=\"transfer_adls_to_blob\",\n",
+        "    source_data_reference=adls_data_ref,\n",
+        "    destination_data_reference=blob_data_ref,\n",
+        "    compute_target=data_factory_compute)\n",
+        "\n",
+        "print(\"data transfer step created\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Build and Submit the Experiment"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "pipeline = Pipeline(\n",
+        "    description=\"data_transfer_101\",\n",
+        "    workspace=ws,\n",
+        "    steps=[transfer_adls_to_blob])\n",
+        "\n",
+        "pipeline_run = Experiment(ws, \"Data_Transfer_example\").submit(pipeline)\n",
+        "pipeline_run.wait_for_completion()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### View Run Details"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.widgets import RunDetails\n",
+        "RunDetails(pipeline_run).show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Next: Databricks as a Compute Target\n",
+        "To use Databricks as a compute target from Azure Machine Learning Pipeline, a DatabricksStep is used. This [notebook](./aml-pipelines-use-databricks-as-compute-target.ipynb) demonstrates the use of a DatabricksStep in an Azure Machine Learning Pipeline."
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
+  "metadata": {
+    "authors": [
+      {
+        "name": "diray"
+      }
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "python",
+      "name": "python36"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.7"
+    }
   },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.6.7"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,368 +1,365 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Copyright (c) Microsoft Corporation. All rights reserved.  \n",
-    "Licensed under the MIT License."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# How to Publish a Pipeline and Invoke the REST endpoint\n",
-    "In this notebook, we will see how we can publish a pipeline and then invoke the REST endpoint."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Prerequisites and Azure Machine Learning Basics\n",
-    "Make sure you go through the configuration Notebook located at https://github.com/Azure/MachineLearningNotebooks first if you haven't. This sets you up with a working config file that has information on your workspace, subscription id, etc. \n",
-    "\n",
-    "### Initialization Steps"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import azureml.core\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, 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",
-    "\n",
-    "ws = Workspace.from_config()\n",
-    "print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')\n",
-    "\n",
-    "# Default datastore (Azure file storage)\n",
-    "def_file_store = ws.get_default_datastore() \n",
-    "print(\"Default datastore's name: {}\".format(def_file_store.name))\n",
-    "\n",
-    "def_blob_store = Datastore(ws, \"workspaceblobstore\")\n",
-    "print(\"Blobstore's name: {}\".format(def_blob_store.name))\n",
-    "\n",
-    "# project folder\n",
-    "project_folder = '.'"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Compute Targets\n",
-    "#### Retrieve an already attached  Azure Machine Learning Compute"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "aml_compute_target = \"aml-compute\"\n",
-    "try:\n",
-    "    aml_compute = AmlCompute(ws, aml_compute_target)\n",
-    "    print(\"found existing compute target.\")\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 the 'status' property\n",
-    "# example: un-comment the following line.\n",
-    "# print(aml_compute.status.serialize())"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Building Pipeline Steps with Inputs and Outputs\n",
-    "As mentioned earlier, a step in the pipeline can take data as input. This data can be a data source that lives in one of the accessible data locations, or intermediate data produced by a previous step in the pipeline."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Reference the data uploaded to blob storage using DataReference\n",
-    "# Assign the datasource to blob_input_data variable\n",
-    "blob_input_data = DataReference(\n",
-    "    datastore=def_blob_store,\n",
-    "    data_reference_name=\"test_data\",\n",
-    "    path_on_datastore=\"20newsgroups/20news.pkl\")\n",
-    "print(\"DataReference object created\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Define intermediate data using PipelineData\n",
-    "processed_data1 = PipelineData(\"processed_data1\",datastore=def_blob_store)\n",
-    "print(\"PipelineData object created\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Define a Step that consumes a datasource and produces intermediate data.\n",
-    "In this step, we define a step that consumes a datasource and produces intermediate data.\n",
-    "\n",
-    "**Open `train.py` in the local machine and examine the arguments, inputs, and outputs for the script. That will give you a good sense of why the script argument names used below are important.** "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# trainStep consumes the datasource (Datareference) in the previous step\n",
-    "# and produces processed_data1\n",
-    "trainStep = PythonScriptStep(\n",
-    "    script_name=\"train.py\", \n",
-    "        arguments=[\"--input_data\", blob_input_data, \"--output_train\", processed_data1],\n",
-    "    inputs=[blob_input_data],\n",
-    "    outputs=[processed_data1],\n",
-    "    compute_target=aml_compute, \n",
-    "    source_directory=project_folder\n",
-    ")\n",
-    "print(\"trainStep created\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Define a Step that consumes intermediate data and produces intermediate data\n",
-    "In this step, we define a step that consumes an intermediate data and produces intermediate data.\n",
-    "\n",
-    "**Open `extract.py` in the local machine and examine the arguments, inputs, and outputs for the script. That will give you a good sense of why the script argument names used below are important.** "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# extractStep to use the intermediate data produced by step4\n",
-    "# This step also produces an output processed_data2\n",
-    "processed_data2 = PipelineData(\"processed_data2\", datastore=def_blob_store)\n",
-    "\n",
-    "extractStep = PythonScriptStep(\n",
-    "    script_name=\"extract.py\",\n",
-    "    arguments=[\"--input_extract\", processed_data1, \"--output_extract\", processed_data2],\n",
-    "    inputs=[processed_data1],\n",
-    "    outputs=[processed_data2],\n",
-    "    compute_target=aml_compute, \n",
-    "    source_directory=project_folder)\n",
-    "print(\"extractStep created\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Define a Step that consumes multiple intermediate data and produces intermediate data\n",
-    "In this step, we define a step that consumes multiple intermediate data and produces intermediate data."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### PipelineParameter"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This step also has a [PipelineParameter](https://docs.microsoft.com/en-us/python/api/azureml-pipeline-core/azureml.pipeline.core.graph.pipelineparameter?view=azure-ml-py) argument that help with calling the REST endpoint of the published pipeline."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# We will use this later in publishing pipeline\n",
-    "pipeline_param = PipelineParameter(name=\"pipeline_arg\", default_value=10)\n",
-    "print(\"pipeline parameter created\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "**Open `compare.py` in the local machine and examine the arguments, inputs, and outputs for the script. That will give you a good sense of why the script argument names used below are important.**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Now define step6 that takes two inputs (both intermediate data), and produce an output\n",
-    "processed_data3 = PipelineData(\"processed_data3\", datastore=def_blob_store)\n",
-    "\n",
-    "\n",
-    "\n",
-    "compareStep = PythonScriptStep(\n",
-    "    script_name=\"compare.py\",\n",
-    "    arguments=[\"--compare_data1\", processed_data1, \"--compare_data2\", processed_data2, \"--output_compare\", processed_data3, \"--pipeline_param\", pipeline_param],\n",
-    "    inputs=[processed_data1, processed_data2],\n",
-    "    outputs=[processed_data3],    \n",
-    "    compute_target=aml_compute, \n",
-    "    source_directory=project_folder)\n",
-    "print(\"compareStep created\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Build the pipeline"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "pipeline1 = Pipeline(workspace=ws, steps=[compareStep])\n",
-    "print (\"Pipeline is built\")\n",
-    "\n",
-    "pipeline1.validate()\n",
-    "print(\"Simple validation complete\") "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Publish the pipeline"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "published_pipeline1 = pipeline1.publish(name=\"My_New_Pipeline\", description=\"My Published Pipeline Description\")\n",
-    "print(published_pipeline1.id)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Run published pipeline using its REST endpoint"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.authentication import AzureCliAuthentication\n",
-    "import requests\n",
-    "\n",
-    "cli_auth = AzureCliAuthentication()\n",
-    "aad_token = cli_auth.get_authentication_header()\n",
-    "\n",
-    "rest_endpoint1 = published_pipeline1.endpoint\n",
-    "\n",
-    "print(rest_endpoint1)\n",
-    "\n",
-    "# specify the param when running the pipeline\n",
-    "response = requests.post(rest_endpoint1, \n",
-    "                         headers=aad_token, \n",
-    "                         json={\"ExperimentName\": \"My_Pipeline1\",\n",
-    "                               \"RunSource\": \"SDK\",\n",
-    "                               \"ParameterAssignments\": {\"pipeline_arg\": 45}})\n",
-    "run_id = response.json()[\"Id\"]\n",
-    "\n",
-    "print(run_id)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Next: Data Transfer\n",
-    "The next [notebook](./aml-pipelines-data-transfer.ipynb) will showcase data transfer steps between different types of data stores."
-   ]
-  }
- ],
- "metadata": {
-  "authors": [
-   {
-    "name": "diray"
-   }
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.  \n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# How to Publish a Pipeline and Invoke the REST endpoint\n",
+        "In this notebook, we will see how we can publish a pipeline and then invoke the REST endpoint."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Prerequisites and Azure Machine Learning Basics\n",
+        "Make sure you go through the configuration Notebook located at https://github.com/Azure/MachineLearningNotebooks first if you haven't. This sets you up with a working config file that has information on your workspace, subscription id, etc. \n",
+        "\n",
+        "### Initialization Steps"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import azureml.core\n",
+        "from azureml.core import Workspace, Datastore\n",
+        "from azureml.core.compute import AmlCompute\n",
+        "from azureml.core.compute import ComputeTarget\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.steps import PythonScriptStep\n",
+        "from azureml.pipeline.core.graph import PipelineParameter\n",
+        "\n",
+        "print(\"Pipeline SDK-specific imports completed\")\n",
+        "\n",
+        "ws = Workspace.from_config()\n",
+        "print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')\n",
+        "\n",
+        "# Default datastore (Azure file storage)\n",
+        "def_file_store = ws.get_default_datastore() \n",
+        "print(\"Default datastore's name: {}\".format(def_file_store.name))\n",
+        "\n",
+        "def_blob_store = Datastore(ws, \"workspaceblobstore\")\n",
+        "print(\"Blobstore's name: {}\".format(def_blob_store.name))\n",
+        "\n",
+        "# project folder\n",
+        "project_folder = '.'"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Compute Targets\n",
+        "#### Retrieve an already attached  Azure Machine Learning Compute"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "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",
+        "    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())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Building Pipeline Steps with Inputs and Outputs\n",
+        "As mentioned earlier, a step in the pipeline can take data as input. This data can be a data source that lives in one of the accessible data locations, or intermediate data produced by a previous step in the pipeline."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Reference the data uploaded to blob storage using DataReference\n",
+        "# Assign the datasource to blob_input_data variable\n",
+        "blob_input_data = DataReference(\n",
+        "    datastore=def_blob_store,\n",
+        "    data_reference_name=\"test_data\",\n",
+        "    path_on_datastore=\"20newsgroups/20news.pkl\")\n",
+        "print(\"DataReference object created\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Define intermediate data using PipelineData\n",
+        "processed_data1 = PipelineData(\"processed_data1\",datastore=def_blob_store)\n",
+        "print(\"PipelineData object created\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Define a Step that consumes a datasource and produces intermediate data.\n",
+        "In this step, we define a step that consumes a datasource and produces intermediate data.\n",
+        "\n",
+        "**Open `train.py` in the local machine and examine the arguments, inputs, and outputs for the script. That will give you a good sense of why the script argument names used below are important.** "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# trainStep consumes the datasource (Datareference) in the previous step\n",
+        "# and produces processed_data1\n",
+        "trainStep = PythonScriptStep(\n",
+        "    script_name=\"train.py\", \n",
+        "        arguments=[\"--input_data\", blob_input_data, \"--output_train\", processed_data1],\n",
+        "    inputs=[blob_input_data],\n",
+        "    outputs=[processed_data1],\n",
+        "    compute_target=aml_compute, \n",
+        "    source_directory=project_folder\n",
+        ")\n",
+        "print(\"trainStep created\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Define a Step that consumes intermediate data and produces intermediate data\n",
+        "In this step, we define a step that consumes an intermediate data and produces intermediate data.\n",
+        "\n",
+        "**Open `extract.py` in the local machine and examine the arguments, inputs, and outputs for the script. That will give you a good sense of why the script argument names used below are important.** "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# extractStep to use the intermediate data produced by step4\n",
+        "# This step also produces an output processed_data2\n",
+        "processed_data2 = PipelineData(\"processed_data2\", datastore=def_blob_store)\n",
+        "\n",
+        "extractStep = PythonScriptStep(\n",
+        "    script_name=\"extract.py\",\n",
+        "    arguments=[\"--input_extract\", processed_data1, \"--output_extract\", processed_data2],\n",
+        "    inputs=[processed_data1],\n",
+        "    outputs=[processed_data2],\n",
+        "    compute_target=aml_compute, \n",
+        "    source_directory=project_folder)\n",
+        "print(\"extractStep created\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Define a Step that consumes multiple intermediate data and produces intermediate data\n",
+        "In this step, we define a step that consumes multiple intermediate data and produces intermediate data."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### PipelineParameter"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "This step also has a [PipelineParameter](https://docs.microsoft.com/en-us/python/api/azureml-pipeline-core/azureml.pipeline.core.graph.pipelineparameter?view=azure-ml-py) argument that help with calling the REST endpoint of the published pipeline."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# We will use this later in publishing pipeline\n",
+        "pipeline_param = PipelineParameter(name=\"pipeline_arg\", default_value=10)\n",
+        "print(\"pipeline parameter created\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "**Open `compare.py` in the local machine and examine the arguments, inputs, and outputs for the script. That will give you a good sense of why the script argument names used below are important.**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Now define step6 that takes two inputs (both intermediate data), and produce an output\n",
+        "processed_data3 = PipelineData(\"processed_data3\", datastore=def_blob_store)\n",
+        "\n",
+        "\n",
+        "\n",
+        "compareStep = PythonScriptStep(\n",
+        "    script_name=\"compare.py\",\n",
+        "    arguments=[\"--compare_data1\", processed_data1, \"--compare_data2\", processed_data2, \"--output_compare\", processed_data3, \"--pipeline_param\", pipeline_param],\n",
+        "    inputs=[processed_data1, processed_data2],\n",
+        "    outputs=[processed_data3],    \n",
+        "    compute_target=aml_compute, \n",
+        "    source_directory=project_folder)\n",
+        "print(\"compareStep created\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Build the pipeline"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "pipeline1 = Pipeline(workspace=ws, steps=[compareStep])\n",
+        "print (\"Pipeline is built\")\n",
+        "\n",
+        "pipeline1.validate()\n",
+        "print(\"Simple validation complete\") "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Publish the pipeline"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "published_pipeline1 = pipeline1.publish(name=\"My_New_Pipeline\", description=\"My Published Pipeline Description\")\n",
+        "print(published_pipeline1.id)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Run published pipeline using its REST endpoint"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.authentication import AzureCliAuthentication\n",
+        "import requests\n",
+        "\n",
+        "cli_auth = AzureCliAuthentication()\n",
+        "aad_token = cli_auth.get_authentication_header()\n",
+        "\n",
+        "rest_endpoint1 = published_pipeline1.endpoint\n",
+        "\n",
+        "print(rest_endpoint1)\n",
+        "\n",
+        "# specify the param when running the pipeline\n",
+        "response = requests.post(rest_endpoint1, \n",
+        "                         headers=aad_token, \n",
+        "                         json={\"ExperimentName\": \"My_Pipeline1\",\n",
+        "                               \"RunSource\": \"SDK\",\n",
+        "                               \"ParameterAssignments\": {\"pipeline_arg\": 45}})\n",
+        "run_id = response.json()[\"Id\"]\n",
+        "\n",
+        "print(run_id)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Next: Data Transfer\n",
+        "The next [notebook](./aml-pipelines-data-transfer.ipynb) will showcase data transfer steps between different types of data stores."
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
+  "metadata": {
+    "authors": [
+      {
+        "name": "diray"
+      }
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "python",
+      "name": "python36"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.7"
+    }
   },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.6.7"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,368 +1,366 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Copyright (c) Microsoft Corporation. All rights reserved.  \n",
-    "Licensed under the MIT License."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# AML Pipeline with AdlaStep\n",
-    "This notebook is used to demonstrate the use of AdlaStep in AML Pipeline."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## AML and Pipeline SDK-specific imports"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "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, 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)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Initialize Workspace\n",
