Merge pull request #459 from datashinobi/yassine/datadrift2

fix link to config nb & settingwithcopywarning

Dockerfiles/1.0.43/Dockerfile

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

README.md

@@ -52,7 +52,6 @@ The [How to use Azure ML](./how-to-use-azureml) folder contains specific example
 
 Visit following repos to see projects contributed by Azure ML users:
 
- - [AMLSamples](https://github.com/Azure/AMLSamples) Number of end-to-end examples, including face recognition, predictive maintenance, customer churn and sentiment analysis.
  - [Fine tune natural language processing models using Azure Machine Learning service](https://github.com/Microsoft/AzureML-BERT)
  - [Fashion MNIST with Azure ML SDK](https://github.com/amynic/azureml-sdk-fashion)
  

configuration.ipynb

@@ -39,6 +39,7 @@
         "    1. Workspace parameters\n",
         "    1. Access your workspace\n",
         "    1. Create a new workspace\n",
+        "    1. Create compute resources\n",
         "1. [Next steps](#Next%20steps)\n",
         "\n",
         "---\n",
@@ -102,7 +103,7 @@
       "source": [
         "import azureml.core\n",
         "\n",
-        "print(\"This notebook was created using version 1.0.43 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version 1.0.45 of the Azure ML SDK\")\n",
         "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },
@@ -241,6 +242,97 @@
         "ws.write_config()"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create compute resources for your training experiments\n",
+        "\n",
+        "Many of the sample notebooks use Azure ML managed compute (AmlCompute) to train models using a dynamically scalable pool of compute. In this section you will create default compute clusters for use by the other notebooks and any other operations you choose.\n",
+        "\n",
+        "To create a cluster, you need to specify a compute configuration that specifies the type of machine to be used and the scalability behaviors.  Then you choose a name for the cluster that is unique within the workspace that can be used to address the cluster later.\n",
+        "\n",
+        "The cluster parameters are:\n",
+        "* vm_size - this describes the virtual machine type and size used in the cluster.  All machines in the cluster are the same type.  You can get the list of vm sizes available in your region by using the CLI command\n",
+        "\n",
+        "```shell\n",
+        "az vm list-skus -o tsv\n",
+        "```\n",
+        "* min_nodes - this sets the minimum size of the cluster.  If you set the minimum to 0 the cluster will shut down all nodes while note in use.  Setting this number to a value higher than 0 will allow for faster start-up times, but you will also be billed when the cluster is not in use.\n",
+        "* max_nodes - this sets the maximum size of the cluster.  Setting this to a larger number allows for more concurrency and a greater distributed processing of scale-out jobs.\n",
+        "\n",
+        "\n",
+        "To create a **CPU** cluster now, run the cell below. The autoscale settings mean that the cluster will scale down to 0 nodes when inactive and up to 4 nodes when busy."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
+        "from azureml.core.compute_target import ComputeTargetException\n",
+        "\n",
+        "# Choose a name for your CPU cluster\n",
+        "cpu_cluster_name = \"cpu-cluster\"\n",
+        "\n",
+        "# Verify that cluster does not exist already\n",
+        "try:\n",
+        "    cpu_cluster = ComputeTarget(workspace=ws, name=cpu_cluster_name)\n",
+        "    print(\"Found existing cpu-cluster\")\n",
+        "except ComputeTargetException:\n",
+        "    print(\"Creating new cpu-cluster\")\n",
+        "    \n",
+        "    # Specify the configuration for the new cluster\n",
+        "    compute_config = AmlCompute.provisioning_configuration(vm_size=\"STANDARD_D2_V2\",\n",
+        "                                                           min_nodes=0,\n",
+        "                                                           max_nodes=4)\n",
+        "\n",
+        "    # Create the cluster with the specified name and configuration\n",
+        "    cpu_cluster = ComputeTarget.create(ws, cpu_cluster_name, compute_config)\n",
+        "    \n",
+        "    # Wait for the cluster to complete, show the output log\n",
+        "    cpu_cluster.wait_for_completion(show_output=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "To create a **GPU** cluster, run the cell below. Note that your subscription must have sufficient quota for GPU VMs or the command will fail. To increase quota, see [these instructions](https://docs.microsoft.com/en-us/azure/azure-supportability/resource-manager-core-quotas-request). "
+      ]
+    },
+    {
+      "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 GPU cluster\n",
+        "gpu_cluster_name = \"gpu-cluster\"\n",
+        "\n",
+        "# Verify that cluster does not exist already\n",
+        "try:\n",
+        "    gpu_cluster = ComputeTarget(workspace=ws, name=gpu_cluster_name)\n",
+        "    print(\"Found existing gpu cluster\")\n",
+        "except ComputeTargetException:\n",
+        "    print(\"Creating new gpu-cluster\")\n",
+        "    \n",
+        "    # Specify the configuration for the new cluster\n",
+        "    compute_config = AmlCompute.provisioning_configuration(vm_size=\"STANDARD_NC6\",\n",
+        "                                                           min_nodes=0,\n",
+        "                                                           max_nodes=4)\n",
+        "    # Create the cluster with the specified name and configuration\n",
+        "    gpu_cluster = ComputeTarget.create(ws, gpu_cluster_name, compute_config)\n",
+        "\n",
+        "    # Wait for the cluster to complete, show the output log\n",
+        "    gpu_cluster.wait_for_completion(show_output=True)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

contrib/datadrift/azure-ml-datadrift.ipynb

@@ -0,0 +1,709 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Track Data Drift between Training and Inference Data in Production \n",
+        "\n",
+        "With this notebook, you will learn how to enable the DataDrift service to automatically track and determine whether your inference data is drifting from the data your model was initially trained on. The DataDrift service provides metrics and visualizations to help stakeholders identify which specific features cause the concept drift to occur.\n",
+        "\n",
+        "Please email driftfeedback@microsoft.com with any issues. A member from the DataDrift team will respond shortly. \n",
+        "\n",
+        "The DataDrift Public Preview API can be found [here](https://docs.microsoft.com/en-us/python/api/azureml-contrib-datadrift/?view=azure-ml-py). "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/contrib/datadrift/azureml-datadrift.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Prerequisites and Setup"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Install the DataDrift package\n",
+        "\n",
+        "Install the azureml-contrib-datadrift, azureml-contrib-opendatasets and lightgbm packages before running this notebook.\n",
+        "```\n",
+        "pip install azureml-contrib-datadrift\n",
+        "pip install azureml-contrib-datasets\n",
+        "pip install lightgbm\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Import Dependencies"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import json\n",
+        "import os\n",
+        "import time\n",
+        "from datetime import datetime, timedelta\n",
+        "\n",
+        "import numpy as np\n",
+        "import pandas as pd\n",
+        "import requests\n",
+        "from azureml.contrib.datadrift import DataDriftDetector, AlertConfiguration\n",
+        "from azureml.contrib.opendatasets import NoaaIsdWeather\n",
+        "from azureml.core import Dataset, Workspace, Run\n",
+        "from azureml.core.compute import AksCompute, ComputeTarget\n",
+        "from azureml.core.conda_dependencies import CondaDependencies\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.image import ContainerImage\n",
+        "from azureml.core.model import Model\n",
+        "from azureml.core.webservice import Webservice, AksWebservice\n",
+        "from azureml.widgets import RunDetails\n",
+        "from sklearn.externals import joblib\n",
+        "from sklearn.model_selection import train_test_split\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Set up Configuraton and Create Azure ML Workspace\n",
+        "\n",
+        "If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, go through the [configuration notebook](../../../configuration.ipynb) first if you haven't already to establish your connection to the AzureML Workspace."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Please type in your initials/alias. The prefix is prepended to the names of resources created by this notebook. \n",
+        "prefix = \"dd\"\n",
+        "\n",
+        "# NOTE: Please do not change the model_name, as it's required by the score.py file\n",
+        "model_name = \"driftmodel\"\n",
+        "image_name = \"{}driftimage\".format(prefix)\n",
+        "service_name = \"{}driftservice\".format(prefix)\n",
+        "\n",
+        "# optionally, set email address to receive an email alert for DataDrift\n",
+        "email_address = \"\""
+      ]
+    },
+    {
+      "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": [
+        "## Generate Train/Testing Data\n",
+        "\n",
+        "For this demo, we will use NOAA weather data from [Azure Open Datasets](https://azure.microsoft.com/services/open-datasets/). You may replace this step with your own dataset. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "usaf_list = ['725724', '722149', '723090', '722159', '723910', '720279',\n",
+        "             '725513', '725254', '726430', '720381', '723074', '726682',\n",
+        "             '725486', '727883', '723177', '722075', '723086', '724053',\n",
+        "             '725070', '722073', '726060', '725224', '725260', '724520',\n",
+        "             '720305', '724020', '726510', '725126', '722523', '703333',\n",
+        "             '722249', '722728', '725483', '722972', '724975', '742079',\n",
+        "             '727468', '722193', '725624', '722030', '726380', '720309',\n",
+        "             '722071', '720326', '725415', '724504', '725665', '725424',\n",
+        "             '725066']\n",
+        "\n",
+        "columns = ['usaf', 'wban', 'datetime', 'latitude', 'longitude', 'elevation', 'windAngle', 'windSpeed', 'temperature', 'stationName', 'p_k']\n",
+        "\n",
+        "\n",
+        "def enrich_weather_noaa_data(noaa_df):\n",
+        "    hours_in_day = 23\n",
+        "    week_in_year = 52\n",
+        "    \n",
+        "    noaa_df[\"hour\"] = noaa_df[\"datetime\"].dt.hour\n",
+        "    noaa_df[\"weekofyear\"] = noaa_df[\"datetime\"].dt.week\n",
+        "    \n",
+        "    noaa_df[\"sine_weekofyear\"] = noaa_df['datetime'].transform(lambda x: np.sin((2*np.pi*x.dt.week-1)/week_in_year))\n",
+        "    noaa_df[\"cosine_weekofyear\"] = noaa_df['datetime'].transform(lambda x: np.cos((2*np.pi*x.dt.week-1)/week_in_year))\n",
+        "\n",
+        "    noaa_df[\"sine_hourofday\"] = noaa_df['datetime'].transform(lambda x: np.sin(2*np.pi*x.dt.hour/hours_in_day))\n",
+        "    noaa_df[\"cosine_hourofday\"] = noaa_df['datetime'].transform(lambda x: np.cos(2*np.pi*x.dt.hour/hours_in_day))\n",
+        "    \n",
+        "    return noaa_df\n",
+        "\n",
+        "def add_window_col(input_df):\n",
+        "    shift_interval = pd.Timedelta('-7 days') # your X days interval\n",
+        "    df_shifted = input_df.copy()\n",
+        "    df_shifted['datetime'] = df_shifted['datetime'] - shift_interval\n",
+        "    df_shifted.drop(list(input_df.columns.difference(['datetime', 'usaf', 'wban', 'sine_hourofday', 'temperature'])), axis=1, inplace=True)\n",
+        "\n",
+        "    # merge, keeping only observations where -1 lag is present\n",
+        "    df2 = pd.merge(input_df,\n",
+        "                   df_shifted,\n",
+        "                   on=['datetime', 'usaf', 'wban', 'sine_hourofday'],\n",
+        "                   how='inner',  # use 'left' to keep observations without lags\n",
+        "                   suffixes=['', '-7'])\n",
+        "    return df2\n",
+        "\n",
+        "def get_noaa_data(start_time, end_time, cols, station_list):\n",
+        "    isd = NoaaIsdWeather(start_time, end_time, cols=cols)\n",
+        "    # Read into Pandas data frame.\n",
+        "    noaa_df = isd.to_pandas_dataframe()\n",
+        "    noaa_df = noaa_df.rename(columns={\"stationName\": \"station_name\"})\n",
+        "    \n",
+        "    df_filtered = noaa_df[noaa_df[\"usaf\"].isin(station_list)]\n",
+        "    df_filtered.reset_index(drop=True)\n",
+        "    \n",
+        "    # Enrich with time features\n",
+        "    df_enriched = enrich_weather_noaa_data(df_filtered)\n",
+        "    \n",
+        "    return df_enriched\n",
+        "\n",
+        "def get_featurized_noaa_df(start_time, end_time, cols, station_list):\n",
+        "    df_1 = get_noaa_data(start_time - timedelta(days=7), start_time - timedelta(seconds=1), cols, station_list)\n",
+        "    df_2 = get_noaa_data(start_time, end_time, cols, station_list)\n",
+        "    noaa_df = pd.concat([df_1, df_2])\n",
+        "    \n",
+        "    print(\"Adding window feature\")\n",
+        "    df_window = add_window_col(noaa_df)\n",
+        "    \n",
+        "    cat_columns = df_window.dtypes == object\n",
+        "    cat_columns = cat_columns[cat_columns == True]\n",
+        "    \n",
+        "    print(\"Encoding categorical columns\")\n",
+        "    df_encoded = pd.get_dummies(df_window, columns=cat_columns.keys().tolist())\n",
+        "    \n",
+        "    print(\"Dropping unnecessary columns\")\n",
+        "    df_featurized = df_encoded.drop(['windAngle', 'windSpeed', 'datetime', 'elevation'], axis=1).dropna().drop_duplicates()\n",
+        "    \n",
+        "    return df_featurized"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Train model on Jan 1 - 14, 2009 data\n",
+        "df = get_featurized_noaa_df(datetime(2009, 1, 1), datetime(2009, 1, 14, 23, 59, 59), columns, usaf_list)\n",
+        "df.head()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "label = \"temperature\"\n",
+        "x_df = df.drop(label, axis=1)\n",
+        "y_df = df[[label]]\n",
+        "x_train, x_test, y_train, y_test = train_test_split(df, y_df, test_size=0.2, random_state=223)\n",
+        "print(x_train.shape, x_test.shape, y_train.shape, y_test.shape)\n",
+        "\n",
+        "training_dir = 'outputs/training'\n",
+        "training_file = \"training.csv\"\n",
+        "\n",
+        "# Generate training dataframe to register as Training Dataset\n",
+        "os.makedirs(training_dir, exist_ok=True)\n",
+        "training_df = pd.merge(x_train.drop(label, axis=1), y_train, left_index=True, right_index=True)\n",
+        "training_df.to_csv(training_dir + \"/\" + training_file)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Create/Register Training Dataset"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "dataset_name = \"dataset\"\n",
+        "name_suffix = datetime.utcnow().strftime(\"%Y-%m-%d-%H-%M-%S\")\n",
+        "snapshot_name = \"snapshot-{}\".format(name_suffix)\n",
+        "\n",
+        "dstore = ws.get_default_datastore()\n",
+        "dstore.upload(training_dir, \"data/training\", show_progress=True)\n",
+        "dpath = dstore.path(\"data/training/training.csv\")\n",
+        "trainingDataset = Dataset.auto_read_files(dpath, include_path=True)\n",
+        "trainingDataset = trainingDataset.register(workspace=ws, name=dataset_name, description=\"dset\", exist_ok=True)\n",
+        "\n",
+        "trainingDataSnapshot = trainingDataset.create_snapshot(snapshot_name=snapshot_name, compute_target=None, create_data_snapshot=True)\n",
+        "datasets = [(Dataset.Scenario.TRAINING, trainingDataSnapshot)]\n",
+        "print(\"dataset registration done.\\n\")\n",
+        "datasets"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train and Save Model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import lightgbm as lgb\n",
+        "\n",
+        "train = lgb.Dataset(data=x_train, \n",
+        "                    label=y_train)\n",
+        "\n",
+        "test = lgb.Dataset(data=x_test, \n",
+        "                   label=y_test,\n",
+        "                   reference=train)\n",
+        "\n",
+        "params = {'learning_rate'    : 0.1,\n",
+        "          'boosting'         : 'gbdt',\n",
+        "          'metric'           : 'rmse',\n",
+        "          'feature_fraction' : 1,\n",
+        "          'bagging_fraction' : 1,\n",
+        "          'max_depth': 6,\n",
+        "          'num_leaves'       : 31,\n",
+        "          'objective'        : 'regression',\n",
+        "          'bagging_freq'     : 1,\n",
+        "          \"verbose\": -1,\n",
+        "          'min_data_per_leaf': 100}\n",
+        "\n",
+        "model = lgb.train(params, \n",
+        "                  num_boost_round=500,\n",
+        "                  train_set=train,\n",
+        "                  valid_sets=[train, test],\n",
+        "                  verbose_eval=50,\n",
+        "                  early_stopping_rounds=25)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "model_file = 'outputs/{}.pkl'.format(model_name)\n",
+        "\n",
+        "os.makedirs('outputs', exist_ok=True)\n",
+        "joblib.dump(model, model_file)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Register Model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "model = Model.register(model_path=model_file,\n",
+        "                       model_name=model_name,\n",
+        "                       workspace=ws,\n",
+        "                       datasets=datasets)\n",
+        "\n",
+        "print(model_name, image_name, service_name, model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Deploy Model To AKS"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Prepare Environment"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn', 'joblib', 'lightgbm', 'pandas'],\n",
+        "                                 pip_packages=['azureml-monitoring', 'azureml-sdk[automl]'])\n",
+        "\n",
+        "with open(\"myenv.yml\",\"w\") as f:\n",
+        "    f.write(myenv.serialize_to_string())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Create Image"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Image creation may take up to 15 minutes.\n",
+        "\n",
+        "image_name = image_name + str(model.version)\n",
+        "\n",
+        "if not image_name in ws.images:\n",
+        "    # Use the score.py defined in this directory as the execution script\n",
+        "    # NOTE: The Model Data Collector must be enabled in the execution script for DataDrift to run correctly\n",
+        "    image_config = ContainerImage.image_configuration(execution_script=\"score.py\",\n",
+        "                                                      runtime=\"python\",\n",
+        "                                                      conda_file=\"myenv.yml\",\n",
+        "                                                      description=\"Image with weather dataset model\")\n",
+        "    image = ContainerImage.create(name=image_name,\n",
+        "                                  models=[model],\n",
+        "                                  image_config=image_config,\n",
+        "                                  workspace=ws)\n",
+        "\n",
+        "    image.wait_for_creation(show_output=True)\n",
+        "else:\n",
+        "    image = ws.images[image_name]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Create Compute Target"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "aks_name = 'dd-demo-e2e'\n",
+        "prov_config = AksCompute.provisioning_configuration()\n",
+        "\n",
+        "if not aks_name in ws.compute_targets:\n",
+        "    aks_target = ComputeTarget.create(workspace=ws,\n",
+        "                                      name=aks_name,\n",
+        "                                      provisioning_configuration=prov_config)\n",
+        "\n",
+        "    aks_target.wait_for_completion(show_output=True)\n",
+        "    print(aks_target.provisioning_state)\n",
+        "    print(aks_target.provisioning_errors)\n",
+        "else:\n",
+        "    aks_target=ws.compute_targets[aks_name]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Deploy Service"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "aks_service_name = service_name\n",
+        "\n",
+        "if not aks_service_name in ws.webservices:\n",
+        "    aks_config = AksWebservice.deploy_configuration(collect_model_data=True, enable_app_insights=True)\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)\n",
+        "else:\n",
+        "    aks_service = ws.webservices[aks_service_name]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Run DataDrift Analysis"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Send Scoring Data to Service"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Download Scoring Data"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Score Model on March 15, 2016 data\n",
+        "scoring_df = get_noaa_data(datetime(2016, 3, 15) - timedelta(days=7), datetime(2016, 3, 16),  columns, usaf_list)\n",
+        "# Add the window feature column\n",
+        "scoring_df = add_window_col(scoring_df)\n",
+        "\n",
+        "# Drop features not used by the model\n",
+        "print(\"Dropping unnecessary columns\")\n",
+        "scoring_df = scoring_df.drop(['windAngle', 'windSpeed', 'datetime', 'elevation'], axis=1).dropna()\n",
+        "scoring_df.head()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# One Hot Encode the scoring dataset to match the training dataset schema\n",
+        "columns_dict = model.datasets[\"training\"][0].get_profile().columns\n",
+        "extra_cols = ('Path', 'Column1')\n",
+        "for k in extra_cols:\n",
+        "    columns_dict.pop(k, None)\n",
+        "training_columns = list(columns_dict.keys())\n",
+        "\n",
+        "categorical_columns = scoring_df.dtypes == object\n",
+        "categorical_columns = categorical_columns[categorical_columns == True]\n",
+        "\n",
+        "test_df = pd.get_dummies(scoring_df[categorical_columns.keys().tolist()])\n",
+        "encoded_df = scoring_df.join(test_df)\n",
+        "\n",
+        "# Populate missing OHE columns with 0 values to match traning dataset schema\n",
+        "difference = list(set(training_columns) - set(encoded_df.columns.tolist()))\n",
+        "for col in difference:\n",
+        "    encoded_df[col] = 0\n",
+        "encoded_df.head()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Serialize dataframe to list of row dictionaries\n",
+        "encoded_dict = encoded_df.to_dict('records')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Submit Scoring Data to Service"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%time\n",
+        "\n",
+        "# retreive the API keys. AML generates two keys.\n",
+        "key1, key2 = aks_service.get_keys()\n",
+        "\n",
+        "total_count = len(scoring_df)\n",
+        "i = 0\n",
+        "load = []\n",
+        "for row in encoded_dict:\n",
+        "    load.append(row)\n",
+        "    i = i + 1\n",
+        "    if i % 100 == 0:\n",
+        "        payload = json.dumps({\"data\": load})\n",
+        "        \n",
+        "        # construct raw HTTP request and send to the service\n",
+        "        payload_binary = bytes(payload,encoding = 'utf8')\n",
+        "        headers = {'Content-Type':'application/json', 'Authorization': 'Bearer ' + key1}\n",
+        "        resp = requests.post(aks_service.scoring_uri, payload_binary, headers=headers)\n",
+        "        \n",
+        "        print(\"prediction:\", resp.content, \"Progress: {}/{}\".format(i, total_count))   \n",
+        "\n",
+        "        load = []\n",
+        "        time.sleep(3)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Configure DataDrift"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "services = [service_name]\n",
+        "start = datetime.now() - timedelta(days=2)\n",
+        "end = datetime(year=2020, month=1, day=22, hour=15, minute=16)\n",
+        "feature_list = ['usaf', 'wban', 'latitude', 'longitude', 'station_name', 'p_k',  'sine_hourofday', 'cosine_hourofday', 'temperature-7']\n",
+        "alert_config = AlertConfiguration([email_address]) if email_address else None\n",
+        "\n",
+        "# there will be an exception indicating using get() method if DataDrift object already exist\n",
+        "try:\n",
+        "    datadrift = DataDriftDetector.create(ws, model.name, model.version, services, frequency=\"Day\", alert_config=alert_config)\n",
+        "except KeyError:\n",
+        "    datadrift = DataDriftDetector.get(ws, model.name, model.version)\n",
+        "    \n",
+        "print(\"Details of DataDrift Object:\\n{}\".format(datadrift))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Run an Adhoc DataDriftDetector Run"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "target_date = datetime.today()\n",
+        "run = datadrift.run(target_date, services, feature_list=feature_list, create_compute_target=True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "exp = Experiment(ws, datadrift._id)\n",
+        "dd_run = Run(experiment=exp, run_id=run)\n",
+        "RunDetails(dd_run).show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Get Drift Analysis Results"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "children = list(dd_run.get_children())\n",
+        "for child in children:\n",
+        "    child.wait_for_completion()\n",
+        "\n",
+        "drift_metrics = datadrift.get_output(start_time=start, end_time=end)\n",
+        "drift_metrics"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Show all drift figures, one per serivice.\n",
+        "# If setting with_details is False (by default), only drift will be shown; if it's True, all details will be shown.\n",
+        "\n",
+        "drift_figures = datadrift.show(with_details=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Enable DataDrift Schedule"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "datadrift.enable_schedule()"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "rafarmah"
+      }
+    ],
+    "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/datadrift/score.py

@@ -0,0 +1,58 @@
+import pickle
+import json
+import numpy
+import azureml.train.automl
+from sklearn.externals import joblib
+from sklearn.linear_model import Ridge
+from azureml.core.model import Model
+from azureml.core.run import Run
+from azureml.monitoring import ModelDataCollector
+import time
+import pandas as pd
+
+
+def init():
+    global model, inputs_dc, prediction_dc, feature_names, categorical_features
+
+    print("Model is initialized" + time.strftime("%H:%M:%S"))
+    model_path = Model.get_model_path(model_name="driftmodel")
+    model = joblib.load(model_path)
+
+    feature_names = ["usaf", "wban", "latitude", "longitude", "station_name", "p_k",
+                     "sine_weekofyear", "cosine_weekofyear", "sine_hourofday", "cosine_hourofday",
+                     "temperature-7"]
+
+    categorical_features = ["usaf", "wban", "p_k", "station_name"]
+
+    inputs_dc = ModelDataCollector(model_name="driftmodel",
+                                   identifier="inputs",
+                                   feature_names=feature_names)
+
+    prediction_dc = ModelDataCollector("driftmodel",
+                                       identifier="predictions",
+                                       feature_names=["temperature"])
+
+
+def run(raw_data):
+    global inputs_dc, prediction_dc
+
+    try:
+        data = json.loads(raw_data)["data"]
+        data = pd.DataFrame(data)
+
+        # Remove the categorical features as the model expects OHE values
+        input_data = data.drop(categorical_features, axis=1)
+
+        result = model.predict(input_data)
+
+        # Collect the non-OHE dataframe
+        collected_df = data[feature_names]
+
+        inputs_dc.collect(collected_df.values)
+        prediction_dc.collect(result)
+        return result.tolist()
+    except Exception as e:
+        error = str(e)
+
+        print(error + time.strftime("%H:%M:%S"))
+        return error

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

@@ -115,16 +115,7 @@ jupyter notebook
     - Simple example of using automated ML for regression
     - Uses local compute for training
 
-- [auto-ml-remote-execution.ipynb](remote-execution/auto-ml-remote-execution.ipynb)
-    - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
-    - Example of using automated ML for classification using a remote linux DSVM for training
-    - Parallel execution of iterations
-    - Async tracking of progress
-    - Cancelling individual iterations or entire run
-    - Retrieving models for any iteration or logged metric
-    - Specify automated ML settings as kwargs
-
-- [auto-ml-remote-amlcompute.ipynb](remote-batchai/auto-ml-remote-amlcompute.ipynb)
+- [auto-ml-remote-amlcompute.ipynb](remote-amlcompute/auto-ml-remote-amlcompute.ipynb)
     - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
     - Example of using automated ML for classification using remote AmlCompute for training
     - Parallel execution of iterations
@@ -133,12 +124,6 @@ jupyter notebook
     - Retrieving models for any iteration or logged metric
     - Specify automated ML settings as kwargs
 
-- [auto-ml-remote-attach.ipynb](remote-attach/auto-ml-remote-attach.ipynb)
-    - Dataset: Scikit learn's [20newsgroup](http://scikit-learn.org/stable/datasets/twenty_newsgroups.html)
-    - handling text data with preprocess flag
-    - Reading data from a blob store for remote executions
-    - using pandas dataframes for reading data
-
 - [auto-ml-missing-data-blacklist-early-termination.ipynb](missing-data-blacklist-early-termination/auto-ml-missing-data-blacklist-early-termination.ipynb)
     - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
     - Blacklist certain pipelines
@@ -156,10 +141,6 @@ jupyter notebook
     - Get details for a automated ML Run. (automated ML settings, run widget & all metrics)
     - Download fitted pipeline for any iteration
 
-- [auto-ml-remote-execution-with-datastore.ipynb](remote-execution-with-datastore/auto-ml-remote-execution-with-datastore.ipynb)
-    - Dataset: Scikit learn's [20newsgroup](http://scikit-learn.org/stable/datasets/twenty_newsgroups.html)
-    - Download the data and store it in DataStore.
-
 - [auto-ml-classification-with-deployment.ipynb](classification-with-deployment/auto-ml-classification-with-deployment.ipynb)
     - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
     - Simple example of using automated ML for classification
@@ -198,6 +179,26 @@ jupyter notebook
     - Simple example of using automated ML for classification with ONNX models
     - Uses local compute for training
 
+- [auto-ml-bank-marketing-subscribers-with-deployment.ipynb](bank-marketing-subscribers-with-deployment/auto-ml-bank-marketing-with-deployment.ipynb)
+    - Dataset: UCI's [bank marketing dataset](https://www.kaggle.com/janiobachmann/bank-marketing-dataset)
+    - Simple example of using automated ML for classification to predict term deposit subscriptions for a bank
+    - Uses azure compute for training
+
+- [auto-ml-creditcard-with-deployment.ipynb](credit-card-fraud-detection-with-deployment/auto-ml-creditcard-with-deployment.ipynb)
+    - Dataset: Kaggle's [credit card fraud detection dataset](https://www.kaggle.com/mlg-ulb/creditcardfraud)
+    - Simple example of using automated ML for classification to fraudulent credit card transactions
+    - Uses azure compute for training
+
+- [auto-ml-hardware-performance-with-deployment.ipynb](hardware-performance-prediction-with-deployment/auto-ml-hardware-performance-with-deployment.ipynb)
+    - Dataset: UCI's [computer hardware dataset](https://archive.ics.uci.edu/ml/datasets/Computer+Hardware)
+    - Simple example of using automated ML for regression to predict the performance of certain combinations of hardware components
+    - Uses azure compute for training
+
+- [auto-ml-concrete-strength-with-deployment.ipynb](predicting-concrete-strength-with-deployment/auto-ml-concrete-strength-with-deployment.ipynb)
+    - Dataset: UCI's [concrete compressive strength dataset](https://www.kaggle.com/pavanraj159/concrete-compressive-strength-data-set)
+    - Simple example of using automated ML for regression to predict the strength  predict the compressive strength of concrete based off of different ingredient combinations and quantities of those ingredients
+    - Uses azure compute for training
+
 <a name="documentation"></a>
 See [Configure automated machine learning experiments](https://docs.microsoft.com/azure/machine-learning/service/how-to-configure-auto-train) to learn how more about the the settings and features available for automated machine learning experiments.
 

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

@@ -9,6 +9,8 @@ IF "%automl_env_file%"=="" SET automl_env_file="automl_env.yml"
 
 IF NOT EXIST %automl_env_file% GOTO YmlMissing
 
+IF "%CONDA_EXE%"=="" GOTO CondaMissing
+
 call conda activate %conda_env_name% 2>nul:
 
 if not errorlevel 1 (
@@ -42,6 +44,15 @@ IF NOT "%options%"=="nolaunch" (
 
 goto End
 
+:CondaMissing
+echo Please run this script from an Anaconda Prompt window.
+echo You can start an Anaconda Prompt window by
+echo typing Anaconda Prompt on the Start menu.
+echo If you don't see the Anaconda Prompt app, install Miniconda.
+echo If you are running an older version of Miniconda or Anaconda,
+echo you can upgrade using the command: conda update conda
+goto End
+
 :YmlMissing
 echo File %automl_env_file% not found.
 

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

@@ -0,0 +1,729 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+    "\n",
+    "Licensed under the MIT License."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/classification-bank-marketing/auto-ml-classification-bank-marketing.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Automated Machine Learning\n",
+    "_**Classification with Deployment using a Bank Marketing Dataset**_\n",
+    "\n",
+    "## Contents\n",
+    "1. [Introduction](#Introduction)\n",
+    "1. [Setup](#Setup)\n",
+    "1. [Train](#Train)\n",
+    "1. [Results](#Results)\n",
+    "1. [Deploy](#Deploy)\n",
+    "1. [Test](#Test)\n",
+    "1. [Acknowledgements](#Acknowledgements)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Introduction\n",
+    "\n",
+    "In this example we use the UCI Bank Marketing dataset to showcase how you can use AutoML for a  classification problem and deploy it to an Azure Container Instance (ACI). The classification goal is to predict if the client will subscribe to a term deposit with the bank.\n",
+    "\n",
+    "If you are using an Azure Machine Learning Notebook VM, you are all set.  Otherwise, go through the [configuration](../../../configuration.ipynb)  notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
+    "\n",
+    "In this notebook you will learn how to:\n",
+    "1. Create an experiment using an existing workspace.\n",
+    "2. Configure AutoML using `AutoMLConfig`.\n",
+    "3. Train the model using local compute.\n",
+    "4. Explore the results.\n",
+    "5. Register the model.\n",
+    "6. Create a container image.\n",
+    "7. Create an Azure Container Instance (ACI) service.\n",
+    "8. Test the ACI service."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "import logging\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import os\n",
+    "from sklearn import datasets\n",
+    "import azureml.dataprep as dprep\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# choose a name for experiment\n",
+    "experiment_name = 'automl-classification-bmarketing'\n",
+    "# project folder\n",
+    "project_folder = './sample_projects/automl-classification-bankmarketing'\n",
+    "\n",
+    "experiment=Experiment(ws, experiment_name)\n",
+    "\n",
+    "output = {}\n",
+    "output['SDK version'] = azureml.core.VERSION\n",
+    "output['Subscription ID'] = ws.subscription_id\n",
+    "output['Workspace'] = ws.name\n",
+    "output['Resource Group'] = ws.resource_group\n",
+    "output['Location'] = ws.location\n",
+    "output['Project Directory'] = project_folder\n",
+    "output['Experiment Name'] = experiment.name\n",
+    "pd.set_option('display.max_colwidth', -1)\n",
+    "outputDf = pd.DataFrame(data = output, index = [''])\n",
+    "outputDf.T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create or Attach existing AmlCompute\n",
+    "You will need to create a compute target for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
+    "#### Creation of AmlCompute takes approximately 5 minutes. \n",
+    "If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
+    "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read this article on the default limits and how to request more quota."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.compute import AmlCompute\n",
+    "from azureml.core.compute import ComputeTarget\n",
+    "\n",
+    "# Choose a name for your cluster.\n",
+    "amlcompute_cluster_name = \"automlcl\"\n",
+    "\n",
+    "found = False\n",
+    "# Check if this compute target already exists in the workspace.\n",
+    "cts = ws.compute_targets\n",
+    "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
+    "    found = True\n",
+    "    print('Found existing compute target.')\n",
+    "    compute_target = cts[amlcompute_cluster_name]\n",
+    "    \n",
+    "if not found:\n",
+    "    print('Creating a new compute target...')\n",
+    "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
+    "                                                                #vm_priority = 'lowpriority', # optional\n",
+    "                                                                max_nodes = 6)\n",
+    "\n",
+    "    # Create the cluster.\n",
+    "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
+    "    \n",
+    "    # Can poll for a minimum number of nodes and for a specific timeout.\n",
+    "    # If no min_node_count is provided, it will use the scale settings for the cluster.\n",
+    "    compute_target.wait_for_completion(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
+    "    \n",
+    "     # For a more detailed view of current AmlCompute status, use get_status()."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Data\n",
+    "\n",
+    "Here load the data in the get_data() script to be utilized in azure compute. To do this  first load all the necessary libraries and dependencies to set up paths for the data and to create the conda_Run_config."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if not os.path.isdir('data'):\n",
+    "    os.mkdir('data')\n",
+    "    \n",
+    "if not os.path.exists(project_folder):\n",
+    "    os.makedirs(project_folder)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.runconfig import RunConfiguration\n",
+    "from azureml.core.conda_dependencies import CondaDependencies\n",
+    "\n",
+    "# create a new RunConfig object\n",
+    "conda_run_config = RunConfiguration(framework=\"python\")\n",
+    "\n",
+    "# Set compute target to AmlCompute\n",
+    "conda_run_config.target = compute_target\n",
+    "conda_run_config.environment.docker.enabled = True\n",
+    "conda_run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
+    "\n",
+    "\n",
+    "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy','py-xgboost<=0.80'])\n",
+    "conda_run_config.environment.python.conda_dependencies = cd"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Load Data\n",
+    "\n",
+    "Here we create the script to be run in azure comput for loading the data, we load the bank marketing dataset into X_train and y_train. Next X_train and y_train is returned for training the model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_train.csv\"\n",
+    "dflow = dprep.auto_read_file(data)\n",
+    "dflow.get_profile()\n",
+    "X_train = dflow.drop_columns(columns=['y'])\n",
+    "y_train = dflow.keep_columns(columns=['y'], validate_column_exists=True)\n",
+    "dflow.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Train\n",
+    "\n",
+    "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
+    "\n",
+    "|Property|Description|\n",
+    "|-|-|\n",
+    "|**task**|classification or regression|\n",
+    "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
+    "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+    "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
+    "|**n_cross_validations**|Number of cross validation splits.|\n",
+    "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+    "|**y**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|\n",
+    "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|\n",
+    "\n",
+    "**_You can find more information about primary metrics_** [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#primary-metric)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_settings = {\n",
+    "    \"iteration_timeout_minutes\": 5,\n",
+    "    \"iterations\": 10,\n",
+    "    \"n_cross_validations\": 2,\n",
+    "    \"primary_metric\": 'AUC_weighted',\n",
+    "    \"preprocess\": True,\n",
+    "    \"max_concurrent_iterations\": 5,\n",
+    "    \"verbosity\": logging.INFO,\n",
+    "}\n",
+    "\n",
+    "automl_config = AutoMLConfig(task = 'classification',\n",
+    "                             debug_log = 'automl_errors.log',\n",
+    "                             path = project_folder,\n",
+    "                             run_configuration=conda_run_config,\n",
+    "                             X = X_train,\n",
+    "                             y = y_train,\n",
+    "                             **automl_settings\n",
+    "                            )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
+    "In this example, we specify `show_output = True` to print currently running iterations to the console."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "remote_run = experiment.submit(automl_config, show_output = True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "remote_run"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Results"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Widget for Monitoring Runs\n",
+    "\n",
+    "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+    "\n",
+    "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.widgets import RunDetails\n",
+    "RunDetails(remote_run).show() "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Deploy\n",
+    "\n",
+    "### Retrieve the Best Model\n",
+    "\n",
+    "Below we select the best pipeline from our iterations. The `get_output` method on `automl_classifier` returns the best run and the fitted model for the last invocation. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_model = remote_run.get_output()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Register the Fitted Model for Deployment\n",
+    "If neither `metric` nor `iteration` are specified in the `register_model` call, the iteration with the best primary metric is registered."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "description = 'AutoML Model trained on bank marketing data to predict if a client will subscribe to a term deposit'\n",
+    "tags = None\n",
+    "model = remote_run.register_model(description = description, tags = tags)\n",
+    "\n",
+    "print(remote_run.model_id) # This will be written to the script file later in the notebook."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create Scoring Script\n",
+    "The scoring script is required to generate the image for deployment. It contains the code to do the predictions on input data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%writefile score.py\n",
+    "import pickle\n",
+    "import json\n",
+    "import numpy\n",
+    "import azureml.train.automl\n",
+    "from sklearn.externals import joblib\n",
+    "from azureml.core.model import Model\n",
+    "\n",
+    "\n",
+    "def init():\n",
+    "    global model\n",
+    "    model_path = Model.get_model_path(model_name = '<<modelid>>') # this name is model.id of model that we want to deploy\n",
+    "    # deserialize the model file back into a sklearn model\n",
+    "    model = joblib.load(model_path)\n",
+    "\n",
+    "def run(rawdata):\n",
+    "    try:\n",
+    "        data = json.loads(rawdata)['data']\n",
+    "        data = numpy.array(data)\n",
+    "        result = model.predict(data)\n",
+    "    except Exception as e:\n",
+    "        result = str(e)\n",
+    "        return json.dumps({\"error\": result})\n",
+    "    return json.dumps({\"result\":result.tolist()})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create a YAML File for the Environment"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To ensure the fit results are consistent with the training results, the SDK dependency versions need to be the same as the environment that trains the model. Details about retrieving the versions can be found in notebook [12.auto-ml-retrieve-the-training-sdk-versions](12.auto-ml-retrieve-the-training-sdk-versions.ipynb)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dependencies = remote_run.get_run_sdk_dependencies(iteration = 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for p in ['azureml-train-automl', 'azureml-sdk', 'azureml-core']:\n",
+    "    print('{}\\t{}'.format(p, dependencies[p]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.conda_dependencies import CondaDependencies\n",
+    "\n",
+    "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn','py-xgboost<=0.80'],\n",
+    "                                 pip_packages=['azureml-sdk[automl]'])\n",
+    "\n",
+    "conda_env_file_name = 'myenv.yml'\n",
+    "myenv.save_to_file('.', conda_env_file_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Substitute the actual version number in the environment file.\n",
+    "# This is not strictly needed in this notebook because the model should have been generated using the current SDK version.\n",
+    "# However, we include this in case this code is used on an experiment from a previous SDK version.\n",
+    "\n",
+    "with open(conda_env_file_name, 'r') as cefr:\n",
+    "    content = cefr.read()\n",
+    "\n",
+    "with open(conda_env_file_name, 'w') as cefw:\n",
+    "    cefw.write(content.replace(azureml.core.VERSION, dependencies['azureml-sdk']))\n",
+    "\n",
+    "# Substitute the actual model id in the script file.\n",
+    "\n",
+    "script_file_name = 'score.py'\n",
+    "\n",
+    "with open(script_file_name, 'r') as cefr:\n",
+    "    content = cefr.read()\n",
+    "\n",
+    "with open(script_file_name, 'w') as cefw:\n",
+    "    cefw.write(content.replace('<<modelid>>', remote_run.model_id))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create a Container Image\n",
+    "\n",
+    "Next use Azure Container Instances for deploying models as a web service for quickly deploying and validating your model\n",
+    "or when testing a model that is under development."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.image import Image, ContainerImage\n",
+    "\n",
+    "image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
+    "                                 execution_script = script_file_name,\n",
+    "                                 conda_file = conda_env_file_name,\n",
+    "                                 tags = {'area': \"bmData\", 'type': \"automl_classification\"},\n",
+    "                                 description = \"Image for automl classification sample\")\n",
+    "\n",
+    "image = Image.create(name = \"automlsampleimage\",\n",
+    "                     # this is the model object \n",
+    "                     models = [model],\n",
+    "                     image_config = image_config, \n",
+    "                     workspace = ws)\n",
+    "\n",
+    "image.wait_for_creation(show_output = True)\n",
+    "\n",
+    "if image.creation_state == 'Failed':\n",
+    "    print(\"Image build log at: \" + image.image_build_log_uri)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Deploy the Image as a Web Service on Azure Container Instance\n",
+    "\n",
+    "Deploy an image that contains the model and other assets needed by the service."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.webservice import AciWebservice\n",
+    "\n",
+    "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
+    "                                               memory_gb = 1, \n",
+    "                                               tags = {'area': \"bmData\", 'type': \"automl_classification\"}, \n",
+    "                                               description = 'sample service for Automl Classification')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.webservice import Webservice\n",
+    "\n",
+    "aci_service_name = 'automl-sample-bankmarketing'\n",
+    "print(aci_service_name)\n",
+    "aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
+    "                                           image = image,\n",
+    "                                           name = aci_service_name,\n",
+    "                                           workspace = ws)\n",
+    "aci_service.wait_for_deployment(True)\n",
+    "print(aci_service.state)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Delete a Web Service\n",
+    "\n",
+    "Deletes the specified web service."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#aci_service.delete()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Get Logs from a Deployed Web Service\n",
+    "\n",
+    "Gets logs from a deployed web service."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#aci_service.get_logs()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test\n",
+    "\n",
+    "Now that the model is trained split our data in the same way the data was split for training (The difference here is the data is being split locally) and then run the test data through the trained model to get the predicted values."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load the bank marketing datasets.\n",
+    "from sklearn.datasets import load_diabetes\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from numpy import array"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_validate.csv\"\n",
+    "dflow = dprep.auto_read_file(data)\n",
+    "dflow.get_profile()\n",
+    "X_test = dflow.drop_columns(columns=['y'])\n",
+    "y_test = dflow.keep_columns(columns=['y'], validate_column_exists=True)\n",
+    "dflow.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_test = X_test.to_pandas_dataframe()\n",
+    "y_test = y_test.to_pandas_dataframe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred  = fitted_model.predict(X_test)\n",
+    "actual = array(y_test)\n",
+    "actual = actual[:,0]\n",
+    "print(y_pred.shape, \" \", actual.shape)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Calculate metrics for the prediction\n",
+    "\n",
+    "Now visualize the data on a scatter plot to show what our truth (actual) values are compared to the predicted values \n",
+    "from the trained model that was returned."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib notebook\n",
+    "test_pred = plt.scatter(actual, y_pred, color='b')\n",
+    "test_test = plt.scatter(actual, actual, color='g')\n",
+    "plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Acknowledgements"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This Bank Marketing dataset is made available under the Creative Commons (CCO: Public Domain) License: https://creativecommons.org/publicdomain/zero/1.0/. Any rights in individual contents of the database are licensed under the Database Contents License: https://creativecommons.org/publicdomain/zero/1.0/ and is available at: https://www.kaggle.com/janiobachmann/bank-marketing-dataset .\n",
+    "\n",
+    "_**Acknowledgements**_\n",
+    "This data set is originally available within the UCI Machine Learning Database: https://archive.ics.uci.edu/ml/datasets/bank+marketing\n",
+    "\n",
+    "[Moro et al., 2014] S. Moro, P. Cortez and P. Rita. A Data-Driven Approach to Predict the Success of Bank Telemarketing. Decision Support Systems, Elsevier, 62:22-31, June 2014"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "v-rasav"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3.6",
+   "language": "python",
+   "name": "python36"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

