Create deploymentconfig.json

Dockerfiles/1.0.41/Dockerfile

@@ -1,29 +0,0 @@
-FROM continuumio/miniconda:4.5.11
-
-# install git
-RUN apt-get update && apt-get upgrade -y && apt-get install -y git
-
-# create a new conda environment named azureml
-RUN conda create -n azureml -y -q Python=3.6
-
-# install additional packages used by sample notebooks. this is optional
-RUN ["/bin/bash", "-c", "source activate azureml && conda install -y tqdm cython matplotlib scikit-learn"]
-
-# install azurmel-sdk components
-RUN ["/bin/bash", "-c", "source activate azureml && pip install azureml-sdk[notebooks]==1.0.41"]
-
-# clone Azure ML GitHub sample notebooks
-RUN cd /home && git clone -b "azureml-sdk-1.0.41" --single-branch https://github.com/Azure/MachineLearningNotebooks.git
-
-# generate jupyter configuration file
-RUN ["/bin/bash", "-c", "source activate azureml && mkdir ~/.jupyter && cd ~/.jupyter && jupyter notebook --generate-config"]
-
-# set an emtpy token for Jupyter to remove authentication. 
-# this is NOT recommended for production environment
-RUN echo "c.NotebookApp.token = ''" >> ~/.jupyter/jupyter_notebook_config.py
-
-# open up port 8887 on the container
-EXPOSE 8887
-
-# start Jupyter notebook server on port 8887 when the container starts
-CMD /bin/bash -c "cd /home/MachineLearningNotebooks && source activate azureml && jupyter notebook --port 8887 --no-browser --ip 0.0.0.0 --allow-root"

Dockerfiles/1.0.43/Dockerfile

@@ -1,29 +0,0 @@
-FROM continuumio/miniconda:4.5.11
-
-# install git
-RUN apt-get update && apt-get upgrade -y && apt-get install -y git
-
-# create a new conda environment named azureml
-RUN conda create -n azureml -y -q Python=3.6
-
-# install additional packages used by sample notebooks. this is optional
-RUN ["/bin/bash", "-c", "source activate azureml && conda install -y tqdm cython matplotlib scikit-learn"]
-
-# install azurmel-sdk components
-RUN ["/bin/bash", "-c", "source activate azureml && pip install azureml-sdk[notebooks]==1.0.43"]
-
-# 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"

NBSETUP.md

@@ -24,8 +24,8 @@ pip install azureml-sdk
 git clone https://github.com/Azure/MachineLearningNotebooks.git
 
 # below steps are optional
-# install the base SDK, Jupyter notebook server and tensorboard
-pip install azureml-sdk[notebooks,tensorboard]
+# install the base SDK and a Jupyter notebook server
+pip install azureml-sdk[notebooks]
 
 # install model explainability component
 pip install azureml-sdk[explain]

README.md

@@ -11,7 +11,7 @@ pip install azureml-sdk
 Read more detailed instructions on [how to set up your environment](./NBSETUP.md) using Azure Notebook service, your own Jupyter notebook server, or Docker.
 
 ## How to navigate and use the example notebooks?
-If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, you should always run the [Configuration](./configuration.ipynb) notebook first when setting up a notebook library on a new machine or in a new environment. It configures your notebook library to connect to an Azure Machine Learning workspace, and sets up your workspace and compute to be used by many of the other examples. 
+You should always run the [Configuration](./configuration.ipynb) notebook first when setting up a notebook library on a new machine or in a new environment. It configures your notebook library to connect to an Azure Machine Learning workspace, and sets up your workspace and compute to be used by many of the other examples. 
 
 If you want to...
 
@@ -20,7 +20,7 @@ If you want to...
  * ...learn about experimentation and tracking run history, first [train within Notebook](./how-to-use-azureml/training/train-within-notebook/train-within-notebook.ipynb), then try [training on remote VM](./how-to-use-azureml/training/train-on-remote-vm/train-on-remote-vm.ipynb) and [using logging APIs](./how-to-use-azureml/training/logging-api/logging-api.ipynb).
  * ...train deep learning models at scale, first learn about [Machine Learning Compute](./how-to-use-azureml/training/train-on-amlcompute/train-on-amlcompute.ipynb), and then try [distributed hyperparameter tuning](./how-to-use-azureml/training-with-deep-learning/train-hyperparameter-tune-deploy-with-pytorch/train-hyperparameter-tune-deploy-with-pytorch.ipynb) and [distributed training](./how-to-use-azureml/training-with-deep-learning/distributed-pytorch-with-horovod/distributed-pytorch-with-horovod.ipynb).
  * ...deploy models as a realtime scoring service, first learn the basics by [training within Notebook and deploying to Azure Container Instance](./how-to-use-azureml/training/train-within-notebook/train-within-notebook.ipynb), then learn how to [register and manage models, and create Docker images](./how-to-use-azureml/deployment/register-model-create-image-deploy-service/register-model-create-image-deploy-service.ipynb), and [production deploy models on Azure Kubernetes Cluster](./how-to-use-azureml/deployment/production-deploy-to-aks/production-deploy-to-aks.ipynb).
- * ...deploy models as a batch scoring service, first [train a model within Notebook](./how-to-use-azureml/training/train-within-notebook/train-within-notebook.ipynb), learn how to [register and manage models](./how-to-use-azureml/deployment/register-model-create-image-deploy-service/register-model-create-image-deploy-service.ipynb), then [create Machine Learning Compute for scoring compute](./how-to-use-azureml/training/train-on-amlcompute/train-on-amlcompute.ipynb), and [use Machine Learning Pipelines to deploy your model](https://aka.ms/pl-batch-scoring).
+ * ...deploy models as a batch scoring service, first [train a model within Notebook](./how-to-use-azureml/training/train-within-notebook/train-within-notebook.ipynb), learn how to [register and manage models](./how-to-use-azureml/deployment/register-model-create-image-deploy-service/register-model-create-image-deploy-service.ipynb), then [create Machine Learning Compute for scoring compute](./how-to-use-azureml/training/train-on-amlcompute/train-on-amlcompute.ipynb), and [use Machine Learning Pipelines to deploy your model](./how-to-use-azureml/machine-learning-pipelines/pipeline-mpi-batch-prediction.ipynb).
  * ...monitor your deployed models, learn about using [App Insights](./how-to-use-azureml/deployment/enable-app-insights-in-production-service/enable-app-insights-in-production-service.ipynb) and [model data collection](./how-to-use-azureml/deployment/enable-data-collection-for-models-in-aks/enable-data-collection-for-models-in-aks.ipynb).
 