-    "\n",
-    "Initialize a workspace object from persisted configuration. Make sure the config file is present at .\\config.json"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "create workspace"
-    ]
-   },
-   "outputs": [],
-   "source": [
-    "ws = Workspace.from_config()\n",
-    "print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "script_folder = '.'\n",
-    "experiment_name = \"adla_101_experiment\"\n",
-    "ws._initialize_folder(experiment_name=experiment_name, directory=script_folder)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Register Datastore"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\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",
-    "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",
-    "\n",
-    "try:\n",
-    "    adls_datastore = Datastore.get(ws, datastore_name)\n",
-    "    print(\"found datastore with name: %s\" % datastore_name)\n",
-    "except:\n",
-    "    adls_datastore = Datastore.register_azure_data_lake(\n",
-    "        workspace=ws,\n",
-    "        datastore_name=datastore_name,\n",
-    "        subscription_id=subscription_id, # subscription id of ADLS account\n",
-    "        resource_group=resource_group, # resource group of ADLS account\n",
-    "        store_name=store_name, # ADLS account name\n",
-    "        tenant_id=tenant_id, # tenant id of service principal\n",
-    "        client_id=client_id, # client id of service principal\n",
-    "        client_secret=client_secret) # the secret of service principal\n",
-    "    print(\"registered datastore with name: %s\" % datastore_name)\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Create DataReferences and PipelineData\n",
-    "\n",
-    "In the code cell below, replace datastorename with your default datastore name. Copy the file `testdata.txt` (located in the pipeline folder that this notebook is in) to the path on the datastore."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "datastorename = \"MyAdlsDatastore\"\n",
-    "\n",
-    "adls_datastore = Datastore(workspace=ws, name=datastorename)\n",
-    "script_input = DataReference(\n",
-    "    datastore=adls_datastore,\n",
-    "    data_reference_name=\"script_input\",\n",
-    "    path_on_datastore=\"testdata/testdata.txt\")\n",
-    "\n",
-    "script_output = PipelineData(\"script_output\", datastore=adls_datastore)\n",
-    "\n",
-    "print(\"Created Pipeline Data\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup Data Lake Account\n",
-    "\n",
-    "ADLA can only use data that is located in the default data store associated with that ADLA account. Through Azure portal, check the name of the default data store corresponding to the ADLA account you are using below. Replace the value associated with `adla_compute_name` in the code cell below accordingly."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "adla_compute_name = 'testadl' # Replace this with your default compute\n",
-    "\n",
-    "from azureml.core.compute import ComputeTarget, AdlaCompute\n",
-    "\n",
-    "def get_or_create_adla_compute(workspace, compute_name):\n",
-    "    try:\n",
-    "        return AdlaCompute(workspace, compute_name)\n",
-    "    except ComputeTargetException as e:\n",
-    "        if 'ComputeTargetNotFound' in e.message:\n",
-    "            print('adla compute not found, creating...')\n",
-    "            provisioning_config = AdlaCompute.provisioning_configuration()\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",
-    "adla_compute = get_or_create_adla_compute(ws, adla_compute_name)\n",
-    "\n",
-    "# CLI:\n",
-    "# Create: az ml computetarget setup adla -n <name>\n",
-    "# BYOC: az ml computetarget attach adla -n <name> -i <resource-id>"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Once the above code cell completes, run the below to check your ADLA compute status:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(\"ADLA compute state:{}\".format(adla_compute.provisioning_state))\n",
-    "print(\"ADLA compute state:{}\".format(adla_compute.provisioning_errors))\n",
-    "print(\"Using ADLA compute:{}\".format(adla_compute.cluster_resource_id))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Create an AdlaStep"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "**AdlaStep** is used to run U-SQL script using Azure Data Lake Analytics.\n",
-    "\n",
-    "- **name:** Name of module\n",
-    "- **script_name:** name of U-SQL script\n",
-    "- **inputs:** List of input port bindings\n",
-    "- **outputs:** List of output port bindings\n",
-    "- **adla_compute:** the ADLA compute to use for this job\n",
-    "- **params:** Dictionary of name-value pairs to pass to U-SQL job *(optional)*\n",
-    "- **degree_of_parallelism:** the degree of parallelism to use for this job *(optional)*\n",
-    "- **priority:** the priority value to use for the current job *(optional)*\n",
-    "- **runtime_version:** the runtime version of the Data Lake Analytics engine *(optional)*\n",
-    "- **root_folder:** folder that contains the script, assemblies etc. *(optional)*\n",
-    "- **hash_paths:** list of paths to hash to detect a change (script file is always hashed) *(optional)*\n",
-    "\n",
-    "### Remarks\n",
-    "\n",
-    "You can use `@@name@@` syntax in your script to refer to inputs, outputs, 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` matches any key in `params` dict, any occurences of `@@name@@` will be replaced with\n",
-    "corresponding value in dict.\n",
-    "\n",
-    "#### Sample script\n",
-    "\n",
-    "```\n",
-    "@resourcereader =\n",
-    "    EXTRACT query string\n",
-    "    FROM \"@@script_input@@\"\n",
-    "    USING Extractors.Csv();\n",
-    "\n",
-    "\n",
-    "OUTPUT @resourcereader\n",
-    "TO \"@@script_output@@\"\n",
-    "USING Outputters.Csv();\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "adla_step = AdlaStep(\n",
-    "    name='adla_script_step',\n",
-    "    script_name='test_adla_script.usql',\n",
-    "    inputs=[script_input],\n",
-    "    outputs=[script_output],\n",
-    "    compute_target=adla_compute)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Build and Submit the Experiment"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "pipeline = Pipeline(\n",
-    "    description=\"adla_102\",\n",
-    "    workspace=ws, \n",
-    "    steps=[adla_step],\n",
-    "    default_source_directory=script_folder)\n",
-    "\n",
-    "pipeline_run = Experiment(workspace, experiment_name).submit(pipeline)\n",
-    "pipeline_run.wait_for_completion()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### View Run Details"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.widgets import RunDetails\n",
-    "RunDetails(pipeline_run).show()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Examine the run\n",
-    "You can cycle through the node_run objects and examine job logs, stdout, and stderr of each of the steps."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "step_runs = pipeline_run.get_children()\n",
-    "for step_run in step_runs:\n",
-    "    status = step_run.get_status()\n",
-    "    print('node', step_run.name, 'status:', status)\n",
-    "    if status == \"Failed\":\n",
-    "        joblog = step_run.get_job_log()\n",
-    "        print('job log:', joblog)\n",
-    "        stdout_log = step_run.get_stdout_log()\n",
-    "        print('stdout log:', stdout_log)\n",
-    "        stderr_log = step_run.get_stderr_log()\n",
-    "        print('stderr log:', stderr_log)\n",
-    "        with open(\"logs-\" + step_run.name + \".txt\", \"w\") as f:\n",
-    "            f.write(joblog)\n",
-    "            print(\"Job log written to logs-\"+ step_run.name + \".txt\")\n",
-    "    if status == \"Finished\":\n",
-    "        stdout_log = step_run.get_stdout_log()\n",
-    "        print('stdout log:', stdout_log)"
-   ]
-  }
- ],
- "metadata": {
-  "authors": [
-   {
-    "name": "diray"
-   }
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.  \n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# AML Pipeline with AdlaStep\n",
+        "This notebook is used to demonstrate the use of AdlaStep in AML Pipeline."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## AML and Pipeline SDK-specific imports"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "import azureml.core\n",
+        "from azureml.exceptions import ComputeTargetException\n",
+        "from azureml.core import Workspace, 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",
+        "\n",
+        "# Check core SDK version number\n",
+        "print(\"SDK version:\", azureml.core.VERSION)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Initialize Workspace\n",
+        "\n",
+        "Initialize a workspace object from persisted configuration. Make sure the config file is present at .\\config.json"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "create workspace"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "script_folder = '.'\n",
+        "experiment_name = \"adla_101_experiment\"\n",
+        "ws._initialize_folder(experiment_name=experiment_name, directory=script_folder)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Register Datastore"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from msrest.exceptions import HttpOperationError\n",
+        "\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",
+        "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",
+        "\n",
+        "try:\n",
+        "    adls_datastore = Datastore.get(ws, datastore_name)\n",
+        "    print(\"found datastore with name: %s\" % datastore_name)\n",
+        "except HttpOperationError:\n",
+        "    adls_datastore = Datastore.register_azure_data_lake(\n",
+        "        workspace=ws,\n",
+        "        datastore_name=datastore_name,\n",
+        "        subscription_id=subscription_id, # subscription id of ADLS account\n",
+        "        resource_group=resource_group, # resource group of ADLS account\n",
+        "        store_name=store_name, # ADLS account name\n",
+        "        tenant_id=tenant_id, # tenant id of service principal\n",
+        "        client_id=client_id, # client id of service principal\n",
+        "        client_secret=client_secret) # the secret of service principal\n",
+        "    print(\"registered datastore with name: %s\" % datastore_name)\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Create DataReferences and PipelineData\n",
+        "\n",
+        "In the code cell below, replace datastorename with your default datastore name. Copy the file `testdata.txt` (located in the pipeline folder that this notebook is in) to the path on the datastore."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "datastorename = \"MyAdlsDatastore\"\n",
+        "\n",
+        "adls_datastore = Datastore(workspace=ws, name=datastorename)\n",
+        "script_input = DataReference(\n",
+        "    datastore=adls_datastore,\n",
+        "    data_reference_name=\"script_input\",\n",
+        "    path_on_datastore=\"testdata/testdata.txt\")\n",
+        "\n",
+        "script_output = PipelineData(\"script_output\", datastore=adls_datastore)\n",
+        "\n",
+        "print(\"Created Pipeline Data\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup Data Lake Account\n",
+        "\n",
+        "ADLA can only use data that is located in the default data store associated with that ADLA account. Through Azure portal, check the name of the default data store corresponding to the ADLA account you are using below. Replace the value associated with `adla_compute_name` in the code cell below accordingly."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "adla_compute_name = 'testadl' # Replace this with your default compute\n",
+        "\n",
+        "from azureml.core.compute import ComputeTarget, AdlaCompute\n",
+        "\n",
+        "def get_or_create_adla_compute(workspace, compute_name):\n",
+        "    try:\n",
+        "        return AdlaCompute(workspace, compute_name)\n",
+        "    except ComputeTargetException as e:\n",
+        "        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",
+        "        else:\n",
+        "            raise e\n",
+        "            \n",
+        "adla_compute = get_or_create_adla_compute(ws, adla_compute_name)\n",
+        "\n",
+        "# CLI:\n",
+        "# Create: az ml computetarget setup adla -n <name>\n",
+        "# BYOC: az ml computetarget attach adla -n <name> -i <resource-id>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Once the above code cell completes, run the below to check your ADLA compute status:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"ADLA compute state:{}\".format(adla_compute.provisioning_state))\n",
+        "print(\"ADLA compute state:{}\".format(adla_compute.provisioning_errors))\n",
+        "print(\"Using ADLA compute:{}\".format(adla_compute.cluster_resource_id))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Create an AdlaStep"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "**AdlaStep** is used to run U-SQL script using Azure Data Lake Analytics.\n",
+        "\n",
+        "- **name:** Name of module\n",
+        "- **script_name:** name of U-SQL script\n",
+        "- **inputs:** List of input port bindings\n",
+        "- **outputs:** List of output port bindings\n",
+        "- **adla_compute:** the ADLA compute to use for this job\n",
+        "- **params:** Dictionary of name-value pairs to pass to U-SQL job *(optional)*\n",
+        "- **degree_of_parallelism:** the degree of parallelism to use for this job *(optional)*\n",
+        "- **priority:** the priority value to use for the current job *(optional)*\n",
+        "- **runtime_version:** the runtime version of the Data Lake Analytics engine *(optional)*\n",
+        "- **root_folder:** folder that contains the script, assemblies etc. *(optional)*\n",
+        "- **hash_paths:** list of paths to hash to detect a change (script file is always hashed) *(optional)*\n",
+        "\n",
+        "### Remarks\n",
+        "\n",
+        "You can use `@@name@@` syntax in your script to refer to inputs, outputs, 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` matches any key in `params` dict, any occurences of `@@name@@` will be replaced with\n",
+        "corresponding value in dict.\n",
+        "\n",
+        "#### Sample script\n",
+        "\n",
+        "```\n",
+        "@resourcereader =\n",
+        "    EXTRACT query string\n",
+        "    FROM \"@@script_input@@\"\n",
+        "    USING Extractors.Csv();\n",
+        "\n",
+        "\n",
+        "OUTPUT @resourcereader\n",
+        "TO \"@@script_output@@\"\n",
+        "USING Outputters.Csv();\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "adla_step = AdlaStep(\n",
+        "    name='adla_script_step',\n",
+        "    script_name='test_adla_script.usql',\n",
+        "    inputs=[script_input],\n",
+        "    outputs=[script_output],\n",
+        "    compute_target=adla_compute)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Build and Submit the Experiment"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "pipeline = Pipeline(\n",
+        "    description=\"adla_102\",\n",
+        "    workspace=ws, \n",
+        "    steps=[adla_step],\n",
+        "    default_source_directory=script_folder)\n",
+        "\n",
+        "pipeline_run = Experiment(ws, experiment_name).submit(pipeline)\n",
+        "pipeline_run.wait_for_completion()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### View Run Details"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.widgets import RunDetails\n",
+        "RunDetails(pipeline_run).show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Examine the run\n",
+        "You can cycle through the node_run objects and examine job logs, stdout, and stderr of each of the steps."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "step_runs = pipeline_run.get_children()\n",
+        "for step_run in step_runs:\n",
+        "    status = step_run.get_status()\n",
+        "    print('node', step_run.name, 'status:', status)\n",
+        "    if status == \"Failed\":\n",
+        "        joblog = step_run.get_job_log()\n",
+        "        print('job log:', joblog)\n",
+        "        stdout_log = step_run.get_stdout_log()\n",
+        "        print('stdout log:', stdout_log)\n",
+        "        stderr_log = step_run.get_stderr_log()\n",
+        "        print('stderr log:', stderr_log)\n",
+        "        with open(\"logs-\" + step_run.name + \".txt\", \"w\") as f:\n",
+        "            f.write(joblog)\n",
+        "            print(\"Job log written to logs-\"+ step_run.name + \".txt\")\n",
+        "    if status == \"Finished\":\n",
+        "        stdout_log = step_run.get_stdout_log()\n",
+        "        print('stdout log:', stdout_log)"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python [default]",
-   "language": "python",
-   "name": "python3"
+  "metadata": {
+    "authors": [
+      {
+        "name": "diray"
+      }
+    ],
+    "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"
+    }
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,418 +1,414 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Copyright (c) Microsoft Corporation. All rights reserved.  \n",
-    "Licensed under the MIT License."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Azure Machine Learning Pipelines with Data Dependency\n",
-    "In this notebook, we will see how we can build a pipeline with implicit data dependancy."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Prerequisites and Azure Machine Learning Basics\n",
-    "Make sure you go through the configuration Notebook located at https://github.com/Azure/MachineLearningNotebooks first if you haven't. This sets you up with a working config file that has information on your workspace, subscription id, etc. \n",
-    "\n",
-    "### Azure Machine Learning and Pipeline SDK-specific Imports"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import azureml.core\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, 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\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Initialize Workspace\n",
-    "\n",
-    "Initialize a [workspace](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.workspace(class%29) object from persisted configuration."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "create workspace"
-    ]
-   },
-   "outputs": [],
-   "source": [
-    "ws = Workspace.from_config()\n",
-    "print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')\n",
-    "\n",
-    "# Default datastore (Azure file storage)\n",
-    "def_file_store = ws.get_default_datastore() \n",
-    "print(\"Default datastore's name: {}\".format(def_file_store.name))\n",
-    "\n",
-    "def_blob_store = Datastore(ws, \"workspaceblobstore\")\n",
-    "print(\"Blobstore's name: {}\".format(def_blob_store.name))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# project folder\n",
-    "project_folder = '.'\n",
-    "    \n",
-    "print('Sample projects will be created in {}.'.format(project_folder))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Required data and script files for the the tutorial\n",
-    "Sample files required to finish this tutorial are already copied to the project folder specified above. Even though the .py provided in the samples don't have much \"ML work,\" as a data scientist, you will work on this extensively as part of your work. To complete this tutorial, the contents of these files are not very important. The one-line files are for demostration purpose only."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Compute Targets\n",
-    "See the list of Compute Targets on the workspace."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "cts = ws.compute_targets\n",
-    "for ct in cts:\n",
-    "    print(ct)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Retrieve or create a Aml compute\n",
-    "Azure Machine Learning Compute is a service for provisioning and managing clusters of Azure virtual machines for running machine learning workloads. Let's create a new Aml Compute in the current workspace, if it doesn't already exist. We will then run the training script on this compute target."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "aml_compute_target = \"aml-compute\"\n",
-    "try:\n",