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

@@ -0,0 +1,712 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+    "\n",
+    "Licensed under the MIT License."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/classification-credit-card-fraud/auto-ml-classification-credit-card-fraud.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Automated Machine Learning\n",
+    "_**Classification with Deployment using Credit Card Dataset**_\n",
+    "\n",
+    "## Contents\n",
+    "1. [Introduction](#Introduction)\n",
+    "1. [Setup](#Setup)\n",
+    "1. [Train](#Train)\n",
+    "1. [Results](#Results)\n",
+    "1. [Deploy](#Deploy)\n",
+    "1. [Test](#Test)\n",
+    "1. [Acknowledgements](#Acknowledgements)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Introduction\n",
+    "\n",
+    "In this example we use the associated credit card dataset to showcase how you can use AutoML for a simple classification problem and deploy it to an Azure Container Instance (ACI). The classification goal is to predict if a creditcard transaction  is or is not considered a fraudulent charge.\n",
+    "\n",
+    "If you are using an Azure Machine Learning Notebook VM, you are all set.  Otherwise, go through the [configuration](../../../configuration.ipynb)  notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
+    "\n",
+    "In this notebook you will learn how to:\n",
+    "1. Create an experiment using an existing workspace.\n",
+    "2. Configure AutoML using `AutoMLConfig`.\n",
+    "3. Train the model using local compute.\n",
+    "4. Explore the results.\n",
+    "5. Register the model.\n",
+    "6. Create a container image.\n",
+    "7. Create an Azure Container Instance (ACI) service.\n",
+    "8. Test the ACI service."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import logging\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "import pandas as pd\n",
+    "import os\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "import azureml.dataprep as dprep\n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# choose a name for experiment\n",
+    "experiment_name = 'automl-classification-ccard'\n",
+    "# project folder\n",
+    "project_folder = './sample_projects/automl-classification-creditcard'\n",
+    "\n",
+    "experiment=Experiment(ws, experiment_name)\n",
+    "\n",
+    "output = {}\n",
+    "output['SDK version'] = azureml.core.VERSION\n",
+    "output['Subscription ID'] = ws.subscription_id\n",
+    "output['Workspace'] = ws.name\n",
+    "output['Resource Group'] = ws.resource_group\n",
+    "output['Location'] = ws.location\n",
+    "output['Project Directory'] = project_folder\n",
+    "output['Experiment Name'] = experiment.name\n",
+    "pd.set_option('display.max_colwidth', -1)\n",
+    "outputDf = pd.DataFrame(data = output, index = [''])\n",
+    "outputDf.T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create or Attach existing AmlCompute\n",
+    "You will need to create a compute target for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
+    "#### Creation of AmlCompute takes approximately 5 minutes. \n",
+    "If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
+    "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read this article on the default limits and how to request more quota."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.compute import AmlCompute\n",
+    "from azureml.core.compute import ComputeTarget\n",
+    "\n",
+    "# Choose a name for your cluster.\n",
+    "amlcompute_cluster_name = \"automlcl\"\n",
+    "\n",
+    "found = False\n",
+    "# Check if this compute target already exists in the workspace.\n",
+    "cts = ws.compute_targets\n",
+    "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
+    "    found = True\n",
+    "    print('Found existing compute target.')\n",
+    "    compute_target = cts[amlcompute_cluster_name]\n",
+    "    \n",
+    "if not found:\n",
+    "    print('Creating a new compute target...')\n",
+    "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
+    "                                                                #vm_priority = 'lowpriority', # optional\n",
+    "                                                                max_nodes = 6)\n",
+    "\n",
+    "    # Create the cluster.\n",
+    "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
+    "    \n",
+    "    # Can poll for a minimum number of nodes and for a specific timeout.\n",
+    "    # If no min_node_count is provided, it will use the scale settings for the cluster.\n",
+    "    compute_target.wait_for_completion(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
+    "    \n",
+    "     # For a more detailed view of current AmlCompute status, use get_status()."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Data\n",
+    "\n",
+    "Here load the data in the get_data script to be utilized in azure compute. To do this, first load all the necessary libraries and dependencies to set up paths for the data and to create the conda_run_config."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if not os.path.isdir('data'):\n",
+    "    os.mkdir('data')\n",
+    "    \n",
+    "if not os.path.exists(project_folder):\n",
+    "    os.makedirs(project_folder)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.runconfig import RunConfiguration\n",
+    "from azureml.core.conda_dependencies import CondaDependencies\n",
+    "\n",
+    "# create a new RunConfig object\n",
+    "conda_run_config = RunConfiguration(framework=\"python\")\n",
+    "\n",
+    "# Set compute target to AmlCompute\n",
+    "conda_run_config.target = compute_target\n",
+    "conda_run_config.environment.docker.enabled = True\n",
+    "conda_run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
+    "\n",
+    "\n",
+    "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy','py-xgboost<=0.80'])\n",
+    "conda_run_config.environment.python.conda_dependencies = cd"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Load Data\n",
+    "\n",
+    "Here create the script to be run in azure compute for loading the data, load the credit card dataset into cards and store the Class column (y) in the y variable and store the remaining data in the x variable. Next split the data  using train_test_split and return X_train and y_train for training the model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/creditcard.csv\"\n",
+    "dflow = dprep.auto_read_file(data)\n",
+    "dflow.get_profile()\n",
+    "X = dflow.drop_columns(columns=['Class'])\n",
+    "y = dflow.keep_columns(columns=['Class'], validate_column_exists=True)\n",
+    "X_train, X_test = X.random_split(percentage=0.8, seed=223)\n",
+    "y_train, y_test = y.random_split(percentage=0.8, seed=223)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Train\n",
+    "\n",
+    "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
+    "\n",
+    "|Property|Description|\n",
+    "|-|-|\n",
+    "|**task**|classification or regression|\n",
+    "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
+    "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+    "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
+    "|**n_cross_validations**|Number of cross validation splits.|\n",
+    "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+    "|**y**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|\n",
+    "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|\n",
+    "\n",
+    "**_You can find more information about primary metrics_** [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#primary-metric)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "##### If you would like to see even better results increase \"iteration_time_out minutes\" to 10+ mins and increase \"iterations\" to a minimum of 30"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_settings = {\n",
+    "    \"iteration_timeout_minutes\": 5,\n",
+    "    \"iterations\": 10,\n",
+    "    \"n_cross_validations\": 2,\n",
+    "    \"primary_metric\": 'average_precision_score_weighted',\n",
+    "    \"preprocess\": True,\n",
+    "    \"max_concurrent_iterations\": 5,\n",
+    "    \"verbosity\": logging.INFO,\n",
+    "}\n",
+    "\n",
+    "automl_config = AutoMLConfig(task = 'classification',\n",
+    "                             debug_log = 'automl_errors_20190417.log',\n",
+    "                             path = project_folder,\n",
+    "                             run_configuration=conda_run_config,\n",
+    "                             X = X_train,\n",
+    "                             y = y_train,\n",
+    "                             **automl_settings\n",
+    "                            )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
+    "In this example, we specify `show_output = True` to print currently running iterations to the console."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "remote_run = experiment.submit(automl_config, show_output = True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "remote_run"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Results"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Widget for Monitoring Runs\n",
+    "\n",
+    "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+    "\n",
+    "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.widgets import RunDetails\n",
+    "RunDetails(remote_run).show() "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Deploy\n",
+    "\n",
+    "### Retrieve the Best Model\n",
+    "\n",
+    "Below we select the best pipeline from our iterations. The `get_output` method on `automl_classifier` returns the best run and the fitted model for the last invocation. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_model = remote_run.get_output()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Register the Fitted Model for Deployment\n",
+    "If neither `metric` nor `iteration` are specified in the `register_model` call, the iteration with the best primary metric is registered."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "description = 'AutoML Model'\n",
+    "tags = None\n",
+    "model = remote_run.register_model(description = description, tags = tags)\n",
+    "\n",
+    "print(remote_run.model_id) # This will be written to the script file later in the notebook."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create Scoring Script\n",
+    "The scoring script is required to generate the image for deployment. It contains the code to do the predictions on input data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%writefile score.py\n",
+    "import pickle\n",
+    "import json\n",
+    "import numpy\n",
+    "import azureml.train.automl\n",
+    "from sklearn.externals import joblib\n",
+    "from azureml.core.model import Model\n",
+    "\n",
+    "def init():\n",
+    "    global model\n",
+    "    model_path = Model.get_model_path(model_name = '<<modelid>>') # this name is model.id of model that we want to deploy\n",
+    "    # deserialize the model file back into a sklearn model\n",
+    "    model = joblib.load(model_path)\n",
+    "\n",
+    "def run(rawdata):\n",
+    "    try:\n",
+    "        data = json.loads(rawdata)['data']\n",
+    "        data = numpy.array(data)\n",
+    "        result = model.predict(data)\n",
+    "    except Exception as e:\n",
+    "        result = str(e)\n",
+    "        return json.dumps({\"error\": result})\n",
+    "    return json.dumps({\"result\":result.tolist()})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create a YAML File for the Environment"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To ensure the fit results are consistent with the training results, the SDK dependency versions need to be the same as the environment that trains the model. Details about retrieving the versions can be found in notebook [12.auto-ml-retrieve-the-training-sdk-versions](12.auto-ml-retrieve-the-training-sdk-versions.ipynb)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dependencies = remote_run.get_run_sdk_dependencies(iteration = 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for p in ['azureml-train-automl', 'azureml-sdk', 'azureml-core']:\n",
+    "    print('{}\\t{}'.format(p, dependencies[p]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn','py-xgboost<=0.80'],\n",
+    "                                 pip_packages=['azureml-sdk[automl]'])\n",
+    "\n",
+    "conda_env_file_name = 'myenv.yml'\n",
+    "myenv.save_to_file('.', conda_env_file_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Substitute the actual version number in the environment file.\n",
+    "# This is not strictly needed in this notebook because the model should have been generated using the current SDK version.\n",
+    "# However, we include this in case this code is used on an experiment from a previous SDK version.\n",
+    "\n",
+    "with open(conda_env_file_name, 'r') as cefr:\n",
+    "    content = cefr.read()\n",
+    "\n",
+    "with open(conda_env_file_name, 'w') as cefw:\n",
+    "    cefw.write(content.replace(azureml.core.VERSION, dependencies['azureml-sdk']))\n",
+    "\n",
+    "# Substitute the actual model id in the script file.\n",
+    "\n",
+    "script_file_name = 'score.py'\n",
+    "\n",
+    "with open(script_file_name, 'r') as cefr:\n",
+    "    content = cefr.read()\n",
+    "\n",
+    "with open(script_file_name, 'w') as cefw:\n",
+    "    cefw.write(content.replace('<<modelid>>', remote_run.model_id))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create a Container Image\n",
+    "\n",
+    "Next use Azure Container Instances for deploying models as a web service for quickly deploying and validating your model\n",
+    "or when testing a model that is under development."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.image import Image, ContainerImage\n",
+    "\n",
+    "image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
+    "                                 execution_script = script_file_name,\n",
+    "                                 conda_file = conda_env_file_name,\n",
+    "                                 tags = {'area': \"cards\", 'type': \"automl_classification\"},\n",
+    "                                 description = \"Image for automl classification sample\")\n",
+    "\n",
+    "image = Image.create(name = \"automlsampleimage\",\n",
+    "                     # this is the model object \n",
+    "                     models = [model],\n",
+    "                     image_config = image_config, \n",
+    "                     workspace = ws)\n",
+    "\n",
+    "image.wait_for_creation(show_output = True)\n",
+    "\n",
+    "if image.creation_state == 'Failed':\n",
+    "    print(\"Image build log at: \" + image.image_build_log_uri)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Deploy the Image as a Web Service on Azure Container Instance\n",
+    "\n",
+    "Deploy an image that contains the model and other assets needed by the service."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.webservice import AciWebservice\n",
+    "\n",
+    "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
+    "                                               memory_gb = 1, \n",
+    "                                               tags = {'area': \"cards\", 'type': \"automl_classification\"}, \n",
+    "                                               description = 'sample service for Automl Classification')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.webservice import Webservice\n",
+    "\n",
+    "aci_service_name = 'automl-sample-creditcard'\n",
+    "print(aci_service_name)\n",
+    "aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
+    "                                           image = image,\n",
+    "                                           name = aci_service_name,\n",
+    "                                           workspace = ws)\n",
+    "aci_service.wait_for_deployment(True)\n",
+    "print(aci_service.state)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Delete a Web Service\n",
+    "\n",
+    "Deletes the specified web service."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#aci_service.delete()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Get Logs from a Deployed Web Service\n",
+    "\n",
+    "Gets logs from a deployed web service."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#aci_service.get_logs()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test\n",
+    "\n",
+    "Now that the model is trained, split the data in the same way the data was split for training (The difference here is the data is being split locally) and then run the test data through the trained model to get the predicted values."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Randomly select and test\n",
+    "X_test = X_test.to_pandas_dataframe()\n",
+    "y_test = y_test.to_pandas_dataframe()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = fitted_model.predict(X_test)\n",
+    "y_pred"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Calculate metrics for the prediction\n",
+    "\n",
+    "Now visualize the data on a scatter plot to show what our truth (actual) values are compared to the predicted values \n",
+    "from the trained model that was returned."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Randomly select and test\n",
+    "# Plot outputs\n",
+    "%matplotlib notebook\n",
+    "test_pred = plt.scatter(y_test, y_pred, color='b')\n",
+    "test_test = plt.scatter(y_test, y_test, color='g')\n",
+    "plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
+    "plt.show()\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Acknowledgements"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This Credit Card fraud Detection dataset is made available under the Open Database License: http://opendatacommons.org/licenses/odbl/1.0/. Any rights in individual contents of the database are licensed under the Database Contents License: http://opendatacommons.org/licenses/dbcl/1.0/ and is available at: https://www.kaggle.com/mlg-ulb/creditcardfraud\n",
+    "\n",
+    "\n",
+    "The dataset has been collected and analysed during a research collaboration of Worldline and the Machine Learning Group (http://mlg.ulb.ac.be) of ULB (Université Libre de Bruxelles) on big data mining and fraud detection. More details on current and past projects on related topics are available on https://www.researchgate.net/project/Fraud-detection-5 and the page of the DefeatFraud project\n",
+    "Please cite the following works: \n",
+    "•\tAndrea Dal Pozzolo, Olivier Caelen, Reid A. Johnson and Gianluca Bontempi. Calibrating Probability with Undersampling for Unbalanced Classification. In Symposium on Computational Intelligence and Data Mining (CIDM), IEEE, 2015\n",
+    "•\tDal Pozzolo, Andrea; Caelen, Olivier; Le Borgne, Yann-Ael; Waterschoot, Serge; Bontempi, Gianluca. Learned lessons in credit card fraud detection from a practitioner perspective, Expert systems with applications,41,10,4915-4928,2014, Pergamon\n",
+    "•\tDal Pozzolo, Andrea; Boracchi, Giacomo; Caelen, Olivier; Alippi, Cesare; Bontempi, Gianluca. Credit card fraud detection: a realistic modeling and a novel learning strategy, IEEE transactions on neural networks and learning systems,29,8,3784-3797,2018,IEEE\n",
+    "o\tDal Pozzolo, Andrea Adaptive Machine learning for credit card fraud detection ULB MLG PhD thesis (supervised by G. Bontempi)\n",
+    "•\tCarcillo, Fabrizio; Dal Pozzolo, Andrea; Le Borgne, Yann-Aël; Caelen, Olivier; Mazzer, Yannis; Bontempi, Gianluca. Scarff: a scalable framework for streaming credit card fraud detection with Spark, Information fusion,41, 182-194,2018,Elsevier\n",
+    "•\tCarcillo, Fabrizio; Le Borgne, Yann-Aël; Caelen, Olivier; Bontempi, Gianluca. Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization, International Journal of Data Science and Analytics, 5,4,285-300,2018,Springer International Publishing"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "v-rasav"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3.6",
+   "language": "python",
+   "name": "python36"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

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

@@ -129,6 +129,22 @@
         "                                                    test_size=0.2, \n",
         "                                                    random_state=0)\n",
         "\n",
+        "\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Ensure the x_train and x_test are pandas DataFrame."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
         "# Convert the X_train and X_test to pandas DataFrame and set column names,\n",
         "# This is needed for initializing the input variable names of ONNX model, \n",
         "# and the prediction with the ONNX model using the inference helper.\n",
@@ -158,6 +174,13 @@
         "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Set the preprocess=True,  currently the InferenceHelper only supports this mode."
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -299,7 +322,7 @@
         "    onnxrt_present = False\n",
         "\n",
         "def get_onnx_res(run):\n",
-        "    res_path = '_debug_y_trans_converter.json'\n",
+        "    res_path = 'onnx_resource.json'\n",
         "    run.download_file(name=constants.MODEL_RESOURCE_PATH_ONNX, output_file_path=res_path)\n",
         "    with open(res_path) as f:\n",
         "        onnx_res = json.load(f)\n",
@@ -316,7 +339,7 @@
         "    print(pred_prob_onnx)\n",
         "else:\n",
         "    if not python_version_compatible:\n",
-        "        print('Please use Python version 3.6 to run the inference helper.')    \n",
+        "        print('Please use Python version 3.6 or 3.7 to run the inference helper.')    \n",
         "    if not onnxrt_present:\n",
         "        print('Please install the onnxruntime package to do the prediction with ONNX model.')"
       ]

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

@@ -21,7 +21,7 @@
       "metadata": {},
       "source": [
         "# Automated Machine Learning\n",
-        "_**Prepare Data using `azureml.dataprep` for Remote Execution (DSVM)**_\n",
+        "_**Prepare Data using `azureml.dataprep` for Remote Execution (AmlCompute)**_\n",
         "\n",
         "## Contents\n",
         "1. [Introduction](#Introduction)\n",
@@ -205,7 +205,7 @@
         "from azureml.core.compute import ComputeTarget\n",
         "\n",
         "# Choose a name for your cluster.\n",
-        "amlcompute_cluster_name = \"cpucluster\"\n",
+        "amlcompute_cluster_name = \"cpu-cluster\"\n",
         "\n",
         "found = False\n",
         "\n",

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

@@ -72,7 +72,6 @@
         "# 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",

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

@@ -65,10 +65,6 @@
         "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",

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

@@ -67,10 +67,6 @@
         "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",

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

@@ -0,0 +1,800 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+    "\n",
+    "Licensed under the MIT License."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/regression-concrete-strength/auto-ml-regression-concrete-strength.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Automated Machine Learning\n",
+    "_**Regression with Deployment using Hardware Performance Dataset**_\n",
+    "\n",
+    "## Contents\n",
+    "1. [Introduction](#Introduction)\n",
+    "1. [Setup](#Setup)\n",
+    "1. [Data](#Data)\n",
+    "1. [Train](#Train)\n",
+    "1. [Results](#Results)\n",
+    "1. [Test](#Test)\n",
+    "1. [Acknowledgements](#Acknowledgements)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Introduction\n",
+    "In this example we use the Predicting Compressive Strength of Concrete Dataset to showcase how you can use AutoML for a regression problem. The regression goal is to predict the compressive strength of concrete based off of different ingredient combinations and the quantities of those ingredients.\n",
+    "\n",
+    "If you are using an Azure Machine Learning Notebook VM, you are all set.  Otherwise, go through the [configuration](../../../configuration.ipynb)  notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
+    "\n",
+    "In this notebook you will learn how to:\n",
+    "1. Create an `Experiment` in an existing `Workspace`.\n",
+    "2. Configure AutoML using `AutoMLConfig`.\n",
+    "3. Train the model using local compute.\n",
+    "4. Explore the results.\n",
+    "5. Test the best fitted model."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "As part of the setup you have already created an Azure ML Workspace object. For AutoML you will need to create an Experiment object, which is a named object in a Workspace used to run experiments."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import logging\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import os\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "import azureml.dataprep as dprep\n",
+    " \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-regression-concrete'\n",
+    "project_folder = './sample_projects/automl-regression-concrete'\n",
+    "\n",
+    "experiment = Experiment(ws, experiment_name)\n",
+    "\n",
+    "output = {}\n",
+    "output['SDK version'] = azureml.core.VERSION\n",
+    "output['Subscription ID'] = ws.subscription_id\n",
+    "output['Workspace Name'] = ws.name\n",
+    "output['Resource Group'] = ws.resource_group\n",
+    "output['Location'] = ws.location\n",
+    "output['Project Directory'] = project_folder\n",
+    "output['Experiment Name'] = experiment.name\n",
+    "pd.set_option('display.max_colwidth', -1)\n",
+    "outputDf = pd.DataFrame(data = output, index = [''])\n",
+    "outputDf.T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create or Attach existing AmlCompute\n",
+    "You will need to create a compute target for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
+    "#### Creation of AmlCompute takes approximately 5 minutes. \n",
+    "If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
+    "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read this article on the default limits and how to request more quota."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.compute import AmlCompute\n",
+    "from azureml.core.compute import ComputeTarget\n",
+    "\n",
+    "# Choose a name for your cluster.\n",
+    "amlcompute_cluster_name = \"automlcl\"\n",
+    "\n",
+    "found = False\n",
+    "# Check if this compute target already exists in the workspace.\n",
+    "cts = ws.compute_targets\n",
+    "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
+    "    found = True\n",
+    "    print('Found existing compute target.')\n",
+    "    compute_target = cts[amlcompute_cluster_name]\n",
+    "    \n",
+    "if not found:\n",
+    "    print('Creating a new compute target...')\n",
+    "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
+    "                                                                #vm_priority = 'lowpriority', # optional\n",
+    "                                                                max_nodes = 6)\n",
+    "\n",
+    "    # Create the cluster.\n",
+    "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
+    "    \n",
+    "    # Can poll for a minimum number of nodes and for a specific timeout.\n",
+    "    # If no min_node_count is provided, it will use the scale settings for the cluster.\n",
+    "    compute_target.wait_for_completion(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
+    "    \n",
+    "     # For a more detailed view of current AmlCompute status, use get_status()."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Data\n",
+    "\n",
+    "Here load the data in the get_data script to be utilized in azure compute. To do this, first load all the necessary libraries and dependencies to set up paths for the data and to create the conda_run_config."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if not os.path.isdir('data'):\n",
+    "    os.mkdir('data')\n",
+    "    \n",
+    "if not os.path.exists(project_folder):\n",
+    "    os.makedirs(project_folder)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.runconfig import RunConfiguration\n",
+    "from azureml.core.conda_dependencies import CondaDependencies\n",
+    "\n",
+    "# create a new RunConfig object\n",
+    "conda_run_config = RunConfiguration(framework=\"python\")\n",
+    "\n",
+    "# Set compute target to AmlCompute\n",
+    "conda_run_config.target = compute_target\n",
+    "conda_run_config.environment.docker.enabled = True\n",
+    "conda_run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
+    "\n",
+    "\n",
+    "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy'])\n",
+    "conda_run_config.environment.python.conda_dependencies = cd"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Load Data\n",
+    "\n",
+    "Here create the script to be run in azure compute for loading the data, load the concrete strength dataset into the X and y  variables. Next, split the data  using train_test_split and return X_train and y_train for training the model. Finally, return X_train and y_train for training the model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/compresive_strength_concrete.csv\"\n",
+    "dflow = dprep.auto_read_file(data)\n",
+    "dflow.get_profile()\n",
+    "X = dflow.drop_columns(columns=['CONCRETE'])\n",
+    "y = dflow.keep_columns(columns=['CONCRETE'], validate_column_exists=True)\n",
+    "X_train, X_test = X.random_split(percentage=0.8, seed=223)\n",
+    "y_train, y_test = y.random_split(percentage=0.8, seed=223) \n",
+    "dflow.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Train\n",
+    "\n",
+    "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
+    "\n",
+    "|Property|Description|\n",
+    "|-|-|\n",
+    "|**task**|classification or regression|\n",
+    "|**primary_metric**|This is the metric that you want to optimize. Regression supports the following primary metrics: <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>|\n",
+    "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+    "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
+    "|**n_cross_validations**|Number of cross validation splits.|\n",
+    "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+    "|**y**|(sparse) array-like, shape = [n_samples, ], targets values.|\n",
+    "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|\n",
+    "\n",
+    "**_You can find more information about primary metrics_** [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#primary-metric)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "##### If you would like to see even better results increase \"iteration_time_out minutes\" to 10+ mins and increase \"iterations\" to a minimum of 30"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_settings = {\n",
+    "    \"iteration_timeout_minutes\": 5,\n",
+    "    \"iterations\": 10,\n",
+    "    \"n_cross_validations\": 5,\n",
+    "    \"primary_metric\": 'spearman_correlation',\n",
+    "    \"preprocess\": True,\n",
+    "    \"max_concurrent_iterations\": 5,\n",
+    "    \"verbosity\": logging.INFO,\n",
+    "}\n",
+    "\n",
+    "automl_config = AutoMLConfig(task = 'regression',\n",
+    "                             debug_log = 'automl.log',\n",
+    "                             path = project_folder,\n",
+    "                             run_configuration=conda_run_config,\n",
+    "                             X = X_train,\n",
+    "                             y = y_train,\n",
+    "                             **automl_settings\n",
+    "                            )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "remote_run = experiment.submit(automl_config, show_output = True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "remote_run"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Results\n",
+    "Widget for Monitoring Runs\n",
+    "The widget will first report a “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",
+    "Note: The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.widgets import RunDetails\n",
+    "RunDetails(remote_run).show() "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\n",
+    "Retrieve All Child Runs\n",
+    "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "children = list(remote_run.get_children())\n",
+    "metricslist = {}\n",
+    "for run in children:\n",
+    "    properties = run.get_properties()\n",
+    "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+    "    metricslist[int(properties['iteration'])] = metrics\n",
+    "\n",
+    "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+    "rundata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Retrieve the Best Model\n",
+    "Below we select the best pipeline from our iterations. The get_output method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing. Overloads on get_output allow you to retrieve the best run and fitted model for any logged metric or for a particular iteration."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_model = remote_run.get_output()\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Best Model Based on Any Other Metric\n",
+    "Show the run and the model that has the smallest root_mean_squared_error value (which turned out to be the same as the one with largest spearman_correlation value):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lookup_metric = \"root_mean_squared_error\"\n",
+    "best_run, fitted_model = remote_run.get_output(metric = lookup_metric)\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "iteration = 3\n",
+    "third_run, third_model = remote_run.get_output(iteration = iteration)\n",
+    "print(third_run)\n",
+    "print(third_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Register the Fitted Model for Deployment\n",
+    "If neither metric nor iteration are specified in the register_model call, the iteration with the best primary metric is registered."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "description = 'AutoML Model'\n",
+    "tags = None\n",
+    "model = remote_run.register_model(description = description, tags = tags)\n",
+    "\n",
+    "print(remote_run.model_id) # This will be written to the script file later in the notebook."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create Scoring Script\n",
+    "The scoring script is required to generate the image for deployment. It contains the code to do the predictions on input data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%writefile score.py\n",
+    "import pickle\n",
+    "import json\n",
+    "import numpy\n",
+    "import azureml.train.automl\n",
+    "from sklearn.externals import joblib\n",
+    "from azureml.core.model import Model\n",
+    "\n",
+    "def init():\n",
+    "    global model\n",
+    "    model_path = Model.get_model_path(model_name = '<<modelid>>') # this name is model.id of model that we want to deploy\n",
+    "    # deserialize the model file back into a sklearn model\n",
+    "    model = joblib.load(model_path)\n",
+    "\n",
+    "def run(rawdata):\n",
+    "    try:\n",
+    "        data = json.loads(rawdata)['data']\n",
+    "        data = numpy.array(data)\n",
+    "        result = model.predict(data)\n",
+    "    except Exception as e:\n",
+    "        result = str(e)\n",
+    "        return json.dumps({\"error\": result})\n",
+    "    return json.dumps({\"result\":result.tolist()})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create a YAML File for the Environment"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To ensure the fit results are consistent with the training results, the SDK dependency versions need to be the same as the environment that trains the model. Details about retrieving the versions can be found in notebook [12.auto-ml-retrieve-the-training-sdk-versions](12.auto-ml-retrieve-the-training-sdk-versions.ipynb)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dependencies = remote_run.get_run_sdk_dependencies(iteration = 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for p in ['azureml-train-automl', 'azureml-sdk', 'azureml-core']:\n",
+    "    print('{}\\t{}'.format(p, dependencies[p]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.conda_dependencies import CondaDependencies\n",
+    "\n",
+    "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn'], pip_packages=['azureml-sdk[automl]'])\n",
+    "\n",
+    "conda_env_file_name = 'myenv.yml'\n",
+    "myenv.save_to_file('.', conda_env_file_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Substitute the actual version number in the environment file.\n",
+    "# This is not strictly needed in this notebook because the model should have been generated using the current SDK version.\n",
+    "# However, we include this in case this code is used on an experiment from a previous SDK version.\n",
+    "\n",
+    "with open(conda_env_file_name, 'r') as cefr:\n",
+    "    content = cefr.read()\n",
+    "\n",
+    "with open(conda_env_file_name, 'w') as cefw:\n",
+    "    cefw.write(content.replace(azureml.core.VERSION, dependencies['azureml-sdk']))\n",
+    "\n",
+    "# Substitute the actual model id in the script file.\n",
+    "\n",
+    "script_file_name = 'score.py'\n",
+    "\n",
+    "with open(script_file_name, 'r') as cefr:\n",
+    "    content = cefr.read()\n",
+    "\n",
+    "with open(script_file_name, 'w') as cefw:\n",
+    "    cefw.write(content.replace('<<modelid>>', remote_run.model_id))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create a Container Image\n",
+    "\n",
+    "Next use Azure Container Instances for deploying models as a web service for quickly deploying and validating your model\n",
+    "or when testing a model that is under development."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.image import Image, ContainerImage\n",
+    "\n",
+    "image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
+    "                                 execution_script = script_file_name,\n",
+    "                                 conda_file = conda_env_file_name,\n",
+    "                                 tags = {'area': \"digits\", 'type': \"automl_regression\"},\n",
+    "                                 description = \"Image for automl regression sample\")\n",
+    "\n",
+    "image = Image.create(name = \"automlsampleimage\",\n",
+    "                     # this is the model object \n",
+    "                     models = [model],\n",
+    "                     image_config = image_config, \n",
+    "                     workspace = ws)\n",
+    "\n",
+    "image.wait_for_creation(show_output = True)\n",
+    "\n",
+    "if image.creation_state == 'Failed':\n",
+    "    print(\"Image build log at: \" + image.image_build_log_uri)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Deploy the Image as a Web Service on Azure Container Instance\n",
+    "\n",
+    "Deploy an image that contains the model and other assets needed by the service."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.webservice import AciWebservice\n",
+    "\n",
+    "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
+    "                                               memory_gb = 1, \n",
+    "                                               tags = {'area': \"digits\", 'type': \"automl_regression\"}, \n",
+    "                                               description = 'sample service for Automl Regression')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.webservice import Webservice\n",
+    "\n",
+    "aci_service_name = 'automl-sample-concrete'\n",
+    "print(aci_service_name)\n",
+    "aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
+    "                                           image = image,\n",
+    "                                           name = aci_service_name,\n",
+    "                                           workspace = ws)\n",
+    "aci_service.wait_for_deployment(True)\n",
+    "print(aci_service.state)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Delete a Web Service\n",
+    "\n",
+    "Deletes the specified web service."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#aci_service.delete()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Get Logs from a Deployed Web Service\n",
+    "\n",
+    "Gets logs from a deployed web service."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#aci_service.get_logs()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Test\n",
+    "\n",
+    "Now that the model is trained, split the data in the same way the data was split for training (The difference here is the data is being split locally) and then run the test data through the trained model to get the predicted values."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_test = X_test.to_pandas_dataframe()\n",
+    "y_test = y_test.to_pandas_dataframe()\n",
+    "y_test = np.array(y_test)\n",
+    "y_test = y_test[:,0]\n",
+    "X_train = X_train.to_pandas_dataframe()\n",
+    "y_train = y_train.to_pandas_dataframe()\n",
+    "y_train = np.array(y_train)\n",
+    "y_train = y_train[:,0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "##### Predict on training and test set, and calculate residual values."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred_train = fitted_model.predict(X_train)\n",
+    "y_residual_train = y_train - y_pred_train\n",
+    "\n",
+    "y_pred_test = fitted_model.predict(X_test)\n",
+    "y_residual_test = y_test - y_pred_test\n",
+    "\n",
+    "y_residual_train.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib inline\n",
+    "from sklearn.metrics import mean_squared_error, r2_score\n",
+    "\n",
+    "# Set up a multi-plot chart.\n",
+    "f, (a0, a1) = plt.subplots(1, 2, gridspec_kw = {'width_ratios':[1, 1], 'wspace':0, 'hspace': 0})\n",
+    "f.suptitle('Regression Residual Values', fontsize = 18)\n",
+    "f.set_figheight(6)\n",
+    "f.set_figwidth(16)\n",
+    "\n",
+    "# Plot residual values of training set.\n",
+    "a0.axis([0, 360, -200, 200])\n",
+    "a0.plot(y_residual_train, 'bo', alpha = 0.5)\n",
+    "a0.plot([-10,360],[0,0], 'r-', lw = 3)\n",
+    "a0.text(16,170,'RMSE = {0:.2f}'.format(np.sqrt(mean_squared_error(y_train, y_pred_train))), fontsize = 12)\n",
+    "a0.text(16,140,'R2 score = {0:.2f}'.format(r2_score(y_train, y_pred_train)), fontsize = 12)\n",
+    "a0.set_xlabel('Training samples', fontsize = 12)\n",
+    "a0.set_ylabel('Residual Values', fontsize = 12)\n",
+    "\n",
+    "# Plot a histogram.\n",
+    "#a0.hist(y_residual_train, orientation = 'horizontal', color = ['b']*len(y_residual_train), bins = 10, histtype = 'step')\n",
+    "#a0.hist(y_residual_train, orientation = 'horizontal', color = ['b']*len(y_residual_train), alpha = 0.2, bins = 10)\n",
+    "\n",
+    "# Plot residual values of test set.\n",
+    "a1.axis([0, 90, -200, 200])\n",
+    "a1.plot(y_residual_test, 'bo', alpha = 0.5)\n",
+    "a1.plot([-10,360],[0,0], 'r-', lw = 3)\n",
+    "a1.text(5,170,'RMSE = {0:.2f}'.format(np.sqrt(mean_squared_error(y_test, y_pred_test))), fontsize = 12)\n",
+    "a1.text(5,140,'R2 score = {0:.2f}'.format(r2_score(y_test, y_pred_test)), fontsize = 12)\n",
+    "a1.set_xlabel('Test samples', fontsize = 12)\n",
+    "a1.set_yticklabels([])\n",
+    "\n",
+    "# Plot a histogram.\n",
+    "#a1.hist(y_residual_test, orientation = 'horizontal', color = ['b']*len(y_residual_test), bins = 10, histtype = 'step')\n",
+    "#a1.hist(y_residual_test, orientation = 'horizontal', color = ['b']*len(y_residual_test), alpha = 0.2, bins = 10)\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Calculate metrics for the prediction\n",
+    "\n",
+    "Now visualize the data on a scatter plot to show what our truth (actual) values are compared to the predicted values \n",
+    "from the trained model that was returned."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Plot outputs\n",
+    "%matplotlib notebook\n",
+    "test_pred = plt.scatter(y_test, y_pred_test, color='b')\n",
+    "test_test = plt.scatter(y_test, y_test, color='g')\n",
+    "plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Acknowledgements\n",
+    "\n",
+    "This Predicting Compressive Strength of Concrete Dataset is made available under the CC0 1.0 Universal (CC0 1.0)\n",
+    "Public Domain Dedication License: https://creativecommons.org/publicdomain/zero/1.0/. Any rights in individual contents of the database are licensed under the CC0 1.0 Universal (CC0 1.0)\n",
+    "Public Domain Dedication License: https://creativecommons.org/publicdomain/zero/1.0/ . The dataset itself can be found here: https://www.kaggle.com/pavanraj159/concrete-compressive-strength-data-set and http://archive.ics.uci.edu/ml/datasets/concrete+compressive+strength\n",
+    "\n",
+    "I-Cheng Yeh, \"Modeling of strength of high performance concrete using artificial neural networks,\" Cement and Concrete Research, Vol. 28, No. 12, pp. 1797-1808 (1998). \n",
+    "\n",
+    "Dua, D. and Graff, C. (2019). UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science."
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "v-rasav"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3.6",
+   "language": "python",
+   "name": "python36"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