 ## Tutorials
@@ -53,16 +53,4 @@ 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:
 
  - [Fine tune natural language processing models using Azure Machine Learning service](https://github.com/Microsoft/AzureML-BERT)
- - [Fashion MNIST with Azure ML SDK](https://github.com/amynic/azureml-sdk-fashion)
- 
-## Data/Telemetry 
-This repository collects usage data and sends it to Mircosoft to help improve our products and services. Read Microsoft's [privacy statement to learn more](https://privacy.microsoft.com/en-US/privacystatement)
-
-To opt out of tracking, please go to the raw markdown or .ipynb files and remove the following line of code:
-
-```sh
-    "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/README.png)"
-```
-This URL will be slightly different depending on the file. 
-
- ![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/README.png)
+ - [Fashion MNIST with Azure ML SDK](https://github.com/amynic/azureml-sdk-fashion)

configuration.ipynb

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/configuration.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -103,7 +96,7 @@
       "source": [
         "import azureml.core\n",
         "\n",
-        "print(\"This notebook was created using version 1.0.45 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version 1.0.23 of the Azure ML SDK\")\n",
         "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },
@@ -275,14 +268,14 @@
         "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# Choose a name for your CPU cluster\n",
-        "cpu_cluster_name = \"cpu-cluster\"\n",
+        "cpu_cluster_name = \"cpucluster\"\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",
+        "    print(\"Found existing cpucluster\")\n",
         "except ComputeTargetException:\n",
-        "    print(\"Creating new cpu-cluster\")\n",
+        "    print(\"Creating new cpucluster\")\n",
         "    \n",
         "    # Specify the configuration for the new cluster\n",
         "    compute_config = AmlCompute.provisioning_configuration(vm_size=\"STANDARD_D2_V2\",\n",
@@ -313,14 +306,14 @@
         "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# Choose a name for your GPU cluster\n",
-        "gpu_cluster_name = \"gpu-cluster\"\n",
+        "gpu_cluster_name = \"gpucluster\"\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",
+        "    print(\"Creating new gpucluster\")\n",
         "    \n",
         "    # Specify the configuration for the new cluster\n",
         "    compute_config = AmlCompute.provisioning_configuration(vm_size=\"STANDARD_NC6\",\n",

contrib/datadrift/azure-ml-datadrift.ipynb

@@ -1,709 +0,0 @@
-{
-  "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

@@ -1,58 +0,0 @@
-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/README.md

@@ -15,3 +15,6 @@ As a pre-requisite, run the [configuration Notebook](../configuration.ipynb) not
 * [enable-app-insights-in-production-service](./deployment/enable-app-insights-in-production-service) Learn how to use App Insights with production web service.
  
 Find quickstarts, end-to-end tutorials, and how-tos on the [official documentation site for Azure Machine Learning service](https://docs.microsoft.com/en-us/azure/machine-learning/service/).
+
+
+ ![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/README.png)

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

@@ -115,7 +115,16 @@ jupyter notebook
     - Simple example of using automated ML for regression
     - Uses local compute for training
 
-- [auto-ml-remote-amlcompute.ipynb](remote-amlcompute/auto-ml-remote-amlcompute.ipynb)
+- [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)
     - 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
@@ -124,6 +133,12 @@ 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
@@ -141,6 +156,10 @@ 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
@@ -179,26 +198,6 @@ 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_env.yml

@@ -10,7 +10,7 @@ dependencies:
 - urllib3<1.24
 - scipy>=1.0.0,<=1.1.0
 - scikit-learn>=0.19.0,<=0.20.3
-- pandas>=0.22.0,<=0.23.4
+- pandas>=0.22.0,<0.23.0
 - py-xgboost<=0.80
 
 - pip:

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

@@ -1,22 +0,0 @@
-name: azure_automl
-dependencies:
-  # The python interpreter version.
-  # Currently Azure ML only supports 3.5.2 and later.
-- nomkl
-- python>=3.5.2,<3.6.8
-- nb_conda
-- matplotlib==2.1.0
-- numpy>=1.11.0,<=1.16.2
-- cython
-- urllib3<1.24
-- scipy>=1.0.0,<=1.1.0
-- scikit-learn>=0.19.0,<=0.20.3
-- pandas>=0.22.0,<0.23.0
-- py-xgboost<=0.80
-
-- pip:
-  # Required packages for AzureML execution, history, and data preparation.
-  - azureml-sdk[automl,explain]
-  - azureml-widgets
-  - pandas_ml
-  

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

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

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

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

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

@@ -1,729 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-    "\n",
-    "Licensed under the MIT License."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "![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

@@ -1,712 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-    "\n",
-    "Licensed under the MIT License."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "![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-deployment/auto-ml-classification-with-deployment.ipynb

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/classification-with-deployment/auto-ml-classification-with-deployment.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