-    "    aml_compute = AmlCompute(ws, aml_compute_target)\n",
-    "    print(\"found existing compute target.\")\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",
-    "    \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 the 'status' property\n",
-    "# example: un-comment the following line.\n",
-    "# print(aml_compute.status.serialize())"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "**Wait for this call to finish before proceeding (you will see the asterisk turning to a number).**\n",
-    "\n",
-    "Now that you have created the compute target, let's see what the workspace's compute_targets() function returns. You should now see one entry named 'amlcompute' of type AmlCompute."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Building Pipeline Steps with Inputs and Outputs\n",
-    "As mentioned earlier, a step in the pipeline can take data as input. This data can be a data source that lives in one of the accessible data locations, or intermediate data produced by a previous step in the pipeline.\n",
-    "\n",
-    "### Datasources\n",
-    "Datasource is represented by **[DataReference](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.data_reference.datareference?view=azure-ml-py)** object and points to data that lives in or is accessible from Datastore. DataReference could be a pointer to a file or a directory."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Reference the data uploaded to blob storage using DataReference\n",
-    "# Assign the datasource to blob_input_data variable\n",
-    "\n",
-    "# DataReference(datastore, \n",
-    "#               data_reference_name=None, \n",
-    "#               path_on_datastore=None, \n",
-    "#               mode='mount', \n",
-    "#               path_on_compute=None, \n",
-    "#               overwrite=False)\n",
-    "\n",
-    "blob_input_data = DataReference(\n",
-    "    datastore=def_blob_store,\n",
-    "    data_reference_name=\"test_data\",\n",
-    "    path_on_datastore=\"20newsgroups/20news.pkl\")\n",
-    "print(\"DataReference object created\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Intermediate/Output Data\n",
-    "Intermediate data (or output of a Step) is represented by **[PipelineData](https://docs.microsoft.com/en-us/python/api/azureml-pipeline-core/azureml.pipeline.core.pipelinedata?view=azure-ml-py)** object. PipelineData can be produced by one step and consumed in another step by providing the PipelineData object as an output of one step and the input of one or more steps.\n",
-    "\n",
-    "#### Constructing PipelineData\n",
-    "- **name:** [*Required*] Name of the data item within the pipeline graph\n",
-    "- **datastore_name:** Name of the Datastore to write this output to\n",
-    "- **output_name:** Name of the output\n",
-    "- **output_mode:** Specifies \"upload\" or \"mount\" modes for producing output (default: mount)\n",
-    "- **output_path_on_compute:** For \"upload\" mode, the path to which the module writes this output during execution\n",
-    "- **output_overwrite:** Flag to overwrite pre-existing data"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Define intermediate data using PipelineData\n",
-    "# Syntax\n",
-    "\n",
-    "# PipelineData(name, \n",
-    "#              datastore=None, \n",
-    "#              output_name=None, \n",
-    "#              output_mode='mount', \n",
-    "#              output_path_on_compute=None, \n",
-    "#              output_overwrite=None, \n",
-    "#              data_type=None, \n",
-    "#              is_directory=None)\n",
-    "\n",
-    "# Naming the intermediate data as processed_data1 and assigning it to the variable processed_data1.\n",
-    "processed_data1 = PipelineData(\"processed_data1\",datastore=def_blob_store)\n",
-    "print(\"PipelineData object created\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Pipelines steps using datasources and intermediate data\n",
-    "Machine learning pipelines can have many steps and these steps could use or reuse datasources and intermediate data. Here's how we construct such a pipeline:"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Define a Step that consumes a datasource and produces intermediate data.\n",
-    "In this step, we define a step that consumes a datasource and produces intermediate data.\n",
-    "\n",
-    "**Open `train.py` in the local machine and examine the arguments, inputs, and outputs for the script. That will give you a good sense of why the script argument names used below are important.** "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# step4 consumes the datasource (Datareference) in the previous step\n",
-    "# and produces processed_data1\n",
-    "trainStep = PythonScriptStep(\n",
-    "    script_name=\"train.py\", \n",
-    "    arguments=[\"--input_data\", blob_input_data, \"--output_train\", processed_data1],\n",
-    "    inputs=[blob_input_data],\n",
-    "    outputs=[processed_data1],\n",
-    "    compute_target=aml_compute, \n",
-    "    source_directory=project_folder\n",
-    ")\n",
-    "print(\"trainStep created\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Define a Step that consumes intermediate data and produces intermediate data\n",
-    "In this step, we define a step that consumes an intermediate data and produces intermediate data.\n",
-    "\n",
-    "**Open `extract.py` in the local machine and examine the arguments, inputs, and outputs for the script. That will give you a good sense of why the script argument names used below are important.** "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# step5 to use the intermediate data produced by step4\n",
-    "# This step also produces an output processed_data2\n",
-    "processed_data2 = PipelineData(\"processed_data2\", datastore=def_blob_store)\n",
-    "\n",
-    "extractStep = PythonScriptStep(\n",
-    "    script_name=\"extract.py\",\n",
-    "    arguments=[\"--input_extract\", processed_data1, \"--output_extract\", processed_data2],\n",
-    "    inputs=[processed_data1],\n",
-    "    outputs=[processed_data2],\n",
-    "    compute_target=aml_compute, \n",
-    "    source_directory=project_folder)\n",
-    "print(\"extractStep created\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Define a Step that consumes multiple intermediate data and produces intermediate data\n",
-    "In this step, we define a step that consumes multiple intermediate data and produces intermediate data.\n",
-    "\n",
-    "**Open `compare.py` in the local machine and examine the arguments, inputs, and outputs for the script. That will give you a good sense of why the script argument names used below are important.**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Now define step6 that takes two inputs (both intermediate data), and produce an output\n",
-    "processed_data3 = PipelineData(\"processed_data3\", datastore=def_blob_store)\n",
-    "\n",
-    "compareStep = PythonScriptStep(\n",
-    "    script_name=\"compare.py\",\n",
-    "    arguments=[\"--compare_data1\", processed_data1, \"--compare_data2\", processed_data2, \"--output_compare\", processed_data3],\n",
-    "    inputs=[processed_data1, processed_data2],\n",
-    "    outputs=[processed_data3],    \n",
-    "    compute_target=aml_compute, \n",
-    "    source_directory=project_folder)\n",
-    "print(\"compareStep created\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Build the pipeline"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "pipeline1 = Pipeline(workspace=ws, steps=[compareStep])\n",
-    "print (\"Pipeline is built\")\n",
-    "\n",
-    "pipeline1.validate()\n",
-    "print(\"Simple validation complete\") "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "pipeline_run1 = Experiment(ws, 'Data_dependency').submit(pipeline1)\n",
-    "print(\"Pipeline is submitted for execution\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "RunDetails(pipeline_run1).show()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Next: Publishing the Pipeline and calling it from the REST endpoint\n",
-    "See this [notebook](./aml-pipelines-publish-and-run-using-rest-endpoint.ipynb) to understand how the pipeline is published and you can call the REST endpoint to run the pipeline."
-   ]
-  }
- ],
- "metadata": {
-  "authors": [
-   {
-    "name": "diray"
-   }
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.  \n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Azure Machine Learning Pipelines with Data Dependency\n",
+        "In this notebook, we will see how we can build a pipeline with implicit data dependancy."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Prerequisites and Azure Machine Learning Basics\n",
+        "Make sure you go through the configuration Notebook located at https://github.com/Azure/MachineLearningNotebooks first if you haven't. This sets you up with a working config file that has information on your workspace, subscription id, etc. \n",
+        "\n",
+        "### Azure Machine Learning and Pipeline SDK-specific Imports"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import azureml.core\n",
+        "from azureml.core import Workspace, Experiment, Datastore\n",
+        "from azureml.core.compute import AmlCompute\n",
+        "from azureml.core.compute import ComputeTarget\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.steps import PythonScriptStep\n",
+        "print(\"Pipeline SDK-specific imports completed\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Initialize Workspace\n",
+        "\n",
+        "Initialize a [workspace](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.workspace(class%29) object from persisted configuration."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "create workspace"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')\n",
+        "\n",
+        "# Default datastore (Azure file storage)\n",
+        "def_file_store = ws.get_default_datastore() \n",
+        "print(\"Default datastore's name: {}\".format(def_file_store.name))\n",
+        "\n",
+        "def_blob_store = Datastore(ws, \"workspaceblobstore\")\n",
+        "print(\"Blobstore's name: {}\".format(def_blob_store.name))"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# project folder\n",
+        "project_folder = '.'\n",
+        "    \n",
+        "print('Sample projects will be created in {}.'.format(project_folder))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Required data and script files for the the tutorial\n",
+        "Sample files required to finish this tutorial are already copied to the project folder specified above. Even though the .py provided in the samples don't have much \"ML work,\" as a data scientist, you will work on this extensively as part of your work. To complete this tutorial, the contents of these files are not very important. The one-line files are for demostration purpose only."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Compute Targets\n",
+        "See the list of Compute Targets on the workspace."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "cts = ws.compute_targets\n",
+        "for ct in cts:\n",
+        "    print(ct)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Retrieve or create a Aml compute\n",
+        "Azure Machine Learning Compute is a service for provisioning and managing clusters of Azure virtual machines for running machine learning workloads. Let's create a new Aml Compute in the current workspace, if it doesn't already exist. We will then run the training script on this compute target."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "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",
+        "    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",
+        "    \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())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "**Wait for this call to finish before proceeding (you will see the asterisk turning to a number).**\n",
+        "\n",
+        "Now that you have created the compute target, let's see what the workspace's compute_targets() function returns. You should now see one entry named 'amlcompute' of type AmlCompute."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Building Pipeline Steps with Inputs and Outputs\n",
+        "As mentioned earlier, a step in the pipeline can take data as input. This data can be a data source that lives in one of the accessible data locations, or intermediate data produced by a previous step in the pipeline.\n",
+        "\n",
+        "### Datasources\n",
+        "Datasource is represented by **[DataReference](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.data_reference.datareference?view=azure-ml-py)** object and points to data that lives in or is accessible from Datastore. DataReference could be a pointer to a file or a directory."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Reference the data uploaded to blob storage using DataReference\n",
+        "# Assign the datasource to blob_input_data variable\n",
+        "\n",
+        "# DataReference(datastore, \n",
+        "#               data_reference_name=None, \n",
+        "#               path_on_datastore=None, \n",
+        "#               mode='mount', \n",
+        "#               path_on_compute=None, \n",
+        "#               overwrite=False)\n",
+        "\n",
+        "blob_input_data = DataReference(\n",
+        "    datastore=def_blob_store,\n",
+        "    data_reference_name=\"test_data\",\n",
+        "    path_on_datastore=\"20newsgroups/20news.pkl\")\n",
+        "print(\"DataReference object created\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Intermediate/Output Data\n",
+        "Intermediate data (or output of a Step) is represented by **[PipelineData](https://docs.microsoft.com/en-us/python/api/azureml-pipeline-core/azureml.pipeline.core.pipelinedata?view=azure-ml-py)** object. PipelineData can be produced by one step and consumed in another step by providing the PipelineData object as an output of one step and the input of one or more steps.\n",
+        "\n",
+        "#### Constructing PipelineData\n",
+        "- **name:** [*Required*] Name of the data item within the pipeline graph\n",
+        "- **datastore_name:** Name of the Datastore to write this output to\n",
+        "- **output_name:** Name of the output\n",
+        "- **output_mode:** Specifies \"upload\" or \"mount\" modes for producing output (default: mount)\n",
+        "- **output_path_on_compute:** For \"upload\" mode, the path to which the module writes this output during execution\n",
+        "- **output_overwrite:** Flag to overwrite pre-existing data"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Define intermediate data using PipelineData\n",
+        "# Syntax\n",
+        "\n",
+        "# PipelineData(name, \n",
+        "#              datastore=None, \n",
+        "#              output_name=None, \n",
+        "#              output_mode='mount', \n",
+        "#              output_path_on_compute=None, \n",
+        "#              output_overwrite=None, \n",
+        "#              data_type=None, \n",
+        "#              is_directory=None)\n",
+        "\n",
+        "# Naming the intermediate data as processed_data1 and assigning it to the variable processed_data1.\n",
+        "processed_data1 = PipelineData(\"processed_data1\",datastore=def_blob_store)\n",
+        "print(\"PipelineData object created\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Pipelines steps using datasources and intermediate data\n",
+        "Machine learning pipelines can have many steps and these steps could use or reuse datasources and intermediate data. Here's how we construct such a pipeline:"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Define a Step that consumes a datasource and produces intermediate data.\n",
+        "In this step, we define a step that consumes a datasource and produces intermediate data.\n",
+        "\n",
+        "**Open `train.py` in the local machine and examine the arguments, inputs, and outputs for the script. That will give you a good sense of why the script argument names used below are important.** "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# step4 consumes the datasource (Datareference) in the previous step\n",
+        "# and produces processed_data1\n",
+        "trainStep = PythonScriptStep(\n",
+        "    script_name=\"train.py\", \n",
+        "    arguments=[\"--input_data\", blob_input_data, \"--output_train\", processed_data1],\n",
+        "    inputs=[blob_input_data],\n",
+        "    outputs=[processed_data1],\n",
+        "    compute_target=aml_compute, \n",
+        "    source_directory=project_folder\n",
+        ")\n",
+        "print(\"trainStep created\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Define a Step that consumes intermediate data and produces intermediate data\n",
+        "In this step, we define a step that consumes an intermediate data and produces intermediate data.\n",
+        "\n",
+        "**Open `extract.py` in the local machine and examine the arguments, inputs, and outputs for the script. That will give you a good sense of why the script argument names used below are important.** "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# step5 to use the intermediate data produced by step4\n",
+        "# This step also produces an output processed_data2\n",
+        "processed_data2 = PipelineData(\"processed_data2\", datastore=def_blob_store)\n",
+        "\n",
+        "extractStep = PythonScriptStep(\n",
+        "    script_name=\"extract.py\",\n",
+        "    arguments=[\"--input_extract\", processed_data1, \"--output_extract\", processed_data2],\n",
+        "    inputs=[processed_data1],\n",
+        "    outputs=[processed_data2],\n",
+        "    compute_target=aml_compute, \n",
+        "    source_directory=project_folder)\n",
+        "print(\"extractStep created\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Define a Step that consumes multiple intermediate data and produces intermediate data\n",
+        "In this step, we define a step that consumes multiple intermediate data and produces intermediate data.\n",
+        "\n",
+        "**Open `compare.py` in the local machine and examine the arguments, inputs, and outputs for the script. That will give you a good sense of why the script argument names used below are important.**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Now define step6 that takes two inputs (both intermediate data), and produce an output\n",
+        "processed_data3 = PipelineData(\"processed_data3\", datastore=def_blob_store)\n",
+        "\n",
+        "compareStep = PythonScriptStep(\n",
+        "    script_name=\"compare.py\",\n",
+        "    arguments=[\"--compare_data1\", processed_data1, \"--compare_data2\", processed_data2, \"--output_compare\", processed_data3],\n",
+        "    inputs=[processed_data1, processed_data2],\n",
+        "    outputs=[processed_data3],    \n",
+        "    compute_target=aml_compute, \n",
+        "    source_directory=project_folder)\n",
+        "print(\"compareStep created\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Build the pipeline"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "pipeline1 = Pipeline(workspace=ws, steps=[compareStep])\n",
+        "print (\"Pipeline is built\")\n",
+        "\n",
+        "pipeline1.validate()\n",
+        "print(\"Simple validation complete\") "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "pipeline_run1 = Experiment(ws, 'Data_dependency').submit(pipeline1)\n",
+        "print(\"Pipeline is submitted for execution\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "RunDetails(pipeline_run1).show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Next: Publishing the Pipeline and calling it from the REST endpoint\n",
+        "See this [notebook](./aml-pipelines-publish-and-run-using-rest-endpoint.ipynb) to understand how the pipeline is published and you can call the REST endpoint to run the pipeline."
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
+  "metadata": {
+    "authors": [
+      {
+        "name": "diray"
+      }
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "python",
+      "name": "python36"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.7"
+    }
   },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.6.7"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,8 +1,16 @@
 ## Azure Machine Learning service training examples
 