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

@@ -0,0 +1,800 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+    "\n",
+    "Licensed under the MIT License."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/regression-hardware-performance/auto-ml-regression-hardware-performance.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Automated Machine Learning\n",
+    "_**Regression with Deployment using Hardware Performance Dataset**_\n",
+    "\n",
+    "## Contents\n",
+    "1. [Introduction](#Introduction)\n",
+    "1. [Setup](#Setup)\n",
+    "1. [Data](#Data)\n",
+    "1. [Train](#Train)\n",
+    "1. [Results](#Results)\n",
+    "1. [Test](#Test)\n",
+    "1. [Acknowledgements](#Acknowledgements)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Introduction\n",
+    "In this example we use the Hardware Performance Dataset to showcase how you can use AutoML for a simple regression problem. The Regression goal is to predict the performance of certain combinations of hardware parts.\n",
+    "\n",
+    "If you are using an Azure Machine Learning Notebook VM, you are all set.  Otherwise, go through the [configuration](../../../configuration.ipynb)  notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
+    "\n",
+    "In this notebook you will learn how to:\n",
+    "1. Create an `Experiment` in an existing `Workspace`.\n",
+    "2. Configure AutoML using `AutoMLConfig`.\n",
+    "3. Train the model using local compute.\n",
+    "4. Explore the results.\n",
+    "5. Test the best fitted model."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "As part of the setup you have already created an Azure ML Workspace object. For AutoML you will need to create an Experiment object, which is a named object in a Workspace used to run experiments."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import logging\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import os\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "import azureml.dataprep as dprep\n",
+    " \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-regression-hardware'\n",
+    "project_folder = './sample_projects/automl-remote-regression'\n",
+    "\n",
+    "experiment = Experiment(ws, experiment_name)\n",
+    "\n",
+    "output = {}\n",
+    "output['SDK version'] = azureml.core.VERSION\n",
+    "output['Subscription ID'] = ws.subscription_id\n",
+    "output['Workspace Name'] = ws.name\n",
+    "output['Resource Group'] = ws.resource_group\n",
+    "output['Location'] = ws.location\n",
+    "output['Project Directory'] = project_folder\n",
+    "output['Experiment Name'] = experiment.name\n",
+    "pd.set_option('display.max_colwidth', -1)\n",
+    "outputDf = pd.DataFrame(data = output, index = [''])\n",
+    "outputDf.T"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create or Attach existing AmlCompute\n",
+    "You will need to create a compute target for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
+    "#### Creation of AmlCompute takes approximately 5 minutes. \n",
+    "If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
+    "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read this article on the default limits and how to request more quota."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.compute import AmlCompute\n",
+    "from azureml.core.compute import ComputeTarget\n",
+    "\n",
+    "# Choose a name for your cluster.\n",
+    "amlcompute_cluster_name = \"automlcl\"\n",
+    "\n",
+    "found = False\n",
+    "# Check if this compute target already exists in the workspace.\n",
+    "cts = ws.compute_targets\n",
+    "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
+    "    found = True\n",
+    "    print('Found existing compute target.')\n",
+    "    compute_target = cts[amlcompute_cluster_name]\n",
+    "    \n",
+    "if not found:\n",
+    "    print('Creating a new compute target...')\n",
+    "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
+    "                                                                #vm_priority = 'lowpriority', # optional\n",
+    "                                                                max_nodes = 6)\n",
+    "\n",
+    "    # Create the cluster.\n",
+    "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
+    "    \n",
+    "    # Can poll for a minimum number of nodes and for a specific timeout.\n",
+    "    # If no min_node_count is provided, it will use the scale settings for the cluster.\n",
+    "    compute_target.wait_for_completion(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
+    "    \n",
+    "     # For a more detailed view of current AmlCompute status, use get_status()."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Data\n",
+    "\n",
+    "Here load the data in the get_data script to be utilized in azure compute. To do this, first load all the necessary libraries and dependencies to set up paths for the data and to create the conda_run_config."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if not os.path.isdir('data'):\n",
+    "    os.mkdir('data')\n",
+    "    \n",
+    "if not os.path.exists(project_folder):\n",
+    "    os.makedirs(project_folder)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.runconfig import RunConfiguration\n",
+    "from azureml.core.conda_dependencies import CondaDependencies\n",
+    "\n",
+    "# create a new RunConfig object\n",
+    "conda_run_config = RunConfiguration(framework=\"python\")\n",
+    "\n",
+    "# Set compute target to AmlCompute\n",
+    "conda_run_config.target = compute_target\n",
+    "conda_run_config.environment.docker.enabled = True\n",
+    "conda_run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
+    "\n",
+    "\n",
+    "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy'])\n",
+    "conda_run_config.environment.python.conda_dependencies = cd"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Load Data\n",
+    "\n",
+    "Here create the script to be run in azure compute for loading the data, load the hardware dataset into the X and y variables. Next split the data  using train_test_split and return X_train and y_train for training the model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/machineData.csv\"\n",
+    "dflow = dprep.auto_read_file(data)\n",
+    "dflow.get_profile()\n",
+    "X = dflow.drop_columns(columns=['ERP'])\n",
+    "y = dflow.keep_columns(columns=['ERP'], validate_column_exists=True)\n",
+    "X_train, X_test = X.random_split(percentage=0.8, seed=223)\n",
+    "y_train, y_test = y.random_split(percentage=0.8, seed=223) \n",
+    "dflow.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\n",
+    "## Train\n",
+    "\n",
+    "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
+    "\n",
+    "|Property|Description|\n",
+    "|-|-|\n",
+    "|**task**|classification or regression|\n",
+    "|**primary_metric**|This is the metric that you want to optimize. Regression supports the following primary metrics: <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>|\n",
+    "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+    "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
+    "|**n_cross_validations**|Number of cross validation splits.|\n",
+    "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+    "|**y**|(sparse) array-like, shape = [n_samples, ], targets values.|\n",
+    "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|\n",
+    "\n",
+    "**_You can find more information about primary metrics_** [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#primary-metric)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "##### If you would like to see even better results increase \"iteration_time_out minutes\" to 10+ mins and increase \"iterations\" to a minimum of 30"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_settings = {\n",
+    "    \"iteration_timeout_minutes\": 5,\n",
+    "    \"iterations\": 10,\n",
+    "    \"n_cross_validations\": 5,\n",
+    "    \"primary_metric\": 'spearman_correlation',\n",
+    "    \"preprocess\": True,\n",
+    "    \"max_concurrent_iterations\": 5,\n",
+    "    \"verbosity\": logging.INFO,\n",
+    "}\n",
+    "\n",
+    "automl_config = AutoMLConfig(task = 'regression',\n",
+    "                             debug_log = 'automl_errors_20190417.log',\n",
+    "                             path = project_folder,\n",
+    "                             run_configuration=conda_run_config,\n",
+    "                             X = X_train,\n",
+    "                             y = y_train,\n",
+    "                             **automl_settings\n",
+    "                            )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "remote_run = experiment.submit(automl_config, show_output = False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "remote_run"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Results"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Widget for Monitoring Runs\n",
+    "\n",
+    "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+    "\n",
+    "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.widgets import RunDetails\n",
+    "RunDetails(remote_run).show() "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Wait until the run finishes.\n",
+    "remote_run.wait_for_completion(show_output = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Retrieve All Child Runs\n",
+    "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "children = list(remote_run.get_children())\n",
+    "metricslist = {}\n",
+    "for run in children:\n",
+    "    properties = run.get_properties()\n",
+    "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+    "    metricslist[int(properties['iteration'])] = metrics\n",
+    "\n",
+    "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+    "rundata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Retrieve the Best Model\n",
+    "Below we select the best pipeline from our iterations. The get_output method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing. Overloads on get_output allow you to retrieve the best run and fitted model for any logged metric or for a particular iteration."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_model = remote_run.get_output()\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Best Model Based on Any Other Metric\n",
+    "Show the run and the model that has the smallest `root_mean_squared_error` value (which turned out to be the same as the one with largest `spearman_correlation` value):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lookup_metric = \"root_mean_squared_error\"\n",
+    "best_run, fitted_model = remote_run.get_output(metric = lookup_metric)\n",
+    "print(best_run)\n",
+    "print(fitted_model)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "iteration = 3\n",
+    "third_run, third_model = remote_run.get_output(iteration = iteration)\n",
+    "print(third_run)\n",
+    "print(third_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Register the Fitted Model for Deployment\n",
+    "If neither metric nor iteration are specified in the register_model call, the iteration with the best primary metric is registered."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "description = 'AutoML Model'\n",
+    "tags = None\n",
+    "model = remote_run.register_model(description = description, tags = tags)\n",
+    "\n",
+    "print(remote_run.model_id) # This will be written to the script file later in the notebook."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create Scoring Script\n",
+    "The scoring script is required to generate the image for deployment. It contains the code to do the predictions on input data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%writefile score.py\n",
+    "import pickle\n",
+    "import json\n",
+    "import numpy\n",
+    "import azureml.train.automl\n",
+    "from sklearn.externals import joblib\n",
+    "from azureml.core.model import Model\n",
+    "\n",
+    "def init():\n",
+    "    global model\n",
+    "    model_path = Model.get_model_path(model_name = '<<modelid>>') # this name is model.id of model that we want to deploy\n",
+    "    # deserialize the model file back into a sklearn model\n",
+    "    model = joblib.load(model_path)\n",
+    "\n",
+    "def run(rawdata):\n",
+    "    try:\n",
+    "        data = json.loads(rawdata)['data']\n",
+    "        data = numpy.array(data)\n",
+    "        result = model.predict(data)\n",
+    "    except Exception as e:\n",
+    "        result = str(e)\n",
+    "        return json.dumps({\"error\": result})\n",
+    "    return json.dumps({\"result\":result.tolist()})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create a YAML File for the Environment"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To ensure the fit results are consistent with the training results, the SDK dependency versions need to be the same as the environment that trains the model. Details about retrieving the versions can be found in notebook [12.auto-ml-retrieve-the-training-sdk-versions](12.auto-ml-retrieve-the-training-sdk-versions.ipynb)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dependencies = remote_run.get_run_sdk_dependencies(iteration = 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for p in ['azureml-train-automl', 'azureml-sdk', 'azureml-core']:\n",
+    "    print('{}\\t{}'.format(p, dependencies[p]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn'], pip_packages=['azureml-sdk[automl]'])\n",
+    "\n",
+    "conda_env_file_name = 'myenv.yml'\n",
+    "myenv.save_to_file('.', conda_env_file_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Substitute the actual version number in the environment file.\n",
+    "# This is not strictly needed in this notebook because the model should have been generated using the current SDK version.\n",
+    "# However, we include this in case this code is used on an experiment from a previous SDK version.\n",
+    "\n",
+    "with open(conda_env_file_name, 'r') as cefr:\n",
+    "    content = cefr.read()\n",
+    "\n",
+    "with open(conda_env_file_name, 'w') as cefw:\n",
+    "    cefw.write(content.replace(azureml.core.VERSION, dependencies['azureml-sdk']))\n",
+    "\n",
+    "# Substitute the actual model id in the script file.\n",
+    "\n",
+    "script_file_name = 'score.py'\n",
+    "\n",
+    "with open(script_file_name, 'r') as cefr:\n",
+    "    content = cefr.read()\n",
+    "\n",
+    "with open(script_file_name, 'w') as cefw:\n",
+    "    cefw.write(content.replace('<<modelid>>', remote_run.model_id))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create a Container Image\n",
+    "\n",
+    "Next use Azure Container Instances for deploying models as a web service for quickly deploying and validating your model\n",
+    "or when testing a model that is under development."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.image import Image, ContainerImage\n",
+    "\n",
+    "image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
+    "                                 execution_script = script_file_name,\n",
+    "                                 conda_file = conda_env_file_name,\n",
+    "                                 tags = {'area': \"digits\", 'type': \"automl_regression\"},\n",
+    "                                 description = \"Image for automl regression sample\")\n",
+    "\n",
+    "image = Image.create(name = \"automlsampleimage\",\n",
+    "                     # this is the model object \n",
+    "                     models = [model],\n",
+    "                     image_config = image_config, \n",
+    "                     workspace = ws)\n",
+    "\n",
+    "image.wait_for_creation(show_output = True)\n",
+    "\n",
+    "if image.creation_state == 'Failed':\n",
+    "    print(\"Image build log at: \" + image.image_build_log_uri)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Deploy the Image as a Web Service on Azure Container Instance\n",
+    "\n",
+    "Deploy an image that contains the model and other assets needed by the service."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.webservice import AciWebservice\n",
+    "\n",
+    "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
+    "                                               memory_gb = 1, \n",
+    "                                               tags = {'area': \"digits\", 'type': \"automl_regression\"}, \n",
+    "                                               description = 'sample service for Automl Regression')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.webservice import Webservice\n",
+    "\n",
+    "aci_service_name = 'automl-sample-hardware'\n",
+    "print(aci_service_name)\n",
+    "aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
+    "                                           image = image,\n",
+    "                                           name = aci_service_name,\n",
+    "                                           workspace = ws)\n",
+    "aci_service.wait_for_deployment(True)\n",
+    "print(aci_service.state)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Delete a Web Service\n",
+    "\n",
+    "Deletes the specified web service."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#aci_service.delete()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Get Logs from a Deployed Web Service\n",
+    "\n",
+    "Gets logs from a deployed web service."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#aci_service.get_logs()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test\n",
+    "\n",
+    "Now that the model is trained, split the data in the same way the data was split for training (The difference here is the data is being split locally) and then run the test data through the trained model to get the predicted values."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_test = X_test.to_pandas_dataframe()\n",
+    "y_test = y_test.to_pandas_dataframe()\n",
+    "y_test = np.array(y_test)\n",
+    "y_test = y_test[:,0]\n",
+    "X_train = X_train.to_pandas_dataframe()\n",
+    "y_train = y_train.to_pandas_dataframe()\n",
+    "y_train = np.array(y_train)\n",
+    "y_train = y_train[:,0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "##### Predict on training and test set, and calculate residual values."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred_train = fitted_model.predict(X_train)\n",
+    "y_residual_train = y_train - y_pred_train\n",
+    "\n",
+    "y_pred_test = fitted_model.predict(X_test)\n",
+    "y_residual_test = y_test - y_pred_test"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Calculate metrics for the prediction\n",
+    "\n",
+    "Now visualize the data on a scatter plot to show what our truth (actual) values are compared to the predicted values \n",
+    "from the trained model that was returned."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib inline\n",
+    "from sklearn.metrics import mean_squared_error, r2_score\n",
+    "\n",
+    "# Set up a multi-plot chart.\n",
+    "f, (a0, a1) = plt.subplots(1, 2, gridspec_kw = {'width_ratios':[1, 1], 'wspace':0, 'hspace': 0})\n",
+    "f.suptitle('Regression Residual Values', fontsize = 18)\n",
+    "f.set_figheight(6)\n",
+    "f.set_figwidth(16)\n",
+    "\n",
+    "# Plot residual values of training set.\n",
+    "a0.axis([0, 360, -200, 200])\n",
+    "a0.plot(y_residual_train, 'bo', alpha = 0.5)\n",
+    "a0.plot([-10,360],[0,0], 'r-', lw = 3)\n",
+    "a0.text(16,170,'RMSE = {0:.2f}'.format(np.sqrt(mean_squared_error(y_train, y_pred_train))), fontsize = 12)\n",
+    "a0.text(16,140,'R2 score = {0:.2f}'.format(r2_score(y_train, y_pred_train)),fontsize = 12)\n",
+    "a0.set_xlabel('Training samples', fontsize = 12)\n",
+    "a0.set_ylabel('Residual Values', fontsize = 12)\n",
+    "\n",
+    "# Plot residual values of test set.\n",
+    "a1.axis([0, 90, -200, 200])\n",
+    "a1.plot(y_residual_test, 'bo', alpha = 0.5)\n",
+    "a1.plot([-10,360],[0,0], 'r-', lw = 3)\n",
+    "a1.text(5,170,'RMSE = {0:.2f}'.format(np.sqrt(mean_squared_error(y_test, y_pred_test))), fontsize = 12)\n",
+    "a1.text(5,140,'R2 score = {0:.2f}'.format(r2_score(y_test, y_pred_test)),fontsize = 12)\n",
+    "a1.set_xlabel('Test samples', fontsize = 12)\n",
+    "a1.set_yticklabels([])\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib notebook\n",
+    "test_pred = plt.scatter(y_test, y_pred_test, color='')\n",
+    "test_test = plt.scatter(y_test, y_test, color='g')\n",
+    "plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Acknowledgements\n",
+    "This Predicting Hardware Performance Dataset is made available under the CC0 1.0 Universal (CC0 1.0) Public Domain Dedication License: https://creativecommons.org/publicdomain/zero/1.0/. Any rights in individual contents of the database are licensed under the CC0 1.0 Universal (CC0 1.0) Public Domain Dedication License: https://creativecommons.org/publicdomain/zero/1.0/ . The dataset itself can be found here: https://www.kaggle.com/faizunnabi/comp-hardware-performance and https://archive.ics.uci.edu/ml/datasets/Computer+Hardware\n",
+    "\n",
+    "_**Citation Found Here**_\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "v-rasav"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3.6",
+   "language": "python",
+   "name": "python36"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

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

@@ -119,7 +119,9 @@
       "metadata": {},
       "source": [
         "### Create or Attach existing AmlCompute\n",
-        "You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) for your AutoML run. In this tutorial, you create an AmlCompute as your training compute resource.\n",
+        "You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) for your AutoML run. In this tutorial, you create `AmlCompute` as your training compute resource.\n",
+        "\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."
       ]
@@ -134,12 +136,10 @@
         "from azureml.core.compute import ComputeTarget\n",
         "\n",
         "# Choose a name for your cluster.\n",
-        "amlcompute_cluster_name = \"cpucluster\"\n",
+        "amlcompute_cluster_name = \"cpu-cluster\"\n",
         "\n",
         "found = False\n",
-        "\n",
         "# Check if this compute target already exists in the workspace.\n",
-        "\n",
         "cts = ws.compute_targets\n",
         "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
         "    found = True\n",

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

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

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

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

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

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

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

@@ -0,0 +1,21 @@
+-- This shows using the AutoMLTrain stored procedure to create a forecasting model for the nyc_energy dataset.
+
+INSERT INTO dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)
+EXEC dbo.AutoMLTrain @input_query='
+SELECT CAST(timeStamp as NVARCHAR(30)) as timeStamp,
+       demand,
+	   precip,
+	   temp,
+	   CASE WHEN timeStamp < ''2017-01-01'' THEN 0 ELSE 1 END AS is_validate_column
+FROM nyc_energy
+WHERE demand IS NOT NULL AND precip IS NOT NULL AND temp IS NOT NULL
+and timeStamp < ''2017-02-01''',
+@label_column='demand',
+@task='forecasting',
+@iterations=10,
+@iteration_timeout_minutes=5,
+@time_column_name='timeStamp',
+@is_validate_column='is_validate_column',
+@experiment_name='automl-sql-forecast',
+@primary_metric='normalized_root_mean_squared_error'
+

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

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

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

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

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

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

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

@@ -0,0 +1,234 @@
+-- This stored procedure uses automated machine learning to train several models
+-- and returns the best model.
+--
+-- The result set has several columns:
+--   best_run - iteration ID for the best model
+--   experiment_name - experiment name pass in with the @experiment_name parameter
+--   fitted_model - best model found
+--   log_file_text - AutoML debug_log contents
+--   workspace - name of the Azure ML workspace where run history is stored
+--
+-- An example call for a classification problem is:
+--    insert into dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)
+--    exec dbo.AutoMLTrain @input_query='
+--    SELECT top 100000 
+--          CAST([pickup_datetime] AS NVARCHAR(30)) AS pickup_datetime
+--          ,CAST([dropoff_datetime] AS NVARCHAR(30)) AS dropoff_datetime
+--          ,[passenger_count]
+--          ,[trip_time_in_secs]
+--          ,[trip_distance]
+--          ,[payment_type]
+--          ,[tip_class]
+--      FROM [dbo].[nyctaxi_sample] order by [hack_license] ',
+--      @label_column = 'tip_class',
+--      @iterations=10
+-- 
+-- An example call for forecasting is:
+--      insert into dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)
+--      exec dbo.AutoMLTrain @input_query='
+--      select cast(timeStamp as nvarchar(30)) as timeStamp,
+--             demand,
+--      	   precip,
+--      	   temp,
+--             case when timeStamp < ''2017-01-01'' then 0 else 1 end as is_validate_column
+--      from nyc_energy
+--      where demand is not null and precip is not null and temp is not null
+--      and timeStamp < ''2017-02-01''',
+--      @label_column='demand',
+--      @task='forecasting',
+--      @iterations=10,
+--      @iteration_timeout_minutes=5,
+--      @time_column_name='timeStamp',
+--      @is_validate_column='is_validate_column',
+--      @experiment_name='automl-sql-forecast',
+--      @primary_metric='normalized_root_mean_squared_error'
+
+SET ANSI_NULLS ON
+GO
+SET QUOTED_IDENTIFIER ON
+GO
+CREATE OR ALTER PROCEDURE [dbo].[AutoMLTrain]
+ (
+    @input_query NVARCHAR(MAX),                      -- The SQL Query that will return the data to train and validate the model.
+    @label_column NVARCHAR(255)='Label',             -- The name of the column in the result of @input_query that is the label.
+    @primary_metric NVARCHAR(40)='AUC_weighted',     -- The metric to optimize.
+    @iterations INT=100,                             -- The maximum number of pipelines to train.
+    @task NVARCHAR(40)='classification',             -- The type of task.  Can be classification, regression or forecasting.
+    @experiment_name NVARCHAR(32)='automl-sql-test', -- This can be used to find the experiment in the Azure Portal.
+    @iteration_timeout_minutes INT = 15,             -- The maximum time in minutes for training a single pipeline. 
+    @experiment_timeout_minutes INT = 60,            -- The maximum time in minutes for training all pipelines.
+    @n_cross_validations INT = 3,                    -- The number of cross validations.
+    @blacklist_models NVARCHAR(MAX) = '',            -- A comma separated list of algos that will not be used.
+                                                     -- The list of possible models can be found at:
+                                                     -- https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#configure-your-experiment-settings
+    @whitelist_models NVARCHAR(MAX) = '',            -- A comma separated list of algos that can be used.
+                                                     -- The list of possible models can be found at:
+                                                     -- https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#configure-your-experiment-settings
+    @experiment_exit_score FLOAT = 0,                -- Stop the experiment if this score is acheived.
+    @sample_weight_column NVARCHAR(255)='',          -- The name of the column in the result of  @input_query that gives a sample weight.
+    @is_validate_column NVARCHAR(255)='',            -- The name of the column in the result of  @input_query that indicates if the row is for training or validation.
+	                                                 -- In the values of the column, 0 means for training and 1 means for validation.
+    @time_column_name  NVARCHAR(255)='',             -- The name of the timestamp column for forecasting.
+	@connection_name NVARCHAR(255)='default'         -- The AML connection to use.
+ ) AS
+BEGIN
+
+    DECLARE @tenantid NVARCHAR(255)
+    DECLARE @appid NVARCHAR(255)
+    DECLARE @password NVARCHAR(255)
+    DECLARE @config_file NVARCHAR(255)
+
+	SELECT @tenantid=TenantId, @appid=AppId, @password=Password, @config_file=ConfigFile
+	FROM aml_connection
+	WHERE ConnectionName = @connection_name;
+
+	EXEC sp_execute_external_script @language = N'Python', @script = N'import pandas as pd
+import logging 
+import azureml.core 
+import pandas as pd
+import numpy as np
+from azureml.core.experiment import Experiment 
+from azureml.train.automl import AutoMLConfig 
+from sklearn import datasets 
+import pickle
+import codecs
+from azureml.core.authentication import ServicePrincipalAuthentication 
+from azureml.core.workspace import Workspace 
+
+if __name__.startswith("sqlindb"):
+    auth = ServicePrincipalAuthentication(tenantid, appid, password) 
+ 
+    ws = Workspace.from_config(path=config_file, auth=auth) 
+ 
+    project_folder = "./sample_projects/" + experiment_name
+ 
+    experiment = Experiment(ws, experiment_name) 
+
+    data_train = input_data
+    X_valid = None
+    y_valid = None
+    sample_weight_valid = None
+
+    if is_validate_column != "" and is_validate_column is not None:
+        data_train = input_data[input_data[is_validate_column] <= 0]
+        data_valid = input_data[input_data[is_validate_column] > 0]
+        data_train.pop(is_validate_column)
+        data_valid.pop(is_validate_column)
+        y_valid = data_valid.pop(label_column).values
+        if sample_weight_column != "" and sample_weight_column is not None:
+            sample_weight_valid = data_valid.pop(sample_weight_column).values
+        X_valid = data_valid
+        n_cross_validations = None
+
+    y_train = data_train.pop(label_column).values
+
+    sample_weight = None
+    if sample_weight_column != "" and sample_weight_column is not None:
+        sample_weight = data_train.pop(sample_weight_column).values
+
+    X_train = data_train
+
+    if experiment_timeout_minutes == 0:
+        experiment_timeout_minutes = None
+
+    if experiment_exit_score == 0:
+        experiment_exit_score = None
+
+    if blacklist_models == "":
+        blacklist_models = None
+
+    if blacklist_models is not None:
+        blacklist_models = blacklist_models.replace(" ", "").split(",")
+
+    if whitelist_models == "":
+        whitelist_models = None
+
+    if whitelist_models is not None:
+        whitelist_models = whitelist_models.replace(" ", "").split(",")
+
+    automl_settings = {}
+    preprocess = True
+    if time_column_name != "" and time_column_name is not None:
+        automl_settings = { "time_column_name": time_column_name }
+        preprocess = False
+
+    log_file_name = "automl_errors.log"
+	 
+    automl_config = AutoMLConfig(task = task, 
+                                 debug_log = log_file_name, 
+                                 primary_metric = primary_metric, 
+                                 iteration_timeout_minutes = iteration_timeout_minutes, 
+                                 experiment_timeout_minutes = experiment_timeout_minutes,
+                                 iterations = iterations, 
+                                 n_cross_validations = n_cross_validations, 
+                                 preprocess = preprocess,
+                                 verbosity = logging.INFO, 
+                                 enable_ensembling = False,
+                                 X = X_train,  
+                                 y = y_train, 
+                                 path = project_folder,
+                                 blacklist_models = blacklist_models,
+                                 whitelist_models = whitelist_models,
+                                 experiment_exit_score = experiment_exit_score,
+                                 sample_weight = sample_weight,
+                                 X_valid = X_valid,
+                                 y_valid = y_valid,
+                                 sample_weight_valid = sample_weight_valid,
+                                 **automl_settings) 
+ 
+    local_run = experiment.submit(automl_config, show_output = True) 
+
+    best_run, fitted_model = local_run.get_output()
+
+    pickled_model = codecs.encode(pickle.dumps(fitted_model), "base64").decode()
+
+    log_file_text = ""
+
+    try:
+        with open(log_file_name, "r") as log_file:
+            log_file_text = log_file.read()
+    except:
+        log_file_text = "Log file not found"
+
+    returned_model = pd.DataFrame({"best_run": [best_run.id], "experiment_name": [experiment_name], "fitted_model": [pickled_model], "log_file_text": [log_file_text], "workspace": [ws.name]}, dtype=np.dtype(np.str))
+'
+	, @input_data_1 = @input_query
+	, @input_data_1_name = N'input_data'
+	, @output_data_1_name = N'returned_model'
+	, @params = N'@label_column NVARCHAR(255), 
+	              @primary_metric NVARCHAR(40),
+				  @iterations INT, @task NVARCHAR(40),
+				  @experiment_name NVARCHAR(32),
+				  @iteration_timeout_minutes INT,
+				  @experiment_timeout_minutes INT,
+				  @n_cross_validations INT,
+				  @blacklist_models NVARCHAR(MAX),
+				  @whitelist_models NVARCHAR(MAX),
+				  @experiment_exit_score FLOAT,
+				  @sample_weight_column NVARCHAR(255),
+				  @is_validate_column NVARCHAR(255),
+				  @time_column_name  NVARCHAR(255),
+				  @tenantid NVARCHAR(255),
+				  @appid NVARCHAR(255),
+				  @password NVARCHAR(255),
+				  @config_file NVARCHAR(255)'
+	, @label_column = @label_column
+	, @primary_metric = @primary_metric
+	, @iterations = @iterations
+	, @task = @task
+	, @experiment_name = @experiment_name
+	, @iteration_timeout_minutes = @iteration_timeout_minutes
+	, @experiment_timeout_minutes = @experiment_timeout_minutes
+	, @n_cross_validations = @n_cross_validations
+	, @blacklist_models = @blacklist_models
+	, @whitelist_models = @whitelist_models
+	, @experiment_exit_score = @experiment_exit_score
+	, @sample_weight_column = @sample_weight_column
+	, @is_validate_column = @is_validate_column
+	, @time_column_name = @time_column_name
+	, @tenantid = @tenantid
+	, @appid = @appid
+	, @password = @password
+	, @config_file = @config_file
+WITH RESULT SETS ((best_run NVARCHAR(250), experiment_name NVARCHAR(100), fitted_model VARCHAR(MAX), log_file_text NVARCHAR(MAX), workspace NVARCHAR(100)))
+END