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

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/classification-with-onnx/auto-ml-classification-with-onnx.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -73,12 +66,11 @@
         "import numpy as np\n",
         "import pandas as pd\n",
         "from sklearn import datasets\n",
-        "from sklearn.model_selection import train_test_split\n",
         "\n",
         "import azureml.core\n",
         "from azureml.core.experiment import Experiment\n",
         "from azureml.core.workspace import Workspace\n",
-        "from azureml.train.automl import AutoMLConfig, constants"
+        "from azureml.train.automl import AutoMLConfig"
       ]
     },
     {
@@ -114,7 +106,7 @@
       "source": [
         "## Data\n",
         "\n",
-        "This uses scikit-learn's [load_iris](https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_iris.html) method."
+        "This uses scikit-learn's [load_digits](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) method."
       ]
     },
     {
@@ -123,33 +115,11 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "iris = datasets.load_iris()\n",
-        "X_train, X_test, y_train, y_test = train_test_split(iris.data, \n",
-        "                                                    iris.target, \n",
-        "                                                    test_size=0.2, \n",
-        "                                                    random_state=0)\n",
+        "digits = datasets.load_digits()\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",
-        "X_train = pd.DataFrame(X_train, columns=['c1', 'c2', 'c3', 'c4'])\n",
-        "X_test = pd.DataFrame(X_test, columns=['c1', 'c2', 'c3', 'c4'])"
+        "# Exclude the first 100 rows from training so that they can be used for test.\n",
+        "X_train = digits.data[100:,:]\n",
+        "y_train = digits.target[100:]"
       ]
     },
     {
@@ -174,13 +144,6 @@
         "|**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,
@@ -192,10 +155,9 @@
         "                             primary_metric = 'AUC_weighted',\n",
         "                             iteration_timeout_minutes = 60,\n",
         "                             iterations = 10,\n",
-        "                             verbosity = logging.INFO,                             \n",
+        "                             verbosity = logging.INFO,\n",
         "                             X = X_train, \n",
         "                             y = y_train,\n",
-        "                             preprocess=True,\n",
         "                             enable_onnx_compatible_models=True,\n",
         "                             path = project_folder)"
       ]
@@ -287,69 +249,10 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.automl.core.onnx_convert import OnnxConverter\n",
+        "from azureml.train.automl._vendor.automl.client.core.common.onnx_convert import OnnxConverter\n",
         "onnx_fl_path = \"./best_model.onnx\"\n",
         "OnnxConverter.save_onnx_model(onnx_mdl, onnx_fl_path)"
       ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Predict with the ONNX model, using onnxruntime package"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import sys\n",
-        "import json\n",
-        "from azureml.automl.core.onnx_convert import OnnxConvertConstants\n",
-        "\n",
-        "if sys.version_info < OnnxConvertConstants.OnnxIncompatiblePythonVersion:\n",
-        "    python_version_compatible = True\n",
-        "else:\n",
-        "    python_version_compatible = False\n",
-        "\n",
-        "try:\n",
-        "    import onnxruntime\n",
-        "    from azureml.automl.core.onnx_convert import OnnxInferenceHelper    \n",
-        "    onnxrt_present = True\n",
-        "except ImportError:\n",
-        "    onnxrt_present = False\n",
-        "\n",
-        "def get_onnx_res(run):\n",
-        "    res_path = 'onnx_resource.json'\n",
-        "    run.download_file(name=constants.MODEL_RESOURCE_PATH_ONNX, output_file_path=res_path)\n",
-        "    with open(res_path) as f:\n",
-        "        onnx_res = json.load(f)\n",
-        "    return onnx_res\n",
-        "\n",
-        "if onnxrt_present and python_version_compatible:    \n",
-        "    mdl_bytes = onnx_mdl.SerializeToString()\n",
-        "    onnx_res = get_onnx_res(best_run)\n",
-        "\n",
-        "    onnxrt_helper = OnnxInferenceHelper(mdl_bytes, onnx_res)\n",
-        "    pred_onnx, pred_prob_onnx = onnxrt_helper.predict(X_test)\n",
-        "\n",
-        "    print(pred_onnx)\n",
-        "    print(pred_prob_onnx)\n",
-        "else:\n",
-        "    if not python_version_compatible:\n",
-        "        print('Please use Python version 3.6 or 3.7 to run the inference helper.')    \n",
-        "    if not onnxrt_present:\n",
-        "        print('Please install the onnxruntime package to do the prediction with ONNX model.')"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": []
     }
   ],
   "metadata": {

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

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/classification-with-whitelisting/auto-ml-classification-with-whitelisting.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

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

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/classification/auto-ml-classification.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -335,12 +328,6 @@
         "            print()\n",
         "            for estimator in step[1].estimators:\n",
         "                print_model(estimator[1], estimator[0]+ ' - ')\n",
-        "        elif hasattr(step[1], '_base_learners') and hasattr(step[1], '_meta_learner'):\n",
-        "            print(\"\\nMeta Learner\")\n",
-        "            pprint(step[1]._meta_learner)\n",
-        "            print()\n",
-        "            for estimator in step[1]._base_learners:\n",
-        "                print_model(estimator[1], estimator[0]+ ' - ')\n",
         "        else:\n",
         "            pprint(step[1].get_params())\n",
         "            print()\n",