 These examples show you:
- * Distributed training of models on Machine Learning Compute cluster
- * Hyperparameter tuning at scale
- * Using Tensorboard with Azure ML Python SDK.
+
+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).

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

@@ -1,394 +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": [
-    "# 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 [00.configuration.ipynb]() notebook 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://review.docs.microsoft.com/en-us/azure/machine-learning/service/concept-azure-machine-learning-architecture?branch=release-ignite-aml#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 the 'status' property to get a detailed status for the current AmlCompute. \n",
-    "print(compute_target.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 *\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"
-   }
+  "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)"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "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"
+    }
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,335 +1,335 @@
 {
- "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 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."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Prerequisites\n",
-    "* Go through the [Configuration](https://github.com/Azure/MachineLearningNotebooks/blob/master/configuration.ipynb) notebook to install the Azure Machine Learning Python SDK and create an Azure ML `Workspace`\n",
-    "* Review the [tutorial](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/training-with-deep-learning/train-hyperparameter-tune-deploy-with-pytorch/train-hyperparameter-tune-deploy-with-pytorch.ipynb) on single-node PyTorch training using Azure Machine Learning"
-   ]
-  },
-  {
-   "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, 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",
-    "\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 the 'status' property to get a detailed status for the current AmlCompute. \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`."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "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."
-   ]
-  },
-  {
-   "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 = './pytorch-distr-hvd'\n",
-    "os.makedirs(project_folder, exist_ok=True)"
-   ]
-  },
-  {
-   "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."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import shutil\n",
-    "\n",
-    "shutil.copy('pytorch_horovod_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 PyTorch tutorial. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core import Experiment\n",
-    "\n",
-    "experiment_name = 'pytorch-distr-hvd'\n",
-    "experiment = Experiment(ws, name=experiment_name)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "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)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.train.dnn import PyTorch\n",
-    "\n",
-    "estimator = PyTorch(source_directory=project_folder,\n",
-    "                    compute_target=compute_target,\n",
-    "                    entry_script='pytorch_horovod_mnist.py',\n",
-    "                    node_count=2,\n",
-    "                    process_count_per_node=1,\n",
-    "                    distributed_backend='mpi',\n",
-    "                    use_gpu=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The above code specifies that we will run our training script on `2` nodes, with one worker per node. In order to execute a distributed run using MPI/Horovod, you must provide the argument `distributed_backend='mpi'`. Using this estimator with these settings, PyTorch, Horovod and their dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `PyTorch` constructor's `pip_packages` or `conda_packages` parameters."
-   ]
-  },
-  {
-   "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. You can see that the widget automatically plots and visualizes the loss metric that we logged to the Azure ML run."
-   ]
-  },
-  {
-   "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) # this provides a verbose log"
-   ]
-  }
- ],
- "metadata": {
-  "authors": [
-   {
-    "name": "minxia"
-   }
+  "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 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."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "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"
+      ]
+    },
+    {
+      "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, 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",
+        "\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": [
+        "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`."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "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."
+      ]
+    },
+    {
+      "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 = './pytorch-distr-hvd'\n",
+        "os.makedirs(project_folder, exist_ok=True)"
+      ]
+    },
+    {
+      "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."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import shutil\n",
+        "\n",
+        "shutil.copy('pytorch_horovod_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 PyTorch tutorial. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core import Experiment\n",
+        "\n",
+        "experiment_name = 'pytorch-distr-hvd'\n",
+        "experiment = Experiment(ws, name=experiment_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "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)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.train.dnn import PyTorch\n",
+        "\n",
+        "estimator = PyTorch(source_directory=project_folder,\n",
+        "                    compute_target=compute_target,\n",
+        "                    entry_script='pytorch_horovod_mnist.py',\n",
+        "                    node_count=2,\n",
+        "                    process_count_per_node=1,\n",
+        "                    distributed_backend='mpi',\n",
+        "                    use_gpu=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "The above code specifies that we will run our training script on `2` nodes, with one worker per node. In order to execute a distributed run using MPI/Horovod, you must provide the argument `distributed_backend='mpi'`. Using this estimator with these settings, PyTorch, Horovod and their dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `PyTorch` constructor's `pip_packages` or `conda_packages` parameters."
+      ]
+    },
+    {
+      "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. You can see that the widget automatically plots and visualizes the loss metric that we logged to the Azure ML run."
+      ]
+    },
+    {
+      "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) # this provides a verbose log"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "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"
+    },
+    "msauthor": "minxia"
   },
-  "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"
-  },
-  "msauthor": "minxia"
- },
- "nbformat": 4,
- "nbformat_minor": 2
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -50,7 +50,7 @@ if args.cuda:
     torch.cuda.manual_seed(args.seed)
 
 
-kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
+kwargs = {}
 train_dataset = \
     datasets.MNIST('data-%d' % hvd.rank(), train=True, download=True,
                    transform=transforms.Compose([