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

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

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

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

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

@@ -0,0 +1,562 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Set up Azure ML Automated Machine Learning on SQL Server 2019 CTP 2.4 big data cluster\r\n",
+    "\r\n",
+    "\\# Prerequisites:  \r\n",
+    "\\# - An Azure subscription and resource group  \r\n",
+    "\\# - An Azure Machine Learning workspace  \r\n",
+    "\\# - A SQL Server 2019 CTP 2.4 big data cluster with Internet access and a database named 'automl'  \r\n",
+    "\\# - Azure CLI  \r\n",
+    "\\# - kubectl command  \r\n",
+    "\\# - The https://github.com/Azure/MachineLearningNotebooks repository downloaded (cloned) to your local machine\r\n",
+    "\r\n",
+    "\\# In the 'automl' database, create a table named 'dbo.nyc_energy' as follows:  \r\n",
+    "\\# - In SQL Server Management Studio, right-click the 'automl' database, select Tasks, then Import Flat File.  \r\n",
+    "\\# - Select the file AzureMlCli\\notebooks\\how-to-use-azureml\\automated-machine-learning\\forecasting-energy-demand\\nyc_energy.csv.  \r\n",
+    "\\# - Using the \"Modify Columns\" page, allow nulls for all columns. \r\n",
+    "\r\n",
+    "\\# Create an Azure Machine Learning Workspace using the instructions at https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-workspace \r\n",
+    "\r\n",
+    "\\# Create an Azure service principal.  You can do this with the following commands: \r\n",
+    "\r\n",
+    "az login  \r\n",
+    "az account set --subscription *subscriptionid*  \r\n",
+    "\r\n",
+    "\\# The following command prints out the **appId** and **tenant**,  \r\n",
+    "\\# which you insert into the indicated cell later in this notebook  \r\n",
+    "\\# to allow AutoML to authenticate with Azure:  \r\n",
+    "\r\n",
+    "az ad sp create-for-rbac --name *principlename* --password *password*\r\n",
+    "\r\n",
+    "\\# Log into the master instance of SQL Server 2019 CTP 2.4:  \r\n",
+    "kubectl exec -it mssql-master-pool-0 -n *clustername* -c mssql-server -- /bin/bash\r\n",
+    "\r\n",
+    "mkdir /tmp/aml\r\n",
+    "\r\n",
+    "cd /tmp/aml\r\n",
+    "\r\n",
+    "\\# **Modify** the following with your subscription_id, resource_group, and workspace_name:  \r\n",
+    "cat > config.json << EOF  \r\n",
+    "{  \r\n",
+    "    \"subscription_id\": \"123456ab-78cd-0123-45ef-abcd12345678\",  \r\n",
+    "    \"resource_group\": \"myrg1\",  \r\n",
+    "    \"workspace_name\": \"myws1\"  \r\n",
+    "}  \r\n",
+    "EOF\r\n",
+    "\r\n",
+    "\\# The directory referenced below is appropriate for the master instance of SQL Server 2019 CTP 2.4.\r\n",
+    "\r\n",
+    "cd /opt/mssql/mlservices/runtime/python/bin\r\n",
+    "\r\n",
+    "./python -m pip install azureml-sdk[automl]\r\n",
+    "\r\n",
+    "./python -m pip install --upgrade numpy \r\n",
+    "\r\n",
+    "./python -m pip install --upgrade sklearn\r\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/sql-server/setup/auto-ml-sql-setup.png)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "-- Enable external scripts to allow invoking Python\r\n",
+    "sp_configure 'external scripts enabled',1 \r\n",
+    "reconfigure with override \r\n",
+    "GO\r\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "-- Use database 'automl'\r\n",
+    "USE [automl]\r\n",
+    "GO"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "-- This is a table to hold the Azure ML connection information.\r\n",
+    "SET ANSI_NULLS ON\r\n",
+    "GO\r\n",
+    "\r\n",
+    "SET QUOTED_IDENTIFIER ON\r\n",
+    "GO\r\n",
+    "\r\n",
+    "CREATE TABLE [dbo].[aml_connection](\r\n",
+    "    [Id] [int] IDENTITY(1,1) NOT NULL PRIMARY KEY,\r\n",
+    "\t[ConnectionName] [nvarchar](255) NULL,\r\n",
+    "\t[TenantId] [nvarchar](255) NULL,\r\n",
+    "\t[AppId] [nvarchar](255) NULL,\r\n",
+    "\t[Password] [nvarchar](255) NULL,\r\n",
+    "\t[ConfigFile] [nvarchar](255) NULL\r\n",
+    ") ON [PRIMARY]\r\n",
+    "GO"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Copy the values from create-for-rbac above into the cell below"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "-- Use the following values:\r\n",
+    "-- Leave the name as 'Default'\r\n",
+    "-- Insert <tenant> returned by create-for-rbac above\r\n",
+    "-- Insert <AppId> returned by create-for-rbac above\r\n",
+    "-- Insert <password> used in create-for-rbac above\r\n",
+    "-- Leave <path> as '/tmp/aml/config.json'\r\n",
+    "INSERT INTO [dbo].[aml_connection]  \r\n",
+    "VALUES (\r\n",
+    "    N'Default', -- Name\r\n",
+    "    N'11111111-2222-3333-4444-555555555555', -- Tenant\r\n",
+    "    N'aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee', -- AppId\r\n",
+    "    N'insertpasswordhere', -- Password\r\n",
+    "    N'/tmp/aml/config.json' -- Path\r\n",
+    "    );\r\n",
+    "GO"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "-- This is a table to hold the results from the AutoMLTrain procedure.\r\n",
+    "SET ANSI_NULLS ON\r\n",
+    "GO\r\n",
+    "\r\n",
+    "SET QUOTED_IDENTIFIER ON\r\n",
+    "GO\r\n",
+    "\r\n",
+    "CREATE TABLE [dbo].[aml_model](\r\n",
+    "    [Id] [int] IDENTITY(1,1) NOT NULL PRIMARY KEY,\r\n",
+    "    [Model] [varchar](max) NOT NULL,        -- The model, which can be passed to AutoMLPredict for testing or prediction.\r\n",
+    "    [RunId] [nvarchar](250) NULL,           -- The RunId, which can be used to view the model in the Azure Portal.\r\n",
+    "    [CreatedDate] [datetime] NULL,\r\n",
+    "    [ExperimentName] [nvarchar](100) NULL,  -- Azure ML Experiment Name\r\n",
+    "    [WorkspaceName] [nvarchar](100) NULL,   -- Azure ML Workspace Name\r\n",
+    "\t[LogFileText] [nvarchar](max) NULL\r\n",
+    ") \r\n",
+    "GO\r\n",
+    "\r\n",
+    "ALTER TABLE [dbo].[aml_model] ADD  DEFAULT (getutcdate()) FOR [CreatedDate]\r\n",
+    "GO\r\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "-- This stored procedure uses automated machine learning to train several models\r\n",
+    "-- and return the best model.\r\n",
+    "--\r\n",
+    "-- The result set has several columns:\r\n",
+    "--   best_run - ID of the best model found\r\n",
+    "--   experiment_name - training run name\r\n",
+    "--   fitted_model - best model found\r\n",
+    "--   log_file_text - console output\r\n",
+    "--   workspace - name of the Azure ML workspace where run history is stored\r\n",
+    "--\r\n",
+    "-- An example call for a classification problem is:\r\n",
+    "--    insert into dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)\r\n",
+    "--    exec dbo.AutoMLTrain @input_query='\r\n",
+    "--    SELECT top 100000 \r\n",
+    "--          CAST([pickup_datetime] AS NVARCHAR(30)) AS pickup_datetime\r\n",
+    "--          ,CAST([dropoff_datetime] AS NVARCHAR(30)) AS dropoff_datetime\r\n",
+    "--          ,[passenger_count]\r\n",
+    "--          ,[trip_time_in_secs]\r\n",
+    "--          ,[trip_distance]\r\n",
+    "--          ,[payment_type]\r\n",
+    "--          ,[tip_class]\r\n",
+    "--      FROM [dbo].[nyctaxi_sample] order by [hack_license] ',\r\n",
+    "--      @label_column = 'tip_class',\r\n",
+    "--      @iterations=10\r\n",
+    "-- \r\n",
+    "-- An example call for forecasting is:\r\n",
+    "--      insert into dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)\r\n",
+    "--      exec dbo.AutoMLTrain @input_query='\r\n",
+    "--      select cast(timeStamp as nvarchar(30)) as timeStamp,\r\n",
+    "--             demand,\r\n",
+    "--      \t   precip,\r\n",
+    "--      \t   temp,\r\n",
+    "--             case when timeStamp < ''2017-01-01'' then 0 else 1 end as is_validate_column\r\n",
+    "--      from nyc_energy\r\n",
+    "--      where demand is not null and precip is not null and temp is not null\r\n",
+    "--      and timeStamp < ''2017-02-01''',\r\n",
+    "--      @label_column='demand',\r\n",
+    "--      @task='forecasting',\r\n",
+    "--      @iterations=10,\r\n",
+    "--      @iteration_timeout_minutes=5,\r\n",
+    "--      @time_column_name='timeStamp',\r\n",
+    "--      @is_validate_column='is_validate_column',\r\n",
+    "--      @experiment_name='automl-sql-forecast',\r\n",
+    "--      @primary_metric='normalized_root_mean_squared_error'\r\n",
+    "\r\n",
+    "SET ANSI_NULLS ON\r\n",
+    "GO\r\n",
+    "SET QUOTED_IDENTIFIER ON\r\n",
+    "GO\r\n",
+    "CREATE OR ALTER PROCEDURE [dbo].[AutoMLTrain]\r\n",
+    " (\r\n",
+    "    @input_query NVARCHAR(MAX),                      -- The SQL Query that will return the data to train and validate the model.\r\n",
+    "    @label_column NVARCHAR(255)='Label',             -- The name of the column in the result of @input_query that is the label.\r\n",
+    "    @primary_metric NVARCHAR(40)='AUC_weighted',     -- The metric to optimize.\r\n",
+    "    @iterations INT=100,                             -- The maximum number of pipelines to train.\r\n",
+    "    @task NVARCHAR(40)='classification',             -- The type of task.  Can be classification, regression or forecasting.\r\n",
+    "    @experiment_name NVARCHAR(32)='automl-sql-test', -- This can be used to find the experiment in the Azure Portal.\r\n",
+    "    @iteration_timeout_minutes INT = 15,             -- The maximum time in minutes for training a single pipeline. \r\n",
+    "    @experiment_timeout_minutes INT = 60,            -- The maximum time in minutes for training all pipelines.\r\n",
+    "    @n_cross_validations INT = 3,                    -- The number of cross validations.\r\n",
+    "    @blacklist_models NVARCHAR(MAX) = '',            -- A comma separated list of algos that will not be used.\r\n",
+    "                                                     -- The list of possible models can be found at:\r\n",
+    "                                                     -- https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#configure-your-experiment-settings\r\n",
+    "    @whitelist_models NVARCHAR(MAX) = '',            -- A comma separated list of algos that can be used.\r\n",
+    "                                                     -- The list of possible models can be found at:\r\n",
+    "                                                     -- https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#configure-your-experiment-settings\r\n",
+    "    @experiment_exit_score FLOAT = 0,                -- Stop the experiment if this score is acheived.\r\n",
+    "    @sample_weight_column NVARCHAR(255)='',          -- The name of the column in the result of  @input_query that gives a sample weight.\r\n",
+    "    @is_validate_column NVARCHAR(255)='',            -- The name of the column in the result of  @input_query that indicates if the row is for training or validation.\r\n",
+    "\t                                                 -- In the values of the column, 0 means for training and 1 means for validation.\r\n",
+    "    @time_column_name  NVARCHAR(255)='',             -- The name of the timestamp column for forecasting.\r\n",
+    "\t@connection_name NVARCHAR(255)='default'         -- The AML connection to use.\r\n",
+    " ) AS\r\n",
+    "BEGIN\r\n",
+    "\r\n",
+    "    DECLARE @tenantid NVARCHAR(255)\r\n",
+    "    DECLARE @appid NVARCHAR(255)\r\n",
+    "    DECLARE @password NVARCHAR(255)\r\n",
+    "    DECLARE @config_file NVARCHAR(255)\r\n",
+    "\r\n",
+    "\tSELECT @tenantid=TenantId, @appid=AppId, @password=Password, @config_file=ConfigFile\r\n",
+    "\tFROM aml_connection\r\n",
+    "\tWHERE ConnectionName = @connection_name;\r\n",
+    "\r\n",
+    "\tEXEC sp_execute_external_script @language = N'Python', @script = N'import pandas as pd\r\n",
+    "import logging \r\n",
+    "import azureml.core \r\n",
+    "import pandas as pd\r\n",
+    "import numpy as np\r\n",
+    "from azureml.core.experiment import Experiment \r\n",
+    "from azureml.train.automl import AutoMLConfig \r\n",
+    "from sklearn import datasets \r\n",
+    "import pickle\r\n",
+    "import codecs\r\n",
+    "from azureml.core.authentication import ServicePrincipalAuthentication \r\n",
+    "from azureml.core.workspace import Workspace \r\n",
+    "\r\n",
+    "if __name__.startswith(\"sqlindb\"):\r\n",
+    "    auth = ServicePrincipalAuthentication(tenantid, appid, password) \r\n",
+    " \r\n",
+    "    ws = Workspace.from_config(path=config_file, auth=auth) \r\n",
+    " \r\n",
+    "    project_folder = \"./sample_projects/\" + experiment_name\r\n",
+    " \r\n",
+    "    experiment = Experiment(ws, experiment_name) \r\n",
+    "\r\n",
+    "    data_train = input_data\r\n",
+    "    X_valid = None\r\n",
+    "    y_valid = None\r\n",
+    "    sample_weight_valid = None\r\n",
+    "\r\n",
+    "    if is_validate_column != \"\" and is_validate_column is not None:\r\n",
+    "        data_train = input_data[input_data[is_validate_column] <= 0]\r\n",
+    "        data_valid = input_data[input_data[is_validate_column] > 0]\r\n",
+    "        data_train.pop(is_validate_column)\r\n",
+    "        data_valid.pop(is_validate_column)\r\n",
+    "        y_valid = data_valid.pop(label_column).values\r\n",
+    "        if sample_weight_column != \"\" and sample_weight_column is not None:\r\n",
+    "            sample_weight_valid = data_valid.pop(sample_weight_column).values\r\n",
+    "        X_valid = data_valid\r\n",
+    "        n_cross_validations = None\r\n",
+    "\r\n",
+    "    y_train = data_train.pop(label_column).values\r\n",
+    "\r\n",
+    "    sample_weight = None\r\n",
+    "    if sample_weight_column != \"\" and sample_weight_column is not None:\r\n",
+    "        sample_weight = data_train.pop(sample_weight_column).values\r\n",
+    "\r\n",
+    "    X_train = data_train\r\n",
+    "\r\n",
+    "    if experiment_timeout_minutes == 0:\r\n",
+    "        experiment_timeout_minutes = None\r\n",
+    "\r\n",
+    "    if experiment_exit_score == 0:\r\n",
+    "        experiment_exit_score = None\r\n",
+    "\r\n",
+    "    if blacklist_models == \"\":\r\n",
+    "        blacklist_models = None\r\n",
+    "\r\n",
+    "    if blacklist_models is not None:\r\n",
+    "        blacklist_models = blacklist_models.replace(\" \", \"\").split(\",\")\r\n",
+    "\r\n",
+    "    if whitelist_models == \"\":\r\n",
+    "        whitelist_models = None\r\n",
+    "\r\n",
+    "    if whitelist_models is not None:\r\n",
+    "        whitelist_models = whitelist_models.replace(\" \", \"\").split(\",\")\r\n",
+    "\r\n",
+    "    automl_settings = {}\r\n",
+    "    preprocess = True\r\n",
+    "    if time_column_name != \"\" and time_column_name is not None:\r\n",
+    "        automl_settings = { \"time_column_name\": time_column_name }\r\n",
+    "        preprocess = False\r\n",
+    "\r\n",
+    "    log_file_name = \"automl_errors.log\"\r\n",
+    "\t \r\n",
+    "    automl_config = AutoMLConfig(task = task, \r\n",
+    "                                 debug_log = log_file_name, \r\n",
+    "                                 primary_metric = primary_metric, \r\n",
+    "                                 iteration_timeout_minutes = iteration_timeout_minutes, \r\n",
+    "                                 experiment_timeout_minutes = experiment_timeout_minutes,\r\n",
+    "                                 iterations = iterations, \r\n",
+    "                                 n_cross_validations = n_cross_validations, \r\n",
+    "                                 preprocess = preprocess,\r\n",
+    "                                 verbosity = logging.INFO, \r\n",
+    "                                 enable_ensembling = False,\r\n",
+    "                                 X = X_train,  \r\n",
+    "                                 y = y_train, \r\n",
+    "                                 path = project_folder,\r\n",
+    "                                 blacklist_models = blacklist_models,\r\n",
+    "                                 whitelist_models = whitelist_models,\r\n",
+    "                                 experiment_exit_score = experiment_exit_score,\r\n",
+    "                                 sample_weight = sample_weight,\r\n",
+    "                                 X_valid = X_valid,\r\n",
+    "                                 y_valid = y_valid,\r\n",
+    "                                 sample_weight_valid = sample_weight_valid,\r\n",
+    "                                 **automl_settings) \r\n",
+    " \r\n",
+    "    local_run = experiment.submit(automl_config, show_output = True) \r\n",
+    "\r\n",
+    "    best_run, fitted_model = local_run.get_output()\r\n",
+    "\r\n",
+    "    pickled_model = codecs.encode(pickle.dumps(fitted_model), \"base64\").decode()\r\n",
+    "\r\n",
+    "    log_file_text = \"\"\r\n",
+    "\r\n",
+    "    try:\r\n",
+    "        with open(log_file_name, \"r\") as log_file:\r\n",
+    "            log_file_text = log_file.read()\r\n",
+    "    except:\r\n",
+    "        log_file_text = \"Log file not found\"\r\n",
+    "\r\n",
+    "    returned_model = pd.DataFrame({\"best_run\": [best_run.id], \"experiment_name\": [experiment_name], \"fitted_model\": [pickled_model], \"log_file_text\": [log_file_text], \"workspace\": [ws.name]}, dtype=np.dtype(np.str))\r\n",
+    "'\r\n",
+    "\t, @input_data_1 = @input_query\r\n",
+    "\t, @input_data_1_name = N'input_data'\r\n",
+    "\t, @output_data_1_name = N'returned_model'\r\n",
+    "\t, @params = N'@label_column NVARCHAR(255), \r\n",
+    "\t              @primary_metric NVARCHAR(40),\r\n",
+    "\t\t\t\t  @iterations INT, @task NVARCHAR(40),\r\n",
+    "\t\t\t\t  @experiment_name NVARCHAR(32),\r\n",
+    "\t\t\t\t  @iteration_timeout_minutes INT,\r\n",
+    "\t\t\t\t  @experiment_timeout_minutes INT,\r\n",
+    "\t\t\t\t  @n_cross_validations INT,\r\n",
+    "\t\t\t\t  @blacklist_models NVARCHAR(MAX),\r\n",
+    "\t\t\t\t  @whitelist_models NVARCHAR(MAX),\r\n",
+    "\t\t\t\t  @experiment_exit_score FLOAT,\r\n",
+    "\t\t\t\t  @sample_weight_column NVARCHAR(255),\r\n",
+    "\t\t\t\t  @is_validate_column NVARCHAR(255),\r\n",
+    "\t\t\t\t  @time_column_name  NVARCHAR(255),\r\n",
+    "\t\t\t\t  @tenantid NVARCHAR(255),\r\n",
+    "\t\t\t\t  @appid NVARCHAR(255),\r\n",
+    "\t\t\t\t  @password NVARCHAR(255),\r\n",
+    "\t\t\t\t  @config_file NVARCHAR(255)'\r\n",
+    "\t, @label_column = @label_column\r\n",
+    "\t, @primary_metric = @primary_metric\r\n",
+    "\t, @iterations = @iterations\r\n",
+    "\t, @task = @task\r\n",
+    "\t, @experiment_name = @experiment_name\r\n",
+    "\t, @iteration_timeout_minutes = @iteration_timeout_minutes\r\n",
+    "\t, @experiment_timeout_minutes = @experiment_timeout_minutes\r\n",
+    "\t, @n_cross_validations = @n_cross_validations\r\n",
+    "\t, @blacklist_models = @blacklist_models\r\n",
+    "\t, @whitelist_models = @whitelist_models\r\n",
+    "\t, @experiment_exit_score = @experiment_exit_score\r\n",
+    "\t, @sample_weight_column = @sample_weight_column\r\n",
+    "\t, @is_validate_column = @is_validate_column\r\n",
+    "\t, @time_column_name = @time_column_name\r\n",
+    "\t, @tenantid = @tenantid\r\n",
+    "\t, @appid = @appid\r\n",
+    "\t, @password = @password\r\n",
+    "\t, @config_file = @config_file\r\n",
+    "WITH RESULT SETS ((best_run NVARCHAR(250), experiment_name NVARCHAR(100), fitted_model VARCHAR(MAX), log_file_text NVARCHAR(MAX), workspace NVARCHAR(100)))\r\n",
+    "END"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "-- This procedure returns a list of metrics for each iteration of a training run.\r\n",
+    "SET ANSI_NULLS ON\r\n",
+    "GO\r\n",
+    "SET QUOTED_IDENTIFIER ON\r\n",
+    "GO\r\n",
+    "CREATE OR ALTER PROCEDURE [dbo].[AutoMLGetMetrics]\r\n",
+    " (\r\n",
+    "\t@run_id NVARCHAR(250),                           -- The RunId\r\n",
+    "    @experiment_name NVARCHAR(32)='automl-sql-test', -- This can be used to find the experiment in the Azure Portal.\r\n",
+    "    @connection_name NVARCHAR(255)='default'         -- The AML connection to use.\r\n",
+    " ) AS\r\n",
+    "BEGIN\r\n",
+    "    DECLARE @tenantid NVARCHAR(255)\r\n",
+    "    DECLARE @appid NVARCHAR(255)\r\n",
+    "    DECLARE @password NVARCHAR(255)\r\n",
+    "    DECLARE @config_file NVARCHAR(255)\r\n",
+    "\r\n",
+    "\tSELECT @tenantid=TenantId, @appid=AppId, @password=Password, @config_file=ConfigFile\r\n",
+    "\tFROM aml_connection\r\n",
+    "\tWHERE ConnectionName = @connection_name;\r\n",
+    "\r\n",
+    "    EXEC sp_execute_external_script @language = N'Python', @script = N'import pandas as pd\r\n",
+    "import logging \r\n",
+    "import azureml.core \r\n",
+    "import numpy as np\r\n",
+    "from azureml.core.experiment import Experiment \r\n",
+    "from azureml.train.automl.run import AutoMLRun\r\n",
+    "from azureml.core.authentication import ServicePrincipalAuthentication \r\n",
+    "from azureml.core.workspace import Workspace \r\n",
+    "\r\n",
+    "auth = ServicePrincipalAuthentication(tenantid, appid, password) \r\n",
+    " \r\n",
+    "ws = Workspace.from_config(path=config_file, auth=auth) \r\n",
+    " \r\n",
+    "experiment = Experiment(ws, experiment_name) \r\n",
+    "\r\n",
+    "ml_run = AutoMLRun(experiment = experiment, run_id = run_id)\r\n",
+    "\r\n",
+    "children = list(ml_run.get_children())\r\n",
+    "iterationlist = []\r\n",
+    "metricnamelist = []\r\n",
+    "metricvaluelist = []\r\n",
+    "\r\n",
+    "for run in children:\r\n",
+    "    properties = run.get_properties()\r\n",
+    "    if \"iteration\" in properties:\r\n",
+    "        iteration = int(properties[\"iteration\"])\r\n",
+    "        for metric_name, metric_value in run.get_metrics().items():\r\n",
+    "            if isinstance(metric_value, float):\r\n",
+    "                iterationlist.append(iteration)\r\n",
+    "                metricnamelist.append(metric_name)\r\n",
+    "                metricvaluelist.append(metric_value)\r\n",
+    "             \r\n",
+    "metrics = pd.DataFrame({\"iteration\": iterationlist, \"metric_name\": metricnamelist, \"metric_value\": metricvaluelist})\r\n",
+    "'\r\n",
+    "    , @output_data_1_name = N'metrics'\r\n",
+    "\t, @params = N'@run_id NVARCHAR(250), \r\n",
+    "\t\t\t\t  @experiment_name NVARCHAR(32),\r\n",
+    "  \t\t\t\t  @tenantid NVARCHAR(255),\r\n",
+    "\t\t\t\t  @appid NVARCHAR(255),\r\n",
+    "\t\t\t\t  @password NVARCHAR(255),\r\n",
+    "\t\t\t\t  @config_file NVARCHAR(255)'\r\n",
+    "    , @run_id = @run_id\r\n",
+    "\t, @experiment_name = @experiment_name\r\n",
+    "\t, @tenantid = @tenantid\r\n",
+    "\t, @appid = @appid\r\n",
+    "\t, @password = @password\r\n",
+    "\t, @config_file = @config_file\r\n",
+    "WITH RESULT SETS ((iteration INT, metric_name NVARCHAR(100), metric_value FLOAT))\r\n",
+    "END"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "-- This procedure predicts values based on a model returned by AutoMLTrain and a dataset.\r\n",
+    "-- It returns the dataset with a new column added, which is the predicted value.\r\n",
+    "SET ANSI_NULLS ON\r\n",
+    "GO\r\n",
+    "SET QUOTED_IDENTIFIER ON\r\n",
+    "GO\r\n",
+    "CREATE OR ALTER PROCEDURE [dbo].[AutoMLPredict]\r\n",
+    " (\r\n",
+    "   @input_query NVARCHAR(MAX),      -- A SQL query returning data to predict on.\r\n",
+    "   @model NVARCHAR(MAX),            -- A model returned from AutoMLTrain.\r\n",
+    "   @label_column  NVARCHAR(255)=''  -- Optional name of the column from input_query, which should be ignored when predicting\r\n",
+    " ) AS \r\n",
+    "BEGIN \r\n",
+    "  \r\n",
+    "    EXEC sp_execute_external_script @language = N'Python', @script = N'import pandas as pd \r\n",
+    "import azureml.core  \r\n",
+    "import numpy as np \r\n",
+    "from azureml.train.automl import AutoMLConfig  \r\n",
+    "import pickle \r\n",
+    "import codecs \r\n",
+    "  \r\n",
+    "model_obj = pickle.loads(codecs.decode(model.encode(), \"base64\")) \r\n",
+    "  \r\n",
+    "test_data = input_data.copy() \r\n",
+    "\r\n",
+    "if label_column != \"\" and label_column is not None:\r\n",
+    "    y_test = test_data.pop(label_column).values \r\n",
+    "X_test = test_data \r\n",
+    "  \r\n",
+    "predicted = model_obj.predict(X_test) \r\n",
+    "  \r\n",
+    "combined_output = input_data.assign(predicted=predicted)\r\n",
+    "  \r\n",
+    "' \r\n",
+    "    , @input_data_1 = @input_query \r\n",
+    "    , @input_data_1_name = N'input_data' \r\n",
+    "    , @output_data_1_name = N'combined_output' \r\n",
+    "    , @params = N'@model NVARCHAR(MAX), @label_column  NVARCHAR(255)' \r\n",
+    "    , @model = @model \r\n",
+    "\t, @label_column = @label_column\r\n",
+    "END"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "jeffshep"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "SQL",
+   "language": "sql",
+   "name": "SQL"
+  },
+  "language_info": {
+   "name": "sql",
+   "version": ""
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

how-to-use-azureml/data-drift/azure-ml-datadrift.ipynb

@@ -0,0 +1,709 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Track Data Drift between Training and Inference Data in Production \n",
+    "\n",
+    "With this notebook, you will learn how to enable the DataDrift service to automatically track and determine whether your inference data is drifting from the data your model was initially trained on. The DataDrift service provides metrics and visualizations to help stakeholders identify which specific features cause the concept drift to occur.\n",
+    "\n",
+    "Please email driftfeedback@microsoft.com with any issues. A member from the DataDrift team will respond shortly. \n",
+    "\n",
+    "The DataDrift Public Preview API can be found [here](https://docs.microsoft.com/en-us/python/api/azureml-contrib-datadrift/?view=azure-ml-py). "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/contrib/datadrift/azureml-datadrift.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Prerequisites and Setup"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Install the DataDrift package\n",
+    "\n",
+    "Install the azureml-contrib-datadrift, azureml-contrib-opendatasets and lightgbm packages before running this notebook.\n",
+    "```\n",
+    "pip install azureml-contrib-datadrift\n",
+    "pip install azureml-contrib-datasets\n",
+    "pip install lightgbm\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Import Dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "import os\n",
+    "import time\n",
+    "from datetime import datetime, timedelta\n",
+    "\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import requests\n",
+    "from azureml.contrib.datadrift import DataDriftDetector, AlertConfiguration\n",
+    "from azureml.contrib.opendatasets import NoaaIsdWeather\n",
+    "from azureml.core import Dataset, Workspace, Run\n",
+    "from azureml.core.compute import AksCompute, ComputeTarget\n",
+    "from azureml.core.conda_dependencies import CondaDependencies\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.image import ContainerImage\n",
+    "from azureml.core.model import Model\n",
+    "from azureml.core.webservice import Webservice, AksWebservice\n",
+    "from azureml.widgets import RunDetails\n",
+    "from sklearn.externals import joblib\n",
+    "from sklearn.model_selection import train_test_split\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Set up Configuraton and Create Azure ML Workspace\n",
+    "\n",
+    "If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, go through the [configuration notebook](../../configuration.ipynb) first if you haven't already to establish your connection to the AzureML Workspace."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Please type in your initials/alias. The prefix is prepended to the names of resources created by this notebook. \n",
+    "prefix = \"dd\"\n",
+    "\n",
+    "# NOTE: Please do not change the model_name, as it's required by the score.py file\n",
+    "model_name = \"driftmodel\"\n",
+    "image_name = \"{}driftimage\".format(prefix)\n",
+    "service_name = \"{}driftservice\".format(prefix)\n",
+    "\n",
+    "# optionally, set email address to receive an email alert for DataDrift\n",
+    "email_address = \"\""
+   ]
+  },
+  {
+   "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": [
+    "## Generate Train/Testing Data\n",
+    "\n",
+    "For this demo, we will use NOAA weather data from [Azure Open Datasets](https://azure.microsoft.com/services/open-datasets/). You may replace this step with your own dataset. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "usaf_list = ['725724', '722149', '723090', '722159', '723910', '720279',\n",
+    "             '725513', '725254', '726430', '720381', '723074', '726682',\n",
+    "             '725486', '727883', '723177', '722075', '723086', '724053',\n",
+    "             '725070', '722073', '726060', '725224', '725260', '724520',\n",
+    "             '720305', '724020', '726510', '725126', '722523', '703333',\n",
+    "             '722249', '722728', '725483', '722972', '724975', '742079',\n",
+    "             '727468', '722193', '725624', '722030', '726380', '720309',\n",
+    "             '722071', '720326', '725415', '724504', '725665', '725424',\n",
+    "             '725066']\n",
+    "\n",
+    "columns = ['usaf', 'wban', 'datetime', 'latitude', 'longitude', 'elevation', 'windAngle', 'windSpeed', 'temperature', 'stationName', 'p_k']\n",
+    "\n",
+    "def enrich_weather_noaa_data(noaa_df):\n",
+    "    hours_in_day = 23\n",
+    "    week_in_year = 52\n",
+    "    \n",
+    "\n",
+    "    noaa_df = noaa_df.assign(hour=noaa_df[\"datetime\"].dt.hour,\n",
+    "                          weekofyear=noaa_df[\"datetime\"].dt.week,\n",
+    "                          sine_weekofyear=noaa_df['datetime'].transform(lambda x: np.sin((2*np.pi*x.dt.week-1)/week_in_year)),\n",
+    "                          cosine_weekofyear=noaa_df['datetime'].transform(lambda x: np.cos((2*np.pi*x.dt.week-1)/week_in_year)),\n",
+    "                          sine_hourofday=noaa_df['datetime'].transform(lambda x: np.sin(2*np.pi*x.dt.hour/hours_in_day)),\n",
+    "                          cosine_hourofday=noaa_df['datetime'].transform(lambda x: np.cos(2*np.pi*x.dt.hour/hours_in_day))\n",
+    "                  )\n",
+    "    \n",
+    "    return noaa_df\n",
+    "\n",
+    "\n",
+    "def add_window_col(input_df):\n",
+    "    shift_interval = pd.Timedelta('-7 days') # your X days interval\n",
+    "    df_shifted = input_df.copy()\n",
+    "    df_shifted.loc[:,'datetime'] = df_shifted['datetime'] - shift_interval\n",
+    "    df_shifted.drop(list(input_df.columns.difference(['datetime', 'usaf', 'wban', 'sine_hourofday', 'temperature'])), axis=1, inplace=True)\n",
+    "\n",
+    "    # merge, keeping only observations where -1 lag is present\n",
+    "    df2 = pd.merge(input_df,\n",
+    "                   df_shifted,\n",
+    "                   on=['datetime', 'usaf', 'wban', 'sine_hourofday'],\n",
+    "                   how='inner',  # use 'left' to keep observations without lags\n",
+    "                   suffixes=['', '-7'])\n",
+    "    return df2\n",
+    "\n",
+    "def get_noaa_data(start_time, end_time, cols, station_list):\n",
+    "    isd = NoaaIsdWeather(start_time, end_time, cols=cols)\n",
+    "    # Read into Pandas data frame.\n",
+    "    noaa_df = isd.to_pandas_dataframe()\n",
+    "    noaa_df = noaa_df.rename(columns={\"stationName\": \"station_name\"})\n",
+    "    \n",
+    "    df_filtered = noaa_df[noaa_df[\"usaf\"].isin(station_list)]\n",
+    "    df_filtered.reset_index(drop=True)\n",
+    "    \n",
+    "    # Enrich with time features\n",
+    "    df_enriched = enrich_weather_noaa_data(df_filtered)\n",
+    "    \n",
+    "    return df_enriched\n",
+    "\n",
+    "def get_featurized_noaa_df(start_time, end_time, cols, station_list):\n",
+    "    df_1 = get_noaa_data(start_time - timedelta(days=7), start_time - timedelta(seconds=1), cols, station_list)\n",
+    "    df_2 = get_noaa_data(start_time, end_time, cols, station_list)\n",
+    "    noaa_df = pd.concat([df_1, df_2])\n",
+    "    \n",
+    "    print(\"Adding window feature\")\n",
+    "    df_window = add_window_col(noaa_df)\n",
+    "    \n",
+    "    cat_columns = df_window.dtypes == object\n",
+    "    cat_columns = cat_columns[cat_columns == True]\n",
+    "    \n",
+    "    print(\"Encoding categorical columns\")\n",
+    "    df_encoded = pd.get_dummies(df_window, columns=cat_columns.keys().tolist())\n",
+    "    \n",
+    "    print(\"Dropping unnecessary columns\")\n",
+    "    df_featurized = df_encoded.drop(['windAngle', 'windSpeed', 'datetime', 'elevation'], axis=1).dropna().drop_duplicates()\n",
+    "    \n",
+    "    return df_featurized"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Train model on Jan 1 - 14, 2009 data\n",
+    "df = get_featurized_noaa_df(datetime(2009, 1, 1), datetime(2009, 1, 14, 23, 59, 59), columns, usaf_list)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "label = \"temperature\"\n",
+    "x_df = df.drop(label, axis=1)\n",
+    "y_df = df[[label]]\n",
+    "x_train, x_test, y_train, y_test = train_test_split(df, y_df, test_size=0.2, random_state=223)\n",
+    "print(x_train.shape, x_test.shape, y_train.shape, y_test.shape)\n",
+    "\n",
+    "training_dir = 'outputs/training'\n",
+    "training_file = \"training.csv\"\n",
+    "\n",
+    "# Generate training dataframe to register as Training Dataset\n",
+    "os.makedirs(training_dir, exist_ok=True)\n",
+    "training_df = pd.merge(x_train.drop(label, axis=1), y_train, left_index=True, right_index=True)\n",
+    "training_df.to_csv(training_dir + \"/\" + training_file)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create/Register Training Dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dataset_name = \"dataset\"\n",
+    "name_suffix = datetime.utcnow().strftime(\"%Y-%m-%d-%H-%M-%S\")\n",
+    "snapshot_name = \"snapshot-{}\".format(name_suffix)\n",
+    "\n",
+    "dstore = ws.get_default_datastore()\n",
+    "dstore.upload(training_dir, \"data/training\", show_progress=True)\n",
+    "dpath = dstore.path(\"data/training/training.csv\")\n",
+    "trainingDataset = Dataset.auto_read_files(dpath, include_path=True)\n",
+    "trainingDataset = trainingDataset.register(workspace=ws, name=dataset_name, description=\"dset\", exist_ok=True)\n",
+    "\n",
+    "trainingDataSnapshot = trainingDataset.create_snapshot(snapshot_name=snapshot_name, compute_target=None, create_data_snapshot=True)\n",
+    "datasets = [(Dataset.Scenario.TRAINING, trainingDataSnapshot)]\n",
+    "print(\"dataset registration done.\\n\")\n",
+    "datasets"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Train and Save Model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import lightgbm as lgb\n",
+    "\n",
+    "train = lgb.Dataset(data=x_train, \n",
+    "                    label=y_train)\n",
+    "\n",
+    "test = lgb.Dataset(data=x_test, \n",
+    "                   label=y_test,\n",
+    "                   reference=train)\n",
+    "\n",
+    "params = {'learning_rate'    : 0.1,\n",
+    "          'boosting'         : 'gbdt',\n",
+    "          'metric'           : 'rmse',\n",
+    "          'feature_fraction' : 1,\n",
+    "          'bagging_fraction' : 1,\n",
+    "          'max_depth': 6,\n",
+    "          'num_leaves'       : 31,\n",
+    "          'objective'        : 'regression',\n",
+    "          'bagging_freq'     : 1,\n",
+    "          \"verbose\": -1,\n",
+    "          'min_data_per_leaf': 100}\n",
+    "\n",
+    "model = lgb.train(params, \n",
+    "                  num_boost_round=500,\n",
+    "                  train_set=train,\n",
+    "                  valid_sets=[train, test],\n",
+    "                  verbose_eval=50,\n",
+    "                  early_stopping_rounds=25)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model_file = 'outputs/{}.pkl'.format(model_name)\n",
+    "\n",
+    "os.makedirs('outputs', exist_ok=True)\n",
+    "joblib.dump(model, model_file)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Register Model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = Model.register(model_path=model_file,\n",
+    "                       model_name=model_name,\n",
+    "                       workspace=ws,\n",
+    "                       datasets=datasets)\n",
+    "\n",
+    "print(model_name, image_name, service_name, model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Deploy Model To AKS"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Prepare Environment"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn', 'joblib', 'lightgbm', 'pandas'],\n",
+    "                                 pip_packages=['azureml-monitoring', 'azureml-sdk[automl]'])\n",
+    "\n",
+    "with open(\"myenv.yml\",\"w\") as f:\n",
+    "    f.write(myenv.serialize_to_string())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create Image"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Image creation may take up to 15 minutes.\n",
+    "\n",
+    "image_name = image_name + str(model.version)\n",
+    "\n",
+    "if not image_name in ws.images:\n",
+    "    # Use the score.py defined in this directory as the execution script\n",
+    "    # NOTE: The Model Data Collector must be enabled in the execution script for DataDrift to run correctly\n",
+    "    image_config = ContainerImage.image_configuration(execution_script=\"score.py\",\n",
+    "                                                      runtime=\"python\",\n",
+    "                                                      conda_file=\"myenv.yml\",\n",
+    "                                                      description=\"Image with weather dataset model\")\n",
+    "    image = ContainerImage.create(name=image_name,\n",
+    "                                  models=[model],\n",
+    "                                  image_config=image_config,\n",
+    "                                  workspace=ws)\n",
+    "\n",
+    "    image.wait_for_creation(show_output=True)\n",
+    "else:\n",
+    "    image = ws.images[image_name]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create Compute Target"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "aks_name = 'dd-demo-e2e'\n",
+    "prov_config = AksCompute.provisioning_configuration()\n",
+    "\n",
+    "if not aks_name in ws.compute_targets:\n",
+    "    aks_target = ComputeTarget.create(workspace=ws,\n",
+    "                                      name=aks_name,\n",
+    "                                      provisioning_configuration=prov_config)\n",
+    "\n",
+    "    aks_target.wait_for_completion(show_output=True)\n",
+    "    print(aks_target.provisioning_state)\n",
+    "    print(aks_target.provisioning_errors)\n",
+    "else:\n",
+    "    aks_target=ws.compute_targets[aks_name]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Deploy Service"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "aks_service_name = service_name\n",
+    "\n",
+    "if not aks_service_name in ws.webservices:\n",
+    "    aks_config = AksWebservice.deploy_configuration(collect_model_data=True, enable_app_insights=True)\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)\n",
+    "else:\n",
+    "    aks_service = ws.webservices[aks_service_name]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Run DataDrift Analysis"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Send Scoring Data to Service"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Download Scoring Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Score Model on March 15, 2016 data\n",
+    "scoring_df = get_noaa_data(datetime(2016, 3, 15) - timedelta(days=7), datetime(2016, 3, 16),  columns, usaf_list)\n",
+    "# Add the window feature column\n",
+    "scoring_df = add_window_col(scoring_df)\n",
+    "\n",
+    "# Drop features not used by the model\n",
+    "print(\"Dropping unnecessary columns\")\n",
+    "scoring_df = scoring_df.drop(['windAngle', 'windSpeed', 'datetime', 'elevation'], axis=1).dropna()\n",
+    "scoring_df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# One Hot Encode the scoring dataset to match the training dataset schema\n",
+    "columns_dict = model.datasets[\"training\"][0].get_profile().columns\n",
+    "extra_cols = ('Path', 'Column1')\n",
+    "for k in extra_cols:\n",
+    "    columns_dict.pop(k, None)\n",
+    "training_columns = list(columns_dict.keys())\n",
+    "\n",
+    "categorical_columns = scoring_df.dtypes == object\n",
+    "categorical_columns = categorical_columns[categorical_columns == True]\n",
+    "\n",
+    "test_df = pd.get_dummies(scoring_df[categorical_columns.keys().tolist()])\n",
+    "encoded_df = scoring_df.join(test_df)\n",
+    "\n",
+    "# Populate missing OHE columns with 0 values to match traning dataset schema\n",
+    "difference = list(set(training_columns) - set(encoded_df.columns.tolist()))\n",
+    "for col in difference:\n",
+    "    encoded_df[col] = 0\n",
+    "encoded_df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Serialize dataframe to list of row dictionaries\n",
+    "encoded_dict = encoded_df.to_dict('records')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Submit Scoring Data to Service"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%time\n",
+    "\n",
+    "# retreive the API keys. AML generates two keys.\n",
+    "key1, key2 = aks_service.get_keys()\n",
+    "\n",
+    "total_count = len(scoring_df)\n",
+    "i = 0\n",
+    "load = []\n",
+    "for row in encoded_dict:\n",
+    "    load.append(row)\n",
+    "    i = i + 1\n",
+    "    if i % 100 == 0:\n",
+    "        payload = json.dumps({\"data\": load})\n",
+    "        \n",
+    "        # construct raw HTTP request and send to the service\n",
+    "        payload_binary = bytes(payload,encoding = 'utf8')\n",
+    "        headers = {'Content-Type':'application/json', 'Authorization': 'Bearer ' + key1}\n",
+    "        resp = requests.post(aks_service.scoring_uri, payload_binary, headers=headers)\n",
+    "        \n",
+    "        print(\"prediction:\", resp.content, \"Progress: {}/{}\".format(i, total_count))   \n",
+    "\n",
+    "        load = []\n",
+    "        time.sleep(3)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Configure DataDrift"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "services = [service_name]\n",
+    "start = datetime.now() - timedelta(days=2)\n",
+    "end = datetime(year=2020, month=1, day=22, hour=15, minute=16)\n",
+    "feature_list = ['usaf', 'wban', 'latitude', 'longitude', 'station_name', 'p_k',  'sine_hourofday', 'cosine_hourofday', 'temperature-7']\n",
+    "alert_config = AlertConfiguration([email_address]) if email_address else None\n",
+    "\n",
+    "# there will be an exception indicating using get() method if DataDrift object already exist\n",
+    "try:\n",
+    "    datadrift = DataDriftDetector.create(ws, model.name, model.version, services, frequency=\"Day\", alert_config=alert_config)\n",
+    "except KeyError:\n",
+    "    datadrift = DataDriftDetector.get(ws, model.name, model.version)\n",
+    "    \n",
+    "print(\"Details of DataDrift Object:\\n{}\".format(datadrift))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Run an Adhoc DataDriftDetector Run"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "target_date = datetime.today()\n",
+    "run = datadrift.run(target_date, services, feature_list=feature_list, create_compute_target=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "exp = Experiment(ws, datadrift._id)\n",
+    "dd_run = Run(experiment=exp, run_id=run)\n",
+    "RunDetails(dd_run).show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Get Drift Analysis Results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "children = list(dd_run.get_children())\n",
+    "for child in children:\n",
+    "    child.wait_for_completion()\n",
+    "\n",
+    "drift_metrics = datadrift.get_output(start_time=start, end_time=end)\n",
+    "drift_metrics"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Show all drift figures, one per serivice.\n",
+    "# If setting with_details is False (by default), only drift will be shown; if it's True, all details will be shown.\n",
+    "\n",
+    "drift_figures = datadrift.show(with_details=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Enable DataDrift Schedule"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "datadrift.enable_schedule()"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "rafarmah"
+   }
+  ],
+  "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/data-drift/readme.md