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

@@ -9,19 +9,12 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/dataprep-remote-execution/auto-ml-dataprep-remote-execution.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
         "# Automated Machine Learning\n",
-        "_**Prepare Data using `azureml.dataprep` for Remote Execution (AmlCompute)**_\n",
+        "_**Prepare Data using `azureml.dataprep` for Remote Execution (DSVM)**_\n",
         "\n",
         "## Contents\n",
         "1. [Introduction](#Introduction)\n",
@@ -124,34 +117,21 @@
       "outputs": [],
       "source": [
         "# You can use `auto_read_file` which intelligently figures out delimiters and datatypes of a file.\n",
-        "# The data referenced here was a 1MB simple random sample of the Chicago Crime data into a local temporary directory.\n",
+        "# The data referenced here was pulled from `sklearn.datasets.load_digits()`.\n",
+        "simple_example_data_root = 'https://dprepdata.blob.core.windows.net/automl-notebook-data/'\n",
+        "X = dprep.auto_read_file(simple_example_data_root + 'X.csv').skip(1)  # Remove the header row.\n",
+        "\n",
         "# You can also use `read_csv` and `to_*` transformations to read (with overridable delimiter)\n",
         "# and convert column types manually.\n",
-        "example_data = 'https://dprepdata.blob.core.windows.net/demo/crime0-random.csv'\n",
-        "dflow = dprep.auto_read_file(example_data).skip(1)  # Remove the header row.\n",
-        "dflow.get_profile()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# As `Primary Type` is our y data, we need to drop the values those are null in this column.\n",
-        "dflow = dflow.drop_nulls('Primary Type')\n",
-        "dflow.head(5)"
+        "# Here we read a comma delimited file and convert all columns to integers.\n",
+        "y = dprep.read_csv(simple_example_data_root + 'y.csv').to_long(dprep.ColumnSelector(term='.*', use_regex = True))"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Review the Data Preparation Result\n",
-        "\n",
-        "You can peek the result of a Dataflow at any range using `skip(i)` and `head(j)`. Doing so evaluates only `j` records for all the steps in the Dataflow, which makes it fast even against large datasets.\n",
-        "\n",
-        "`Dataflow` objects are immutable and are composed of a list of data preparation steps. A `Dataflow` object can be branched at any point for further usage."
+        "You can peek the result of a Dataflow at any range using `skip(i)` and `head(j)`. Doing so evaluates only `j` records for all the steps in the Dataflow, which makes it fast even against large datasets."
       ]
     },
     {
@@ -160,8 +140,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "X = dflow.drop_columns(columns=['Primary Type', 'FBI Code'])\n",
-        "y = dflow.keep_columns(columns=['Primary Type'], validate_column_exists=True)"
+        "X.skip(1).head(5)"
       ]
     },
     {
@@ -183,8 +162,9 @@
         "    \"iteration_timeout_minutes\" : 10,\n",
         "    \"iterations\" : 2,\n",
         "    \"primary_metric\" : 'AUC_weighted',\n",
-        "    \"preprocess\" : True,\n",
-        "    \"verbosity\" : logging.INFO\n",
+        "    \"preprocess\" : False,\n",
+        "    \"verbosity\" : logging.INFO,\n",
+        "    \"n_cross_validations\": 3\n",
         "}"
       ]
     },
@@ -192,7 +172,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Create or Attach an AmlCompute cluster"
+        "### Create or Attach a Remote Linux DSVM"
       ]
     },
     {
@@ -201,36 +181,21 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.core.compute import AmlCompute\n",
-        "from azureml.core.compute import ComputeTarget\n",
+        "dsvm_name = 'mydsvmc'\n",
         "\n",
-        "# Choose a name for your cluster.\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",
-        "    print('Found existing compute target.')\n",
-        "    compute_target = cts[amlcompute_cluster_name]\n",
-        "\n",
-        "if not found:\n",
-        "    print('Creating a new compute target...')\n",
-        "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
-        "                                                                #vm_priority = 'lowpriority', # optional\n",
-        "                                                                max_nodes = 6)\n",
-        "\n",
-        "    # Create the cluster.\\n\",\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
-        "\n",
-        "    # 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()."
+        "try:\n",
+        "    while ws.compute_targets[dsvm_name].provisioning_state == 'Creating':\n",
+        "        time.sleep(1)\n",
+        "        \n",
+        "    dsvm_compute = DsvmCompute(ws, dsvm_name)\n",
+        "    print('Found existing DVSM.')\n",
+        "except:\n",
+        "    print('Creating a new DSVM.')\n",
+        "    dsvm_config = DsvmCompute.provisioning_configuration(vm_size = \"Standard_D2_v2\")\n",
+        "    dsvm_compute = DsvmCompute.create(ws, name = dsvm_name, provisioning_configuration = dsvm_config)\n",
+        "    dsvm_compute.wait_for_completion(show_output = True)\n",
+        "    print(\"Waiting one minute for ssh to be accessible\")\n",
+        "    time.sleep(90) # Wait for ssh to be accessible"
       ]
     },
     {
@@ -242,13 +207,9 @@
         "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",
+        "conda_run_config.target = dsvm_compute\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"
@@ -296,44 +257,6 @@
         "remote_run"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Pre-process cache cleanup\n",
-        "The preprocess data gets cache at user default file store. When the run is completed the cache can be cleaned by running below cell"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run.clean_preprocessor_cache()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Cancelling Runs\n",
-        "You can cancel ongoing remote runs using the `cancel` and `cancel_iteration` functions."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Cancel the ongoing experiment and stop scheduling new iterations.\n",
-        "# remote_run.cancel()\n",
-        "\n",
-        "# Cancel iteration 1 and move onto iteration 2.\n",
-        "# remote_run.cancel_iteration(1)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -453,8 +376,7 @@
       "source": [
         "## Test\n",
         "\n",
-        "#### Load Test Data\n",
-        "For the test data, it should have the same preparation step as the train data. Otherwise it might get failed at the preprocessing step."
+        "#### Load Test Data"
       ]
     },
     {
@@ -463,8 +385,12 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "dflow_test = dprep.auto_read_file(path='https://dprepdata.blob.core.windows.net/demo/crime0-test.csv').skip(1)\n",
-        "dflow_test = dflow_test.drop_nulls('Primary Type')"
+        "from sklearn import datasets\n",
+        "\n",
+        "digits = datasets.load_digits()\n",
+        "X_test = digits.data[:10, :]\n",
+        "y_test = digits.target[:10]\n",
+        "images = digits.images[:10]"
       ]
     },
     {
@@ -472,7 +398,7 @@
       "metadata": {},
       "source": [
         "#### Testing Our Best Fitted Model\n",
-        "We will use confusion matrix to see how our model works."
+        "We will try to predict 2 digits and see how our model works."
       ]
     },
     {
@@ -481,19 +407,65 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from pandas_ml import ConfusionMatrix\n",
+        "#Randomly select digits and test\n",
+        "from matplotlib import pyplot as plt\n",
+        "import numpy as np\n",
         "\n",
-        "y_test = dflow_test.keep_columns(columns=['Primary Type']).to_pandas_dataframe()\n",
-        "X_test = dflow_test.drop_columns(columns=['Primary Type', 'FBI Code']).to_pandas_dataframe()\n",
+        "for index in np.random.choice(len(y_test), 2, replace = False):\n",
+        "    print(index)\n",
+        "    predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
+        "    label = y_test[index]\n",
+        "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
+        "    fig = plt.figure(1, figsize=(3,3))\n",
+        "    ax1 = fig.add_axes((0,0,.8,.8))\n",
+        "    ax1.set_title(title)\n",
+        "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
+        "    plt.show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Appendix"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Capture the `Dataflow` Objects for Later Use in AutoML\n",
         "\n",
-        "\n",
-        "ypred = fitted_model.predict(X_test)\n",
-        "\n",
-        "cm = ConfusionMatrix(y_test['Primary Type'], ypred)\n",
-        "\n",
-        "print(cm)\n",
-        "\n",
-        "cm.plot()"
+        "`Dataflow` objects are immutable and are composed of a list of data preparation steps. A `Dataflow` object can be branched at any point for further usage."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# sklearn.digits.data + target\n",
+        "digits_complete = dprep.auto_read_file('https://dprepdata.blob.core.windows.net/automl-notebook-data/digits-complete.csv')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "`digits_complete` (sourced from `sklearn.datasets.load_digits()`) is forked into `dflow_X` to capture all the feature columns and `dflow_y` to capture the label column."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(digits_complete.to_pandas_dataframe().shape)\n",
+        "labels_column = 'Column64'\n",
+        "dflow_X = digits_complete.drop_columns(columns = [labels_column])\n",
+        "dflow_y = digits_complete.keep_columns(columns = [labels_column])"
       ]
     }
   ],