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

@@ -1,404 +1,402 @@
 {
- "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 Tensorflow with Horovod\n",
-    "In this tutorial, you will train a word2vec model in TensorFlow using distributed training via [Horovod](https://github.com/uber/horovod)."
-   ]
-  },
-  {
-   "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 (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-hyperdrive) on single-node TensorFlow training using the SDK"
-   ]
-  },
-  {
-   "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",
-    "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 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 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`."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Upload data to datastore\n",
-    "To make data accessible for remote training, 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 to Azure Storage, and interact with it from your remote compute targets. \n",
-    "\n",
-    "If your data is already stored in Azure, or you download the data as part of your training script, you will not need to do this step. For this tutorial, although you can download the data in your training script, we will demonstrate how to upload the training data to a datastore and access it during training to illustrate the datastore functionality."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "First, download the training data from [here](http://mattmahoney.net/dc/text8.zip) to your local machine:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "import urllib\n",
-    "\n",
-    "os.makedirs('./data', exist_ok=True)\n",
-    "download_url = 'http://mattmahoney.net/dc/text8.zip'\n",
-    "urllib.request.urlretrieve(download_url, filename='./data/text8.zip')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Each workspace is associated with a default datastore. In this tutorial, we will upload the training data to this default datastore."
-   ]
-  },
-  {
-   "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": [
-    "Upload the contents of the data directory to the path `./data` on the default datastore."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "ds.upload(src_dir='data', target_path='data', overwrite=True, show_progress=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "For convenience, let's get a reference to the path on the datastore with the zip file of 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 `--input_data` argument. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "path_on_datastore = 'data/text8.zip'\n",
-    "ds_data = ds.path(path_on_datastore)\n",
-    "print(ds_data)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Train model on the remote compute"
-   ]
-  },
-  {
-   "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 = './tf-distr-hvd'\n",
-    "os.makedirs(project_folder, exist_ok=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Copy the training script `tf_horovod_word2vec.py` into this project directory."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import shutil\n",
-    "\n",
-    "shutil.copy('tf_horovod_word2vec.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 TensorFlow tutorial. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core import Experiment\n",
-    "\n",
-    "experiment_name = 'tf-distr-hvd'\n",
-    "experiment = Experiment(ws, name=experiment_name)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Create a TensorFlow estimator\n",
-    "The AML SDK's TensorFlow estimator enables you to easily submit TensorFlow training jobs for both single-node and distributed runs. For more information on the TensorFlow estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-tensorflow)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.train.dnn import TensorFlow\n",
-    "\n",
-    "script_params={\n",
-    "    '--input_data': ds_data\n",
-    "}\n",
-    "\n",
-    "estimator= TensorFlow(source_directory=project_folder,\n",
-    "                      compute_target=compute_target,\n",
-    "                      script_params=script_params,\n",
-    "                      entry_script='tf_horovod_word2vec.py',\n",
-    "                      node_count=2,\n",
-    "                      process_count_per_node=1,\n",
-    "                      distributed_backend='mpi',\n",
-    "                      use_gpu=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The above code specifies that we will run our training script on `2` nodes, with one worker per node. In order to execute a distributed run using MPI/Horovod, you must provide the argument `distributed_backend='mpi'`. Using this estimator with these settings, TensorFlow, Horovod and their dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `TensorFlow` constructor's `pip_packages` or `conda_packages` parameters.\n",
-    "\n",
-    "Note that we passed our training data reference `ds_data` to our script's `--input_data` argument. This will 1) mount our datastore on the remote compute and 2) provide the path to the data zip file on our datastore."
-   ]
-  },
-  {
-   "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",
-    "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": "roastala"
-   }
+  "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 Tensorflow with Horovod\n",
+        "In this tutorial, you will train a word2vec model in TensorFlow using distributed training via [Horovod](https://github.com/uber/horovod)."
+      ]
+    },
+    {
+      "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 (AML)\n",
+        "* Go through the [configuration notebook](../../../configuration.ipynb) 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"
+      ]
+    },
+    {
+      "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",
+        "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/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 cluster. \n",
+        "print(compute_target.get_status().serialize())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "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`."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Upload data to datastore\n",
+        "To make data accessible for remote training, 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 to Azure Storage, and interact with it from your remote compute targets. \n",
+        "\n",
+        "If your data is already stored in Azure, or you download the data as part of your training script, you will not need to do this step. For this tutorial, although you can download the data in your training script, we will demonstrate how to upload the training data to a datastore and access it during training to illustrate the datastore functionality."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "First, download the training data from [here](http://mattmahoney.net/dc/text8.zip) to your local machine:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "import urllib\n",
+        "\n",
+        "os.makedirs('./data', exist_ok=True)\n",
+        "download_url = 'http://mattmahoney.net/dc/text8.zip'\n",
+        "urllib.request.urlretrieve(download_url, filename='./data/text8.zip')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Each workspace is associated with a default datastore. In this tutorial, we will upload the training data to this default datastore."
+      ]
+    },
+    {
+      "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": [
+        "Upload the contents of the data directory to the path `./data` on the default datastore."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ds.upload(src_dir='data', target_path='data', overwrite=True, show_progress=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "For convenience, let's get a reference to the path on the datastore with the zip file of 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 `--input_data` argument. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "path_on_datastore = 'data/text8.zip'\n",
+        "ds_data = ds.path(path_on_datastore)\n",
+        "print(ds_data)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train model on the remote compute"
+      ]
+    },
+    {
+      "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": [
+        "project_folder = './tf-distr-hvd'\n",
+        "os.makedirs(project_folder, exist_ok=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copy the training script `tf_horovod_word2vec.py` into this project directory."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import shutil\n",
+        "\n",
+        "shutil.copy('tf_horovod_word2vec.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 TensorFlow tutorial. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core import Experiment\n",
+        "\n",
+        "experiment_name = 'tf-distr-hvd'\n",
+        "experiment = Experiment(ws, name=experiment_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create a TensorFlow estimator\n",
+        "The AML SDK's TensorFlow estimator enables you to easily submit TensorFlow training jobs for both single-node and distributed runs. For more information on the TensorFlow estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-tensorflow)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.train.dnn import TensorFlow\n",
+        "\n",
+        "script_params={\n",
+        "    '--input_data': ds_data\n",
+        "}\n",
+        "\n",
+        "estimator= TensorFlow(source_directory=project_folder,\n",
+        "                      compute_target=compute_target,\n",
+        "                      script_params=script_params,\n",
+        "                      entry_script='tf_horovod_word2vec.py',\n",
+        "                      node_count=2,\n",
+        "                      process_count_per_node=1,\n",
+        "                      distributed_backend='mpi',\n",
+        "                      use_gpu=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "The above code specifies that we will run our training script on `2` nodes, with one worker per node. In order to execute a distributed run using MPI/Horovod, you must provide the argument `distributed_backend='mpi'`. Using this estimator with these settings, TensorFlow, Horovod and their dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `TensorFlow` constructor's `pip_packages` or `conda_packages` parameters.\n",
+        "\n",
+        "Note that we passed our training data reference `ds_data` to our script's `--input_data` argument. This will 1) mount our datastore on the remote compute and 2) provide the path to the data zip file on our datastore."
+      ]
+    },
+    {
+      "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",
+        "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)"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "metadata": {
+    "authors": [
+      {
+        "name": "roastala"
+      }
+    ],
+    "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"
+    },
+    "msauthor": "minxia"
   },
-  "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"
-  },
-  "msauthor": "minxia"
- },
- "nbformat": 4,
- "nbformat_minor": 2
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,317 +1,317 @@
 {
- "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 TensorFlow with parameter server\n",
-    "In this tutorial, you will train a TensorFlow model on the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset using native [distributed TensorFlow](https://www.tensorflow.org/deploy/distributed)."
-   ]
-  },
-  {
-   "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 (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-hyperdrive) on single-node TensorFlow training using the SDK"
-   ]
-  },
-  {
-   "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",
-    "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 the 'status' property to get a detailed status for the current cluster. \n",
-    "print(compute_target.status.serialize())"
-   ]
-  },
-  {
-   "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 = './tf-distr-ps'\n",
-    "os.makedirs(project_folder, exist_ok=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Copy the training script `tf_mnist_replica.py` into this project directory."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import shutil\n",
-    "\n",
-    "shutil.copy('tf_mnist_replica.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 TensorFlow tutorial. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core import Experiment\n",
-    "\n",
-    "experiment_name = 'tf-distr-ps'\n",
-    "experiment = Experiment(ws, name=experiment_name)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Create a TensorFlow estimator\n",
-    "The AML SDK's TensorFlow estimator enables you to easily submit TensorFlow training jobs for both single-node and distributed runs. For more information on the TensorFlow estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-tensorflow)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.train.dnn import TensorFlow\n",
-    "\n",
-    "script_params={\n",
-    "    '--num_gpus': 1,\n",
-    "    '--train_steps': 500\n",
-    "}\n",
-    "\n",
-    "estimator = TensorFlow(source_directory=project_folder,\n",
-    "                       compute_target=compute_target,\n",
-    "                       script_params=script_params,\n",
-    "                       entry_script='tf_mnist_replica.py',\n",
-    "                       node_count=2,\n",
-    "                       worker_count=2,\n",
-    "                       parameter_server_count=1,   \n",
-    "                       distributed_backend='ps',\n",
-    "                       use_gpu=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The above code specifies that we will run our training script on `2` nodes, with two workers and one parameter server. In order to execute a native distributed TensorFlow run, you must provide the argument `distributed_backend='ps'`. Using this estimator with these settings, TensorFlow and its dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `TensorFlow` constructor's `pip_packages` or `conda_packages` parameters."
-   ]
-  },
-  {
-   "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) # this provides a verbose log"
-   ]
-  }
- ],
- "metadata": {
-  "authors": [
-   {
-    "name": "minxia"
-   }
+  "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 TensorFlow with parameter server\n",
+        "In this tutorial, you will train a TensorFlow model on the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset using native [distributed TensorFlow](https://www.tensorflow.org/deploy/distributed)."
+      ]
+    },
+    {
+      "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 (AML)\n",
+        "* Go through the [configuration notebook](../../../configuration.ipynb) 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"
+      ]
+    },
+    {
+      "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",
+        "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 cluster. \n",
+        "print(compute_target.get_status().serialize())"
+      ]
+    },
+    {
+      "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 = './tf-distr-ps'\n",
+        "os.makedirs(project_folder, exist_ok=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copy the training script `tf_mnist_replica.py` into this project directory."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import shutil\n",
+        "\n",
+        "shutil.copy('tf_mnist_replica.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 TensorFlow tutorial. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core import Experiment\n",
+        "\n",
+        "experiment_name = 'tf-distr-ps'\n",
+        "experiment = Experiment(ws, name=experiment_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create a TensorFlow estimator\n",
+        "The AML SDK's TensorFlow estimator enables you to easily submit TensorFlow training jobs for both single-node and distributed runs. For more information on the TensorFlow estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-tensorflow)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.train.dnn import TensorFlow\n",
+        "\n",
+        "script_params={\n",
+        "    '--num_gpus': 1,\n",
+        "    '--train_steps': 500\n",
+        "}\n",
+        "\n",
+        "estimator = TensorFlow(source_directory=project_folder,\n",
+        "                       compute_target=compute_target,\n",
+        "                       script_params=script_params,\n",
+        "                       entry_script='tf_mnist_replica.py',\n",
+        "                       node_count=2,\n",
+        "                       worker_count=2,\n",
+        "                       parameter_server_count=1,   \n",
+        "                       distributed_backend='ps',\n",
+        "                       use_gpu=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "The above code specifies that we will run our training script on `2` nodes, with two workers and one parameter server. In order to execute a native distributed TensorFlow run, you must provide the argument `distributed_backend='ps'`. Using this estimator with these settings, TensorFlow and its dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `TensorFlow` constructor's `pip_packages` or `conda_packages` parameters."
+      ]
+    },
+    {
+      "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) # this provides a verbose log"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "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"
+    },
+    "msauthor": "minxia"
   },
-  "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"
-  },
-  "msauthor": "minxia"
- },
- "nbformat": 4,
- "nbformat_minor": 2
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

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

@@ -1,267 +1,265 @@
 {
- "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": [
-    "# Export Run History as Tensorboard logs\n",
-    "\n",
-    "1. Run some training and log some metrics into Run History\n",
-    "2. Export the run history to some directory as Tensorboard logs\n",
-    "3. Launch a local Tensorboard to view the run history"
-   ]
-  },
-  {
-   "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 [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`)"
-   ]
-  },
-  {
-   "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": [
-    "Install the Azure ML TensorBoard integration package if you haven't already."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip install azureml-contrib-tensorboard"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Initialize Workspace\n",
-    "\n",
-    "Initialize a workspace object from persisted configuration."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "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')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Set experiment name and start the run"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "experiment_name = 'export-to-tensorboard'\n",
-    "exp = Experiment(ws, experiment_name)\n",
-    "root_run = exp.start_logging()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# load 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)\n",
-    "data = {\n",
-    "    \"train\":{\"x\":x_train, \"y\":y_train},        \n",
-    "    \"test\":{\"x\":x_test, \"y\":y_test}\n",
-    "}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Example experiment\n",
-    "from tqdm import tqdm\n",
-    "\n",
-    "alphas = [.1, .2, .3, .4, .5, .6 , .7]\n",
-    "\n",
-    "# try a bunch of alpha values in a Linear Regression (Ridge) model\n",
-    "for alpha in tqdm(alphas):\n",
-    "    # create a bunch of child runs\n",
-    "    with root_run.child_run(\"alpha\" + str(alpha)) as run:\n",
-    "        # More data science stuff\n",
-    "        reg = Ridge(alpha=alpha)\n",
-    "        reg.fit(data[\"train\"][\"x\"], data[\"train\"][\"y\"])\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",
-    "\n",
-    "        # log alpha, mean_squared_error and feature names in run history\n",
-    "        root_run.log(\"alpha\", alpha)\n",
-    "        root_run.log(\"mse\", mse)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Export Run History to Tensorboard logs"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# 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",
-    "try:\n",
-    "    os.stat(log_path)\n",
-    "except os.error:\n",
-    "    os.mkdir(log_path)\n",
-    "print(logdir)\n",
-    "\n",
-    "# export run history for the project\n",
-    "export_to_tensorboard(root_run, logdir)\n",
-    "\n",
-    "# or export a particular run\n",
-    "# export_to_tensorboard(run, logdir)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "root_run.complete()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Start Tensorboard\n",
-    "\n",
-    "Or you can start the Tensorboard outside this notebook to view the result"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.contrib.tensorboard import Tensorboard\n",
-    "\n",
-    "# The Tensorboard constructor takes an array of runs, so be sure and pass it in as a single-element array here\n",
-    "tb = Tensorboard([], local_root=logdir, port=6006)\n",
-    "\n",
-    "# If successful, start() returns a string with the URI of the instance.\n",
-    "tb.start()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Stop Tensorboard\n",
-    "\n",
-    "When you're done, make sure to call the `stop()` method of the Tensorboard object."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tb.stop()"
-   ]
-  }
- ],
- "metadata": {
-  "authors": [
-   {
-    "name": "roastala"
-   }
+  "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": [
+        "# Export Run History as Tensorboard logs\n",
+        "\n",
+        "1. Run some training and log some metrics into Run History\n",
+        "2. Export the run history to some directory as Tensorboard logs\n",
+        "3. Launch a local Tensorboard to view the run history"
+      ]
+    },
+    {
+      "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) notebook 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": [
+        "Install the Azure ML TensorBoard integration package if you haven't already."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "!pip install azureml-contrib-tensorboard"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Initialize Workspace\n",
+        "\n",
+        "Initialize a workspace object from persisted configuration."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core import Workspace, Experiment\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": [
+        "## Set experiment name and start the run"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "experiment_name = 'export-to-tensorboard'\n",
+        "exp = Experiment(ws, experiment_name)\n",
+        "root_run = exp.start_logging()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# load 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)\n",
+        "data = {\n",
+        "    \"train\":{\"x\":x_train, \"y\":y_train},        \n",
+        "    \"test\":{\"x\":x_test, \"y\":y_test}\n",
+        "}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Example experiment\n",
+        "from tqdm import tqdm\n",
+        "\n",
+        "alphas = [.1, .2, .3, .4, .5, .6 , .7]\n",
+        "\n",
+        "# try a bunch of alpha values in a Linear Regression (Ridge) model\n",
+        "for alpha in tqdm(alphas):\n",
+        "    # create a bunch of child runs\n",
+        "    with root_run.child_run(\"alpha\" + str(alpha)) as run:\n",
+        "        # More data science stuff\n",
+        "        reg = Ridge(alpha=alpha)\n",
+        "        reg.fit(data[\"train\"][\"x\"], data[\"train\"][\"y\"])\n",
+        "        \n",
+        "        preds = reg.predict(data[\"test\"][\"x\"])\n",
+        "        mse = mean_squared_error(preds, data[\"test\"][\"y\"])\n",
+        "        # End train and eval\n",
+        "\n",
+        "        # log alpha, mean_squared_error and feature names in run history\n",
+        "        root_run.log(\"alpha\", alpha)\n",
+        "        root_run.log(\"mse\", mse)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Export Run History to Tensorboard logs"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Export Run History to Tensorboard logs\n",
+        "from azureml.contrib.tensorboard.export import export_to_tensorboard\n",
+        "import os\n",
+        "\n",
+        "logdir = 'exportedTBlogs'\n",
+        "log_path = os.path.join(os.getcwd(), logdir)\n",
+        "try:\n",
+        "    os.stat(log_path)\n",
+        "except os.error:\n",
+        "    os.mkdir(log_path)\n",
+        "print(logdir)\n",
+        "\n",
+        "# export run history for the project\n",
+        "export_to_tensorboard(root_run, logdir)\n",
+        "\n",
+        "# or export a particular run\n",
+        "# export_to_tensorboard(run, logdir)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "root_run.complete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Start Tensorboard\n",
+        "\n",
+        "Or you can start the Tensorboard outside this notebook to view the result"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.contrib.tensorboard import Tensorboard\n",
+        "\n",
+        "# The Tensorboard constructor takes an array of runs, so be sure and pass it in as a single-element array here\n",
+        "tb = Tensorboard([], local_root=logdir, port=6006)\n",
+        "\n",
+        "# If successful, start() returns a string with the URI of the instance.\n",
+        "tb.start()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Stop Tensorboard\n",
+        "\n",
+        "When you're done, make sure to call the `stop()` method of the Tensorboard object."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "tb.stop()"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "metadata": {
+    "authors": [
+      {
+        "name": "roastala"
+      }
+    ],
+    "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"
+    }
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