@@ -1 +1,3 @@
-Under contruction...please visit again soon!
+## Using data drift APIs
+
+1. [Detect data drift for a model](azure-ml-datadrift.ipynb): Detect data drift for a deployed model.

how-to-use-azureml/data-drift/score.py

@@ -0,0 +1,58 @@
+import pickle
+import json
+import numpy
+import azureml.train.automl
+from sklearn.externals import joblib
+from sklearn.linear_model import Ridge
+from azureml.core.model import Model
+from azureml.core.run import Run
+from azureml.monitoring import ModelDataCollector
+import time
+import pandas as pd
+
+
+def init():
+    global model, inputs_dc, prediction_dc, feature_names, categorical_features
+
+    print("Model is initialized" + time.strftime("%H:%M:%S"))
+    model_path = Model.get_model_path(model_name="driftmodel")
+    model = joblib.load(model_path)
+
+    feature_names = ["usaf", "wban", "latitude", "longitude", "station_name", "p_k",
+                     "sine_weekofyear", "cosine_weekofyear", "sine_hourofday", "cosine_hourofday",
+                     "temperature-7"]
+
+    categorical_features = ["usaf", "wban", "p_k", "station_name"]
+
+    inputs_dc = ModelDataCollector(model_name="driftmodel",
+                                   identifier="inputs",
+                                   feature_names=feature_names)
+
+    prediction_dc = ModelDataCollector("driftmodel",
+                                       identifier="predictions",
+                                       feature_names=["temperature"])
+
+
+def run(raw_data):
+    global inputs_dc, prediction_dc
+
+    try:
+        data = json.loads(raw_data)["data"]
+        data = pd.DataFrame(data)
+
+        # Remove the categorical features as the model expects OHE values
+        input_data = data.drop(categorical_features, axis=1)
+
+        result = model.predict(input_data)
+
+        # Collect the non-OHE dataframe
+        collected_df = data[feature_names]
+
+        inputs_dc.collect(collected_df.values)
+        prediction_dc.collect(result)
+        return result.tolist()
+    except Exception as e:
+        error = str(e)
+
+        print(error + time.strftime("%H:%M:%S"))
+        return error

how-to-use-azureml/deployment/accelerated-models/accelerated-models-object-detection.ipynb

@@ -1,492 +1,494 @@
 {
- "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": [
-    "# Azure ML Hardware Accelerated Object Detection"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This tutorial will show you how to deploy an object detection service based on the SSD-VGG model in just a few minutes using the Azure Machine Learning Accelerated AI service.\n",
-    "\n",
-    "We will use the SSD-VGG model accelerated on an FPGA. Our Accelerated Models Service handles translating deep neural networks (DNN) into an FPGA program.\n",
-    "\n",
-    "The steps in this notebook are: \n",
-    "1. [Setup Environment](#set-up-environment)\n",
-    "* [Construct Model](#construct-model)\n",
-    "    * Image Preprocessing\n",
-    "    * Featurizer\n",
-    "    * Save Model\n",
-    "    * Save input and output tensor names\n",
-    "* [Create Image](#create-image)\n",
-    "* [Deploy Image](#deploy-image)\n",
-    "* [Test the Service](#test-service)\n",
-    "    * Create Client\n",
-    "    * Serve the model\n",
-    "* [Cleanup](#cleanup)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "<a id=\"set-up-environment\"></a>\n",
-    "## 1. Set up Environment\n",
-    "### 1.a. Imports"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "import tensorflow as tf"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### 1.b. Retrieve Workspace\n",
-    "If you haven't created a Workspace, please follow [this notebook](\"../../../configuration.ipynb\") to do so. If you have, run the codeblock below to retrieve it. "
-   ]
-  },
-  {
-   "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.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "<a id=\"construct-model\"></a>\n",
-    "## 2. Construct model\n",
-    "### 2.a. Image preprocessing\n",
-    "We'd like our service to accept JPEG images as input. However the input to SSD-VGG is a float tensor of shape \\[1, 300, 300, 3\\]. The first dimension is batch, then height, width, and channels (i.e. NHWC). To bridge this gap, we need code that decodes JPEG images and resizes them appropriately for input to SSD-VGG. The Accelerated AI service can execute TensorFlow graphs as part of the service and we'll use that ability to do the image preprocessing. This code defines a TensorFlow graph that preprocesses an array of JPEG images (as TensorFlow strings) and produces a tensor that is ready to be featurized by SSD-VGG.\n",
-    "\n",
-    "**Note:** Expect to see TF deprecation warnings until we port our SDK over to use Tensorflow 2.0."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Input images as a two-dimensional tensor containing an arbitrary number of images represented a strings\n",
-    "import azureml.accel.models.utils as utils\n",
-    "tf.reset_default_graph()\n",
-    "\n",
-    "in_images = tf.placeholder(tf.string)\n",
-    "image_tensors = utils.preprocess_array(in_images, output_width=300, output_height=300, preserve_aspect_ratio=False)\n",
-    "print(image_tensors.shape)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### 2.b. Featurizer\n",
-    "The SSD-VGG model is different from our other models in that it generates 12 tensor outputs. These corresponds to x,y displacements of the anchor boxes and the detection confidence (for 21 classes). Because these outputs are not convenient to work with, we will later use a pre-defined post-processing utility to transform the outputs into a simplified list of bounding boxes with their respective class and confidence.\n",
-    "\n",
-    "For more information about the output tensors, take this example: the output tensor 'ssd_300_vgg/block4_box/Reshape_1:0' has a shape of [None, 37, 37, 4, 21]. This gives the pre-softmax confidence for 4 anchor boxes situated at each site of a 37 x 37 grid imposed on the image, one confidence score for each of the 21 classes. The first dimension is the batch dimension. Likewise, 'ssd_300_vgg/block4_box/Reshape:0' has shape [None, 37, 37, 4, 4] and encodes the (cx, cy) center shift and rescaling (sw, sh) relative to each anchor box. Refer to the [SSD-VGG paper](https://arxiv.org/abs/1512.02325) to understand how these are computed. The other 10 tensors are defined similarly."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.accel.models import SsdVgg\n",
-    "\n",
-    "saved_model_dir = os.path.join(os.path.expanduser('~'), 'models')\n",
-    "model_graph = SsdVgg(saved_model_dir, is_frozen = True)\n",
-    "\n",
-    "print('SSD-VGG Input Tensors:')\n",
-    "for idx, input_name in enumerate(model_graph.input_tensor_list):\n",
-    "    print('{}, {}'.format(input_name, model_graph.get_input_dims(idx)))\n",
-    "    \n",
-    "print('SSD-VGG Output Tensors:')\n",
-    "for idx, output_name in enumerate(model_graph.output_tensor_list):\n",
-    "    print('{}, {}'.format(output_name, model_graph.get_output_dims(idx)))\n",
-    "\n",
-    "ssd_outputs = model_graph.import_graph_def(image_tensors, is_training=False)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### 2.c. Save Model\n",
-    "Now that we loaded both parts of the tensorflow graph (preprocessor and SSD-VGG featurizer), we can save the graph and associated variables to a directory which we can register as an Azure ML Model."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "model_name = \"ssdvgg\"\n",
-    "model_save_path = os.path.join(saved_model_dir, model_name, \"saved_model\")\n",
-    "print(\"Saving model in {}\".format(model_save_path))\n",
-    "\n",
-    "output_map = {}\n",
-    "for i, output in enumerate(ssd_outputs):\n",
-    "    output_map['out_{}'.format(i)] = output\n",
-    "\n",
-    "with tf.Session() as sess:\n",
-    "    model_graph.restore_weights(sess)\n",
-    "    tf.saved_model.simple_save(sess, \n",
-    "                               model_save_path, \n",
-    "                               inputs={'images': in_images}, \n",
-    "                               outputs=output_map)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### 2.d. Important! Save names of input and output tensors\n",
-    "\n",
-    "These input and output tensors that were created during the preprocessing and classifier steps are also going to be used when **converting the model** to an Accelerated Model that can run on FPGA's and for **making an inferencing request**. It is very important to save this information!"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "register model from file"
-    ]
-   },
-   "outputs": [],
-   "source": [
-    "input_tensors = in_images.name\n",
-    "# We will use the list of output tensors during inferencing\n",
-    "output_tensors = [output.name for output in ssd_outputs]\n",
-    "# However, for multiple output tensors, our AccelOnnxConverter will \n",
-    "#    accept comma-delimited strings (lists will cause error)\n",
-    "output_tensors_str = \",\".join(output_tensors)\n",
-    "\n",
-    "print(input_tensors)\n",
-    "print(output_tensors)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "<a id=\"create-image\"></a>\n",
-    "## 3. Create AccelContainerImage\n",
-    "Below we will execute all the same steps as in the [Quickstart](./accelerated-models-quickstart.ipynb#create-image) to package the model we have saved locally into an accelerated Docker image saved in our workspace. To complete all the steps, it may take a few minutes. For more details on each step, check out the [Quickstart section on model registration](./accelerated-models-quickstart.ipynb#register-model)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core import Workspace\n",
-    "from azureml.core.model import Model\n",
-    "from azureml.core.image import Image\n",
-    "from azureml.accel import AccelOnnxConverter\n",
-    "from azureml.accel import AccelContainerImage\n",
-    "\n",
-    "# Retrieve workspace\n",
-    "ws = Workspace.from_config()\n",
-    "print(\"Successfully retrieved workspace:\", ws.name, ws.resource_group, ws.location, ws.subscription_id, '\\n')\n",
-    "\n",
-    "# Register model\n",
-    "registered_model = Model.register(workspace = ws,\n",
-    "                                  model_path = model_save_path,\n",
-    "                                  model_name = model_name)\n",
-    "print(\"Successfully registered: \", registered_model.name, registered_model.description, registered_model.version, '\\n', sep = '\\t')\n",
-    "\n",
-    "# Convert model\n",
-    "convert_request = AccelOnnxConverter.convert_tf_model(ws, registered_model, input_tensors, output_tensors_str)\n",
-    "# If it fails, you can run wait_for_completion again with show_output=True.\n",
-    "convert_request.wait_for_completion(show_output=False)\n",
-    "converted_model = convert_request.result\n",
-    "print(\"\\nSuccessfully converted: \", converted_model.name, converted_model.url, converted_model.version, \n",
-    "      converted_model.id, converted_model.created_time, '\\n')\n",
-    "\n",
-    "# Package into AccelContainerImage\n",
-    "image_config = AccelContainerImage.image_configuration()\n",
-    "# Image name must be lowercase\n",
-    "image_name = \"{}-image\".format(model_name)\n",
-    "image = Image.create(name = image_name,\n",
-    "                     models = [converted_model],\n",
-    "                     image_config = image_config, \n",
-    "                     workspace = ws)\n",
-    "image.wait_for_creation()\n",
-    "print(\"Created AccelContainerImage: {} {} {}\\n\".format(image.name, image.creation_state, image.image_location))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "<a id=\"deploy-image\"></a>\n",
-    "## 4. Deploy image\n",
-    "Once you have an Azure ML Accelerated Image in your Workspace, you can deploy it to two destinations, to a Databox Edge machine or to an AKS cluster. \n",
-    "\n",
-    "### 4.a. Deploy to Databox Edge Machine using IoT Hub\n",
-    "See the sample [here](https://github.com/Azure-Samples/aml-real-time-ai/) for using the Azure IoT CLI extension for deploying your Docker image to your Databox Edge Machine.\n",
-    "\n",
-    "### 4.b. Deploy to AKS Cluster\n",
-    "Same as in the [Quickstart section on image deployment](./accelerated-models-quickstart.ipynb#deploy-image), we are going to create an AKS cluster with FPGA-enabled machines, then deploy our service to it.\n",
-    "#### Create AKS ComputeTarget"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.compute import AksCompute, ComputeTarget\n",
-    "\n",
-    "# Uses the specific FPGA enabled VM (sku: Standard_PB6s)\n",
-    "# Standard_PB6s are available in: eastus, westus2, westeurope, southeastasia\n",
-    "prov_config = AksCompute.provisioning_configuration(vm_size = \"Standard_PB6s\",\n",
-    "                                                    agent_count = 1, \n",
-    "                                                    location = \"eastus\")\n",
-    "\n",
-    "aks_name = 'aks-pb6-obj'\n",
-    "# Create the cluster\n",
-    "aks_target = ComputeTarget.create(workspace = ws, \n",
-    "                                  name = aks_name, \n",
-    "                                  provisioning_configuration = prov_config)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Provisioning an AKS cluster might take awhile (15 or so minutes), and we want to wait until it's successfully provisioned before we can deploy a service to it. If you interrupt this cell, provisioning of the cluster will continue. You can re-run it or check the status in your Workspace under Compute."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "aks_target.wait_for_completion(show_output = True)\n",
-    "print(aks_target.provisioning_state)\n",
-    "print(aks_target.provisioning_errors)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Deploy AccelContainerImage to AKS ComputeTarget"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.webservice import Webservice, AksWebservice\n",
-    "\n",
-    "# Set the web service configuration (for creating a test service, we don't want autoscale enabled)\n",
-    "# Authentication is enabled by default, but for testing we specify False\n",
-    "aks_config = AksWebservice.deploy_configuration(autoscale_enabled=False,\n",
-    "                                                num_replicas=1,\n",
-    "                                                auth_enabled = False)\n",
-    "\n",
-    "aks_service_name ='my-aks-service'\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)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "<a id=\"test-service\"></a>\n",
-    "## 5. Test the service\n",
-    "<a id=\"create-client\"></a>\n",
-    "### 5.a. Create Client\n",
-    "The image supports gRPC and the TensorFlow Serving \"predict\" API. We have a client that can call into the docker image to get predictions. \n",
-    "\n",
-    "**Note:** If you chose to use auth_enabled=True when creating your AksWebservice.deploy_configuration(), see documentation [here](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.webservice(class)?view=azure-ml-py#get-keys--) on how to retrieve your keys and use either key as an argument to PredictionClient(...,access_token=key)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Using the grpc client in AzureML Accelerated Models SDK\n",
-    "from azureml.accel.client import PredictionClient\n",
-    "\n",
-    "address = aks_service.scoring_uri\n",
-    "ssl_enabled = address.startswith(\"https\")\n",
-    "address = address[address.find('/')+2:].strip('/')\n",
-    "port = 443 if ssl_enabled else 80\n",
-    "\n",
-    "# Initialize AzureML Accelerated Models client\n",
-    "client = PredictionClient(address=address,\n",
-    "                          port=port,\n",
-    "                          use_ssl=ssl_enabled,\n",
-    "                          service_name=aks_service.name)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can adapt the client [code](https://github.com/Azure/aml-real-time-ai/blob/master/pythonlib/amlrealtimeai/client.py) to meet your needs. There is also an example C# [client](https://github.com/Azure/aml-real-time-ai/blob/master/sample-clients/csharp).\n",
-    "\n",
-    "The service provides an API that is compatible with TensorFlow Serving. There are instructions to download a sample client [here](https://www.tensorflow.org/serving/setup)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "<a id=\"serve-model\"></a>\n",
-    "### 5.b. Serve the model\n",
-    "The SSD-VGG model returns the confidence and bounding boxes for all possible anchor boxes. As mentioned earlier, we will use a post-processing routine to transform this into a list of bounding boxes (y1, x1, y2, x2) where x, y are fractional coordinates measured from left and top respectively. A respective list of classes and scores is also returned to tag each bounding box. Below we make use of this information to draw the bounding boxes on top the original image. Note that in the post-processing routine we select a confidence threshold of 0.5."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import cv2\n",
-    "from matplotlib import pyplot as plt\n",
-    "\n",
-    "colors_tableau = [(255, 255, 255), (31, 119, 180), (174, 199, 232), (255, 127, 14), (255, 187, 120),\n",
-    "                  (44, 160, 44), (152, 223, 138), (214, 39, 40), (255, 152, 150),\n",
-    "                  (148, 103, 189), (197, 176, 213), (140, 86, 75), (196, 156, 148),\n",
-    "                  (227, 119, 194), (247, 182, 210), (127, 127, 127), (199, 199, 199),\n",
-    "                  (188, 189, 34), (219, 219, 141), (23, 190, 207), (158, 218, 229)]\n",
-    "\n",
-    "\n",
-    "def draw_boxes_on_img(img, classes, scores, bboxes, thickness=2):\n",
-    "    shape = img.shape\n",
-    "    for i in range(bboxes.shape[0]):\n",
-    "        bbox = bboxes[i]\n",
-    "        color = colors_tableau[classes[i]]\n",
-    "        # Draw bounding box...\n",
-    "        p1 = (int(bbox[0] * shape[0]), int(bbox[1] * shape[1]))\n",
-    "        p2 = (int(bbox[2] * shape[0]), int(bbox[3] * shape[1]))\n",
-    "        cv2.rectangle(img, p1[::-1], p2[::-1], color, thickness)\n",
-    "        # Draw text...\n",
-    "        s = '%s/%.3f' % (classes[i], scores[i])\n",
-    "        p1 = (p1[0]-5, p1[1])\n",
-    "        cv2.putText(img, s, p1[::-1], cv2.FONT_HERSHEY_DUPLEX, 0.4, color, 1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import azureml.accel._external.ssdvgg_utils as ssdvgg_utils\n",
-    "\n",
-    "result = client.score_file(path=\"meeting.jpg\", input_name=input_tensors, outputs=output_tensors)\n",
-    "classes, scores, bboxes = ssdvgg_utils.postprocess(result, select_threshold=0.5)\n",
-    "\n",
-    "img = cv2.imread('meeting.jpg', 1)\n",
-    "img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n",
-    "draw_boxes_on_img(img, classes, scores, bboxes)\n",
-    "plt.imshow(img)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "<a id=\"cleanup\"></a>\n",
-    "## 6. Cleanup\n",
-    "It's important to clean up your resources, so that you won't incur unnecessary costs. In the [next notebook](./accelerated-models-training.ipynb) you will learn how to train a classfier on a new dataset using transfer learning."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "aks_service.delete()\n",
-    "aks_target.delete()\n",
-    "image.delete()\n",
-    "registered_model.delete()\n",
-    "converted_model.delete()"
-   ]
-  }
- ],
- "metadata": {
-  "authors": [
-   {
-    "name": "coverste"
-   },
-   {
-    "name": "paledger"
-   },
-   {
-    "name": "sukha"
-   }
+  "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": [
+        "# Azure ML Hardware Accelerated Object Detection"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "This tutorial will show you how to deploy an object detection service based on the SSD-VGG model in just a few minutes using the Azure Machine Learning Accelerated AI service.\n",
+        "\n",
+        "We will use the SSD-VGG model accelerated on an FPGA. Our Accelerated Models Service handles translating deep neural networks (DNN) into an FPGA program.\n",
+        "\n",
+        "The steps in this notebook are: \n",
+        "1. [Setup Environment](#set-up-environment)\n",
+        "* [Construct Model](#construct-model)\n",
+        "    * Image Preprocessing\n",
+        "    * Featurizer\n",
+        "    * Save Model\n",
+        "    * Save input and output tensor names\n",
+        "* [Create Image](#create-image)\n",
+        "* [Deploy Image](#deploy-image)\n",
+        "* [Test the Service](#test-service)\n",
+        "    * Create Client\n",
+        "    * Serve the model\n",
+        "* [Cleanup](#cleanup)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"set-up-environment\"></a>\n",
+        "## 1. Set up Environment\n",
+        "### 1.a. Imports"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "import tensorflow as tf"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### 1.b. Retrieve Workspace\n",
+        "If you haven't created a Workspace, please follow [this notebook](\"../../../configuration.ipynb\") to do so. If you have, run the codeblock below to retrieve it. "
+      ]
+    },
+    {
+      "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.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"construct-model\"></a>\n",
+        "## 2. Construct model\n",
+        "### 2.a. Image preprocessing\n",
+        "We'd like our service to accept JPEG images as input. However the input to SSD-VGG is a float tensor of shape \\[1, 300, 300, 3\\]. The first dimension is batch, then height, width, and channels (i.e. NHWC). To bridge this gap, we need code that decodes JPEG images and resizes them appropriately for input to SSD-VGG. The Accelerated AI service can execute TensorFlow graphs as part of the service and we'll use that ability to do the image preprocessing. This code defines a TensorFlow graph that preprocesses an array of JPEG images (as TensorFlow strings) and produces a tensor that is ready to be featurized by SSD-VGG.\n",
+        "\n",
+        "**Note:** Expect to see TF deprecation warnings until we port our SDK over to use Tensorflow 2.0."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Input images as a two-dimensional tensor containing an arbitrary number of images represented a strings\n",
+        "import azureml.accel.models.utils as utils\n",
+        "tf.reset_default_graph()\n",
+        "\n",
+        "in_images = tf.placeholder(tf.string)\n",
+        "image_tensors = utils.preprocess_array(in_images, output_width=300, output_height=300, preserve_aspect_ratio=False)\n",
+        "print(image_tensors.shape)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### 2.b. Featurizer\n",
+        "The SSD-VGG model is different from our other models in that it generates 12 tensor outputs. These corresponds to x,y displacements of the anchor boxes and the detection confidence (for 21 classes). Because these outputs are not convenient to work with, we will later use a pre-defined post-processing utility to transform the outputs into a simplified list of bounding boxes with their respective class and confidence.\n",
+        "\n",
+        "For more information about the output tensors, take this example: the output tensor 'ssd_300_vgg/block4_box/Reshape_1:0' has a shape of [None, 37, 37, 4, 21]. This gives the pre-softmax confidence for 4 anchor boxes situated at each site of a 37 x 37 grid imposed on the image, one confidence score for each of the 21 classes. The first dimension is the batch dimension. Likewise, 'ssd_300_vgg/block4_box/Reshape:0' has shape [None, 37, 37, 4, 4] and encodes the (cx, cy) center shift and rescaling (sw, sh) relative to each anchor box. Refer to the [SSD-VGG paper](https://arxiv.org/abs/1512.02325) to understand how these are computed. The other 10 tensors are defined similarly."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.accel.models import SsdVgg\n",
+        "\n",
+        "saved_model_dir = os.path.join(os.path.expanduser('~'), 'models')\n",
+        "model_graph = SsdVgg(saved_model_dir, is_frozen = True)\n",
+        "\n",
+        "print('SSD-VGG Input Tensors:')\n",
+        "for idx, input_name in enumerate(model_graph.input_tensor_list):\n",
+        "    print('{}, {}'.format(input_name, model_graph.get_input_dims(idx)))\n",
+        "    \n",
+        "print('SSD-VGG Output Tensors:')\n",
+        "for idx, output_name in enumerate(model_graph.output_tensor_list):\n",
+        "    print('{}, {}'.format(output_name, model_graph.get_output_dims(idx)))\n",
+        "\n",
+        "ssd_outputs = model_graph.import_graph_def(image_tensors, is_training=False)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### 2.c. Save Model\n",
+        "Now that we loaded both parts of the tensorflow graph (preprocessor and SSD-VGG featurizer), we can save the graph and associated variables to a directory which we can register as an Azure ML Model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "model_name = \"ssdvgg\"\n",
+        "model_save_path = os.path.join(saved_model_dir, model_name, \"saved_model\")\n",
+        "print(\"Saving model in {}\".format(model_save_path))\n",
+        "\n",
+        "output_map = {}\n",
+        "for i, output in enumerate(ssd_outputs):\n",
+        "    output_map['out_{}'.format(i)] = output\n",
+        "\n",
+        "with tf.Session() as sess:\n",
+        "    model_graph.restore_weights(sess)\n",
+        "    tf.saved_model.simple_save(sess, \n",
+        "                               model_save_path, \n",
+        "                               inputs={'images': in_images}, \n",
+        "                               outputs=output_map)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### 2.d. Important! Save names of input and output tensors\n",
+        "\n",
+        "These input and output tensors that were created during the preprocessing and classifier steps are also going to be used when **converting the model** to an Accelerated Model that can run on FPGA's and for **making an inferencing request**. It is very important to save this information!"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "register model from file"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "input_tensors = in_images.name\n",
+        "# We will use the list of output tensors during inferencing\n",
+        "output_tensors = [output.name for output in ssd_outputs]\n",
+        "# However, for multiple output tensors, our AccelOnnxConverter will \n",
+        "#    accept comma-delimited strings (lists will cause error)\n",
+        "output_tensors_str = \",\".join(output_tensors)\n",
+        "\n",
+        "print(input_tensors)\n",
+        "print(output_tensors)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"create-image\"></a>\n",
+        "## 3. Create AccelContainerImage\n",
+        "Below we will execute all the same steps as in the [Quickstart](./accelerated-models-quickstart.ipynb#create-image) to package the model we have saved locally into an accelerated Docker image saved in our workspace. To complete all the steps, it may take a few minutes. For more details on each step, check out the [Quickstart section on model registration](./accelerated-models-quickstart.ipynb#register-model)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core import Workspace\n",
+        "from azureml.core.model import Model\n",
+        "from azureml.core.image import Image\n",
+        "from azureml.accel import AccelOnnxConverter\n",
+        "from azureml.accel import AccelContainerImage\n",
+        "\n",
+        "# Retrieve workspace\n",
+        "ws = Workspace.from_config()\n",
+        "print(\"Successfully retrieved workspace:\", ws.name, ws.resource_group, ws.location, ws.subscription_id, '\\n')\n",
+        "\n",
+        "# Register model\n",
+        "registered_model = Model.register(workspace = ws,\n",
+        "                                  model_path = model_save_path,\n",
+        "                                  model_name = model_name)\n",
+        "print(\"Successfully registered: \", registered_model.name, registered_model.description, registered_model.version, '\\n', sep = '\\t')\n",
+        "\n",
+        "# Convert model\n",
+        "convert_request = AccelOnnxConverter.convert_tf_model(ws, registered_model, input_tensors, output_tensors_str)\n",
+        "# If it fails, you can run wait_for_completion again with show_output=True.\n",
+        "convert_request.wait_for_completion(show_output=False)\n",
+        "converted_model = convert_request.result\n",
+        "print(\"\\nSuccessfully converted: \", converted_model.name, converted_model.url, converted_model.version, \n",
+        "      converted_model.id, converted_model.created_time, '\\n')\n",
+        "\n",
+        "# Package into AccelContainerImage\n",
+        "image_config = AccelContainerImage.image_configuration()\n",
+        "# Image name must be lowercase\n",
+        "image_name = \"{}-image\".format(model_name)\n",
+        "image = Image.create(name = image_name,\n",
+        "                     models = [converted_model],\n",
+        "                     image_config = image_config, \n",
+        "                     workspace = ws)\n",
+        "image.wait_for_creation()\n",
+        "print(\"Created AccelContainerImage: {} {} {}\\n\".format(image.name, image.creation_state, image.image_location))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"deploy-image\"></a>\n",
+        "## 4. Deploy image\n",
+        "Once you have an Azure ML Accelerated Image in your Workspace, you can deploy it to two destinations, to a Databox Edge machine or to an AKS cluster. \n",
+        "\n",
+        "### 4.a. Deploy to Databox Edge Machine using IoT Hub\n",
+        "See the sample [here](https://github.com/Azure-Samples/aml-real-time-ai/) for using the Azure IoT CLI extension for deploying your Docker image to your Databox Edge Machine.\n",
+        "\n",
+        "### 4.b. Deploy to AKS Cluster\n",
+        "Same as in the [Quickstart section on image deployment](./accelerated-models-quickstart.ipynb#deploy-image), we are going to create an AKS cluster with FPGA-enabled machines, then deploy our service to it.\n",
+        "#### Create AKS ComputeTarget"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.compute import AksCompute, ComputeTarget\n",
+        "\n",
+        "# Uses the specific FPGA enabled VM (sku: Standard_PB6s)\n",
+        "# Standard_PB6s are available in: eastus, westus2, westeurope, southeastasia\n",
+        "prov_config = AksCompute.provisioning_configuration(vm_size = \"Standard_PB6s\",\n",
+        "                                                    agent_count = 1, \n",
+        "                                                    location = \"eastus\")\n",
+        "\n",
+        "aks_name = 'aks-pb6-obj'\n",
+        "# Create the cluster\n",
+        "aks_target = ComputeTarget.create(workspace = ws, \n",
+        "                                  name = aks_name, \n",
+        "                                  provisioning_configuration = prov_config)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Provisioning an AKS cluster might take awhile (15 or so minutes), and we want to wait until it's successfully provisioned before we can deploy a service to it. If you interrupt this cell, provisioning of the cluster will continue. You can re-run it or check the status in your Workspace under Compute."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "aks_target.wait_for_completion(show_output = True)\n",
+        "print(aks_target.provisioning_state)\n",
+        "print(aks_target.provisioning_errors)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Deploy AccelContainerImage to AKS ComputeTarget"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.webservice import Webservice, AksWebservice\n",
+        "\n",
+        "# Set the web service configuration (for creating a test service, we don't want autoscale enabled)\n",
+        "# Authentication is enabled by default, but for testing we specify False\n",
+        "aks_config = AksWebservice.deploy_configuration(autoscale_enabled=False,\n",
+        "                                                num_replicas=1,\n",
+        "                                                auth_enabled = False)\n",
+        "\n",
+        "aks_service_name ='my-aks-service'\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)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"test-service\"></a>\n",
+        "## 5. Test the service\n",
+        "<a id=\"create-client\"></a>\n",
+        "### 5.a. Create Client\n",
+        "The image supports gRPC and the TensorFlow Serving \"predict\" API. We have a client that can call into the docker image to get predictions. \n",
+        "\n",
+        "**Note:** If you chose to use auth_enabled=True when creating your AksWebservice.deploy_configuration(), see documentation [here](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.webservice(class)?view=azure-ml-py#get-keys--) on how to retrieve your keys and use either key as an argument to PredictionClient(...,access_token=key).",
+        "\n",
+        "**WARNING:** If you are running on Azure Notebooks free compute, you will not be able to make outgoing calls to your service. Try locating your client on a different machine to consume it."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Using the grpc client in AzureML Accelerated Models SDK\n",
+        "from azureml.accel.client import PredictionClient\n",
+        "\n",
+        "address = aks_service.scoring_uri\n",
+        "ssl_enabled = address.startswith(\"https\")\n",
+        "address = address[address.find('/')+2:].strip('/')\n",
+        "port = 443 if ssl_enabled else 80\n",
+        "\n",
+        "# Initialize AzureML Accelerated Models client\n",
+        "client = PredictionClient(address=address,\n",
+        "                          port=port,\n",
+        "                          use_ssl=ssl_enabled,\n",
+        "                          service_name=aks_service.name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can adapt the client [code](https://github.com/Azure/aml-real-time-ai/blob/master/pythonlib/amlrealtimeai/client.py) to meet your needs. There is also an example C# [client](https://github.com/Azure/aml-real-time-ai/blob/master/sample-clients/csharp).\n",
+        "\n",
+        "The service provides an API that is compatible with TensorFlow Serving. There are instructions to download a sample client [here](https://www.tensorflow.org/serving/setup)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"serve-model\"></a>\n",
+        "### 5.b. Serve the model\n",
+        "The SSD-VGG model returns the confidence and bounding boxes for all possible anchor boxes. As mentioned earlier, we will use a post-processing routine to transform this into a list of bounding boxes (y1, x1, y2, x2) where x, y are fractional coordinates measured from left and top respectively. A respective list of classes and scores is also returned to tag each bounding box. Below we make use of this information to draw the bounding boxes on top the original image. Note that in the post-processing routine we select a confidence threshold of 0.5."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import cv2\n",
+        "from matplotlib import pyplot as plt\n",
+        "\n",
+        "colors_tableau = [(255, 255, 255), (31, 119, 180), (174, 199, 232), (255, 127, 14), (255, 187, 120),\n",
+        "                  (44, 160, 44), (152, 223, 138), (214, 39, 40), (255, 152, 150),\n",
+        "                  (148, 103, 189), (197, 176, 213), (140, 86, 75), (196, 156, 148),\n",
+        "                  (227, 119, 194), (247, 182, 210), (127, 127, 127), (199, 199, 199),\n",
+        "                  (188, 189, 34), (219, 219, 141), (23, 190, 207), (158, 218, 229)]\n",
+        "\n",
+        "\n",
+        "def draw_boxes_on_img(img, classes, scores, bboxes, thickness=2):\n",
+        "    shape = img.shape\n",
+        "    for i in range(bboxes.shape[0]):\n",
+        "        bbox = bboxes[i]\n",
+        "        color = colors_tableau[classes[i]]\n",
+        "        # Draw bounding box...\n",
+        "        p1 = (int(bbox[0] * shape[0]), int(bbox[1] * shape[1]))\n",
+        "        p2 = (int(bbox[2] * shape[0]), int(bbox[3] * shape[1]))\n",
+        "        cv2.rectangle(img, p1[::-1], p2[::-1], color, thickness)\n",
+        "        # Draw text...\n",
+        "        s = '%s/%.3f' % (classes[i], scores[i])\n",
+        "        p1 = (p1[0]-5, p1[1])\n",
+        "        cv2.putText(img, s, p1[::-1], cv2.FONT_HERSHEY_DUPLEX, 0.4, color, 1)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import azureml.accel._external.ssdvgg_utils as ssdvgg_utils\n",
+        "\n",
+        "result = client.score_file(path=\"meeting.jpg\", input_name=input_tensors, outputs=output_tensors)\n",
+        "classes, scores, bboxes = ssdvgg_utils.postprocess(result, select_threshold=0.5)\n",
+        "\n",
+        "img = cv2.imread('meeting.jpg', 1)\n",
+        "img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n",
+        "draw_boxes_on_img(img, classes, scores, bboxes)\n",
+        "plt.imshow(img)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"cleanup\"></a>\n",
+        "## 6. Cleanup\n",
+        "It's important to clean up your resources, so that you won't incur unnecessary costs. In the [next notebook](./accelerated-models-training.ipynb) you will learn how to train a classfier on a new dataset using transfer learning."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "aks_service.delete()\n",
+        "aks_target.delete()\n",
+        "image.delete()\n",
+        "registered_model.delete()\n",
+        "converted_model.delete()"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "metadata": {
+    "authors": [
+      {
+        "name": "coverste"
+      },
+      {
+        "name": "paledger"
+      },
+      {
+        "name": "sukha"
+      }
+    ],
+    "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": "3.6.0"
+    }
   },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.6.0"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

how-to-use-azureml/deployment/onnx/onnx-train-pytorch-aml-deploy-mnist.ipynb

@@ -98,7 +98,7 @@
         "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# choose a name for your cluster\n",
-        "cluster_name = \"gpucluster\"\n",
+        "cluster_name = \"gpu-cluster\"\n",
         "\n",
         "try:\n",
         "    compute_target = ComputeTarget(workspace=ws, name=cluster_name)\n",