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

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/dataprep/auto-ml-dataprep.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -122,23 +115,14 @@
       "outputs": [],
       "source": [
         "# You can use `auto_read_file` which intelligently figures out delimiters and datatypes of a file.\n",
-        "# The data referenced here was a 1MB simple random sample of the Chicago Crime data into a local temporary directory.\n",
+        "# The data referenced here was pulled from `sklearn.datasets.load_digits()`.\n",
+        "simple_example_data_root = 'https://dprepdata.blob.core.windows.net/automl-notebook-data/'\n",
+        "X = dprep.auto_read_file(simple_example_data_root + 'X.csv').skip(1)  # Remove the header row.\n",
+        "\n",
         "# You can also use `read_csv` and `to_*` transformations to read (with overridable delimiter)\n",
         "# and convert column types manually.\n",
-        "example_data = 'https://dprepdata.blob.core.windows.net/demo/crime0-random.csv'\n",
-        "dflow = dprep.auto_read_file(example_data).skip(1)  # Remove the header row.\n",
-        "dflow.get_profile()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# As `Primary Type` is our y data, we need to drop the values those are null in this column.\n",
-        "dflow = dflow.drop_nulls('Primary Type')\n",
-        "dflow.head(5)"
+        "# Here we read a comma delimited file and convert all columns to integers.\n",
+        "y = dprep.read_csv(simple_example_data_root + 'y.csv').to_long(dprep.ColumnSelector(term='.*', use_regex = True))"
       ]
     },
     {
@@ -147,9 +131,7 @@
       "source": [
         "### Review the Data Preparation Result\n",
         "\n",
-        "You can peek the result of a Dataflow at any range using `skip(i)` and `head(j)`. Doing so evaluates only `j` records for all the steps in the Dataflow, which makes it fast even against large datasets.\n",
-        "\n",
-        "`Dataflow` objects are immutable and are composed of a list of data preparation steps. A `Dataflow` object can be branched at any point for further usage."
+        "You can peek the result of a Dataflow at any range using `skip(i)` and `head(j)`. Doing so evaluates only `j` records for all the steps in the Dataflow, which makes it fast even against large datasets."
       ]
     },
     {
@@ -158,8 +140,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "X = dflow.drop_columns(columns=['Primary Type', 'FBI Code'])\n",
-        "y = dflow.keep_columns(columns=['Primary Type'], validate_column_exists=True)"
+        "X.skip(1).head(5)"
       ]
     },
     {
@@ -181,7 +162,7 @@
         "    \"iteration_timeout_minutes\" : 10,\n",
         "    \"iterations\" : 2,\n",
         "    \"primary_metric\" : 'AUC_weighted',\n",
-        "    \"preprocess\" : True,\n",
+        "    \"preprocess\" : False,\n",
         "    \"verbosity\" : logging.INFO\n",
         "}"
       ]
@@ -345,8 +326,7 @@
       "source": [
         "## Test\n",
         "\n",
-        "#### Load Test Data\n",
-        "For the test data, it should have the same preparation step as the train data. Otherwise it might get failed at the preprocessing step."
+        "#### Load Test Data"
       ]
     },
     {
@@ -355,8 +335,12 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "dflow_test = dprep.auto_read_file(path='https://dprepdata.blob.core.windows.net/demo/crime0-test.csv').skip(1)\n",
-        "dflow_test = dflow_test.drop_nulls('Primary Type')"
+        "from sklearn import datasets\n",
+        "\n",
+        "digits = datasets.load_digits()\n",
+        "X_test = digits.data[:10, :]\n",
+        "y_test = digits.target[:10]\n",
+        "images = digits.images[:10]"
       ]
     },
     {
@@ -364,7 +348,7 @@
       "metadata": {},
       "source": [
         "#### Testing Our Best Fitted Model\n",
-        "We will use confusion matrix to see how our model works."
+        "We will try to predict 2 digits and see how our model works."
       ]
     },
     {
@@ -373,18 +357,65 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from pandas_ml import ConfusionMatrix\n",
+        "#Randomly select digits and test\n",
+        "from matplotlib import pyplot as plt\n",
+        "import numpy as np\n",
         "\n",
-        "y_test = dflow_test.keep_columns(columns=['Primary Type']).to_pandas_dataframe()\n",
-        "X_test = dflow_test.drop_columns(columns=['Primary Type', 'FBI Code']).to_pandas_dataframe()\n",
+        "for index in np.random.choice(len(y_test), 2, replace = False):\n",
+        "    print(index)\n",
+        "    predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
+        "    label = y_test[index]\n",
+        "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
+        "    fig = plt.figure(1, figsize=(3,3))\n",
+        "    ax1 = fig.add_axes((0,0,.8,.8))\n",
+        "    ax1.set_title(title)\n",
+        "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
+        "    plt.show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Appendix"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Capture the `Dataflow` Objects for Later Use in AutoML\n",
         "\n",
-        "ypred = fitted_model.predict(X_test)\n",
-        "\n",
-        "cm = ConfusionMatrix(y_test['Primary Type'], ypred)\n",
-        "\n",
-        "print(cm)\n",
-        "\n",
-        "cm.plot()"
+        "`Dataflow` objects are immutable and are composed of a list of data preparation steps. A `Dataflow` object can be branched at any point for further usage."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# sklearn.digits.data + target\n",
+        "digits_complete = dprep.auto_read_file('https://dprepdata.blob.core.windows.net/automl-notebook-data/digits-complete.csv')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "`digits_complete` (sourced from `sklearn.datasets.load_digits()`) is forked into `dflow_X` to capture all the feature columns and `dflow_y` to capture the label column."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(digits_complete.to_pandas_dataframe().shape)\n",
+        "labels_column = 'Column64'\n",
+        "dflow_X = digits_complete.drop_columns(columns = [labels_column])\n",
+        "dflow_y = digits_complete.keep_columns(columns = [labels_column])"
       ]
     }
   ],

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

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/exploring-previous-runs/auto-ml-exploring-previous-runs.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

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

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/forecasting-bike-share/auto-ml-forecasting-bike-share.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -72,6 +65,7 @@
         "# 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",
@@ -226,7 +220,7 @@
         "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
         "|**y**|(sparse) array-like, shape = [n_samples, ], targets values.|\n",
         "|**n_cross_validations**|Number of cross validation splits.|\n",
-        "|**country_or_region**|The country/region used to generate holiday features. These should be ISO 3166 two-letter country/region codes (i.e. 'US', 'GB').|\n",
+        "|**country**|The country used to generate holiday features. These should be ISO 3166 two-letter country codes (i.e. 'US', 'GB').|\n",
         "|**path**|Relative path to the project folder.  AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder. "
       ]
     },
@@ -241,8 +235,8 @@
         "    \"time_column_name\": time_column_name,\n",
         "    # these columns are a breakdown of the total and therefore a leak\n",
         "    \"drop_column_names\": ['casual', 'registered'],\n",
-        "    # knowing the country/region allows Automated ML to bring in holidays\n",
-        "    \"country_or_region\" : 'US',\n",
+        "    # knowing the country allows Automated ML to bring in holidays\n",
+        "    \"country\" : 'US',\n",
         "    \"max_horizon\" : max_horizon,\n",
         "    \"target_lags\": 1    \n",
         "}\n",