how-to-use-azureml/training-with-deep-learning/how-to-use-estimator/dummy_train.py

@@ -0,0 +1,16 @@
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License.
+
+print("*********************************************************")
+print("Hello Azure ML!")
+
+try:
+    from azureml.core import Run
+    run = Run.get_context()
+    print("Log Fibonacci numbers.")
+    run.log_list('Fibonacci numbers', [0, 1, 1, 2, 3, 5, 8, 13, 21, 34])
+    run.complete()
+except:
+    print("Warning: you need to install Azure ML SDK in order to log metrics.")
+
+print("*********************************************************")

how-to-use-azureml/training-with-deep-learning/how-to-use-estimator/how-to-use-estimator.ipynb

@@ -0,0 +1,365 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "nbpresent": {
+          "id": "bf74d2e9-2708-49b1-934b-e0ede342f475"
+        }
+      },
+      "source": [
+        "# How to use Estimator in Azure ML\n",
+        "\n",
+        "## Introduction\n",
+        "This tutorial shows how to use the Estimator pattern in Azure Machine Learning SDK. Estimator is a convenient object in Azure Machine Learning that wraps run configuration information to help simplify the tasks of specifying how a script is executed.\n",
+        "\n",
+        "\n",
+        "## Prerequisite:\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": "markdown",
+      "metadata": {},
+      "source": [
+        "Let's get started. First let's import some Python libraries."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "nbpresent": {
+          "id": "edaa7f2f-2439-4148-b57a-8c794c0945ec"
+        }
+      },
+      "outputs": [],
+      "source": [
+        "import azureml.core\n",
+        "from azureml.core import Workspace\n",
+        "\n",
+        "# check core SDK version number\n",
+        "print(\"Azure ML SDK Version: \", azureml.core.VERSION)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Initialize workspace\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": [
+        "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": {
+        "nbpresent": {
+          "id": "59f52294-4a25-4c92-bab8-3b07f0f44d15"
+        }
+      },
+      "source": [
+        "## Create an Azure ML experiment\n",
+        "Let's create an experiment named \"estimator-test\". The script runs will be recorded under this experiment in Azure."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "nbpresent": {
+          "id": "bc70f780-c240-4779-96f3-bc5ef9a37d59"
+        }
+      },
+      "outputs": [],
+      "source": [
+        "from azureml.core import Experiment\n",
+        "\n",
+        "exp = Experiment(workspace=ws, name='estimator-test')"
+      ]
+    },
+    {
+      "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."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "If we could not find the cluster with the given name, then we will create a new cluster here. We will create an `AmlCompute` cluster of `STANDARD_NC6` GPU VMs. This process is broken down into 3 steps:\n",
+        "1. create the configuration (this step is local and only takes a second)\n",
+        "2. create the cluster (this step will take about **20 seconds**)\n",
+        "3. provision the VMs to bring the cluster to the initial size (of 1 in this case). This step will take about **3-5 minutes** and is providing only sparse output in the process. Please make sure to wait until the call returns before moving to the next cell"
+      ]
+    },
+    {
+      "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 = \"cpucluster\"\n",
+        "\n",
+        "try:\n",
+        "    cpu_cluster = 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', max_nodes=4)\n",
+        "\n",
+        "    # create the cluster\n",
+        "    cpu_cluster = ComputeTarget.create(ws, cluster_name, compute_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 uses the scale settings for the cluster\n",
+        "    cpu_cluster.wait_for_completion(show_output=True, min_node_count=None, timeout_in_minutes=20)\n",
+        "\n",
+        "# use get_status() to get a detailed status for the current cluster. \n",
+        "print(cpu_cluster.get_status().serialize())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Now that you have created the compute target, let's see what the workspace's `compute_targets` property returns. You should now see one entry named 'cpucluster' of type `AmlCompute`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "compute_targets = ws.compute_targets\n",
+        "for name, ct in compute_targets.items():\n",
+        "    print(name, ct.type, ct.provisioning_state)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "nbpresent": {
+          "id": "2039d2d5-aca6-4f25-a12f-df9ae6529cae"
+        }
+      },
+      "source": [
+        "## Use a simple script\n",
+        "We have already created a simple \"hello world\" script. This is the script that we will submit through the estimator pattern. It prints a hello-world message, and if Azure ML SDK is installed, it will also logs an array of values ([Fibonacci numbers](https://en.wikipedia.org/wiki/Fibonacci_number))."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "with open('./dummy_train.py', 'r') as f:\n",
+        "    print(f.read())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Create A Generic Estimator"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "First we import the Estimator class and also a widget to visualize a run."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.train.estimator import Estimator\n",
+        "from azureml.widgets import RunDetails"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "The simplest estimator is to submit the current folder to the local computer. Estimator by default will attempt to use Docker-based execution. Let's turn that off for now. It then builds a conda environment locally, installs Azure ML SDK in it, and runs your script."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# use a conda environment, don't use Docker, on local computer\n",
+        "est = Estimator(source_directory='.', compute_target='local', entry_script='dummy_train.py', use_docker=False)\n",
+        "run = exp.submit(est)\n",
+        "RunDetails(run).show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can also enable Docker and let estimator pick the default CPU image supplied by Azure ML for execution. You can target an AmlCompute cluster (or any other supported compute target types)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# use a conda environment on default Docker image in an AmlCompute cluster\n",
+        "est = Estimator(source_directory='.', compute_target=cpu_cluster, entry_script='dummy_train.py', use_docker=True)\n",
+        "run = exp.submit(est)\n",
+        "RunDetails(run).show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can customize the conda environment by adding conda and/or pip packages."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# add a conda package\n",
+        "est = Estimator(source_directory='.', \n",
+        "                compute_target='local', \n",
+        "                entry_script='dummy_train.py', \n",
+        "                use_docker=False, \n",
+        "                conda_packages=['scikit-learn'])\n",
+        "run = exp.submit(est)\n",
+        "RunDetails(run).show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can also specify a custom Docker image for exeution. In this case, you probably want to tell the system not to build a new conda environment for you. Instead, you can specify the path to an existing Python environment in the custom Docker image.\n",
+        "\n",
+        "**Note**: since the below example points to the preinstalled Python environment in the miniconda3 image maintained by continuum.io on Docker Hub where Azure ML SDK is not present, the logging metric code is not triggered. But a run history record is still recorded. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# use a custom Docker image\n",
+        "from azureml.core import RunConfiguration\n",
+        "\n",
+        "rc = RunConfiguration()\n",
+        "rc.environment.docker.enabled = True\n",
+        "\n",
+        "# this is an image available in Docker Hub\n",
+        "rc.environment.docker.base_image = 'continuumio/miniconda3'\n",
+        "\n",
+        "# you can also point to an image in a private ACR\n",
+        "#rc.environment.docker.base_image = \"mycustomimage:1.0\"\n",
+        "#rc.environment.docker.base_image_registry.address = \"myregistry.azurecr.io\"\n",
+        "#rc.environment.docker.base_image_registry.username = \"username\"\n",
+        "#rc.environment.docker.base_image_registry.password = \"password\"\n",
+        "\n",
+        "# don't let the system build a new conda environment\n",
+        "rc.environment.python.user_managed_dependencies = True\n",
+        "# point to an existing python environment instead\n",
+        "rc.environment.python.interpreter_path = '/opt/conda/bin/python'\n",
+        "\n",
+        "# submit to a local Docker container. if you don't have Docker engine running locally, you can set compute_target to cpu_cluster.\n",
+        "est = Estimator(source_directory='.', compute_target='local', \n",
+        "                entry_script='dummy_train.py',\n",
+        "                environment_definition=rc.environment)\n",
+        "\n",
+        "run = exp.submit(est)\n",
+        "RunDetails(run).show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Note: if you need to cancel a run, you can follow [these instructions](https://aka.ms/aml-docs-cancel-run)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Next Steps\n",
+        "Now you can proceed to explore the other types of estimators, such as TensorFlow estimator, PyTorch estimator, etc. in the sample folder."
+      ]
+    }
+  ],
+  "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": "3.6.8"
+    },
+    "msauthor": "haining"
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/training-with-deep-learning/train-hyperparameter-tune-deploy-with-keras/keras_mnist.py

@@ -0,0 +1,121 @@
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License.
+
+import numpy as np
+import argparse
+import os
+
+import matplotlib.pyplot as plt
+
+import keras
+from keras.models import Sequential, model_from_json
+from keras.layers import Dense
+from keras.optimizers import RMSprop
+from keras.callbacks import Callback
+
+import tensorflow as tf
+
+from azureml.core import Run
+from utils import load_data, one_hot_encode
+
+print("Keras version:", keras.__version__)
+print("Tensorflow version:", tf.__version__)
+
+parser = argparse.ArgumentParser()
+parser.add_argument('--data-folder', type=str, dest='data_folder', help='data folder mounting point')
+parser.add_argument('--batch-size', type=int, dest='batch_size', default=50, help='mini batch size for training')
+parser.add_argument('--first-layer-neurons', type=int, dest='n_hidden_1', default=100,
+                    help='# of neurons in the first layer')
+parser.add_argument('--second-layer-neurons', type=int, dest='n_hidden_2', default=100,
+                    help='# of neurons in the second layer')
+args = parser.parse_args()
+
+data_folder = args.data_folder
+
+print('training dataset is stored here:', data_folder)
+
+X_train = load_data(os.path.join(data_folder, 'train-images.gz'), False) / 255.0
+X_test = load_data(os.path.join(data_folder, 'test-images.gz'), False) / 255.0
+
+y_train = load_data(os.path.join(data_folder, 'train-labels.gz'), True).reshape(-1)
+y_test = load_data(os.path.join(data_folder, 'test-labels.gz'), True).reshape(-1)
+
+training_set_size = X_train.shape[0]
+
+n_inputs = 28 * 28
+n_h1 = args.n_hidden_1
+n_h2 = args.n_hidden_2
+n_outputs = 10
+
+n_epochs = 20
+batch_size = args.batch_size
+
+y_train = one_hot_encode(y_train, n_outputs)
+y_test = one_hot_encode(y_test, n_outputs)
+print(X_train.shape, y_train.shape, X_test.shape, y_test.shape, sep='\n')
+
+# Build a simple MLP model
+model = Sequential()
+# input layer
+model.add(Dense(n_h1, activation='relu', input_shape=(n_inputs,)))
+# hidden layer
+model.add(Dense(n_h2, activation='relu'))
+# output layer
+model.add(Dense(n_outputs, activation='softmax'))
+
+model.summary()
+
+model.compile(loss='categorical_crossentropy',
+              optimizer=RMSprop(),
+              metrics=['accuracy'])
+
+# start an Azure ML run
+run = Run.get_context()
+
+
+class LogRunMetrics(Callback):
+    # callback at the end of every epoch
+    def on_epoch_end(self, epoch, log):
+        # log a value repeated which creates a list
+        run.log('Loss', log['loss'])
+        run.log('Accuracy', log['acc'])
+
+
+history = model.fit(X_train, y_train,
+                    batch_size=batch_size,
+                    epochs=n_epochs,
+                    verbose=2,
+                    validation_data=(X_test, y_test),
+                    callbacks=[LogRunMetrics()])
+
+score = model.evaluate(X_test, y_test, verbose=0)
+
+# log a single value
+run.log("Final test loss", score[0])
+print('Test loss:', score[0])
+
+run.log('Final test accuracy', score[1])
+print('Test accuracy:', score[1])
+
+plt.figure(figsize=(6, 3))
+plt.title('MNIST with Keras MLP ({} epochs)'.format(n_epochs), fontsize=14)
+plt.plot(history.history['acc'], 'b-', label='Accuracy', lw=4, alpha=0.5)
+plt.plot(history.history['loss'], 'r--', label='Loss', lw=4, alpha=0.5)
+plt.legend(fontsize=12)
+plt.grid(True)
+
+# log an image
+run.log_image('Accuracy vs Loss', plot=plt)
+
+# create a ./outputs/model folder in the compute target
+# files saved in the "./outputs" folder are automatically uploaded into run history
+os.makedirs('./outputs/model', exist_ok=True)
+
+# serialize NN architecture to JSON
+model_json = model.to_json()
+# save model JSON
+with open('./outputs/model/model.json', 'w') as f:
+    f.write(model_json)
+# save model weights
+model.save_weights('./outputs/model/model.h5')
+print("model saved in ./outputs/model folder")

how-to-use-azureml/training-with-deep-learning/train-hyperparameter-tune-deploy-with-keras/utils.py