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

@@ -1,407 +1,407 @@
 {
- "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. Prior to registering the model, you should have a TensorFlow [Saved Model](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/saved_model/README.md) in the `resnet50` directory. You can download a [pretrained resnet50](https://github.com/tensorflow/models/tree/master/official/resnet#pre-trained-model) and unpack it to that directory."
-   ]
-  },
-  {
-   "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 = \"resnet50\", # this points to a local file\n",
-    "                       model_name = \"resnet50\", # this is the name the model is registered as\n",
-    "                       tags = {'area': \"Image classification\", 'type': \"classification\"},\n",
-    "                       description = \"Image classification trained on Imagenet Dataset\",\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 tensorflow as tf\n",
-    "import numpy as np\n",
-    "import ujson\n",
-    "from azureml.core.model import Model\n",
-    "from azureml.contrib.services.aml_request import AMLRequest, rawhttp\n",
-    "from azureml.contrib.services.aml_response import AMLResponse\n",
-    "\n",
-    "def init():\n",
-    "    global session\n",
-    "    global input_name\n",
-    "    global output_name\n",
-    "    \n",
-    "    session = tf.Session()\n",
-    "\n",
-    "    model_path = Model.get_model_path('resnet50')\n",
-    "    model = tf.saved_model.loader.load(session, ['serve'], model_path)\n",
-    "    if len(model.signature_def['serving_default'].inputs) > 1:\n",
-    "        raise ValueError(\"This score.py only supports one input\")\n",
-    "    if len(model.signature_def['serving_default'].outputs) > 1:\n",
-    "        raise ValueError(\"This score.py only supports one input\")\n",
-    "    input_name = [tensor.name for tensor in model.signature_def['serving_default'].inputs.values()][0]\n",
-    "    output_name = [tensor.name for tensor in model.signature_def['serving_default'].outputs.values()][0]\n",
-    "    \n",
-    "\n",
-    "@rawhttp\n",
-    "def run(request):\n",
-    "    if request.method == 'POST':\n",
-    "        reqBody = request.get_data(False)\n",
-    "        resp = score(reqBody)\n",
-    "        return AMLResponse(resp, 200)\n",
-    "    if request.method == 'GET':\n",
-    "        respBody = str.encode(\"GET is not supported\")\n",
-    "        return AMLResponse(respBody, 405)\n",
-    "    return AMLResponse(\"bad request\", 500)\n",
-    "\n",
-    "def score(data):\n",
-    "    result = session.run(output_name, {input_name: [data]})\n",
-    "    return ujson.dumps(result[0])\n",
-    "\n",
-    "if __name__ == \"__main__\":\n",
-    "    init()\n",
-    "    with open(\"test_image.jpg\", 'rb') as f:\n",
-    "        content = f.read()\n",
-    "        print(score(content))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.conda_dependencies import CondaDependencies \n",
-    "\n",
-    "myenv = CondaDependencies.create(conda_packages=['tensorflow-gpu==1.12.0','numpy','ujson','azureml-contrib-services'])\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",
-    "                                                  gpu_enabled = True\n",
-    "                                                 )\n",
-    "\n",
-    "image = ContainerImage.create(name = \"GpuImage\",\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(vm_size=\"Standard_NC6\")\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": "markdown",
-   "metadata": {},
-   "source": [
-    "# Create AKS Cluster in an existing virtual network (optional)\n",
-    "See code snippet below. Check the documentation [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-enable-virtual-network#use-azure-kubernetes-service) for more details."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "'''\n",
-    "from azureml.core.compute import ComputeTarget, AksCompute\n",
-    "\n",
-    "# Create the compute configuration and set virtual network information\n",
-    "config = AksCompute.provisioning_configuration(vm_size=\"Standard_NC6\", location=\"eastus2\")\n",
-    "config.vnet_resourcegroup_name = \"mygroup\"\n",
-    "config.vnet_name = \"mynetwork\"\n",
-    "config.subnet_name = \"default\"\n",
-    "config.service_cidr = \"10.0.0.0/16\"\n",
-    "config.dns_service_ip = \"10.0.0.10\"\n",
-    "config.docker_bridge_cidr = \"172.17.0.1/16\"\n",
-    "\n",
-    "# Create the compute target\n",
-    "aks_target = ComputeTarget.create(workspace = ws,\n",
-    "                                  name = \"myaks\",\n",
-    "                                  provisioning_configuration = config)\n",
-    "'''"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Enable SSL on the AKS Cluster (optional)\n",
-    "See code snippet below. Check the documentation [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-secure-web-service) for more details"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# provisioning_config = AksCompute.provisioning_configuration(ssl_cert_pem_file=\"cert.pem\", ssl_key_pem_file=\"key.pem\", ssl_cname=\"www.contoso.com\")"
-   ]
-  },
-  {
-   "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 the test images content."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%time\n",
-    "import requests\n",
-    "key1, key2 = aks_service.get_keys()\n",
-    "\n",
-    "headers = {'Content-Type':'application/json', 'Authorization': 'Bearer ' + key1}\n",
-    "test_sampe = open('test_image.jpg', 'rb').read()\n",
-    "resp = requests.post(aks_service.scoring_uri, test_sample, headers=headers)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Clean up\n",
-    "Delete the service, image, model and compute target"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%time\n",
-    "aks_service.delete()\n",
-    "image.delete()\n",
-    "model.delete()\n",
-    "aks_target.delete()"
-   ]
-  }
- ],
- "metadata": {
-  "authors": [
-   {
-    "name": "aashishb"
-   }
+  "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. Prior to registering the model, you should have a TensorFlow [Saved Model](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/saved_model/README.md) in the `resnet50` directory. You can download a [pretrained resnet50](https://github.com/tensorflow/models/tree/master/official/resnet#pre-trained-model) and unpack it to that directory."
+      ]
+    },
+    {
+      "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 = \"resnet50\", # this points to a local file\n",
+        "                       model_name = \"resnet50\", # this is the name the model is registered as\n",
+        "                       tags = {'area': \"Image classification\", 'type': \"classification\"},\n",
+        "                       description = \"Image classification trained on Imagenet Dataset\",\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 tensorflow as tf\n",
+        "import numpy as np\n",
+        "import ujson\n",
+        "from azureml.core.model import Model\n",
+        "from azureml.contrib.services.aml_request import AMLRequest, rawhttp\n",
+        "from azureml.contrib.services.aml_response import AMLResponse\n",
+        "\n",
+        "def init():\n",
+        "    global session\n",
+        "    global input_name\n",
+        "    global output_name\n",
+        "    \n",
+        "    session = tf.Session()\n",
+        "\n",
+        "    model_path = Model.get_model_path('resnet50')\n",
+        "    model = tf.saved_model.loader.load(session, ['serve'], model_path)\n",
+        "    if len(model.signature_def['serving_default'].inputs) > 1:\n",
+        "        raise ValueError(\"This score.py only supports one input\")\n",
+        "    if len(model.signature_def['serving_default'].outputs) > 1:\n",
+        "        raise ValueError(\"This score.py only supports one input\")\n",
+        "    input_name = [tensor.name for tensor in model.signature_def['serving_default'].inputs.values()][0]\n",
+        "    output_name = [tensor.name for tensor in model.signature_def['serving_default'].outputs.values()][0]\n",
+        "    \n",
+        "\n",
+        "@rawhttp\n",
+        "def run(request):\n",
+        "    if request.method == 'POST':\n",
+        "        reqBody = request.get_data(False)\n",
+        "        resp = score(reqBody)\n",
+        "        return AMLResponse(resp, 200)\n",
+        "    if request.method == 'GET':\n",
+        "        respBody = str.encode(\"GET is not supported\")\n",
+        "        return AMLResponse(respBody, 405)\n",
+        "    return AMLResponse(\"bad request\", 500)\n",
+        "\n",
+        "def score(data):\n",
+        "    result = session.run(output_name, {input_name: [data]})\n",
+        "    return ujson.dumps(result[0])\n",
+        "\n",
+        "if __name__ == \"__main__\":\n",
+        "    init()\n",
+        "    with open(\"test_image.jpg\", 'rb') as f:\n",
+        "        content = f.read()\n",
+        "        print(score(content))"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.conda_dependencies import CondaDependencies \n",
+        "\n",
+        "myenv = CondaDependencies.create(conda_packages=['tensorflow-gpu==1.12.0','numpy','ujson','azureml-contrib-services'])\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",
+        "                                                  gpu_enabled = True\n",
+        "                                                 )\n",
+        "\n",
+        "image = ContainerImage.create(name = \"GpuImage\",\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(vm_size=\"Standard_NC6\")\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": "markdown",
+      "metadata": {},
+      "source": [
+        "# Create AKS Cluster in an existing virtual network (optional)\n",
+        "See code snippet below. Check the documentation [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-enable-virtual-network#use-azure-kubernetes-service) for more details."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "'''\n",
+        "from azureml.core.compute import ComputeTarget, AksCompute\n",
+        "\n",
+        "# Create the compute configuration and set virtual network information\n",
+        "config = AksCompute.provisioning_configuration(vm_size=\"Standard_NC6\", location=\"eastus2\")\n",
+        "config.vnet_resourcegroup_name = \"mygroup\"\n",
+        "config.vnet_name = \"mynetwork\"\n",
+        "config.subnet_name = \"default\"\n",
+        "config.service_cidr = \"10.0.0.0/16\"\n",
+        "config.dns_service_ip = \"10.0.0.10\"\n",
+        "config.docker_bridge_cidr = \"172.17.0.1/16\"\n",
+        "\n",
+        "# Create the compute target\n",
+        "aks_target = ComputeTarget.create(workspace = ws,\n",
+        "                                  name = \"myaks\",\n",
+        "                                  provisioning_configuration = config)\n",
+        "'''"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Enable SSL on the AKS Cluster (optional)\n",
+        "See code snippet below. Check the documentation [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-secure-web-service) for more details"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# provisioning_config = AksCompute.provisioning_configuration(ssl_cert_pem_file=\"cert.pem\", ssl_key_pem_file=\"key.pem\", ssl_cname=\"www.contoso.com\")"
+      ]
+    },
+    {
+      "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 the test images content."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%time\n",
+        "import requests\n",
+        "key1, key2 = aks_service.get_keys()\n",
+        "\n",
+        "headers = {'Content-Type':'application/json', 'Authorization': 'Bearer ' + key1}\n",
+        "test_sampe = open('test_image.jpg', 'rb').read()\n",
+        "resp = requests.post(aks_service.scoring_uri, test_sample, headers=headers)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Clean up\n",
+        "Delete the service, image, model and compute target"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%time\n",
+        "aks_service.delete()\n",
+        "image.delete()\n",
+        "model.delete()\n",
+        "aks_target.delete()"
+      ]
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
+  "metadata": {
+    "authors": [
+      {
+        "name": "aashishb"
+      }
+    ],
+    "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"
+    }
   },
-  "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"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

how-to-use-azureml/explain-model/explain-on-amlcompute/regression-sklearn-on-amlcompute.ipynb

@@ -265,7 +265,7 @@
         "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# Choose a name for your CPU cluster\n",
-        "cpu_cluster_name = \"cpucluster\"\n",
+        "cpu_cluster_name = \"cpu-cluster\"\n",
         "\n",
         "# Verify that cluster does not exist already\n",
         "try:\n",
@@ -370,7 +370,7 @@
         "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# Choose a name for your CPU cluster\n",
-        "cpu_cluster_name = \"cpucluster\"\n",
+        "cpu_cluster_name = \"cpu-cluster\"\n",
         "\n",
         "# Verify that cluster does not exist already\n",
         "try:\n",
@@ -506,7 +506,7 @@
       "outputs": [],
       "source": [
         "# Delete () is used to deprovision and delete the AmlCompute target. Useful if you want to re-use the compute name \n",
-        "# 'cpucluster' in this case but use a different VM family for instance.\n",
+        "# 'cpu-cluster' in this case but use a different VM family for instance.\n",
         "\n",
         "# cpu_cluster.delete()"
       ]

how-to-use-azureml/explain-model/explain-tabular-data-raw-features/explain-sklearn-raw-features.ipynb

@@ -36,22 +36,6 @@
         "4. Visualize the global and local explanations with the visualization dashboard."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "This example needs sklearn-pandas. If it is not installed, uncomment and run the following line."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#!pip install sklearn-pandas"
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -63,7 +47,6 @@
         "from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
         "from sklearn.linear_model import LogisticRegression\n",
         "from azureml.explain.model.tabular_explainer import TabularExplainer\n",
-        "from sklearn_pandas import DataFrameMapper\n",
         "import pandas as pd\n",
         "import numpy as np"
       ]
@@ -113,6 +96,13 @@
         "x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "sklearn imports"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -121,7 +111,51 @@
       "source": [
         "from sklearn.pipeline import Pipeline\n",
         "from sklearn.impute import SimpleImputer\n",
-        "from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
+        "from sklearn.preprocessing import StandardScaler, OneHotEncoder"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We can explain raw features by either using a `sklearn.compose.ColumnTransformer` or a list of fitted transformer tuples. The cell below uses `sklearn.compose.ColumnTransformer`. In case you want to run the example with the list of fitted transformer tuples, comment the cell below and uncomment the cell that follows after. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from sklearn.compose import ColumnTransformer\n",
+        "\n",
+        "transformations = ColumnTransformer([\n",
+        "    (\"age_fare\", Pipeline(steps=[\n",
+        "        ('imputer', SimpleImputer(strategy='median')),\n",
+        "        ('scaler', StandardScaler())\n",
+        "    ]), [\"age\", \"fare\"]),\n",
+        "    (\"embarked\", Pipeline(steps=[\n",
+        "        (\"imputer\", SimpleImputer(strategy='constant', fill_value='missing')), \n",
+        "        (\"encoder\", OneHotEncoder(sparse=False))]), [\"embarked\"]),\n",
+        "    (\"sex_pclass\", OneHotEncoder(sparse=False), [\"sex\", \"pclass\"])    \n",
+        "])\n",
+        "\n",
+        "\n",
+        "# Append classifier to preprocessing pipeline.\n",
+        "# Now we have a full prediction pipeline.\n",
+        "clf = Pipeline(steps=[('preprocessor', transformations),\n",
+        "                      ('classifier', LogisticRegression(solver='lbfgs'))])\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "'''\n",
+        "# Uncomment below if sklearn-pandas is not installed\n",
+        "#!pip install sklearn-pandas\n",
         "from sklearn_pandas import DataFrameMapper\n",
         "\n",
         "# Impute, standardize the numeric features and one-hot encode the categorical features.    \n",
@@ -141,7 +175,8 @@
         "# Append classifier to preprocessing pipeline.\n",
         "# Now we have a full prediction pipeline.\n",
         "clf = Pipeline(steps=[('preprocessor', DataFrameMapper(transformations)),\n",
-        "                      ('classifier', LogisticRegression(solver='lbfgs'))])"
+        "                      ('classifier', LogisticRegression(solver='lbfgs'))])\n",
+        "'''"
       ]
     },
     {

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

@@ -206,8 +206,15 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "#### Retrieve default Azure Machine Learning 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 get the default Azure Machine Learning Compute in the current workspace. We will then run the training script on this compute target."
+        "#### Retrieve or create a Azure Machine Learning 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 Azure Machine Learning Compute in the current workspace, if it doesn't already exist. We will then run the training script on this compute target.\n",
+        "\n",
+        "If we could not find the compute with the given name in the previous cell, then we will create a new compute here. We will create an Azure Machine Learning Compute containing **STANDARD_D2_V2 CPU VMs**. This process is broken down into the following steps:\n",
+        "\n",
+        "1. Create the configuration\n",
+        "2. Create the Azure Machine Learning compute\n",
+        "\n",
+        "**This process will take about 3 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.**"
       ]
     },
     {
@@ -216,7 +223,23 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "aml_compute = ws.get_default_compute_target(\"CPU\")"
+        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
+        "from azureml.core.compute_target import ComputeTargetException\n",
+        "\n",
+        "aml_compute_target = \"cpu-cluster\"\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(\"Azure Machine Learning Compute attached\")\n"
       ]
     },
     {

how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-how-to-use-azurebatch-to-run-a-windows-executable.ipynb

@@ -113,7 +113,25 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "batch_compute = ws.get_default_compute_target(\"CPU\")"
+        "batch_compute_name = 'mybatchcompute' # Name to associate with new compute in workspace\n",
+        "\n",
+        "# Batch account details needed to attach as compute to workspace\n",
+        "batch_account_name = \"<batch_account_name>\" # Name of the Batch account\n",
+        "batch_resource_group = \"<batch_resource_group>\" # Name of the resource group which contains this account\n",
+        "\n",
+        "try:\n",
+        "    # check if already attached\n",
+        "    batch_compute = BatchCompute(ws, batch_compute_name)\n",
+        "except ComputeTargetException:\n",
+        "    print('Attaching Batch compute...')\n",
+        "    provisioning_config = BatchCompute.attach_configuration(resource_group=batch_resource_group, \n",
+        "                                                            account_name=batch_account_name)\n",
+        "    batch_compute = ComputeTarget.attach(ws, batch_compute_name, provisioning_config)\n",
+        "    batch_compute.wait_for_completion()\n",
+        "    print(\"Provisioning state:{}\".format(batch_compute.provisioning_state))\n",
+        "    print(\"Provisioning errors:{}\".format(batch_compute.provisioning_errors))\n",
+        "\n",
+        "print(\"Using Batch compute:{}\".format(batch_compute.cluster_resource_id))"
       ]
     },
     {

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

@@ -76,8 +76,18 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Get default AmlCompute\n",
-        "You can 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 use default `AmlCompute` as your training compute resource."
+        "## 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"
       ]
     },
     {
@@ -86,7 +96,25 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "cpu_cluster = ws.get_default_compute_target(\"CPU\")\n",
+        "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 = \"cpu-cluster\"\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())"
@@ -96,7 +124,7 @@
       "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`."
+        "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 'cpu-cluster' of type `AmlCompute`."
       ]
     },
     {

how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-parameter-tuning-with-hyperdrive.ipynb

@@ -184,37 +184,36 @@
       "metadata": {},
       "source": [
         "## Retrieve or create a Azure Machine Learning compute\n",
-        "Azure Machine Learning Compute is a service for provisioning and managing clusters of Azure virtual machines for running machine learning workloads.\n",
-        "Let's check the available computes first."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "cts = ws.compute_targets\n",
-        "for name, ct in cts.items():\n",
-        "    print(name, ct.type, ct.provisioning_state)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Now let's get the default Azure Machine Learning Compute in the current workspace. We will then run the training script on this compute target."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "compute_target = ws.get_default_compute_target(\"GPU\")\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 Azure Machine Learning Compute in the current workspace, if it doesn't already exist. We will then run the training script on this compute target.\n",
         "\n",
-        "print(compute_target.get_status().serialize())"
+        "If we could not find the compute with the given name in the previous cell, then we will create a new compute here. This process is broken down into the following steps:\n",
+        "\n",
+        "1. Create the configuration\n",
+        "2. Create the Azure Machine Learning compute\n",
+        "\n",
+        "**This process will take a few 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.**\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "cluster_name = \"gpu-cluster\"\n",
+        "\n",
+        "try:\n",
+        "    compute_target = ComputeTarget(workspace=ws, name=cluster_name)\n",
+        "    print('Found existing compute target {}.'.format(cluster_name))\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",
+        "    compute_target = ComputeTarget.create(ws, cluster_name, compute_config)\n",
+        "    compute_target.wait_for_completion(show_output=True, timeout_in_minutes=20)\n",
+        "\n",
+        "print(\"Azure Machine Learning Compute attached\")"
       ]
     },
     {

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

@@ -79,7 +79,20 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "aml_compute = ws.get_default_compute_target(\"CPU\")"
+        "from azureml.core.compute_target import ComputeTargetException\n",
+        "\n",
+        "aml_compute_target = \"cpu-cluster\"\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"
       ]
     },
     {

how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-setup-schedule-for-a-published-pipeline.ipynb

@@ -54,7 +54,7 @@
       "metadata": {},
       "source": [
         "### Compute Targets\n",
-        "#### Retrieve the default Azure Machine Learning Compute"
+        "#### Retrieve an already attached Azure Machine Learning Compute"
       ]
     },
     {
@@ -63,7 +63,31 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "aml_compute_target = ws.get_default_compute_target(\"CPU\")"
+        "from azureml.core import Run, Experiment, Datastore\n",
+        "\n",
+        "from azureml.widgets import RunDetails\n",
+        "\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.compute import AmlCompute, ComputeTarget\n",
+        "aml_compute_target = \"cpu-cluster\"\n",
+        "try:\n",
+        "    aml_compute = AmlCompute(ws, aml_compute_target)\n",
+        "    print(\"Found existing compute target: {}\".format(aml_compute_target))\n",
+        "except:\n",
+        "    print(\"Creating new compute target: {}\".format(aml_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)"
       ]
     },
     {

how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-setup-versioned-pipeline-endpoints.ipynb

@@ -85,10 +85,24 @@
       "metadata": {},
       "outputs": [],
       "source": [
+        "from azureml.core import Run, Experiment, Datastore\n",
+        "from azureml.core.compute import AmlCompute, ComputeTarget\n",
         "from azureml.pipeline.steps import PythonScriptStep\n",
         "from azureml.pipeline.core import Pipeline\n",
         "\n",
-        "aml_compute = ws.get_default_compute_target(\"CPU\")\n",
+        "#Retrieve an already attached Azure Machine Learning Compute\n",
+        "aml_compute_target = \"cpu-cluster\"\n",
+        "try:\n",
+        "    aml_compute = AmlCompute(ws, aml_compute_target)\n",
+        "    print(\"Found existing compute target: {}\".format(aml_compute_target))\n",
+        "except:\n",
+        "    print(\"Creating new compute target: {}\".format(aml_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",
         "# source_directory\n",
         "source_directory = '.'\n",

how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-automated-machine-learning-step.ipynb

@@ -139,7 +139,31 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "compute_target = ws.get_default_compute_target(\"CPU\")"
+        "# Choose a name for your cluster.\n",
+        "amlcompute_cluster_name = \"cpu-cluster\"\n",
+        "\n",
+        "found = False\n",
+        "# Check if this compute target already exists in the workspace.\n",
+        "cts = ws.compute_targets\n",
+        "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
+        "    found = True\n",
+        "    print('Found existing compute target.')\n",
+        "    compute_target = cts[amlcompute_cluster_name]\n",
+        "    \n",
+        "if not found:\n",
+        "    print('Creating a new compute target...')\n",
+        "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
+        "                                                                #vm_priority = 'lowpriority', # optional\n",
+        "                                                                max_nodes = 4)\n",
+        "\n",
+        "    # Create the cluster.\n",
+        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
+        "    \n",
+        "    # Can poll for a minimum number of nodes and for a specific timeout.\n",
+        "    # If no min_node_count is provided, it will use the scale settings for the cluster.\n",
+        "    compute_target.wait_for_completion(show_output = True, min_node_count = 1, timeout_in_minutes = 10)\n",
+        "    \n",
+        "     # For a more detailed view of current AmlCompute status, use get_status()."
       ]
     },
     {

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

@@ -137,7 +137,22 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "aml_compute = ws.get_default_compute_target(\"CPU\")\n"
+        "from azureml.core.compute_target import ComputeTargetException\n",
+        "\n",
+        "aml_compute_target = \"cpu-cluster\"\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"
       ]
     },
     {
@@ -418,13 +433,31 @@
         "RunDetails(pipeline_run1).show()"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Wait for pipeline run to complete"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "pipeline_run1.wait_for_completion(show_output=True)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
         "### See Outputs\n",
         "\n",
-        "See where outputs of each pipeline step are located on your datastore."
+        "See where outputs of each pipeline step are located on your datastore.\n",
+        "\n",
+        "***Wait for pipeline run to complete, to make sure all the outputs are ready***"
       ]
     },
     {

how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/compare/compare.py

@@ -0,0 +1,24 @@
+# Copyright (c) Microsoft. All rights reserved.
+# Licensed under the MIT license.
+
+import argparse
+import os
+
+print("In compare.py")
+print("As a data scientist, this is where I use my compare code.")
+parser = argparse.ArgumentParser("compare")
+parser.add_argument("--compare_data1", type=str, help="compare_data1 data")
+parser.add_argument("--compare_data2", type=str, help="compare_data2 data")
+parser.add_argument("--output_compare", type=str, help="output_compare directory")
+parser.add_argument("--pipeline_param", type=int, help="pipeline parameter")
+
+args = parser.parse_args()
+
+print("Argument 1: %s" % args.compare_data1)
+print("Argument 2: %s" % args.compare_data2)
+print("Argument 3: %s" % args.output_compare)
+print("Argument 4: %s" % args.pipeline_param)
+
+if not (args.output_compare is None):
+    os.makedirs(args.output_compare, exist_ok=True)
+    print("%s created" % args.output_compare)

how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/extract/extract.py

@@ -0,0 +1,21 @@
+# Copyright (c) Microsoft. All rights reserved.
+# Licensed under the MIT license.
+
+import argparse
+import os
+
+print("In extract.py")
+print("As a data scientist, this is where I use my extract code.")
+
+parser = argparse.ArgumentParser("extract")
+parser.add_argument("--input_extract", type=str, help="input_extract data")
+parser.add_argument("--output_extract", type=str, help="output_extract directory")
+
+args = parser.parse_args()
+
+print("Argument 1: %s" % args.input_extract)
+print("Argument 2: %s" % args.output_extract)
+
+if not (args.output_extract is None):
+    os.makedirs(args.output_extract, exist_ok=True)
+    print("%s created" % args.output_extract)

how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/train/train.py

@@ -0,0 +1,22 @@
+# Copyright (c) Microsoft. All rights reserved.
+# Licensed under the MIT license.
+
+import argparse
+import os
+
+print("In train.py")
+print("As a data scientist, this is where I use my training code.")
+
+parser = argparse.ArgumentParser("train")
+
+parser.add_argument("--input_data", type=str, help="input data")
+parser.add_argument("--output_train", type=str, help="output_train directory")
+
+args = parser.parse_args()
+
+print("Argument 1: %s" % args.input_data)
+print("Argument 2: %s" % args.output_train)
+
+if not (args.output_train is None):
+    os.makedirs(args.output_train, exist_ok=True)
+    print("%s created" % args.output_train)

how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/prepdata/cleanse.py

@@ -0,0 +1,58 @@
+# Copyright (c) Microsoft. All rights reserved.
+# Licensed under the MIT license.
+
+import argparse
+import os
+import pandas as pd
+import azureml.dataprep as dprep
+
+
+def get_dict(dict_str):
+    pairs = dict_str.strip("{}").split("\;")
+    new_dict = {}
+    for pair in pairs:
+        key, value = pair.strip('\\').split(":")
+        new_dict[key.strip().strip("'")] = value.strip().strip("'")
+
+    return new_dict
+
+
+print("Cleans the input data")
+
+parser = argparse.ArgumentParser("cleanse")
+parser.add_argument("--input_cleanse", type=str, help="raw taxi data")
+parser.add_argument("--output_cleanse", type=str, help="cleaned taxi data directory")
+parser.add_argument("--useful_columns", type=str, help="useful columns to keep")
+parser.add_argument("--columns", type=str, help="rename column pattern")
+
+args = parser.parse_args()
+
+print("Argument 1(input taxi data path): %s" % args.input_cleanse)
+print("Argument 2(columns to keep): %s" % str(args.useful_columns.strip("[]").split("\;")))
+print("Argument 3(columns renaming mapping): %s" % str(args.columns.strip("{}").split("\;")))
+print("Argument 4(output cleansed taxi data path): %s" % args.output_cleanse)
+
+raw_df = dprep.read_csv(path=args.input_cleanse, header=dprep.PromoteHeadersMode.GROUPED)
+
+# These functions ensure that null data is removed from the data set,
+# which will help increase machine learning model accuracy.
+# Visit https://docs.microsoft.com/en-us/azure/machine-learning/service/tutorial-data-prep
+# for more details
+
+useful_columns = [s.strip().strip("'") for s in args.useful_columns.strip("[]").split("\;")]
+columns = get_dict(args.columns)
+
+all_columns = dprep.ColumnSelector(term=".*", use_regex=True)
+drop_if_all_null = [all_columns, dprep.ColumnRelationship(dprep.ColumnRelationship.ALL)]
+
+new_df = (raw_df
+          .replace_na(columns=all_columns)
+          .drop_nulls(*drop_if_all_null)
+          .rename_columns(column_pairs=columns)
+          .keep_columns(columns=useful_columns))
+
+if not (args.output_cleanse is None):
+    os.makedirs(args.output_cleanse, exist_ok=True)
+    print("%s created" % args.output_cleanse)
+    write_df = new_df.write_to_csv(directory_path=dprep.LocalFileOutput(args.output_cleanse))
+    write_df.run_local()

how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/prepdata/filter.py

@@ -0,0 +1,55 @@
+import argparse
+import os
+import azureml.dataprep as dprep
+
+print("Filters out coordinates for locations that are outside the city border.",
+      "Chain the column filter commands within the filter() function",
+      "and define the minimum and maximum bounds for each field.")
+
+parser = argparse.ArgumentParser("filter")
+parser.add_argument("--input_filter", type=str, help="merged taxi data directory")
+parser.add_argument("--output_filter", type=str, help="filter out out of city locations")
+
+args = parser.parse_args()
+
+print("Argument 1(input taxi data path): %s" % args.input_filter)
+print("Argument 2(output filtered taxi data path): %s" % args.output_filter)
+
+combined_df = dprep.read_csv(args.input_filter + '/part-*')
+
+# These functions filter out coordinates for locations that are outside the city border.
+# Visit https://docs.microsoft.com/en-us/azure/machine-learning/service/tutorial-data-prep for more details
+
+# Create a condensed view of the dataflow to just show the lat/long fields,
+# which makes it easier to evaluate missing or out-of-scope coordinates
+decimal_type = dprep.TypeConverter(data_type=dprep.FieldType.DECIMAL)
+combined_df = combined_df.set_column_types(type_conversions={
+    "pickup_longitude": decimal_type,
+    "pickup_latitude": decimal_type,
+    "dropoff_longitude": decimal_type,
+    "dropoff_latitude": decimal_type
+})
+
+# Filter out coordinates for locations that are outside the city border.
+# Chain the column filter commands within the filter() function
+# and define the minimum and maximum bounds for each field
+latlong_filtered_df = (combined_df
+                       .drop_nulls(columns=["pickup_longitude",
+                                            "pickup_latitude",
+                                            "dropoff_longitude",
+                                            "dropoff_latitude"],
+                                   column_relationship=dprep.ColumnRelationship(dprep.ColumnRelationship.ANY))
+                       .filter(dprep.f_and(dprep.col("pickup_longitude") <= -73.72,
+                                           dprep.col("pickup_longitude") >= -74.09,
+                                           dprep.col("pickup_latitude") <= 40.88,
+                                           dprep.col("pickup_latitude") >= 40.53,
+                                           dprep.col("dropoff_longitude") <= -73.72,
+                                           dprep.col("dropoff_longitude") >= -74.09,
+                                           dprep.col("dropoff_latitude") <= 40.88,
+                                           dprep.col("dropoff_latitude") >= 40.53)))
+
+if not (args.output_filter is None):
+    os.makedirs(args.output_filter, exist_ok=True)
+    print("%s created" % args.output_filter)
+    write_df = latlong_filtered_df.write_to_csv(directory_path=dprep.LocalFileOutput(args.output_filter))
+    write_df.run_local()

how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/prepdata/merge.py

@@ -0,0 +1,29 @@
+
+import argparse
+import os
+import azureml.dataprep as dprep
+
+print("Merge Green and Yellow taxi data")
+
+parser = argparse.ArgumentParser("merge")
+parser.add_argument("--input_green_merge", type=str, help="cleaned green taxi data directory")
+parser.add_argument("--input_yellow_merge", type=str, help="cleaned yellow taxi data directory")
+parser.add_argument("--output_merge", type=str, help="green and yellow taxi data merged")
+
+args = parser.parse_args()
+
+print("Argument 1(input green taxi data path): %s" % args.input_green_merge)
+print("Argument 2(input yellow taxi data path): %s" % args.input_yellow_merge)
+print("Argument 3(output merge taxi data path): %s" % args.output_merge)
+
+green_df = dprep.read_csv(args.input_green_merge + '/part-*')
+yellow_df = dprep.read_csv(args.input_yellow_merge + '/part-*')
+
+# Appending yellow data to green data
+combined_df = green_df.append_rows([yellow_df])
+
+if not (args.output_merge is None):
+    os.makedirs(args.output_merge, exist_ok=True)
+    print("%s created" % args.output_merge)
+    write_df = combined_df.write_to_csv(directory_path=dprep.LocalFileOutput(args.output_merge))
+    write_df.run_local()

how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/prepdata/normalize.py

@@ -0,0 +1,47 @@
+import argparse
+import os
+import azureml.dataprep as dprep
+
+print("Replace undefined values to relavant values and rename columns to meaningful names")
+
+parser = argparse.ArgumentParser("normalize")
+parser.add_argument("--input_normalize", type=str, help="combined and converted taxi data")
+parser.add_argument("--output_normalize", type=str, help="replaced undefined values and renamed columns")
+
+args = parser.parse_args()
+
+print("Argument 1(input taxi data path): %s" % args.input_normalize)
+print("Argument 2(output normalized taxi data path): %s" % args.output_normalize)
+
+combined_converted_df = dprep.read_csv(args.input_normalize + '/part-*')
+
+# These functions replace undefined values and rename to use meaningful names.
+# Visit https://docs.microsoft.com/en-us/azure/machine-learning/service/tutorial-data-prep for more details
+
+replaced_stfor_vals_df = combined_converted_df.replace(columns="store_forward",
+                                                       find="0",
+                                                       replace_with="N").fill_nulls("store_forward", "N")
+
+replaced_distance_vals_df = replaced_stfor_vals_df.replace(columns="distance",
+                                                           find=".00",
+                                                           replace_with=0).fill_nulls("distance", 0)
+
+replaced_distance_vals_df = replaced_distance_vals_df.to_number(["distance"])
+
+time_split_df = (replaced_distance_vals_df
+                 .split_column_by_example(source_column="pickup_datetime")
+                 .split_column_by_example(source_column="dropoff_datetime"))
+
+# Split the pickup and dropoff datetime values into the respective date and time columns
+renamed_col_df = (time_split_df
+                  .rename_columns(column_pairs={
+                      "pickup_datetime_1": "pickup_date",
+                      "pickup_datetime_2": "pickup_time",
+                      "dropoff_datetime_1": "dropoff_date",
+                      "dropoff_datetime_2": "dropoff_time"}))
+
+if not (args.output_normalize is None):
+    os.makedirs(args.output_normalize, exist_ok=True)
+    print("%s created" % args.output_normalize)
+    write_df = renamed_col_df.write_to_csv(directory_path=dprep.LocalFileOutput(args.output_normalize))
+    write_df.run_local()

how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/prepdata/transform.py

@@ -0,0 +1,88 @@
+import argparse
+import os
+import azureml.dataprep as dprep
+
+print("Transforms the renamed taxi data to the required format")
+
+parser = argparse.ArgumentParser("transform")
+parser.add_argument("--input_transform", type=str, help="renamed taxi data")
+parser.add_argument("--output_transform", type=str, help="transformed taxi data")
+
+args = parser.parse_args()
+
+print("Argument 1(input taxi data path): %s" % args.input_transform)
+print("Argument 2(output final transformed taxi data): %s" % args.output_transform)
+
+renamed_df = dprep.read_csv(args.input_transform + '/part-*')
+
+# These functions transform the renamed data to be used finally for training.
+# Visit https://docs.microsoft.com/en-us/azure/machine-learning/service/tutorial-data-prep for more details
+
+# Split the pickup and dropoff date further into the day of the week, day of the month, and month values.
+# To get the day of the week value, use the derive_column_by_example() function.
+# The function takes an array parameter of example objects that define the input data,
+# and the preferred output. The function automatically determines your preferred transformation.
+# For the pickup and dropoff time columns, split the time into the hour, minute, and second by using
+# the split_column_by_example() function with no example parameter. After you generate the new features,
+# use the drop_columns() function to delete the original fields as the newly generated features are preferred.
+# Rename the rest of the fields to use meaningful descriptions.
+
+transformed_features_df = (renamed_df
+                           .derive_column_by_example(
+                               source_columns="pickup_date",
+                               new_column_name="pickup_weekday",
+                               example_data=[("2009-01-04", "Sunday"), ("2013-08-22", "Thursday")])
+                           .derive_column_by_example(
+                               source_columns="dropoff_date",
+                               new_column_name="dropoff_weekday",
+                               example_data=[("2013-08-22", "Thursday"), ("2013-11-03", "Sunday")])
+
+                           .split_column_by_example(source_column="pickup_time")
+                           .split_column_by_example(source_column="dropoff_time")
+
+                           .split_column_by_example(source_column="pickup_time_1")
+                           .split_column_by_example(source_column="dropoff_time_1")
+                           .drop_columns(columns=[
+                               "pickup_date", "pickup_time", "dropoff_date", "dropoff_time",
+                               "pickup_date_1", "dropoff_date_1", "pickup_time_1", "dropoff_time_1"])
+
+                           .rename_columns(column_pairs={
+                               "pickup_date_2": "pickup_month",
+                               "pickup_date_3": "pickup_monthday",
+                               "pickup_time_1_1": "pickup_hour",
+                               "pickup_time_1_2": "pickup_minute",
+                               "pickup_time_2": "pickup_second",
+                               "dropoff_date_2": "dropoff_month",
+                               "dropoff_date_3": "dropoff_monthday",
+                               "dropoff_time_1_1": "dropoff_hour",
+                               "dropoff_time_1_2": "dropoff_minute",
+                               "dropoff_time_2": "dropoff_second"}))
+
+# Drop the pickup_datetime and dropoff_datetime columns because they're
+# no longer needed (granular time features like hour,
+# minute and second are more useful for model training).
+processed_df = transformed_features_df.drop_columns(columns=["pickup_datetime", "dropoff_datetime"])
+
+# Use the type inference functionality to automatically check the data type of each field,
+# and display the inference results.
+type_infer = processed_df.builders.set_column_types()
+type_infer.learn()
+
+# The inference results look correct based on the data. Now apply the type conversions to the dataflow.
+type_converted_df = type_infer.to_dataflow()
+
+# Before you package the dataflow, run two final filters on the data set.
+# To eliminate incorrectly captured data points,
+# filter the dataflow on records where both the cost and distance variable values are greater than zero.
+# This step will significantly improve machine learning model accuracy,
+# because data points with a zero cost or distance represent major outliers that throw off prediction accuracy.
+
+final_df = type_converted_df.filter(dprep.col("distance") > 0)
+final_df = final_df.filter(dprep.col("cost") > 0)
+
+# Writing the final dataframe to use for training in the following steps
+if not (args.output_transform is None):
+    os.makedirs(args.output_transform, exist_ok=True)
+    print("%s created" % args.output_transform)
+    write_df = final_df.write_to_csv(directory_path=dprep.LocalFileOutput(args.output_transform))
+    write_df.run_local()

how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/trainmodel/featurization.py

@@ -0,0 +1,31 @@
+import argparse
+import os
+import azureml.dataprep as dprep
+import azureml.core
+
+print("Extracts important features from prepared data")
+
+parser = argparse.ArgumentParser("featurization")
+parser.add_argument("--input_featurization", type=str, help="input featurization")
+parser.add_argument("--useful_columns", type=str, help="columns to use")
+parser.add_argument("--output_featurization", type=str, help="output featurization")
+
+args = parser.parse_args()
+
+print("Argument 1(input training data path): %s" % args.input_featurization)
+print("Argument 2(column features to use): %s" % str(args.useful_columns.strip("[]").split("\;")))
+print("Argument 3:(output featurized training data path) %s" % args.output_featurization)
+
+dflow_prepared = dprep.read_csv(args.input_featurization + '/part-*')
+
+# These functions extracts useful features for training
+# Visit https://docs.microsoft.com/en-us/azure/machine-learning/service/tutorial-auto-train-models for more detail
+
+useful_columns = [s.strip().strip("'") for s in args.useful_columns.strip("[]").split("\;")]
+dflow = dflow_prepared.keep_columns(useful_columns)
+
+if not (args.output_featurization is None):
+    os.makedirs(args.output_featurization, exist_ok=True)
+    print("%s created" % args.output_featurization)
+    write_df = dflow.write_to_csv(directory_path=dprep.LocalFileOutput(args.output_featurization))
+    write_df.run_local()

how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/trainmodel/get_data.py

@@ -0,0 +1,12 @@
+
+import os
+import pandas as pd
+
+
+def get_data():
+    print("In get_data")
+    print(os.environ['AZUREML_DATAREFERENCE_output_split_train_x'])
+    X_train = pd.read_csv(os.environ['AZUREML_DATAREFERENCE_output_split_train_x'] + "/part-00000", header=0)
+    y_train = pd.read_csv(os.environ['AZUREML_DATAREFERENCE_output_split_train_y'] + "/part-00000", header=0)
+
+    return {"X": X_train.values, "y": y_train.values.flatten()}

how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/trainmodel/train_test_split.py