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

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand/auto-ml-forecasting-energy-demand.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -65,6 +58,10 @@
         "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

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales/auto-ml-forecasting-orange-juice-sales.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -67,6 +60,10 @@
         "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/missing-data-blacklist-early-termination/auto-ml-missing-data-blacklist-early-termination.ipynb

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/missing-data-blacklist-early-termination/auto-ml-missing-data-blacklist-early-termination.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

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

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/model-explanation/auto-ml-model-explanation.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

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

@@ -1,800 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-    "\n",
-    "Licensed under the MIT License."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "![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

@@ -1,800 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-    "\n",
-    "Licensed under the MIT License."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "![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/regression/auto-ml-regression.ipynb

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/regression/auto-ml-regression.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

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

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/remote-amlcompute/auto-ml-remote-amlcompute.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -136,7 +129,7 @@
         "from azureml.core.compute import ComputeTarget\n",
         "\n",
         "# Choose a name for your cluster.\n",
-        "amlcompute_cluster_name = \"cpu-cluster\"\n",
+        "amlcompute_cluster_name = \"automlcl\"\n",
         "\n",
         "found = False\n",
         "# Check if this compute target already exists in the workspace.\n",
@@ -145,23 +138,30 @@
         "    found = True\n",
         "    print('Found existing compute target.')\n",
         "    compute_target = cts[amlcompute_cluster_name]\n",
-        "\n",
+        "    \n",
         "if not found:\n",
         "    print('Creating a new compute target...')\n",
         "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
         "                                                                #vm_priority = 'lowpriority', # optional\n",
         "                                                                max_nodes = 6)\n",
         "\n",
-        "    # Create the cluster.\\n\",\n",
+        "    # Create the cluster.\n",
         "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
-        "\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",
+        "    \n",
         "     # For a more detailed view of current AmlCompute status, use get_status()."
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": []
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