@@ -0,0 +1,27 @@
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License.
+
+import gzip
+import numpy as np
+import struct
+
+
+# load compressed MNIST gz files and return numpy arrays
+def load_data(filename, label=False):
+    with gzip.open(filename) as gz:
+        struct.unpack('I', gz.read(4))
+        n_items = struct.unpack('>I', gz.read(4))
+        if not label:
+            n_rows = struct.unpack('>I', gz.read(4))[0]
+            n_cols = struct.unpack('>I', gz.read(4))[0]
+            res = np.frombuffer(gz.read(n_items[0] * n_rows * n_cols), dtype=np.uint8)
+            res = res.reshape(n_items[0], n_rows * n_cols)
+        else:
+            res = np.frombuffer(gz.read(n_items[0]), dtype=np.uint8)
+            res = res.reshape(n_items[0], 1)
+    return res
+
+
+# one-hot encode a 1-D array
+def one_hot_encode(array, num_of_classes):
+    return np.eye(num_of_classes)[array.reshape(-1)]

how-to-use-azureml/training/README.md

@@ -6,4 +6,5 @@ Follow these sample notebooks to learn:
 2. [Train on local](train-on-local): train a model using local computer as compute target.
 3. [Train on remote VM](train-on-remote-vm): train a model using a remote Azure VM as compute target.
 4. [Train on AmlCompute](train-on-amlcompute): train a model using an AmlCompute cluster as compute target.
-5. [Logging API](logging-api): experiment with various logging functions to create runs and automatically generate graphs.
+5. [Train in an HDI Spark cluster](train-in-spark): train a Spark ML model using an HDInsight Spark cluster as compute target.
+6. [Logging API](logging-api): experiment with various logging functions to create runs and automatically generate graphs.

how-to-use-azureml/training/logging-api/logging-api.ipynb

@@ -1,328 +1,328 @@
 {
- "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": [
-    "# 06. Logging APIs\n",
-    "This notebook showcase various ways to use the Azure Machine Learning service run logging APIs, and view the results in the Azure portal."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Prerequisites\n",
-    "Make sure you go through the [00. Installation and Configuration](../../00.configuration.ipynb) Notebook first if you haven't. Also make sure you have tqdm and matplotlib installed in the current kernel.\n",
-    "\n",
-    "```\n",
-    "(myenv) $ conda install -y tqdm matplotlib\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Validate Azure ML SDK installation and get version number for debugging purposes"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "install"
-    ]
-   },
-   "outputs": [],
-   "source": [
-    "from azureml.core import Experiment, Run, Workspace\n",
-    "import azureml.core\n",
-    "import numpy as np\n",
-    "\n",
-    "# Check core SDK version number\n",
-    "print(\"SDK version:\", azureml.core.VERSION)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Initialize Workspace\n",
-    "\n",
-    "Initialize a workspace object from persisted configuration."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "create workspace"
-    ]
-   },
-   "outputs": [],
-   "source": [
-    "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": [
-    "## Set experiment\n",
-    "Create a new experiment (or get the one with such name)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "exp = Experiment(workspace=ws, name='logging-api-test')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Log metrics\n",
-    "We will start a run, and use the various logging APIs to record different types of metrics during the run."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from tqdm import tqdm\n",
-    "\n",
-    "# start logging for the run\n",
-    "run = exp.start_logging()\n",
-    "\n",
-    "# log a string value\n",
-    "run.log(name='Name', value='Logging API run')\n",
-    "\n",
-    "# log a numerical value\n",
-    "run.log(name='Magic Number', value=42)\n",
-    "\n",
-    "# Log a list of values. Note this will generate a single-variable line chart.\n",
-    "run.log_list(name='Fibonacci', value=[0, 1, 1, 2, 3, 5, 8, 13, 21, 34, 55, 89])\n",
-    "\n",
-    "# create a dictionary to hold a table of values\n",
-    "sines = {}\n",
-    "sines['angle'] = []\n",
-    "sines['sine'] = []\n",
-    "\n",
-    "for i in tqdm(range(-10, 10)):\n",
-    "    # log a metric value repeatedly, this will generate a single-variable line chart.\n",
-    "    run.log(name='Sigmoid', value=1 / (1 + np.exp(-i)))\n",
-    "    angle = i / 2.0\n",
-    "    \n",
-    "    # log a 2 (or more) values as a metric repeatedly. This will generate a 2-variable line chart if you have 2 numerical columns.\n",
-    "    run.log_row(name='Cosine Wave', angle=angle, cos=np.cos(angle))\n",
-    "        \n",
-    "    sines['angle'].append(angle)\n",
-    "    sines['sine'].append(np.sin(angle))\n",
-    "\n",
-    "# log a dictionary as a table, this will generate a 2-variable chart if you have 2 numerical columns\n",
-    "run.log_table(name='Sine Wave', value=sines)\n",
-    "\n",
-    "run.complete()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Even after the run is marked completed, you can still log things."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Log an image\n",
-    "This is how to log a _matplotlib_ pyplot object."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%matplotlib inline\n",
-    "import matplotlib.pyplot as plt\n",
-    "angle = np.linspace(-3, 3, 50)\n",
-    "plt.plot(angle, np.tanh(angle), label='tanh')\n",
-    "plt.legend(fontsize=12)\n",
-    "plt.title('Hyperbolic Tangent', fontsize=16)\n",
-    "plt.grid(True)\n",
-    "\n",
-    "run.log_image(name='Hyperbolic Tangent', plot=plt)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Upload a file"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can also upload an abitrary file. First, let's create a dummy file locally."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%writefile myfile.txt\n",
-    "\n",
-    "This is a dummy file."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Now let's upload this file into the run record as a run artifact, and display the properties after the upload."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "props = run.upload_file(name='myfile_in_the_cloud.txt', path_or_stream='./myfile.txt')\n",
-    "props.serialize()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Examine the run"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Now let's take a look at the run detail page in Azure portal. Make sure you checkout the various charts and plots generated/uploaded."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "run"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can get all the metrics in that run back."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "run.get_metrics()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can also see the files uploaded for this run."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "run.get_file_names()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can also download all the files locally."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "os.makedirs('files', exist_ok=True)\n",
-    "\n",
-    "for f in run.get_file_names():\n",
-    "    dest = os.path.join('files', f.split('/')[-1])\n",
-    "    print('Downloading file {} to {}...'.format(f, dest))\n",
-    "    run.download_file(f, dest)   "
-   ]
-  }
- ],
- "metadata": {
-  "authors": [
-   {
-    "name": "haining"
-   }
+  "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": [
+        "# 06. Logging APIs\n",
+        "This notebook showcase various ways to use the Azure Machine Learning service run logging APIs, and view the results in the Azure portal."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Prerequisites\n",
+        "Make sure you go through the [configuration notebook](../../../configuration.ipynb) first if you haven't. Also make sure you have tqdm and matplotlib installed in the current kernel.\n",
+        "\n",
+        "```\n",
+        "(myenv) $ conda install -y tqdm matplotlib\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Validate Azure ML SDK installation and get version number for debugging purposes"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "install"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "from azureml.core import Experiment, Workspace\n",
+        "import azureml.core\n",
+        "import numpy as np\n",
+        "\n",
+        "# Check core SDK version number\n",
+        "print(\"SDK version:\", azureml.core.VERSION)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Initialize Workspace\n",
+        "\n",
+        "Initialize a workspace object from persisted configuration."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "create workspace"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "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": [
+        "## Set experiment\n",
+        "Create a new experiment (or get the one with such name)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "exp = Experiment(workspace=ws, name='logging-api-test')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Log metrics\n",
+        "We will start a run, and use the various logging APIs to record different types of metrics during the run."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from tqdm import tqdm\n",
+        "\n",
+        "# start logging for the run\n",
+        "run = exp.start_logging()\n",
+        "\n",
+        "# log a string value\n",
+        "run.log(name='Name', value='Logging API run')\n",
+        "\n",
+        "# log a numerical value\n",
+        "run.log(name='Magic Number', value=42)\n",
+        "\n",
+        "# Log a list of values. Note this will generate a single-variable line chart.\n",
+        "run.log_list(name='Fibonacci', value=[0, 1, 1, 2, 3, 5, 8, 13, 21, 34, 55, 89])\n",
+        "\n",
+        "# create a dictionary to hold a table of values\n",
+        "sines = {}\n",
+        "sines['angle'] = []\n",
+        "sines['sine'] = []\n",
+        "\n",
+        "for i in tqdm(range(-10, 10)):\n",
+        "    # log a metric value repeatedly, this will generate a single-variable line chart.\n",
+        "    run.log(name='Sigmoid', value=1 / (1 + np.exp(-i)))\n",
+        "    angle = i / 2.0\n",
+        "    \n",
+        "    # log a 2 (or more) values as a metric repeatedly. This will generate a 2-variable line chart if you have 2 numerical columns.\n",
+        "    run.log_row(name='Cosine Wave', angle=angle, cos=np.cos(angle))\n",
+        "        \n",
+        "    sines['angle'].append(angle)\n",
+        "    sines['sine'].append(np.sin(angle))\n",
+        "\n",
+        "# log a dictionary as a table, this will generate a 2-variable chart if you have 2 numerical columns\n",
+        "run.log_table(name='Sine Wave', value=sines)\n",
+        "\n",
+        "run.complete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Even after the run is marked completed, you can still log things."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Log an image\n",
+        "This is how to log a _matplotlib_ pyplot object."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%matplotlib inline\n",
+        "import matplotlib.pyplot as plt\n",
+        "angle = np.linspace(-3, 3, 50)\n",
+        "plt.plot(angle, np.tanh(angle), label='tanh')\n",
+        "plt.legend(fontsize=12)\n",
+        "plt.title('Hyperbolic Tangent', fontsize=16)\n",
+        "plt.grid(True)\n",
+        "\n",
+        "run.log_image(name='Hyperbolic Tangent', plot=plt)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Upload a file"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can also upload an abitrary file. First, let's create a dummy file locally."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%writefile myfile.txt\n",
+        "\n",
+        "This is a dummy file."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Now let's upload this file into the run record as a run artifact, and display the properties after the upload."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "props = run.upload_file(name='myfile_in_the_cloud.txt', path_or_stream='./myfile.txt')\n",
+        "props.serialize()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Examine the run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Now let's take a look at the run detail page in Azure portal. Make sure you checkout the various charts and plots generated/uploaded."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can get all the metrics in that run back."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run.get_metrics()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can also see the files uploaded for this run."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run.get_file_names()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can also download all the files locally."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "os.makedirs('files', exist_ok=True)\n",
+        "\n",
+        "for f in run.get_file_names():\n",
+        "    dest = os.path.join('files', f.split('/')[-1])\n",
+        "    print('Downloading file {} to {}...'.format(f, dest))\n",
+        "    run.download_file(f, dest)   "
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "metadata": {
+    "authors": [
+      {
+        "name": "haining"
+      }
+    ],
+    "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"
+    }
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