@@ -0,0 +1,48 @@
+import argparse
+import os
+import azureml.dataprep as dprep
+import azureml.core
+from sklearn.model_selection import train_test_split
+
+
+def write_output(df, path):
+    os.makedirs(path, exist_ok=True)
+    print("%s created" % path)
+    df.to_csv(path + "/part-00000", index=False)
+
+
+print("Split the data into train and test")
+
+parser = argparse.ArgumentParser("split")
+parser.add_argument("--input_split_features", type=str, help="input split features")
+parser.add_argument("--input_split_labels", type=str, help="input split labels")
+parser.add_argument("--output_split_train_x", type=str, help="output split train features")
+parser.add_argument("--output_split_train_y", type=str, help="output split train labels")
+parser.add_argument("--output_split_test_x", type=str, help="output split test features")
+parser.add_argument("--output_split_test_y", type=str, help="output split test labels")
+
+args = parser.parse_args()
+
+print("Argument 1(input taxi data features path): %s" % args.input_split_features)
+print("Argument 2(input taxi data labels path): %s" % args.input_split_labels)
+print("Argument 3(output training features split path): %s" % args.output_split_train_x)
+print("Argument 4(output training labels split path): %s" % args.output_split_train_y)
+print("Argument 5(output test features split path): %s" % args.output_split_test_x)
+print("Argument 6(output test labels split path): %s" % args.output_split_test_y)
+
+x_df = dprep.read_csv(path=args.input_split_features, header=dprep.PromoteHeadersMode.GROUPED).to_pandas_dataframe()
+y_df = dprep.read_csv(path=args.input_split_labels, header=dprep.PromoteHeadersMode.GROUPED).to_pandas_dataframe()
+
+# These functions splits the input features and labels into test and train data
+# Visit https://docs.microsoft.com/en-us/azure/machine-learning/service/tutorial-auto-train-models for more detail
+
+x_train, x_test, y_train, y_test = train_test_split(x_df, y_df, test_size=0.2, random_state=223)
+
+if not (args.output_split_train_x is None and
+        args.output_split_test_x is None and
+        args.output_split_train_y is None and
+        args.output_split_test_y is None):
+    write_output(x_train, args.output_split_train_x)
+    write_output(y_train, args.output_split_train_y)
+    write_output(x_test, args.output_split_test_x)
+    write_output(y_test, args.output_split_test_y)

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

@@ -162,7 +162,7 @@
       "metadata": {},
       "source": [
         "### Create and attach Compute targets\n",
-        "Use the below code to get the default Compute target. "
+        "Use the below code to create and attach Compute targets. "
       ]
     },
     {
@@ -171,9 +171,33 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "cluster_type = os.environ.get(\"AML_CLUSTER_TYPE\", \"GPU\")\n",
+        "# choose a name for your cluster\n",
+        "aml_compute_name = os.environ.get(\"AML_COMPUTE_NAME\", \"gpu-cluster\")\n",
+        "cluster_min_nodes = os.environ.get(\"AML_COMPUTE_MIN_NODES\", 0)\n",
+        "cluster_max_nodes = os.environ.get(\"AML_COMPUTE_MAX_NODES\", 1)\n",
+        "vm_size = os.environ.get(\"AML_COMPUTE_SKU\", \"STANDARD_NC6\")\n",
         "\n",
-        "compute_target = ws.get_default_compute_target(cluster_type)"
+        "\n",
+        "if aml_compute_name in ws.compute_targets:\n",
+        "    compute_target = ws.compute_targets[aml_compute_name]\n",
+        "    if compute_target and type(compute_target) is AmlCompute:\n",
+        "        print('found compute target. just use it. ' + aml_compute_name)\n",
+        "else:\n",
+        "    print('creating a new compute target...')\n",
+        "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = vm_size, # NC6 is GPU-enabled\n",
+        "                                                                vm_priority = 'lowpriority', # optional\n",
+        "                                                                min_nodes = cluster_min_nodes, \n",
+        "                                                                max_nodes = cluster_max_nodes)\n",
+        "\n",
+        "    # create the cluster\n",
+        "    compute_target = ComputeTarget.create(ws, aml_compute_name, provisioning_config)\n",
+        "    \n",
+        "    # can poll for a minimum number of nodes and for a specific timeout. \n",
+        "    # if no min node count is provided it will use the scale settings for the cluster\n",
+        "    compute_target.wait_for_completion(show_output=True, min_node_count=None, timeout_in_minutes=20)\n",
+        "    \n",
+        "     # For a more detailed view of current Azure Machine Learning Compute  status, use get_status()\n",
+        "    print(compute_target.get_status().serialize())"
       ]
     },
     {

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

@@ -94,7 +94,7 @@
       "outputs": [],
       "source": [
         "# AmlCompute\n",
-        "cpu_cluster_name = \"cpucluster\"\n",
+        "cpu_cluster_name = \"cpu-cluster\"\n",
         "try:\n",
         "    cpu_cluster = AmlCompute(ws, cpu_cluster_name)\n",
         "    print(\"found existing cluster.\")\n",
@@ -108,7 +108,7 @@
         "    cpu_cluster.wait_for_completion(show_output=True)\n",
         "    \n",
         "# AmlCompute\n",
-        "gpu_cluster_name = \"gpucluster\"\n",
+        "gpu_cluster_name = \"gpu-cluster\"\n",
         "try:\n",
         "    gpu_cluster = AmlCompute(ws, gpu_cluster_name)\n",
         "    print(\"found existing cluster.\")\n",
@@ -351,7 +351,6 @@
         "    inputs=[models_dir, ffmpeg_images],\n",
         "    outputs=[processed_images],\n",
         "    pip_packages=[\"mpi4py\", \"torch\", \"torchvision\"],\n",
-        "    runconfig=amlcompute_run_config,\n",
         "    use_gpu=True,\n",
         "    source_directory=scripts_folder\n",
         ")\n",

how-to-use-azureml/manage-azureml-service/authentication-in-azureml/authentication-in-azure-ml.ipynb

@@ -19,12 +19,12 @@
         "The interactive authentication is suitable for local experimentation on your own computer. Azure CLI authentication is suitable if you are already using Azure CLI for managing Azure resources, and want to sign in only once. The Service Principal authentication is suitable for automated workflows, for example as part of Azure Devops build."
       ]
     },
-     {
+    {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-          "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/manage-azureml-service/authentication-in-azureml/authentication-in-azureml.png)"
-         ] 
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/manage-azureml-service/authentication-in-azureml/authentication-in-azureml.png)"
+      ]
     },
     {
       "cell_type": "code",

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

@@ -95,8 +95,10 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Get default AmlCompute\n",
-        "You can 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 gets the default compute cluster.\n",
+        "## 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."
       ]
@@ -107,7 +109,24 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "compute_target = ws.get_default_compute_target(type=\"GPU\")\n",
+        "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 = \"gpu-cluster\"\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())"
@@ -117,7 +136,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "The above code retrieves the default GPU compute. If you instead want to use default CPU compute, provide type=\"CPU\"."
+        "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`."
       ]
     },
     {
@@ -223,7 +242,7 @@
       "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, you must provide the argument `distributed_training=MpiConfiguration()`. Using this estimator with these settings, Chainer and its dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `Chainer` constructor's `pip_packages` or `conda_packages` parameters."
+        "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, you must provide the argument `distributed_backend='mpi'`. Using this estimator with these settings, Chainer and its dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `Chainer` constructor's `pip_packages` or `conda_packages` parameters."
       ]
     },
     {

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

@@ -98,8 +98,10 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Get default AmlCompute\n",
-        "You can 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 default `AmlCompute` as the training compute resource.\n",
+        "## 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."
       ]
@@ -110,7 +112,24 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "compute_target = ws.get_default_compute_target(type=\"GPU\")\n",
+        "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 = \"gpu-cluster\"\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())"
@@ -270,7 +289,6 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.core.runconfig import MpiConfiguration\n",
         "from azureml.train.estimator import Estimator\n",
         "\n",
         "script_params = {\n",
@@ -284,7 +302,8 @@
         "                      entry_script='cntk_distr_mnist.py',\n",
         "                      script_params=script_params,\n",
         "                      node_count=2,\n",
-        "                      distributed_training=MpiConfiguration(),\n",
+        "                      process_count_per_node=1,\n",
+        "                      distributed_backend='mpi',\n",
         "                      pip_packages=['cntk-gpu==2.6'],\n",
         "                      custom_docker_image='microsoft/mmlspark:gpu-0.12',\n",
         "                      use_gpu=True)"
@@ -296,7 +315,7 @@
       "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_image`. 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_training=MpiConfiguration()`."
+        "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'`."
       ]
     },
     {

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

@@ -96,8 +96,10 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Get default AmlCompute\n",
-        "You can 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 uses the default compute in the workspace.\n",
+        "## 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."
       ]
@@ -108,7 +110,24 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "compute_target = ws.get_default_compute_target(type=\"GPU\")\n",
+        "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 = \"gpu-cluster\"\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())"
@@ -118,7 +137,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "The above code retrieves the default GPU compute. If you instead want to use default CPU compute, provide type=\"CPU\"."
+        "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`."
       ]
     },
     {
@@ -236,7 +255,7 @@
       "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_training=MpiConfiguration()`. 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."
+        "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."
       ]
     },
     {

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

@@ -98,8 +98,10 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Get default AmlCompute\n",
-        "You can 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 use default `AmlCompute` as your training compute resource.\n",
+        "## 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."
       ]
@@ -110,7 +112,24 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "compute_target = ws.get_default_compute_target(\"GPU\")\n",
+        "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 = \"gpu-cluster\"\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())"
@@ -120,7 +139,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "The above code retrieves the default GPU compute. If you instead want to use default CPU compute, provide type=\"CPU\"."
+        "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`."
       ]
     },
     {
@@ -304,7 +323,7 @@
       "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_training=MpiConfiguration()`. 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",
+        "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."
       ]

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

@@ -98,8 +98,10 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Get default AmlCompute\n",
-        "You can 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 use default `AmlCompute` as your training compute resource.\n",
+        "## 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."
       ]
@@ -110,7 +112,24 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "compute_target = ws.get_default_compute_target(type=\"GPU\")\n",
+        "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 = \"gpu-cluster\"\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())"
@@ -220,7 +239,7 @@
       "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_training=TensorflowConfiguration()`. 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."
+        "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."
       ]
     },
     {

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

@@ -9,8 +9,16 @@ print("Hello Azure ML!")
 parser = argparse.ArgumentParser()
 parser.add_argument('--numbers-in-sequence', type=int, dest='num_in_sequence', default=10,
                     help='number of fibonacci numbers in sequence')
+
+# This is how you can use a bool argument in Python. If you want the 'my_bool_var' to be True, just pass it
+# in Estimator's script_param as script+params:{'my_bool_var': ''}.
+# And, if you want to use it as False, then do not pass it in the Estimator's script_params.
+# You can reverse the behavior by setting action='store_false' in the next line.
+parser.add_argument("--my_bool_var", action='store_true')
+
 args = parser.parse_args()
 num = args.num_in_sequence
+my_bool_var = args.my_bool_var
 
 
 def fibo(n):
@@ -23,6 +31,7 @@ def fibo(n):
 try:
     from azureml.core import Run
     run = Run.get_context()
+    print("The value of boolean parameter 'my_bool_var' is {}".format(my_bool_var))
     print("Log Fibonacci numbers.")
     for i in range(0, num - 1):
         run.log('Fibonacci numbers', fibo(i))

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

@@ -113,8 +113,18 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Get default AmlCompute\n",
-        "You can 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 use default `AmlCompute` as your training compute resource."
+        "## 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"
       ]
     },
     {
@@ -123,7 +133,25 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "cpu_cluster = ws.get_default_compute_target(\"CPU\")\n",
+        "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 = \"cpu-cluster\"\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())"
@@ -207,8 +235,11 @@
       "outputs": [],
       "source": [
         "# use a conda environment, don't use Docker, on local computer\n",
+        "# Let's see how you can pass bool arguments in the script_params. Passing `'--my_bool_var': ''` will set my_bool_var as True and\n",
+        "# if you want it to be False, just do not pass it in the script_params.\n",
         "script_params = {\n",
-        "    '--numbers-in-sequence': 10\n",
+        "    '--numbers-in-sequence': 10,\n",
+        "    '--my_bool_var': ''\n",
         "}\n",
         "est = Estimator(source_directory='.', script_params=script_params, compute_target='local', entry_script='dummy_train.py', use_docker=False)\n",
         "run = exp.submit(est)\n",
@@ -268,7 +299,7 @@
       "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",
+        "You can also specify a custom Docker image for execution. 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. If custom Docker image information is not specified, Azure ML uses the default Docker image to run your training. For more information about Docker containers used in Azure ML training, please see [Azure ML Containers repository](https://github.com/Azure/AzureML-Containers).\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. "
       ]

how-to-use-azureml/training-with-deep-learning/train-hyperparameter-tune-deploy-with-chainer/train-hyperparameter-tune-deploy-with-chainer.ipynb

@@ -95,8 +95,10 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Get default AmlCompute\n",
-        "You can 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.\n",
+        "## 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.\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."
       ]
@@ -107,7 +109,24 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "compute_target = ws.get_default_compute_target(type=\"GPU\")\n",
+        "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 = \"gpu-cluster\"\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())"
@@ -117,7 +136,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "The above code retrieves the default GPU compute. If you instead want to use default CPU compute, provide type=\"CPU\"."
+        "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`."
       ]
     },
     {

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

@@ -239,8 +239,18 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Get default AmlCompute\n",
-        "You can 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 use default `AmlCompute` as your training compute resource."
+        "## 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"
       ]
     },
     {
@@ -249,7 +259,26 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "compute_target = ws.get_default_compute_target(type=\"GPU\")\n",
+        "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 = \"gpu-cluster\"\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",
+        "    # 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",
+        "    compute_target.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(compute_target.get_status().serialize())"
@@ -259,7 +288,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Now that you have retrtieved the compute target, let's see what the workspace's `compute_targets` property returns."
+        "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 \"gpu-cluster\" of type `AmlCompute`."
       ]
     },
     {
@@ -351,7 +380,7 @@
       "metadata": {},
       "source": [
         "## Create TensorFlow estimator & add Keras\n",
-        "Next, we construct an `azureml.train.dnn.TensorFlow` estimator object, use the `gpucluster` as compute target, and pass the mount-point of the datastore to the training code as a parameter.\n",
+        "Next, we construct an `azureml.train.dnn.TensorFlow` estimator object, use the `gpu-cluster` as compute target, and pass the mount-point of the datastore to the training code as a parameter.\n",
         "The TensorFlow estimator is providing a simple way of launching a TensorFlow training job on a compute target. It will automatically provide a docker image that has TensorFlow installed. In this case, we add `keras` package (for the Keras framework obviously), and `matplotlib` package for plotting a \"Loss vs. Accuracy\" chart and record it in run history."
       ]
     },
@@ -524,7 +553,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "In the training script, the Keras model is saved into two files, `model.json` and `model.h5`, in the `outputs/models` folder on the gpucluster AmlCompute node. Azure ML automatically uploaded anything written in the `./outputs` folder into run history file store. Subsequently, we can use the `run` object to download the model files. They are under the the `outputs/model` folder in the run history file store, and are downloaded into a local folder named `model`."
+        "In the training script, the Keras model is saved into two files, `model.json` and `model.h5`, in the `outputs/models` folder on the gpu-cluster AmlCompute node. Azure ML automatically uploaded anything written in the `./outputs` folder into run history file store. Subsequently, we can use the `run` object to download the model files. They are under the the `outputs/model` folder in the run history file store, and are downloaded into a local folder named `model`."
       ]
     },
     {

how-to-use-azureml/training-with-deep-learning/train-hyperparameter-tune-deploy-with-pytorch/train-hyperparameter-tune-deploy-with-pytorch.ipynb

@@ -9,12 +9,12 @@
         "Licensed under the MIT License."
       ]
     },
-     {
+    {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-          "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/training-with-deep-learning/train-hyperparameter-tune-deploy-with-pytorch/train-hyperparameter-tune-deploy-with-pytorch.png)"
-         ] 
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/training-with-deep-learning/train-hyperparameter-tune-deploy-with-pytorch/train-hyperparameter-tune-deploy-with-pytorch.png)"
+      ]
     },
     {
       "cell_type": "markdown",
@@ -115,7 +115,7 @@
         "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# choose a name for your cluster\n",
-        "cluster_name = \"gpucluster\"\n",
+        "cluster_name = \"gpu-cluster\"\n",
         "\n",
         "try:\n",
         "    compute_target = ComputeTarget(workspace=ws, name=cluster_name)\n",
@@ -264,7 +264,8 @@
         "                    script_params=script_params,\n",
         "                    compute_target=compute_target,\n",
         "                    entry_script='pytorch_train.py',\n",
-        "                    use_gpu=True)"
+        "                    use_gpu=True,\n",
+        "                    pip_packages=['pillow==5.4.1'])"
       ]
     },
     {
@@ -366,7 +367,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.train.hyperdrive import RandomParameterSampling, BanditPolicy, HyperDriveRunConfig, uniform, PrimaryMetricGoal\n",
+        "from azureml.train.hyperdrive import RandomParameterSampling, BanditPolicy, HyperDriveConfig, uniform, PrimaryMetricGoal\n",
         "\n",
         "param_sampling = RandomParameterSampling( {\n",
         "        'learning_rate': uniform(0.0005, 0.005),\n",
@@ -376,13 +377,13 @@
         "\n",
         "early_termination_policy = BanditPolicy(slack_factor=0.15, evaluation_interval=1, delay_evaluation=10)\n",
         "\n",
-        "hyperdrive_run_config = HyperDriveRunConfig(estimator=estimator,\n",
-        "                                            hyperparameter_sampling=param_sampling, \n",
-        "                                            policy=early_termination_policy,\n",
-        "                                            primary_metric_name='best_val_acc',\n",
-        "                                            primary_metric_goal=PrimaryMetricGoal.MAXIMIZE,\n",
-        "                                            max_total_runs=8,\n",
-        "                                            max_concurrent_runs=4)"
+        "hyperdrive_config = HyperDriveConfig(estimator=estimator,\n",
+        "                                     hyperparameter_sampling=param_sampling, \n",
+        "                                     policy=early_termination_policy,\n",
+        "                                     primary_metric_name='best_val_acc',\n",
+        "                                     primary_metric_goal=PrimaryMetricGoal.MAXIMIZE,\n",
+        "                                     max_total_runs=8,\n",
+        "                                     max_concurrent_runs=4)"
       ]
     },
     {
@@ -399,7 +400,7 @@
       "outputs": [],
       "source": [
         "# start the HyperDrive run\n",
-        "hyperdrive_run = experiment.submit(hyperdrive_run_config)"
+        "hyperdrive_run = experiment.submit(hyperdrive_config)"
       ]
     },
     {

how-to-use-azureml/training-with-deep-learning/train-hyperparameter-tune-deploy-with-tensorflow/train-hyperparameter-tune-deploy-with-tensorflow.ipynb

@@ -261,8 +261,18 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Get default AmlCompute\n",
-        "You can 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 use default `AmlCompute` as your training compute resource."
+        "## 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"
       ]
     },
     {
@@ -271,7 +281,26 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "compute_target = ws.get_default_compute_target(type=\"GPU\")\n",
+        "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 = \"gpu-cluster\"\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",
+        "    # 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",
+        "    compute_target.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(compute_target.get_status().serialize())"
@@ -281,7 +310,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Now that you have retrieved the compute target, let's see what the workspace's `compute_targets` property returns."
+        "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 'gpu-cluster' of type `AmlCompute`."
       ]
     },
     {

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

@@ -100,7 +100,7 @@
         "\n",
         "# Check core SDK version number\n",
         "\n",
-        "print(\"This notebook was created using SDK version 1.0.43, you are currently running version\", azureml.core.VERSION)"
+        "print(\"This notebook was created using SDK version 1.0.45, you are currently running version\", azureml.core.VERSION)"
       ]
     },
     {

how-to-use-azureml/training/train-hyperparameter-tune-deploy-with-sklearn/train-hyperparameter-tune-deploy-with-sklearn.ipynb

@@ -108,7 +108,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Get default AmlCompute"
+        "## Create AmlCompute"
       ]
     },
     {
@@ -126,7 +126,24 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "compute_target = ws.get_default_compute_target(type=\"CPU\")\n",
+        "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 = \"gpu-cluster\"\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())"
@@ -136,7 +153,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "The above code retrieves the default CPU compute."
+        "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`."
       ]
     },
     {

how-to-use-azureml/training/train-hyperparameter-tune-deploy-with-sklearn/train_iris.py

@@ -22,7 +22,7 @@ def main():
                         help='Penalty parameter of the error term')
 
     args = parser.parse_args()
-    run.log('Kernel type', np.string(args.kernel))
+    run.log('Kernel type', np.str(args.kernel))
     run.log('Penalty', np.float(args.penalty))
 
     # loading the iris dataset

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

@@ -188,79 +188,6 @@
         "myenv.python.conda_dependencies = CondaDependencies.create(conda_packages=['scikit-learn'])"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Get the default compute target\n",
-        "\n",
-        "In this case, we use the default `AmlCompute`target from the workspace."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core import ScriptRunConfig\n",
-        "from azureml.core.runconfig import DEFAULT_CPU_IMAGE\n",
-        "\n",
-        "src = ScriptRunConfig(source_directory=project_folder, script='train.py')\n",
-        "\n",
-        "# Use default compute target\n",
-        "src.run_config.target = ws.get_default_compute_target(type=\"CPU\").name\n",
-        "\n",
-        "# Set environment\n",
-        "src.run_config.environment = myenv"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Submit run"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "run = experiment.submit(src)\n",
-        "\n",
-        "# Show run details\n",
-        "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": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "%%time\n",
-        "# Shows output of the run on stdout.\n",
-        "run.wait_for_completion(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "run.get_metrics()"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -283,7 +210,7 @@
         "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# Choose a name for your CPU cluster\n",
-        "cpu_cluster_name = \"cpucluster\"\n",
+        "cpu_cluster_name = \"cpu-cluster\"\n",
         "\n",
         "# Verify that cluster does not exist already\n",
         "try:\n",
@@ -310,13 +237,28 @@
       "metadata": {},
       "outputs": [],
       "source": [
+        "from azureml.core import ScriptRunConfig\n",
+        "from azureml.core.runconfig import DEFAULT_CPU_IMAGE\n",
+        "\n",
+        "src = ScriptRunConfig(source_directory=project_folder, script='train.py')\n",
+        "\n",
         "# Set compute target to the one created in previous step\n",
         "src.run_config.target = cpu_cluster.name\n",
+        "\n",
+        "# Set environment\n",
+        "src.run_config.environment = myenv\n",
         " \n",
         "run = experiment.submit(config=src)\n",
         "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": "code",
       "execution_count": null,
@@ -364,7 +306,7 @@
         "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# Choose a name for your CPU cluster\n",
-        "cpu_cluster_name = \"cpucluster\"\n",
+        "cpu_cluster_name = \"cpu-cluster\"\n",
         "\n",
         "# Verify that cluster does not exist already\n",
         "try:\n",
@@ -463,7 +405,7 @@
       "outputs": [],
       "source": [
         "#Delete () is used to deprovision and delete the AmlCompute target. Useful if you want to re-use the compute name \n",
-        "#'cpucluster' in this case but use a different VM family for instance.\n",
+        "#'cpu-cluster' in this case but use a different VM family for instance.\n",
         "\n",
         "#cpu_cluster.delete()"
       ]

how-to-use-azureml/using-mlflow/README.md

@@ -4,8 +4,8 @@
 
 Try out the sample notebooks:
 
-* [Use MLflow with Azure Machine Learning for local training run](./train-local/train-local.ipynb)
-* [Use MLflow with Azure Machine Learning for remote training run](./train-remote/train-remote.ipynb)
-* [Deploy Model as Azure Machine Learning web service using MLflow](./deploy-model/deploy-model.ipynb)
+* [Use MLflow with Azure Machine Learning for Local Training Run](./train-local/train-local.ipynb)
+* [Use MLflow with Azure Machine Learning for Remote Training Run](./train-remote/train-remote.ipynb)
+* [Deploy Model as Azure Machine Learning Web Service using MLflow](./deploy-model/deploy-model.ipynb)
 
 ![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/using-mlflow/README..png) 

how-to-use-azureml/using-mlflow/deploy-model/deploy-model.ipynb

@@ -1,322 +1,322 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-    "\n",
-    "Licensed under the MIT License."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/using-mlflow/deploy-model/deploy-model.png)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Deploy Model as Azure Machine Learning Web Service using MLflow\n",
-    "\n",
-    "This example shows you how to use mlflow together with Azure Machine Learning services for deploying a model as a web service. You'll learn how to:\n",
-    "\n",
-    " 1. Retrieve a previously trained scikit-learn model\n",
-    " 2. Create a Docker image from the model\n",
-    " 3. Deploy the model as a web service on Azure Container Instance\n",
-    " 4. Make a scoring request against the web service.\n",
-    "\n",
-    "## Prerequisites and Set-up\n",
-    "\n",
-    "This notebook requires you to first complete the [Use MLflow with Azure Machine Learning for Local Training Run](../train-local/train-local.ipnyb) or [Use MLflow with Azure Machine Learning for Remote Training Run](../train-remote/train-remote.ipnyb) notebook, so as to have an experiment run with uploaded model in your Azure Machine Learning Workspace.\n",
-    "\n",
-    "Also install following packages if you haven't already\n",
-    "\n",
-    "```\n",
-    "pip install azureml-mlflow pandas\n",
-    "```\n",
-    "\n",
-    "Then, import necessary packages:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import mlflow\n",
-    "import azureml.mlflow\n",
-    "import azureml.core\n",
-    "from azureml.core import Workspace\n",
-    "\n",
-    "# Check core SDK version number\n",
-    "print(\"SDK version:\", azureml.core.VERSION)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Connect to workspace and set MLflow tracking URI\n",
-    "\n",
-    "Setting the tracking URI is required for retrieving the model and creating an image using the MLflow APIs."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "ws = Workspace.from_config()\n",
-    "\n",
-    "mlflow.set_tracking_uri(ws.get_mlflow_tracking_uri())"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Retrieve model from previous run\n",
-    "\n",
-    "Let's retrieve the experiment from training notebook, and list the runs within that experiment."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "experiment_name = \"experiment-with-mlflow\"\n",
-    "exp = ws.experiments[experiment_name]\n",
-    "\n",
-    "runs = list(exp.get_runs())\n",
-    "runs"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Then, let's select the most recent training run and find its ID. You also need to specify the path in run history where the model was saved. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "runid = runs[0].id\n",
-    "model_save_path = \"model\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Create Docker image\n",
-    "\n",
-    "To create a Docker image with Azure Machine Learning for Model Management, use ```mlflow.azureml.build_image``` method. Specify the model path, your workspace, run ID and other parameters.\n",
-    "\n",
-    "MLflow automatically recognizes the model framework as scikit-learn, and creates the scoring logic and includes library dependencies for you.\n",
-    "\n",
-    "Note that the image creation can take several minutes."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import mlflow.azureml\n",
-    "\n",
-    "azure_image, azure_model = mlflow.azureml.build_image(model_uri=\"runs:/{}/{}\".format(runid, model_save_path),\n",
-    "                                                      workspace=ws,\n",
-    "                                                      model_name='diabetes-sklearn-model',\n",
-    "                                                      image_name='diabetes-sklearn-image',\n",
-    "                                                      synchronous=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Deploy web service\n",
-    "\n",
-    "Let's use Azure Machine Learning SDK to deploy the image as a web service. \n",
-    "\n",
-    "First, specify the deployment configuration. Azure Container Instance is a suitable choice for a quick dev-test deployment, while Azure Kubernetes Service is suitable for scalable production deployments.\n",
-    "\n",
-    "Then, deploy the image using Azure Machine Learning SDK's ```deploy_from_image``` method.\n",
-    "\n",
-    "Note that the deployment can take several minutes."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.webservice import AciWebservice, Webservice\n",
-    "\n",
-    "\n",
-    "aci_config = AciWebservice.deploy_configuration(cpu_cores=1, \n",
-    "                                                memory_gb=1, \n",
-    "                                                tags={\"method\" : \"sklearn\"}, \n",
-    "                                                description='Diabetes model',\n",
-    "                                                location='eastus2')\n",
-    "\n",
-    "\n",
-    "# Deploy the image to Azure Container Instances (ACI) for real-time serving\n",
-    "webservice = Webservice.deploy_from_image(\n",
-    "    image=azure_image, workspace=ws, name=\"diabetes-model-1\", deployment_config=aci_config)\n",
-    "\n",
-    "\n",
-    "webservice.wait_for_deployment(show_output=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Make a scoring request\n",
-    "\n",
-    "Let's take the first few rows of test data and score them using the web service"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "test_rows = [\n",
-    "    [0.01991321,  0.05068012,  0.10480869,  0.07007254, -0.03596778,\n",
-    "     -0.0266789 , -0.02499266, -0.00259226,  0.00371174,  0.04034337],\n",
-    "    [-0.01277963, -0.04464164,  0.06061839,  0.05285819,  0.04796534,\n",
-    "     0.02937467, -0.01762938,  0.03430886,  0.0702113 ,  0.00720652],\n",
-    "    [ 0.03807591,  0.05068012,  0.00888341,  0.04252958, -0.04284755,\n",
-    "     -0.02104223, -0.03971921, -0.00259226, -0.01811827,  0.00720652]]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "MLflow-based web service for scikit-learn model requires the data to be converted to Pandas DataFrame, and then serialized as JSON. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import json\n",
-    "import pandas as pd\n",
-    "\n",
-    "test_rows_as_json = pd.DataFrame(test_rows).to_json(orient=\"split\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Let's pass the conveted and serialized data to web service to get the predictions."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "predictions = webservice.run(test_rows_as_json)\n",
-    "\n",
-    "print(predictions)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can use the web service's scoring URI to make a raw HTTP request"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "webservice.scoring_uri"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can diagnose the web service using ```get_logs``` method."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "webservice.get_logs()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Next Steps\n",
-    "\n",
-    "Learn about [model management and inferencing in Azure Machine Learning service](https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-model-management-and-deployment)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "authors": [
-   {
-    "name": "rastala"
-   }
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/using-mlflow/deploy-model/deploy-model.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Deploy Model as Azure Machine Learning Web Service using MLflow\n",
+        "\n",
+        "This example shows you how to use mlflow together with Azure Machine Learning services for deploying a model as a web service. You'll learn how to:\n",
+        "\n",
+        " 1. Retrieve a previously trained scikit-learn model\n",
+        " 2. Create a Docker image from the model\n",
+        " 3. Deploy the model as a web service on Azure Container Instance\n",
+        " 4. Make a scoring request against the web service.\n",
+        "\n",
+        "## Prerequisites and Set-up\n",
+        "\n",
+        "This notebook requires you to first complete the [Use MLflow with Azure Machine Learning for Local Training Run](../train-local/train-local.ipnyb) or [Use MLflow with Azure Machine Learning for Remote Training Run](../train-remote/train-remote.ipnyb) notebook, so as to have an experiment run with uploaded model in your Azure Machine Learning Workspace.\n",
+        "\n",
+        "Also install following packages if you haven't already\n",
+        "\n",
+        "```\n",
+        "pip install azureml-mlflow pandas\n",
+        "```\n",
+        "\n",
+        "Then, import necessary packages:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import mlflow\n",
+        "import azureml.mlflow\n",
+        "import azureml.core\n",
+        "from azureml.core import Workspace\n",
+        "\n",
+        "# Check core SDK version number\n",
+        "print(\"SDK version:\", azureml.core.VERSION)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Connect to workspace and set MLflow tracking URI\n",
+        "\n",
+        "Setting the tracking URI is required for retrieving the model and creating an image using the MLflow APIs."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "mlflow.set_tracking_uri(ws.get_mlflow_tracking_uri())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Retrieve model from previous run\n",
+        "\n",
+        "Let's retrieve the experiment from training notebook, and list the runs within that experiment."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "experiment_name = \"experiment-with-mlflow\"\n",
+        "exp = ws.experiments[experiment_name]\n",
+        "\n",
+        "runs = list(exp.get_runs())\n",
+        "runs"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Then, let's select the most recent training run and find its ID. You also need to specify the path in run history where the model was saved. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "runid = runs[0].id\n",
+        "model_save_path = \"model\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create Docker image\n",
+        "\n",
+        "To create a Docker image with Azure Machine Learning for Model Management, use ```mlflow.azureml.build_image``` method. Specify the model path, your workspace, run ID and other parameters.\n",
+        "\n",
+        "MLflow automatically recognizes the model framework as scikit-learn, and creates the scoring logic and includes library dependencies for you.\n",
+        "\n",
+        "Note that the image creation can take several minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import mlflow.azureml\n",
+        "\n",
+        "azure_image, azure_model = mlflow.azureml.build_image(model_uri=\"runs:/{}/{}\".format(runid, model_save_path),\n",
+        "                                                      workspace=ws,\n",
+        "                                                      model_name='diabetes-sklearn-model',\n",
+        "                                                      image_name='diabetes-sklearn-image',\n",
+        "                                                      synchronous=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Deploy web service\n",
+        "\n",
+        "Let's use Azure Machine Learning SDK to deploy the image as a web service. \n",
+        "\n",
+        "First, specify the deployment configuration. Azure Container Instance is a suitable choice for a quick dev-test deployment, while Azure Kubernetes Service is suitable for scalable production deployments.\n",
+        "\n",
+        "Then, deploy the image using Azure Machine Learning SDK's ```deploy_from_image``` method.\n",
+        "\n",
+        "Note that the deployment can take several minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.webservice import AciWebservice, Webservice\n",
+        "\n",
+        "\n",
+        "aci_config = AciWebservice.deploy_configuration(cpu_cores=1, \n",
+        "                                                memory_gb=1, \n",
+        "                                                tags={\"method\" : \"sklearn\"}, \n",
+        "                                                description='Diabetes model',\n",
+        "                                                location='eastus2')\n",
+        "\n",
+        "\n",
+        "# Deploy the image to Azure Container Instances (ACI) for real-time serving\n",
+        "webservice = Webservice.deploy_from_image(\n",
+        "    image=azure_image, workspace=ws, name=\"diabetes-model-1\", deployment_config=aci_config)\n",
+        "\n",
+        "\n",
+        "webservice.wait_for_deployment(show_output=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Make a scoring request\n",
+        "\n",
+        "Let's take the first few rows of test data and score them using the web service"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "test_rows = [\n",
+        "    [0.01991321,  0.05068012,  0.10480869,  0.07007254, -0.03596778,\n",
+        "     -0.0266789 , -0.02499266, -0.00259226,  0.00371174,  0.04034337],\n",
+        "    [-0.01277963, -0.04464164,  0.06061839,  0.05285819,  0.04796534,\n",
+        "     0.02937467, -0.01762938,  0.03430886,  0.0702113 ,  0.00720652],\n",
+        "    [ 0.03807591,  0.05068012,  0.00888341,  0.04252958, -0.04284755,\n",
+        "     -0.02104223, -0.03971921, -0.00259226, -0.01811827,  0.00720652]]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "MLflow-based web service for scikit-learn model requires the data to be converted to Pandas DataFrame, and then serialized as JSON. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import json\n",
+        "import pandas as pd\n",
+        "\n",
+        "test_rows_as_json = pd.DataFrame(test_rows).to_json(orient=\"split\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Let's pass the conveted and serialized data to web service to get the predictions."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "predictions = webservice.run(test_rows_as_json)\n",
+        "\n",
+        "print(predictions)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can use the web service's scoring URI to make a raw HTTP request"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "webservice.scoring_uri"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can diagnose the web service using ```get_logs``` method."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "webservice.get_logs()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Next Steps\n",
+        "\n",
+        "Learn about [model management and inferencing in Azure Machine Learning service](https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-model-management-and-deployment)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": []
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "metadata": {
+    "authors": [
+      {
+        "name": "rastala"
+      }
+    ],
+    "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": "3.6.4"
+    }
   },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.6.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

how-to-use-azureml/using-mlflow/train-deploy-pytorch/scripts/train.py

@@ -0,0 +1,150 @@
+# Copyright (c) 2017, PyTorch Team
+# All rights reserved
+# Licensed under BSD 3-Clause License.
+
+# This example is based on PyTorch MNIST example:
+# https://github.com/pytorch/examples/blob/master/mnist/main.py
+
+import mlflow
+import mlflow.pytorch
+from mlflow.utils.environment import _mlflow_conda_env
+import warnings
+import cloudpickle
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import torch.optim as optim
+import torchvision
+from torchvision import datasets, transforms
+
+
+class Net(nn.Module):
+    def __init__(self):
+        super(Net, self).__init__()
+        self.conv1 = nn.Conv2d(1, 20, 5, 1)
+        self.conv2 = nn.Conv2d(20, 50, 5, 1)
+        self.fc1 = nn.Linear(4 * 4 * 50, 500)
+        self.fc2 = nn.Linear(500, 10)
+
+    def forward(self, x):
+        # Added the view for reshaping score requests
+        x = x.view(-1, 1, 28, 28)
+        x = F.relu(self.conv1(x))
+        x = F.max_pool2d(x, 2, 2)
+        x = F.relu(self.conv2(x))
+        x = F.max_pool2d(x, 2, 2)
+        x = x.view(-1, 4 * 4 * 50)
+        x = F.relu(self.fc1(x))
+        x = self.fc2(x)
+        return F.log_softmax(x, dim=1)
+
+
+def train(args, model, device, train_loader, optimizer, epoch):
+    model.train()
+    for batch_idx, (data, target) in enumerate(train_loader):
+        data, target = data.to(device), target.to(device)
+        optimizer.zero_grad()
+        output = model(data)
+        loss = F.nll_loss(output, target)
+        loss.backward()
+        optimizer.step()
+        if batch_idx % args.log_interval == 0:
+            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
+                epoch, batch_idx * len(data), len(train_loader.dataset),
+                100. * batch_idx / len(train_loader), loss.item()))
+            # Use MLflow logging
+            mlflow.log_metric("epoch_loss", loss.item())
+
+
+def test(args, model, device, test_loader):
+    model.eval()
+    test_loss = 0
+    correct = 0
+    with torch.no_grad():
+        for data, target in test_loader:
+            data, target = data.to(device), target.to(device)
+            output = model(data)
+            # sum up batch loss
+            test_loss += F.nll_loss(output, target, reduction="sum").item()
+            # get the index of the max log-probability
+            pred = output.argmax(dim=1, keepdim=True)
+            correct += pred.eq(target.view_as(pred)).sum().item()
+
+    test_loss /= len(test_loader.dataset)
+    print("\n")
+    print("Test set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n".format(
+        test_loss, correct, len(test_loader.dataset),
+        100. * correct / len(test_loader.dataset)))
+    # Use MLflow logging
+    mlflow.log_metric("average_loss", test_loss)
+
+
+class Args(object):
+    pass
+
+
+# Training settings
+args = Args()
+setattr(args, 'batch_size', 64)
+setattr(args, 'test_batch_size', 1000)
+setattr(args, 'epochs', 3)  # Higher number for better convergence
+setattr(args, 'lr', 0.01)
+setattr(args, 'momentum', 0.5)
+setattr(args, 'no_cuda', True)
+setattr(args, 'seed', 1)
+setattr(args, 'log_interval', 10)
+setattr(args, 'save_model', True)
+
+use_cuda = not args.no_cuda and torch.cuda.is_available()
+
+torch.manual_seed(args.seed)
+
+device = torch.device("cuda" if use_cuda else "cpu")
+
+kwargs = {'num_workers': 1, 'pin_memory': True} if use_cuda else {}
+train_loader = torch.utils.data.DataLoader(
+    datasets.MNIST('../data', train=True, download=True,
+                   transform=transforms.Compose([
+                       transforms.ToTensor(),
+                       transforms.Normalize((0.1307,), (0.3081,))
+                   ])),
+    batch_size=args.batch_size, shuffle=True, **kwargs)
+test_loader = torch.utils.data.DataLoader(
+    datasets.MNIST(
+        '../data',
+        train=False,
+        transform=transforms.Compose([
+            transforms.ToTensor(),
+            transforms.Normalize((0.1307,), (0.3081,))])),
+    batch_size=args.test_batch_size, shuffle=True, **kwargs)
+
+
+def driver():
+    warnings.filterwarnings("ignore")
+    # Dependencies for deploying the model
+    pytorch_index = "https://download.pytorch.org/whl/"
+    pytorch_version = "cpu/torch-1.1.0-cp36-cp36m-linux_x86_64.whl"
+    deps = [
+        "cloudpickle=={}".format(cloudpickle.__version__),
+        pytorch_index + pytorch_version,
+        "torchvision=={}".format(torchvision.__version__),
+        "Pillow=={}".format("6.0.0")
+    ]
+    with mlflow.start_run() as run:
+        model = Net().to(device)
+        optimizer = optim.SGD(
+            model.parameters(),
+            lr=args.lr,
+            momentum=args.momentum)
+        for epoch in range(1, args.epochs + 1):
+            train(args, model, device, train_loader, optimizer, epoch)
+            test(args, model, device, test_loader)
+        # Log model to run history using MLflow
+        if args.save_model:
+            model_env = _mlflow_conda_env(additional_pip_deps=deps)
+            mlflow.pytorch.log_model(model, "model", conda_env=model_env)
+    return run
+
+
+if __name__ == "__main__":
+    driver()

how-to-use-azureml/using-mlflow/train-deploy-pytorch/train-and-deploy-pytorch.ipynb