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

@@ -0,0 +1,558 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "_**Remote Execution using attach**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Data](#Data)\n",
+        "1. [Train](#Train)\n",
+        "1. [Results](#Results)\n",
+        "1. [Test](#Test)\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "In this example we use the scikit-learn's [20newsgroup](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.fetch_20newsgroups.html) to showcase how you can use AutoML to handle text data with remote attach.\n",
+        "\n",
+        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+        "\n",
+        "In this notebook you will learn how to:\n",
+        "1. Create an `Experiment` in an existing `Workspace`.\n",
+        "2. Attach an existing DSVM to a workspace.\n",
+        "3. Configure AutoML using `AutoMLConfig`.\n",
+        "4. Train the model using the DSVM.\n",
+        "5. Explore the results.\n",
+        "6. Viewing the engineered names for featurized data and featurization summary for all raw features.\n",
+        "7. Test the best fitted model.\n",
+        "\n",
+        "In addition this notebook showcases the following features\n",
+        "- **Parallel** executions for iterations\n",
+        "- **Asynchronous** tracking of progress\n",
+        "- **Cancellation** of individual iterations or the entire run\n",
+        "- Retrieving models for any iteration or logged metric\n",
+        "- Specifying AutoML settings as `**kwargs`\n",
+        "- Handling **text** data using the `preprocess` flag"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup\n",
+        "\n",
+        "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "import numpy as np\n",
+        "import pandas as pd\n",
+        "\n",
+        "import azureml.core\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "from azureml.train.automl import AutoMLConfig"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "# Choose a name for the run history container in the workspace.\n",
+        "experiment_name = 'automl-remote-attach'\n",
+        "project_folder = './sample_projects/automl-remote-attach'\n",
+        "\n",
+        "experiment = Experiment(ws, experiment_name)\n",
+        "\n",
+        "output = {}\n",
+        "output['SDK version'] = azureml.core.VERSION\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace'] = ws.name\n",
+        "output['Resource Group'] = ws.resource_group\n",
+        "output['Location'] = ws.location\n",
+        "output['Project Directory'] = project_folder\n",
+        "output['Experiment Name'] = experiment.name\n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
+        "outputDf.T"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Attach a Remote Linux DSVM\n",
+        "To use a remote Docker compute target:\n",
+        "1. Create a Linux DSVM in Azure, following these [instructions](https://docs.microsoft.com/en-us/azure/machine-learning/data-science-virtual-machine/dsvm-ubuntu-intro). Make sure you use the Ubuntu flavor (not CentOS). Make sure that disk space is available under `/tmp` because AutoML creates files under `/tmp/azureml_run`s. The DSVM should have more cores than the number of parallel runs that you plan to enable. It should also have at least 4GB per core.\n",
+        "2. Enter the IP address, user name and password below.\n",
+        "\n",
+        "**Note:** By default, SSH runs on port 22 and you don't need to change the port number below. If you've configured SSH to use a different port, change `dsvm_ssh_port` accordinglyaddress. [Read more](https://docs.microsoft.com/en-us/azure/virtual-machines/troubleshooting/detailed-troubleshoot-ssh-connection) on changing SSH ports for security reasons."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.compute import ComputeTarget, RemoteCompute\n",
+        "import time\n",
+        "\n",
+        "# Add your VM information below\n",
+        "# If a compute with the specified compute_name already exists, it will be used and the dsvm_ip_addr, dsvm_ssh_port, \n",
+        "# dsvm_username and dsvm_password will be ignored.\n",
+        "compute_name  = 'mydsvmb'\n",
+        "dsvm_ip_addr  = '<<ip_addr>>'\n",
+        "dsvm_ssh_port = 22\n",
+        "dsvm_username = '<<username>>'\n",
+        "dsvm_password = '<<password>>'\n",
+        "\n",
+        "if compute_name in ws.compute_targets:\n",
+        "    print('Using existing compute.')\n",
+        "    dsvm_compute = ws.compute_targets[compute_name]\n",
+        "else:\n",
+        "    attach_config = RemoteCompute.attach_configuration(address=dsvm_ip_addr, username=dsvm_username, password=dsvm_password, ssh_port=dsvm_ssh_port)\n",
+        "    ComputeTarget.attach(workspace=ws, name=compute_name, attach_configuration=attach_config)\n",
+        "\n",
+        "    while ws.compute_targets[compute_name].provisioning_state == 'Creating':\n",
+        "        time.sleep(1)\n",
+        "\n",
+        "    dsvm_compute = ws.compute_targets[compute_name]\n",
+        "    \n",
+        "    if dsvm_compute.provisioning_state == 'Failed':\n",
+        "        print('Attached failed.')\n",
+        "        print(dsvm_compute.provisioning_errors)\n",
+        "        dsvm_compute.detach()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.runconfig import RunConfiguration\n",
+        "from azureml.core.conda_dependencies import CondaDependencies\n",
+        "import pkg_resources\n",
+        "\n",
+        "# create a new RunConfig object\n",
+        "conda_run_config = RunConfiguration(framework=\"python\")\n",
+        "\n",
+        "# Set compute target to the Linux DSVM\n",
+        "conda_run_config.target = dsvm_compute\n",
+        "\n",
+        "pandas_dependency = 'pandas==' + pkg_resources.get_distribution(\"pandas\").version\n",
+        "\n",
+        "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy','py-xgboost<=0.80',pandas_dependency])\n",
+        "conda_run_config.environment.python.conda_dependencies = cd"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Data\n",
+        "For remote executions you should author a `get_data.py` file containing a `get_data()` function. This file should be in the root directory of the project. You can encapsulate code to read data either from a blob storage or local disk in this file.\n",
+        "In this example, the `get_data()` function returns a [dictionary](README.md#getdata)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "if not os.path.exists(project_folder):\n",
+        "    os.makedirs(project_folder)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%writefile $project_folder/get_data.py\n",
+        "\n",
+        "import numpy as np\n",
+        "from sklearn.datasets import fetch_20newsgroups\n",
+        "\n",
+        "def get_data():\n",
+        "    remove = ('headers', 'footers', 'quotes')\n",
+        "    categories = [\n",
+        "        'alt.atheism',\n",
+        "        'talk.religion.misc',\n",
+        "        'comp.graphics',\n",
+        "        'sci.space',\n",
+        "    ]\n",
+        "    data_train = fetch_20newsgroups(subset = 'train', categories = categories,\n",
+        "                                    shuffle = True, random_state = 42,\n",
+        "                                    remove = remove)\n",
+        "    \n",
+        "    X_train = np.array(data_train.data).reshape((len(data_train.data),1))\n",
+        "    y_train = np.array(data_train.target)\n",
+        "    \n",
+        "    return { \"X\" : X_train, \"y\" : y_train }"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train\n",
+        "\n",
+        "You can specify `automl_settings` as `**kwargs` as well. Also note that you can use a `get_data()` function for local excutions too.\n",
+        "\n",
+        "**Note:** When using Remote DSVM, you can't pass Numpy arrays directly to the fit method.\n",
+        "\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
+        "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+        "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
+        "|**n_cross_validations**|Number of cross validation splits.|\n",
+        "|**max_concurrent_iterations**|Maximum number of iterations that would be executed in parallel. This should be less than the number of cores on the DSVM.|\n",
+        "|**preprocess**|Setting this to *True* enables AutoML to perform preprocessing on the input to handle *missing data*, and to perform some common *feature extraction*.|\n",
+        "|**enable_cache**|Setting this to *True* enables preprocess done once and reuse the same preprocessed data for all the iterations. Default value is True.\n",
+        "|**max_cores_per_iteration**|Indicates how many cores on the compute target would be used to train a single pipeline.<br>Default is *1*; you can set it to *-1* to use all cores.|"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "automl_settings = {\n",
+        "    \"iteration_timeout_minutes\": 60,\n",
+        "    \"iterations\": 4,\n",
+        "    \"n_cross_validations\": 5,\n",
+        "    \"primary_metric\": 'AUC_weighted',\n",
+        "    \"preprocess\": True,\n",
+        "    \"max_cores_per_iteration\": 2\n",
+        "}\n",
+        "\n",
+        "automl_config = AutoMLConfig(task = 'classification',\n",
+        "                             path = project_folder,\n",
+        "                             run_configuration=conda_run_config,\n",
+        "                             data_script = project_folder + \"/get_data.py\",\n",
+        "                             **automl_settings\n",
+        "                            )\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Call the `submit` method on the experiment object and pass the run configuration. For remote runs the execution is asynchronous, so you will see the iterations get populated as they complete. You can interact with the widgets and models even when the experiment is running to retrieve the best model up to that point. Once you are satisfied with the model, you can cancel a particular iteration or the whole run."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run = experiment.submit(automl_config)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Results\n",
+        "#### Widget for Monitoring Runs\n",
+        "\n",
+        "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+        "\n",
+        "You can click on a pipeline to see run properties and output logs.  Logs are also available on the DSVM under `/tmp/azureml_run/{iterationid}/azureml-logs`\n",
+        "\n",
+        "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.widgets import RunDetails\n",
+        "RunDetails(remote_run).show() "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Wait until the run finishes.\n",
+        "remote_run.wait_for_completion(show_output = True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Pre-process cache cleanup\n",
+        "The preprocess data gets cache at user default file store. When the run is completed the cache can be cleaned by running below cell"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run.clean_preprocessor_cache()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "\n",
+        "#### Retrieve All Child Runs\n",
+        "You can also use SDK methods to fetch all the child runs and see individual metrics that we log. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "children = list(remote_run.get_children())\n",
+        "metricslist = {}\n",
+        "for run in children:\n",
+        "    properties = run.get_properties()\n",
+        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+        "    metricslist[int(properties['iteration'])] = metrics\n",
+        "\n",
+        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+        "rundata"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Cancelling Runs\n",
+        "You can cancel ongoing remote runs using the `cancel` and `cancel_iteration` functions."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Cancel the ongoing experiment and stop scheduling new iterations.\n",
+        "# remote_run.cancel()\n",
+        "\n",
+        "# Cancel iteration 1 and move onto iteration 2.\n",
+        "# remote_run.cancel_iteration(1)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Retrieve the Best Model\n",
+        "\n",
+        "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run, fitted_model = remote_run.get_output()\n",
+        "print(best_run)\n",
+        "print(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### View the engineered names for featurized data\n",
+        "Below we display the engineered feature names generated for the featurized data using the preprocessing featurization."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "fitted_model.named_steps['datatransformer'].get_engineered_feature_names()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### View the featurization summary\n",
+        "Below we display the featurization that was performed on different raw features in the user data. For each raw feature in the user data, the following information is displayed:-\n",
+        "- Raw feature name\n",
+        "- Number of engineered features formed out of this raw feature\n",
+        "- Type detected\n",
+        "- If feature was dropped\n",
+        "- List of feature transformations for the raw feature"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "fitted_model.named_steps['datatransformer'].get_featurization_summary()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Best Model Based on Any Other Metric\n",
+        "Show the run and the model which has the smallest `accuracy` value:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# lookup_metric = \"accuracy\"\n",
+        "# best_run, fitted_model = remote_run.get_output(metric = lookup_metric)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Model from a Specific Iteration"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "iteration = 0\n",
+        "zero_run, zero_model = remote_run.get_output(iteration = iteration)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Test"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Load test data.\n",
+        "from pandas_ml import ConfusionMatrix\n",
+        "from sklearn.datasets import fetch_20newsgroups\n",
+        "\n",
+        "remove = ('headers', 'footers', 'quotes')\n",
+        "categories = [\n",
+        "        'alt.atheism',\n",
+        "        'talk.religion.misc',\n",
+        "        'comp.graphics',\n",
+        "        'sci.space',\n",
+        "    ]\n",
+        "\n",
+        "data_test = fetch_20newsgroups(subset = 'test', categories = categories,\n",
+        "                               shuffle = True, random_state = 42,\n",
+        "                               remove = remove)\n",
+        "\n",
+        "X_test = np.array(data_test.data).reshape((len(data_test.data),1))\n",
+        "y_test = data_test.target\n",
+        "\n",
+        "# Test our best pipeline.\n",
+        "\n",
+        "y_pred = fitted_model.predict(X_test)\n",
+        "y_pred_strings = [data_test.target_names[i] for i in y_pred]\n",
+        "y_test_strings = [data_test.target_names[i] for i in y_test]\n",
+        "\n",
+        "cm = ConfusionMatrix(y_test_strings, y_pred_strings)\n",
+        "print(cm)\n",
+        "cm.plot()"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "savitam"
+      }
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "python",
+      "name": "python36"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.6"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