how-to-use-azureml/training/train-on-local/train-on-local.ipynb

@@ -1,478 +1,514 @@
 {
- "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": [
-    "# 02. Train locally\n",
-    "* Create or load workspace.\n",
-    "* Create scripts locally.\n",
-    "* Create `train.py` in a folder, along with a `my.lib` file.\n",
-    "* Configure & execute a local run in a user-managed Python environment.\n",
-    "* Configure & execute a local run in a system-managed Python environment.\n",
-    "* Configure & execute a local run in a Docker environment.\n",
-    "* Query run metrics to find the best model\n",
-    "* Register model for operationalization."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Prerequisites\n",
-    "Make sure you go through the [00. Installation and Configuration](00.configuration.ipynb) Notebook first if you haven't."
-   ]
-  },
-  {
-   "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": [
-    "## Initialize Workspace\n",
-    "\n",
-    "Initialize a workspace object from persisted configuration."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.workspace import Workspace\n",
-    "\n",
-    "ws = Workspace.from_config()\n",
-    "print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep='\\n')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Create An Experiment\n",
-    "**Experiment** is a logical container in an Azure ML Workspace. It hosts run records which can include run metrics and output artifacts from your experiments."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core import Experiment\n",
-    "experiment_name = 'train-on-local'\n",
-    "exp = Experiment(workspace=ws, name=experiment_name)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## View `train.py`\n",
-    "\n",
-    "`train.py` is already created for you."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "with open('./train.py', 'r') as f:\n",
-    "    print(f.read())"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Note `train.py` also references a `mylib.py` file."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "with open('./mylib.py', 'r') as f:\n",
-    "    print(f.read())"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Configure & Run\n",
-    "### User-managed environment\n",
-    "Below, we use a user-managed run, which means you are responsible to ensure all the necessary packages are available in the Python environment you choose to run the script."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.runconfig import RunConfiguration\n",
-    "\n",
-    "# Editing a run configuration property on-fly.\n",
-    "run_config_user_managed = RunConfiguration()\n",
-    "\n",
-    "run_config_user_managed.environment.python.user_managed_dependencies = True\n",
-    "\n",
-    "# You can choose a specific Python environment by pointing to a Python path \n",
-    "#run_config.environment.python.interpreter_path = '/home/johndoe/miniconda3/envs/sdk2/bin/python'"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Submit script to run in the user-managed environment\n",
-    "Note whole script folder is submitted for execution, including the `mylib.py` file."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core import ScriptRunConfig\n",
-    "\n",
-    "src = ScriptRunConfig(source_directory='./', script='train.py', run_config=run_config_user_managed)\n",
-    "run = exp.submit(src)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Get run history details"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "run"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Block to wait till run finishes."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "run.wait_for_completion(show_output=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### System-managed environment\n",
-    "You can also ask the system to build a new conda environment and execute your scripts in it. The environment is built once and will be reused in subsequent executions as long as the conda dependencies remain unchanged. "
-   ]
-  },
-  {
-   "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",
-    "run_config_system_managed = RunConfiguration()\n",
-    "\n",
-    "run_config_system_managed.environment.python.user_managed_dependencies = False\n",
-    "run_config_system_managed.auto_prepare_environment = True\n",
-    "\n",
-    "# Specify conda dependencies with scikit-learn\n",
-    "cd = CondaDependencies.create(conda_packages=['scikit-learn'])\n",
-    "run_config_system_managed.environment.python.conda_dependencies = cd"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Submit script to run in the system-managed environment\n",
-    "A new conda environment is built based on the conda dependencies object. If you are running this for the first time,  this might take up to 5 mninutes. But this conda environment is reused so long as you don't change the conda dependencies."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "src = ScriptRunConfig(source_directory=\"./\", script='train.py', run_config=run_config_system_managed)\n",
-    "run = exp.submit(src)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Get run history details"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "run"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Block and wait till run finishes."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "run.wait_for_completion(show_output = True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Docker-based execution\n",
-    "**IMPORTANT**: You must have Docker engine installed locally in order to use this execution mode. If your kernel is already running in a Docker container, such as **Azure Notebooks**, this mode will **NOT** work.\n",
-    "NOTE: The GPU base image must be used on Microsoft Azure Services only such as ACI, AML Compute, Azure VMs, and AKS.\n",
-    "\n",
-    "You can also ask the system to pull down a Docker image and execute your scripts in it."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "run_config_docker = RunConfiguration()\n",
-    "run_config_docker.environment.python.user_managed_dependencies = False\n",
-    "run_config_docker.auto_prepare_environment = True\n",
-    "run_config_docker.environment.docker.enabled = True\n",
-    "run_config_docker.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
-    "\n",
-    "# Specify conda dependencies with scikit-learn\n",
-    "cd = CondaDependencies.create(conda_packages=['scikit-learn'])\n",
-    "run_config_docker.environment.python.conda_dependencies = cd\n",
-    "\n",
-    "src = ScriptRunConfig(source_directory=\"./\", script='train.py', run_config=run_config_docker)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Submit script to run in the system-managed environment\n",
-    "A new conda environment is built based on the conda dependencies object. If you are running this for the first time, this might take up to 5 mninutes. But this conda environment is reused so long as you don't change the conda dependencies.\n",
-    "\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import subprocess\n",
-    "\n",
-    "# Check if Docker is installed and Linux containers are enables\n",
-    "if subprocess.run(\"docker -v\", shell=True) == 0:\n",
-    "    out = subprocess.check_output(\"docker system info\", shell=True, encoding=\"ascii\").split(\"\\n\")\n",
-    "    if not \"OSType: linux\" in out:\n",
-    "        print(\"Switch Docker engine to use Linux containers.\")\n",
-    "    else:\n",
-    "        run = exp.submit(src)\n",
-    "else:\n",
-    "    print(\"Docker engine not installed.\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#Get run history details\n",
-    "run"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "run.wait_for_completion(show_output=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Query run metrics"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "query history",
-     "get metrics"
-    ]
-   },
-   "outputs": [],
-   "source": [
-    "# get all metris logged in the run\n",
-    "run.get_metrics()\n",
-    "metrics = run.get_metrics()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Let's find the model that has the lowest MSE value logged."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import numpy as np\n",
-    "\n",
-    "best_alpha = metrics['alpha'][np.argmin(metrics['mse'])]\n",
-    "\n",
-    "print('When alpha is {1:0.2f}, we have min MSE {0:0.2f}.'.format(\n",
-    "    min(metrics['mse']), \n",
-    "    best_alpha\n",
-    "))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can also list all the files that are associated with this run record"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "run.get_file_names()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We know the model `ridge_0.40.pkl` is the best performing model from the eariler queries. So let's register it with the workspace."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# supply a model name, and the full path to the serialized model file.\n",
-    "model = run.register_model(model_name='best_ridge_model', model_path='./outputs/ridge_0.40.pkl')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(model.name, model.version, model.url)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Now you can deploy this model following the example in the 01 notebook."
-   ]
-  }
- ],
- "metadata": {
-  "authors": [
-   {
-    "name": "roastala"
-   }
+  "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": [
+        "# 02. Train locally\n",
+        "* Create or load workspace.\n",
+        "* Create scripts locally.\n",
+        "* Create `train.py` in a folder, along with a `my.lib` file.\n",
+        "* Configure & execute a local run in a user-managed Python environment.\n",
+        "* Configure & execute a local run in a system-managed Python environment.\n",
+        "* Configure & execute a local run in a Docker environment.\n",
+        "* Query run metrics to find the best model\n",
+        "* Register model for operationalization."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Prerequisites\n",
+        "Make sure you go through the [configuration notebook](../../../configuration.ipynb) first if you haven't."
+      ]
+    },
+    {
+      "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": [
+        "## Initialize Workspace\n",
+        "\n",
+        "Initialize a workspace object from persisted configuration."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.workspace import Workspace\n",
+        "\n",
+        "ws = Workspace.from_config()\n",
+        "print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep='\\n')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Create An Experiment\n",
+        "**Experiment** is a logical container in an Azure ML Workspace. It hosts run records which can include run metrics and output artifacts from your experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core import Experiment\n",
+        "experiment_name = 'train-on-local'\n",
+        "exp = Experiment(workspace=ws, name=experiment_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## View `train.py`\n",
+        "\n",
+        "`train.py` is already created for you."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "with open('./train.py', 'r') as f:\n",
+        "    print(f.read())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Note `train.py` also references a `mylib.py` file."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "with open('./mylib.py', 'r') as f:\n",
+        "    print(f.read())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Configure & Run\n",
+        "### User-managed environment\n",
+        "Below, we use a user-managed run, which means you are responsible to ensure all the necessary packages are available in the Python environment you choose to run the script."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.runconfig import RunConfiguration\n",
+        "\n",
+        "# Editing a run configuration property on-fly.\n",
+        "run_config_user_managed = RunConfiguration()\n",
+        "\n",
+        "run_config_user_managed.environment.python.user_managed_dependencies = True\n",
+        "\n",
+        "# You can choose a specific Python environment by pointing to a Python path \n",
+        "#run_config.environment.python.interpreter_path = '/home/johndoe/miniconda3/envs/myenv/bin/python'"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Submit script to run in the user-managed environment\n",
+        "Note whole script folder is submitted for execution, including the `mylib.py` file."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core import ScriptRunConfig\n",
+        "\n",
+        "src = ScriptRunConfig(source_directory='./', script='train.py', run_config=run_config_user_managed)\n",
+        "run = exp.submit(src)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Get run history details"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Note: if you need to cancel a run, you can follow [these instructions](https://aka.ms/aml-docs-cancel-run)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Block to wait till run finishes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run.wait_for_completion(show_output=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### System-managed environment\n",
+        "You can also ask the system to build a new conda environment and execute your scripts in it. The environment is built once and will be reused in subsequent executions as long as the conda dependencies remain unchanged. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.conda_dependencies import CondaDependencies\n",
+        "\n",
+        "run_config_system_managed = RunConfiguration()\n",
+        "\n",
+        "run_config_system_managed.environment.python.user_managed_dependencies = False\n",
+        "run_config_system_managed.auto_prepare_environment = True\n",
+        "\n",
+        "# Specify conda dependencies with scikit-learn\n",
+        "cd = CondaDependencies.create(conda_packages=['scikit-learn'])\n",
+        "run_config_system_managed.environment.python.conda_dependencies = cd"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Submit script to run in the system-managed environment\n",
+        "A new conda environment is built based on the conda dependencies object. If you are running this for the first time,  this might take up to 5 mninutes. But this conda environment is reused so long as you don't change the conda dependencies."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "src = ScriptRunConfig(source_directory=\"./\", script='train.py', run_config=run_config_system_managed)\n",
+        "run = exp.submit(src)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Get run history details"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Block and wait till run finishes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run.wait_for_completion(show_output = True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Docker-based execution\n",
+        "**IMPORTANT**: You must have Docker engine installed locally in order to use this execution mode. If your kernel is already running in a Docker container, such as **Azure Notebooks**, this mode will **NOT** work.\n",
+        "\n",
+        "NOTE: The GPU base image must be used on Microsoft Azure Services only such as ACI, AML Compute, Azure VMs, and AKS.\n",
+        "\n",
+        "You can also ask the system to pull down a Docker image and execute your scripts in it."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run_config_docker = RunConfiguration()\n",
+        "run_config_docker.environment.python.user_managed_dependencies = False\n",
+        "run_config_docker.auto_prepare_environment = True\n",
+        "run_config_docker.environment.docker.enabled = True\n",
+        "\n",
+        "# use the default CPU-based Docker image from Azure ML\n",
+        "run_config_docker.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
+        "\n",
+        "# Specify conda dependencies with scikit-learn\n",
+        "cd = CondaDependencies.create(conda_packages=['scikit-learn'])\n",
+        "run_config_docker.environment.python.conda_dependencies = cd\n",
+        "\n",
+        "src = ScriptRunConfig(source_directory=\"./\", script='train.py', run_config=run_config_docker)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Submit script to run in the system-managed environment\n",
+        "A new conda environment is built based on the conda dependencies object. If you are running this for the first time, this might take up to 5 mninutes. But this conda environment is reused so long as you don't change the conda dependencies.\n",
+        "\n",
+        "\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import subprocess\n",
+        "\n",
+        "# Check if Docker is installed and Linux containers are enables\n",
+        "if subprocess.run(\"docker -v\", shell=True) == 0:\n",
+        "    out = subprocess.check_output(\"docker system info\", shell=True, encoding=\"ascii\").split(\"\\n\")\n",
+        "    if not \"OSType: linux\" in out:\n",
+        "        print(\"Switch Docker engine to use Linux containers.\")\n",
+        "    else:\n",
+        "        run = exp.submit(src)\n",
+        "else:\n",
+        "    print(\"Docker engine not installed.\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "#Get run history details\n",
+        "run"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run.wait_for_completion(show_output=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Use a custom Docker image\n",
+        "\n",
+        "You can also specify a custom Docker image if you don't want to use the default image provided by Azure ML.\n",
+        "\n",
+        "```python\n",
+        "# use an image available in Docker Hub without authentication\n",
+        "run_config_docker.environment.docker.base_image = \"continuumio/miniconda3\"\n",
+        "\n",
+        "# or, use an image available in a private Azure Container Registry\n",
+        "run_config_docker.environment.docker.base_image = \"mycustomimage:1.0\"\n",
+        "run_config_docker.environment.docker.base_image_registry.address = \"myregistry.azurecr.io\"\n",
+        "run_config_docker.environment.docker.base_image_registry.username = \"username\"\n",
+        "run_config_docker.environment.docker.base_image_registry.password = \"password\"\n",
+        "```\n",
+        "\n",
+        "When you are using a custom Docker image, you might already have your environment setup properly in a Python environment in the Docker image. In that case, you can skip specifying conda dependencies, and just use `user_managed_dependencies` option instead:\n",
+        "```python\n",
+        "run_config_docker.environment.python.user_managed_dependencies = True\n",
+        "# path to the Python environment in the custom Docker image\n",
+        "run_config.environment.python.interpreter_path = '/opt/conda/bin/python'\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Query run metrics"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "query history",
+          "get metrics"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "# get all metris logged in the run\n",
+        "run.get_metrics()\n",
+        "metrics = run.get_metrics()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Let's find the model that has the lowest MSE value logged."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import numpy as np\n",
+        "\n",
+        "best_alpha = metrics['alpha'][np.argmin(metrics['mse'])]\n",
+        "\n",
+        "print('When alpha is {1:0.2f}, we have min MSE {0:0.2f}.'.format(\n",
+        "    min(metrics['mse']), \n",
+        "    best_alpha\n",
+        "))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can also list all the files that are associated with this run record"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run.get_file_names()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We know the model `ridge_0.40.pkl` is the best performing model from the eariler queries. So let's register it with the workspace."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# supply a model name, and the full path to the serialized model file.\n",
+        "model = run.register_model(model_name='best_ridge_model', model_path='./outputs/ridge_0.40.pkl')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(model.name, model.version, model.url)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Now you can deploy this model following the example in the 01 notebook."
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "metadata": {
+    "authors": [
+      {
+        "name": "haining"
+      }
+    ],
+    "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"
+    }
   },
-  "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
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

how-to-use-azureml/training/train-on-remote-vm/train2.py

@@ -0,0 +1,6 @@
+# Copyright (c) Microsoft. All rights reserved.
+# Licensed under the MIT license.
+
+print('####################################')
+print('Hello World (without Azure ML SDK)!')
+print('####################################')