@@ -0,0 +1,481 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/using-mlflow/train-deploy-pytorch/train-deploy-pytorch.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Use MLflow with Azure Machine Learning to Train and Deploy PyTorch Image Classifier\n",
+        "\n",
+        "This example shows you how to use MLflow together with Azure Machine Learning services for tracking the metrics and artifacts while training a PyTorch model to classify MNIST digit images, and then deploy the model  as a web service. You'll learn how to:\n",
+        "\n",
+        " 1. Set up MLflow tracking URI so as to use Azure ML\n",
+        " 2. Create experiment\n",
+        " 3. Instrument your model with MLflow tracking\n",
+        " 4. Train a PyTorch model locally\n",
+        " 5. Train a model on GPU compute on Azure\n",
+        " 6. View your experiment within your Azure ML Workspace in Azure Portal\n",
+        " 7. Create a Docker image from the trained model\n",
+        " 8. Deploy the model as a web service on Azure Container Instance\n",
+        " 9. Call the model to make predictions\n",
+        " \n",
+        "### Pre-requisites\n",
+        " \n",
+        "Make sure you have completed the [Configuration](../../../configuration.ipnyb) notebook to set up your Azure Machine Learning workspace and ensure other common prerequisites are met.\n",
+        "\n",
+        "Also, install mlflow-azureml package using ```pip install mlflow-azureml```. Note that mlflow-azureml installs mlflow package itself as a dependency, if you haven't done so previously.\n",
+        "\n",
+        "### Set-up\n",
+        "\n",
+        "Import packages and check versions of Azure ML SDK and MLflow installed on your computer. Then connect to your Workspace."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import sys, os\n",
+        "import mlflow\n",
+        "import mlflow.azureml\n",
+        "import mlflow.sklearn\n",
+        "\n",
+        "import azureml.core\n",
+        "from azureml.core import Workspace\n",
+        "\n",
+        "\n",
+        "print(\"SDK version:\", azureml.core.VERSION)\n",
+        "print(\"MLflow version:\", mlflow.version.VERSION)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "ws.get_details()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Set tracking URI\n",
+        "\n",
+        "Set the MLFlow tracking URI to point to your Azure ML Workspace. The subsequent logging calls from MLFlow APIs will go to Azure ML services and will be tracked under your Workspace."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "mlflow.set_tracking_uri(ws.get_mlflow_tracking_uri())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create Experiment\n",
+        "\n",
+        "In both MLflow and Azure ML, training runs are grouped into experiments. Let's create one for our experimentation."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "experiment_name = \"pytorch-with-mlflow\"\n",
+        "mlflow.set_experiment(experiment_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Train model locally while logging metrics and artifacts\n",
+        "\n",
+        "The ```scripts/train.py``` program contains the code to load the image dataset, and train and test the model. Within this program, the train.driver function wraps the end-to-end workflow.\n",
+        "\n",
+        "Within the driver, the ```mlflow.start_run``` starts MLflow tracking. Then, ```mlflow.log_metric``` functions are used to track the convergence of the neural network training iterations. Finally ```mlflow.pytorch.save_model``` is used to save the trained model in framework-aware manner.\n",
+        "\n",
+        "Let's add the program to search path, import it as a module, and then invoke the driver function. Note that the training can take few minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "lib_path = os.path.abspath(\"scripts\")\n",
+        "sys.path.append(lib_path)\n",
+        "\n",
+        "import train"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run = train.driver()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can view the metrics of the run at Azure Portal"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(azureml.mlflow.get_portal_url(run))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Train model on GPU compute on Azure\n",
+        "\n",
+        "Next, let's run the same script on GPU-enabled compute for faster training. If you've completed the the [Configuration](../../../configuration.ipnyb) notebook, you should have a GPU cluster named \"gpu-cluster\" available in your workspace. Otherwise, follow the instructions in the notebook to create one. For simplicity, this example uses single process on single VM to train the model.\n",
+        "\n",
+        "Create a PyTorch estimator to specify the training configuration: script, compute as well as additional packages needed. To enable MLflow tracking, include ```azureml-mlflow``` as pip package. The low-level specifications for the training run are encapsulated in the estimator instance."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.train.dnn import PyTorch\n",
+        "\n",
+        "pt = PyTorch(source_directory=\"./scripts\", \n",
+        "             entry_script = \"train.py\", \n",
+        "             compute_target = \"gpu-cluster\", \n",
+        "             node_count = 1, \n",
+        "             process_count_per_node = 1, \n",
+        "             use_gpu=True,\n",
+        "             pip_packages = [\"azureml-mlflow\", \"Pillow==6.0.0\"])\n",
+        "\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Get a reference to the experiment you created previously, but this time, as Azure Machine Learning experiment object.\n",
+        "\n",
+        "Then, use ```Experiment.submit``` method to start the remote training run. Note that the first training run often takes longer as Azure Machine Learning service builds the Docker image for executing the script. Subsequent runs will be faster as cached image is used."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core import Experiment\n",
+        "\n",
+        "exp = Experiment(ws, experiment_name)\n",
+        "run = exp.submit(pt)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can monitor the run and its metrics on Azure Portal."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Also, you can wait for run to complete."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run.wait_for_completion(show_output=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Deploy model as web service\n",
+        "\n",
+        "To deploy a web service, first create a Docker image, and then deploy that Docker image on inferencing compute.\n",
+        "\n",
+        "The ```mlflow.azureml.build_image``` function builds a Docker image from saved PyTorch model in a framework-aware manner. It automatically creates the PyTorch-specific inferencing wrapper code and specififies package dependencies for you."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run.get_file_names()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Then build a docker image using *runs:/<run.id>/model* as the model_uri path.\n",
+        "\n",
+        "Note that the image building can take several minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "model_path = \"model\"\n",
+        "\n",
+        "\n",
+        "azure_image, azure_model = mlflow.azureml.build_image(model_uri='runs:/{}/{}'.format(run.id, model_path),\n",
+        "                                                      workspace=ws,\n",
+        "                                                      model_name='pytorch_mnist',\n",
+        "                                                      image_name='pytorch-mnist-img',\n",
+        "                                                      synchronous=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Then, deploy the Docker image to Azure Container Instance: a serverless compute capable of running a single container. You can tag and add descriptions to help keep track of your web service. \n",
+        "\n",
+        "[Other inferencing compute choices](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-deploy-and-where) include Azure Kubernetes Service which provides scalable endpoint suitable for production use.\n",
+        "\n",
+        "Note that the service deployment can take several minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.webservice import AciWebservice, Webservice\n",
+        "\n",
+        "aci_config = AciWebservice.deploy_configuration(cpu_cores=2, \n",
+        "                                                memory_gb=5, \n",
+        "                                                tags={\"data\": \"MNIST\",  \"method\" : \"pytorch\"}, \n",
+        "                                                description=\"Predict using webservice\")\n",
+        "\n",
+        "\n",
+        "# Deploy the image to Azure Container Instances (ACI) for real-time serving\n",
+        "webservice = Webservice.deploy_from_image(\n",
+        "    image=azure_image, workspace=ws, name=\"pytorch-mnist-1\", deployment_config=aci_config)\n",
+        "\n",
+        "\n",
+        "webservice.wait_for_deployment()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Once the deployment has completed you can check the scoring URI of the web service."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"Scoring URI is: {}\".format(webservice.scoring_uri))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "In case of a service creation issue, you can use ```webservice.get_logs()``` to get logs to debug."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Make predictions using web service\n",
+        "\n",
+        "To make the web service, create a test data set as normalized PyTorch tensors. \n",
+        "\n",
+        "Then, let's define a utility function that takes a random image and converts it into format and shape suitable for as input to PyTorch inferencing end-point. The conversion is done by: \n",
+        "\n",
+        " 1. Select a random (image, label) tuple\n",
+        " 2. Take the image and converting the tensor to NumPy array \n",
+        " 3. Reshape array into 1 x 1 x N array\n",
+        "    * 1 image in batch, 1 color channel, N = 784 pixels for MNIST images\n",
+        "    * Note also ```x = x.view(-1, 1, 28, 28)``` in net definition in ```train.py``` program to shape incoming scoring requests.\n",
+        " 4. Convert the NumPy array to list to make it into a built-in type.\n",
+        " 5. Create a dictionary {\"data\", <list>} that can be converted to JSON string for web service requests."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from torchvision import datasets, transforms\n",
+        "import random\n",
+        "import numpy as np\n",
+        "\n",
+        "test_data = datasets.MNIST('../data', train=False, transform=transforms.Compose([\n",
+        "                       transforms.ToTensor(),\n",
+        "                       transforms.Normalize((0.1307,), (0.3081,))]))\n",
+        "\n",
+        "\n",
+        "def get_random_image():\n",
+        "    image_idx = random.randint(0,len(test_data))\n",
+        "    image_as_tensor = test_data[image_idx][0]\n",
+        "    return {\"data\": elem for elem in image_as_tensor.numpy().reshape(1,1,-1).tolist()}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Then, invoke the web service using a random test image. Convert the dictionary containing the image to JSON string before passing it to web service.\n",
+        "\n",
+        "The response contains the raw scores for each label, with greater value indicating higher probability. Sort the labels and select the one with greatest score to get the prediction. Let's also plot the image sent to web service for comparison purposes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%matplotlib inline\n",
+        "\n",
+        "import json\n",
+        "import matplotlib.pyplot as plt\n",
+        "\n",
+        "test_image = get_random_image()\n",
+        "\n",
+        "response = webservice.run(json.dumps(test_image))\n",
+        "\n",
+        "response = sorted(response[0].items(), key = lambda x: x[1], reverse = True)\n",
+        "\n",
+        "\n",
+        "print(\"Predicted label:\", response[0][0])\n",
+        "plt.imshow(np.array(test_image[\"data\"]).reshape(28,28), cmap = \"gray\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can also call the web service using a raw POST method against the web service"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import requests\n",
+        "\n",
+        "response = requests.post(url=webservice.scoring_uri, data=json.dumps(test_image),headers={\"Content-type\": \"application/json\"})\n",
+        "print(response.text)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": []
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": []
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "roastala"
+      }
+    ],
+    "celltoolbar": "Edit Metadata",
+    "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": "3.7.3"
+    },
+    "name": "mlflow-sparksummit-pytorch",
+    "notebookId": 2495374963457641
+  },
+  "nbformat": 4,
+  "nbformat_minor": 1
+}

how-to-use-azureml/using-mlflow/train-local/train-local.ipynb

@@ -1,248 +1,248 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-    "\n",
-    "Licensed under the MIT License."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/using-mlflow/train-local/train-local.png)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Use MLflow with Azure Machine Learning for Local Training Run\n",
-    "\n",
-    "This example shows you how to use mlflow tracking APIs together with Azure Machine Learning services for storing your metrics and artifacts, from local Notebook run. You'll learn how to:\n",
-    "\n",
-    " 1. Set up MLflow tracking URI so as to use Azure ML\n",
-    " 2. Create experiment\n",
-    " 3. Train a model on your local computer while logging metrics and artifacts\n",
-    " 4. View your experiment within your Azure ML Workspace in Azure Portal.\n",
-    "\n",
-    "## Prerequisites and Set-up\n",
-    "\n",
-    "Make sure you have completed the [Configuration](../../../configuration.ipnyb) notebook to set up your Azure Machine Learning workspace and ensure other common prerequisites are met.\n",
-    "\n",
-    "Install azureml-mlflow package before running this notebook. Note that mlflow itself gets installed as dependency if you haven't installed it yet.\n",
-    "\n",
-    "```\n",
-    "pip install azureml-mlflow\n",
-    "```\n",
-    "\n",
-    "This example also uses scikit-learn and matplotlib packages. Install them:\n",
-    "```\n",
-    "pip install scikit-learn matplotlib\n",
-    "```\n",
-    "\n",
-    "Then, import necessary packages"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import mlflow\n",
-    "import mlflow.sklearn\n",
-    "import azureml.core\n",
-    "from azureml.core import Workspace\n",
-    "import matplotlib.pyplot as plt\n",
-    "\n",
-    "# Check core SDK version number\n",
-    "print(\"SDK version:\", azureml.core.VERSION)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Set tracking URI\n",
-    "\n",
-    "Set the MLflow tracking URI to point to your Azure ML Workspace. The subsequent logging calls from MLflow APIs will go to Azure ML services and will be tracked under your Workspace."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "ws = Workspace.from_config()\n",
-    "\n",
-    "mlflow.set_tracking_uri(ws.get_mlflow_tracking_uri())"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Create Experiment\n",
-    "\n",
-    "In both MLflow and Azure ML, training runs are grouped into experiments. Let's create one for our experimentation."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "experiment_name = \"experiment-with-mlflow\"\n",
-    "mlflow.set_experiment(experiment_name)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Create training and test data set\n",
-    "\n",
-    "This example uses diabetes dataset to build a simple regression model. Let's load the dataset and split it into training and test sets."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import numpy as np\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",
-    "columns = ['age', 'gender', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']\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",
-    "}\n",
-    "\n",
-    "print (\"Data contains\", len(data['train']['X']), \"training samples and\",len(data['test']['X']), \"test samples\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Train while logging metrics and artifacts\n",
-    "\n",
-    "Next, start a mlflow run to train a scikit-learn regression model. Note that the training script has been instrumented using MLflow to:\n",
-    " * Log model hyperparameter alpha value\n",
-    " * Log mean squared error against test set\n",
-    " * Save the scikit-learn based regression model produced by training\n",
-    " * Save an image that shows actuals vs predictions against test set.\n",
-    " \n",
-    "These metrics and artifacts have been recorded to your Azure ML Workspace; in the next step you'll learn how to view them."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Create a run object in the experiment\n",
-    "model_save_path = \"model\"\n",
-    "\n",
-    "with mlflow.start_run() as run:\n",
-    "    # Log the algorithm parameter alpha to the run\n",
-    "    mlflow.log_metric('alpha', 0.03)\n",
-    "    # Create, fit, and test the scikit-learn Ridge regression model\n",
-    "    regression_model = Ridge(alpha=0.03)\n",
-    "    regression_model.fit(data['train']['X'], data['train']['y'])\n",
-    "    preds = regression_model.predict(data['test']['X'])\n",
-    "\n",
-    "    # Log mean squared error\n",
-    "    print('Mean Squared Error is', mean_squared_error(data['test']['y'], preds))\n",
-    "    mlflow.log_metric('mse', mean_squared_error(data['test']['y'], preds))\n",
-    "    \n",
-    "    # Save the model to the outputs directory for capture\n",
-    "    mlflow.sklearn.log_model(regression_model,model_save_path)\n",
-    "    \n",
-    "    # Plot actuals vs predictions and save the plot within the run\n",
-    "    fig = plt.figure(1)\n",
-    "    idx = np.argsort(data['test']['y'])\n",
-    "    plt.plot(data['test']['y'][idx],preds[idx])\n",
-    "    fig.savefig(\"actuals_vs_predictions.png\")\n",
-    "    mlflow.log_artifact(\"actuals_vs_predictions.png\") "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can open the report page for your experiment and runs within it from Azure Portal.\n",
-    "\n",
-    "Select one of the runs to view the metrics, and the plot you saved. The saved scikit-learn model appears under **outputs** tab."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "ws.experiments[experiment_name]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Next steps\n",
-    "\n",
-    "Try out these notebooks to learn more about MLflow-Azure Machine Learning integration:\n",
-    "\n",
-    " * [Train a model using remote compute on Azure Cloud](../train-on-remote/train-on-remote.ipynb)\n",
-    " * [Deploy the model as a web service](../deploy-model/deploy-model.ipynb)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "authors": [
-   {
-    "name": "rastala"
-   }
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/using-mlflow/train-local/train-local.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Use MLflow with Azure Machine Learning for Local Training Run\n",
+        "\n",
+        "This example shows you how to use mlflow tracking APIs together with Azure Machine Learning services for storing your metrics and artifacts, from local Notebook run. You'll learn how to:\n",
+        "\n",
+        " 1. Set up MLflow tracking URI so as to use Azure ML\n",
+        " 2. Create experiment\n",
+        " 3. Train a model on your local computer while logging metrics and artifacts\n",
+        " 4. View your experiment within your Azure ML Workspace in Azure Portal.\n",
+        "\n",
+        "## Prerequisites and Set-up\n",
+        "\n",
+        "Make sure you have completed the [Configuration](../../../configuration.ipnyb) notebook to set up your Azure Machine Learning workspace and ensure other common prerequisites are met.\n",
+        "\n",
+        "Install azureml-mlflow package before running this notebook. Note that mlflow itself gets installed as dependency if you haven't installed it yet.\n",
+        "\n",
+        "```\n",
+        "pip install azureml-mlflow\n",
+        "```\n",
+        "\n",
+        "This example also uses scikit-learn and matplotlib packages. Install them:\n",
+        "```\n",
+        "pip install scikit-learn matplotlib\n",
+        "```\n",
+        "\n",
+        "Then, import necessary packages"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import mlflow\n",
+        "import mlflow.sklearn\n",
+        "import azureml.core\n",
+        "from azureml.core import Workspace\n",
+        "import matplotlib.pyplot as plt\n",
+        "\n",
+        "# Check core SDK version number\n",
+        "print(\"SDK version:\", azureml.core.VERSION)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Set tracking URI\n",
+        "\n",
+        "Set the MLflow tracking URI to point to your Azure ML Workspace. The subsequent logging calls from MLflow APIs will go to Azure ML services and will be tracked under your Workspace."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "mlflow.set_tracking_uri(ws.get_mlflow_tracking_uri())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Create Experiment\n",
+        "\n",
+        "In both MLflow and Azure ML, training runs are grouped into experiments. Let's create one for our experimentation."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "experiment_name = \"experiment-with-mlflow\"\n",
+        "mlflow.set_experiment(experiment_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Create training and test data set\n",
+        "\n",
+        "This example uses diabetes dataset to build a simple regression model. Let's load the dataset and split it into training and test sets."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import numpy as np\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",
+        "columns = ['age', 'gender', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']\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",
+        "}\n",
+        "\n",
+        "print (\"Data contains\", len(data['train']['X']), \"training samples and\",len(data['test']['X']), \"test samples\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train while logging metrics and artifacts\n",
+        "\n",
+        "Next, start a mlflow run to train a scikit-learn regression model. Note that the training script has been instrumented using MLflow to:\n",
+        " * Log model hyperparameter alpha value\n",
+        " * Log mean squared error against test set\n",
+        " * Save the scikit-learn based regression model produced by training\n",
+        " * Save an image that shows actuals vs predictions against test set.\n",
+        " \n",
+        "These metrics and artifacts have been recorded to your Azure ML Workspace; in the next step you'll learn how to view them."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Create a run object in the experiment\n",
+        "model_save_path = \"model\"\n",
+        "\n",
+        "with mlflow.start_run() as run:\n",
+        "    # Log the algorithm parameter alpha to the run\n",
+        "    mlflow.log_metric('alpha', 0.03)\n",
+        "    # Create, fit, and test the scikit-learn Ridge regression model\n",
+        "    regression_model = Ridge(alpha=0.03)\n",
+        "    regression_model.fit(data['train']['X'], data['train']['y'])\n",
+        "    preds = regression_model.predict(data['test']['X'])\n",
+        "\n",
+        "    # Log mean squared error\n",
+        "    print('Mean Squared Error is', mean_squared_error(data['test']['y'], preds))\n",
+        "    mlflow.log_metric('mse', mean_squared_error(data['test']['y'], preds))\n",
+        "    \n",
+        "    # Save the model to the outputs directory for capture\n",
+        "    mlflow.sklearn.log_model(regression_model,model_save_path)\n",
+        "    \n",
+        "    # Plot actuals vs predictions and save the plot within the run\n",
+        "    fig = plt.figure(1)\n",
+        "    idx = np.argsort(data['test']['y'])\n",
+        "    plt.plot(data['test']['y'][idx],preds[idx])\n",
+        "    fig.savefig(\"actuals_vs_predictions.png\")\n",
+        "    mlflow.log_artifact(\"actuals_vs_predictions.png\") "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can open the report page for your experiment and runs within it from Azure Portal.\n",
+        "\n",
+        "Select one of the runs to view the metrics, and the plot you saved. The saved scikit-learn model appears under **outputs** tab."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws.experiments[experiment_name]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Next steps\n",
+        "\n",
+        "Try out these notebooks to learn more about MLflow-Azure Machine Learning integration:\n",
+        "\n",
+        " * [Train a model using remote compute on Azure Cloud](../train-on-remote/train-on-remote.ipynb)\n",
+        " * [Deploy the model as a web service](../deploy-model/deploy-model.ipynb)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": []
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "metadata": {
+    "authors": [
+      {
+        "name": "rastala"
+      }
+    ],
+    "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": "3.6.4"
+    }
   },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.6.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

how-to-use-azureml/using-mlflow/train-remote/train-remote.ipynb

@@ -1,318 +1,318 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-    "\n",
-    "Licensed under the MIT License."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/using-mlflow/train-remote/train-remote.png)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Use MLflow with Azure Machine Learning for Remote Training Run\n",
-    "\n",
-    "This example shows you how to use MLflow tracking APIs together with Azure Machine Learning services for storing your metrics and artifacts, from local Notebook run. You'll learn how to:\n",
-    "\n",
-    " 1. Set up MLflow tracking URI so as to use Azure ML\n",
-    " 2. Create experiment\n",
-    " 3. Train a model on Machine Learning Compute while logging metrics and artifacts\n",
-    " 4. View your experiment within your Azure ML Workspace in Azure Portal."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Prerequisites\n",
-    "\n",
-    "Make sure you have completed the [Configuration](../../../configuration.ipnyb) notebook to set up your Azure Machine Learning workspace and ensure other common prerequisites are met."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Set-up\n",
-    "\n",
-    "Check Azure ML SDK version installed on your computer, and then connect to your Workspace."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Check core SDK version number\n",
-    "import azureml.core\n",
-    "from azureml.core import Workspace, Experiment\n",
-    "\n",
-    "print(\"SDK version:\", azureml.core.VERSION)\n",
-    "\n",
-    "ws = Workspace.from_config()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Let's also create a Machine Learning Compute cluster for submitting the remote run. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core.compute import ComputeTarget, AmlCompute\n",
-    "from azureml.core.compute_target import ComputeTargetException\n",
-    "\n",
-    "# Choose a name for your CPU cluster\n",
-    "cpu_cluster_name = \"cpu-cluster\"\n",
-    "\n",
-    "# Verify that cluster does not exist already\n",
-    "try:\n",
-    "    cpu_cluster = ComputeTarget(workspace=ws, name=cpu_cluster_name)\n",
-    "    print(\"Found existing cpu-cluster\")\n",
-    "except ComputeTargetException:\n",
-    "    print(\"Creating new cpu-cluster\")\n",
-    "    \n",
-    "    # Specify the configuration for the new cluster\n",
-    "    compute_config = AmlCompute.provisioning_configuration(vm_size=\"STANDARD_D2_V2\",\n",
-    "                                                           min_nodes=0,\n",
-    "                                                           max_nodes=1)\n",
-    "\n",
-    "    # Create the cluster with the specified name and configuration\n",
-    "    cpu_cluster = ComputeTarget.create(ws, cpu_cluster_name, compute_config)\n",
-    "    \n",
-    "    # Wait for the cluster to complete, show the output log\n",
-    "    cpu_cluster.wait_for_completion(show_output=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Create Azure ML Experiment"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The following steps show how to submit a training Python script to a cluster as an Azure ML run, while logging happens through MLflow APIs to your Azure ML Workspace. Let's first create an experiment to hold the training runs."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core import Experiment\n",
-    "\n",
-    "experiment_name = \"experiment-with-mlflow\"\n",
-    "exp = Experiment(workspace=ws, name=experiment_name)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Instrument remote training script using MLflow"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Let's use [*train_diabetes.py*](train_diabetes.py) to train a regression model against diabetes dataset as the example. Note that the training script uses mlflow.start_run() to start logging, and then logs metrics, saves the trained scikit-learn model, and saves a plot as an artifact.\n",
-    "\n",
-    "Run following command to view the script file. Notice the mlflow logging statements, and also notice that the script doesn't have explicit dependencies on azureml library."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "training_script = 'train_diabetes.py'\n",
-    "with open(training_script, 'r') as f:\n",
-    "    print(f.read())"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Submit Run to Cluster \n",
-    "\n",
-    "Let's submit the run to cluster. When running on the remote cluster as submitted run, Azure ML sets the MLflow tracking URI to point to your Azure ML Workspace, so that the metrics and artifacts are automatically logged there.\n",
-    "\n",
-    "Note that you have to specify the packages your script depends on, including *azureml-mlflow* that implicitly enables the MLflow logging to Azure ML. \n",
-    "\n",
-    "First, create a environment with Docker enable and required package dependencies specified."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "mlflow"
-    ]
-   },
-   "outputs": [],
-   "source": [
-    "from azureml.core import Environment\n",
-    "from azureml.core.conda_dependencies import CondaDependencies\n",
-    "\n",
-    "env = Environment(name=\"mlflow-env\")\n",
-    "\n",
-    "env.docker.enabled = True\n",
-    "\n",
-    "# Specify conda dependencies with scikit-learn and temporary pointers to mlflow extensions\n",
-    "cd = CondaDependencies.create(\n",
-    "    conda_packages=[\"scikit-learn\", \"matplotlib\"],\n",
-    "    pip_packages=[\"azureml-mlflow\", \"numpy\"]\n",
-    "    )\n",
-    "\n",
-    "env.python.conda_dependencies = cd"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Next, specify a script run configuration that includes the training script, environment and CPU cluster created earlier."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from azureml.core import ScriptRunConfig\n",
-    "\n",
-    "src = ScriptRunConfig(source_directory=\".\", script=training_script)\n",
-    "src.run_config.environment = env\n",
-    "src.run_config.target = cpu_cluster.name"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Finally, submit the run. Note that the first instance of the run typically takes longer as the Docker-based environment is created, several minutes. Subsequent runs reuse the image and are faster."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "run = exp.submit(src)\n",
-    "run.wait_for_completion(show_output=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can navigate to your Azure ML Workspace at Azure Portal to view the run metrics and artifacts. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "run.id"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can also get the metrics and bring them to your local notebook, and view the details of the run."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "run.get_metrics()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "ws.get_details()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Next steps\n",
-    "\n",
-    " * [Deploy the model as a web service](../deploy-model/deploy-model.ipynb)\n",
-    " * [Learn more about Azure Machine Learning compute options](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-set-up-training-targets)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "authors": [
-   {
-    "name": "rastala"
-   }
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/using-mlflow/train-remote/train-remote.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Use MLflow with Azure Machine Learning for Remote Training Run\n",
+        "\n",
+        "This example shows you how to use MLflow tracking APIs together with Azure Machine Learning services for storing your metrics and artifacts, from local Notebook run. You'll learn how to:\n",
+        "\n",
+        " 1. Set up MLflow tracking URI so as to use Azure ML\n",
+        " 2. Create experiment\n",
+        " 3. Train a model on Machine Learning Compute while logging metrics and artifacts\n",
+        " 4. View your experiment within your Azure ML Workspace in Azure Portal."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Prerequisites\n",
+        "\n",
+        "Make sure you have completed the [Configuration](../../../configuration.ipnyb) notebook to set up your Azure Machine Learning workspace and ensure other common prerequisites are met."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Set-up\n",
+        "\n",
+        "Check Azure ML SDK version installed on your computer, and then connect to your Workspace."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Check core SDK version number\n",
+        "import azureml.core\n",
+        "from azureml.core import Workspace, Experiment\n",
+        "\n",
+        "print(\"SDK version:\", azureml.core.VERSION)\n",
+        "\n",
+        "ws = Workspace.from_config()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Let's also create a Machine Learning Compute cluster for submitting the remote run. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
+        "from azureml.core.compute_target import ComputeTargetException\n",
+        "\n",
+        "# Choose a name for your CPU cluster\n",
+        "cpu_cluster_name = \"cpu-cluster\"\n",
+        "\n",
+        "# Verify that cluster does not exist already\n",
+        "try:\n",
+        "    cpu_cluster = ComputeTarget(workspace=ws, name=cpu_cluster_name)\n",
+        "    print(\"Found existing cpu-cluster\")\n",
+        "except ComputeTargetException:\n",
+        "    print(\"Creating new cpu-cluster\")\n",
+        "    \n",
+        "    # Specify the configuration for the new cluster\n",
+        "    compute_config = AmlCompute.provisioning_configuration(vm_size=\"STANDARD_D2_V2\",\n",
+        "                                                           min_nodes=0,\n",
+        "                                                           max_nodes=1)\n",
+        "\n",
+        "    # Create the cluster with the specified name and configuration\n",
+        "    cpu_cluster = ComputeTarget.create(ws, cpu_cluster_name, compute_config)\n",
+        "    \n",
+        "    # Wait for the cluster to complete, show the output log\n",
+        "    cpu_cluster.wait_for_completion(show_output=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create Azure ML Experiment"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "The following steps show how to submit a training Python script to a cluster as an Azure ML run, while logging happens through MLflow APIs to your Azure ML Workspace. Let's first create an experiment to hold the training runs."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core import Experiment\n",
+        "\n",
+        "experiment_name = \"experiment-with-mlflow\"\n",
+        "exp = Experiment(workspace=ws, name=experiment_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Instrument remote training script using MLflow"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Let's use [*train_diabetes.py*](train_diabetes.py) to train a regression model against diabetes dataset as the example. Note that the training script uses mlflow.start_run() to start logging, and then logs metrics, saves the trained scikit-learn model, and saves a plot as an artifact.\n",
+        "\n",
+        "Run following command to view the script file. Notice the mlflow logging statements, and also notice that the script doesn't have explicit dependencies on azureml library."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "training_script = 'train_diabetes.py'\n",
+        "with open(training_script, 'r') as f:\n",
+        "    print(f.read())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Submit Run to Cluster \n",
+        "\n",
+        "Let's submit the run to cluster. When running on the remote cluster as submitted run, Azure ML sets the MLflow tracking URI to point to your Azure ML Workspace, so that the metrics and artifacts are automatically logged there.\n",
+        "\n",
+        "Note that you have to specify the packages your script depends on, including *azureml-mlflow* that implicitly enables the MLflow logging to Azure ML. \n",
+        "\n",
+        "First, create a environment with Docker enable and required package dependencies specified."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "mlflow"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "from azureml.core import Environment\n",
+        "from azureml.core.conda_dependencies import CondaDependencies\n",
+        "\n",
+        "env = Environment(name=\"mlflow-env\")\n",
+        "\n",
+        "env.docker.enabled = True\n",
+        "\n",
+        "# Specify conda dependencies with scikit-learn and temporary pointers to mlflow extensions\n",
+        "cd = CondaDependencies.create(\n",
+        "    conda_packages=[\"scikit-learn\", \"matplotlib\"],\n",
+        "    pip_packages=[\"azureml-mlflow\", \"numpy\"]\n",
+        "    )\n",
+        "\n",
+        "env.python.conda_dependencies = cd"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Next, specify a script run configuration that includes the training script, environment and CPU cluster created earlier."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core import ScriptRunConfig\n",
+        "\n",
+        "src = ScriptRunConfig(source_directory=\".\", script=training_script)\n",
+        "src.run_config.environment = env\n",
+        "src.run_config.target = cpu_cluster.name"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Finally, submit the run. Note that the first instance of the run typically takes longer as the Docker-based environment is created, several minutes. Subsequent runs reuse the image and are faster."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run = exp.submit(src)\n",
+        "run.wait_for_completion(show_output=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can navigate to your Azure ML Workspace at Azure Portal to view the run metrics and artifacts. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can also get the metrics and bring them to your local notebook, and view the details of the run."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run.get_metrics()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws.get_details()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Next steps\n",
+        "\n",
+        " * [Deploy the model as a web service](../deploy-model/deploy-model.ipynb)\n",
+        " * [Learn more about Azure Machine Learning compute options](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-set-up-training-targets)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": []
+    }
   ],
-  "kernelspec": {
-   "display_name": "Python 3.6",
-   "language": "python",
-   "name": "python36"
+  "metadata": {
+    "authors": [
+      {
+        "name": "rastala"
+      }
+    ],
+    "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": "3.6.4"
+    }
   },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.6.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
+  "nbformat": 4,
+  "nbformat_minor": 2
 }

how-to-use-azureml/work-with-data/dataprep/how-to-guides/add-column-using-expression.ipynb

@@ -1,5 +1,12 @@
 {
   "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/work-with-data/dataprep/how-to-guides/add-column-using-expression.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

how-to-use-azureml/work-with-data/dataprep/how-to-guides/append-columns-and-rows.ipynb

@@ -1,5 +1,12 @@
 {
   "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/work-with-data/dataprep/how-to-guides/append-columns-and-rows.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

how-to-use-azureml/work-with-data/dataprep/how-to-guides/assertions.ipynb

@@ -1,5 +1,12 @@
 {
   "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/work-with-data/dataprep/how-to-guides/assertions.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

how-to-use-azureml/work-with-data/dataprep/how-to-guides/auto-read-file.ipynb

@@ -1,5 +1,12 @@
 {
   "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/work-with-data/dataprep/how-to-guides/auto-read-file.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

how-to-use-azureml/work-with-data/dataprep/how-to-guides/cache.ipynb

@@ -1,5 +1,12 @@
 {
   "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/work-with-data/dataprep/how-to-guides/cache.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

how-to-use-azureml/work-with-data/dataprep/how-to-guides/column-manipulations.ipynb

@@ -1,5 +1,12 @@
 {
   "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/work-with-data/dataprep/how-to-guides/column-manipulations.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

how-to-use-azureml/work-with-data/dataprep/how-to-guides/column-type-transforms.ipynb

@@ -1,5 +1,12 @@
 {
   "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/work-with-data/dataprep/how-to-guides/column-type-transforms.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

how-to-use-azureml/work-with-data/dataprep/how-to-guides/custom-python-transforms.ipynb

@@ -1,5 +1,12 @@
 {
   "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/work-with-data/dataprep/how-to-guides/custom-python-transforms.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

how-to-use-azureml/work-with-data/dataprep/how-to-guides/data-ingestion.ipynb

@@ -1,5 +1,12 @@
 {
   "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/work-with-data/dataprep/how-to-guides/data-ingestion.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

how-to-use-azureml/work-with-data/dataprep/how-to-guides/data-profile.ipynb

@@ -1,5 +1,12 @@
 {
   "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/work-with-data/dataprep/how-to-guides/data-profile.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

how-to-use-azureml/work-with-data/dataprep/how-to-guides/datastore.ipynb

@@ -1,5 +1,12 @@
 {
   "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/work-with-data/dataprep/how-to-guides/datastore.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

how-to-use-azureml/work-with-data/dataprep/how-to-guides/derive-column-by-example.ipynb

@@ -1,5 +1,12 @@
 {
   "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/work-with-data/dataprep/how-to-guides/derive-column-by-example.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

how-to-use-azureml/work-with-data/dataprep/how-to-guides/external-references.ipynb

@@ -1,5 +1,12 @@
 {
   "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/work-with-data/dataprep/how-to-guides/external-references.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

how-to-use-azureml/work-with-data/dataprep/how-to-guides/filtering.ipynb

@@ -1,5 +1,12 @@
 {
   "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/work-with-data/dataprep/how-to-guides/filtering.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

how-to-use-azureml/work-with-data/dataprep/how-to-guides/fuzzy-group.ipynb

@@ -1,5 +1,12 @@
 {
   "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/work-with-data/dataprep/how-to-guides/fuzzy-group.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

how-to-use-azureml/work-with-data/dataprep/how-to-guides/impute-missing-values.ipynb

@@ -1,5 +1,12 @@
 {
   "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/work-with-data/dataprep/how-to-guides/impute-missing-values.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},