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

@@ -0,0 +1,555 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "_**Remote Execution using AmlCompute**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Data](#Data)\n",
+        "1. [Train](#Train)\n",
+        "1. [Results](#Results)\n",
+        "1. [Test](#Test)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset) to showcase how you can use AutoML for a simple classification problem.\n",
+        "\n",
+        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+        "\n",
+        "In this notebook you would see\n",
+        "1. Create an `Experiment` in an existing `Workspace`.\n",
+        "2. Create or Attach existing AmlCompute to a workspace.\n",
+        "3. Configure AutoML using `AutoMLConfig`.\n",
+        "4. Train the model using AmlCompute\n",
+        "5. Explore the results.\n",
+        "6. Test the best fitted model.\n",
+        "\n",
+        "In addition this notebook showcases the following features\n",
+        "- **Parallel** executions for iterations\n",
+        "- **Asynchronous** tracking of progress\n",
+        "- **Cancellation** of individual iterations or the entire run\n",
+        "- Retrieving models for any iteration or logged metric\n",
+        "- Specifying AutoML settings as `**kwargs`"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup\n",
+        "\n",
+        "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import logging\n",
+        "import os\n",
+        "import csv\n",
+        "\n",
+        "from matplotlib import pyplot as plt\n",
+        "import numpy as np\n",
+        "import pandas as pd\n",
+        "from sklearn import datasets\n",
+        "\n",
+        "import azureml.core\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "from azureml.train.automl import AutoMLConfig"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "# Choose a name for the run history container in the workspace.\n",
+        "experiment_name = 'automl-remote-amlcompute'\n",
+        "project_folder = './project'\n",
+        "\n",
+        "experiment = Experiment(ws, experiment_name)\n",
+        "\n",
+        "output = {}\n",
+        "output['SDK version'] = azureml.core.VERSION\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace Name'] = ws.name\n",
+        "output['Resource Group'] = ws.resource_group\n",
+        "output['Location'] = ws.location\n",
+        "output['Project Directory'] = project_folder\n",
+        "output['Experiment Name'] = experiment.name\n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
+        "outputDf.T"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create or Attach existing AmlCompute\n",
+        "You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) for your AutoML run. In this tutorial, you create `AmlCompute` as your training compute resource.\n",
+        "\n",
+        "**Creation of AmlCompute takes approximately 5 minutes.** If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
+        "\n",
+        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.compute import 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": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Data\n",
+        "For remote executions, you need to make the data accessible from the remote compute.\n",
+        "This can be done by uploading the data to DataStore.\n",
+        "In this example, we upload scikit-learn's [load_digits](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) data."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "data_train = datasets.load_digits()\n",
+        "\n",
+        "if not os.path.isdir('data'):\n",
+        "    os.mkdir('data')\n",
+        "    \n",
+        "if not os.path.exists(project_folder):\n",
+        "    os.makedirs(project_folder)\n",
+        "    \n",
+        "pd.DataFrame(data_train.data).to_csv(\"data/X_train.tsv\", index=False, header=False, quoting=csv.QUOTE_ALL, sep=\"\\t\")\n",
+        "pd.DataFrame(data_train.target).to_csv(\"data/y_train.tsv\", index=False, header=False, sep=\"\\t\")\n",
+        "\n",
+        "ds = ws.get_default_datastore()\n",
+        "ds.upload(src_dir='./data', target_path='bai_data', overwrite=True, show_progress=True)\n",
+        "\n",
+        "from azureml.core.runconfig import DataReferenceConfiguration\n",
+        "dr = DataReferenceConfiguration(datastore_name=ds.name, \n",
+        "                   path_on_datastore='bai_data', \n",
+        "                   path_on_compute='/tmp/azureml_runs',\n",
+        "                   mode='download', # download files from datastore to compute target\n",
+        "                   overwrite=False)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.runconfig import RunConfiguration\n",
+        "from azureml.core.conda_dependencies import CondaDependencies\n",
+        "\n",
+        "# create a new RunConfig object\n",
+        "conda_run_config = RunConfiguration(framework=\"python\")\n",
+        "\n",
+        "# Set compute target to AmlCompute\n",
+        "conda_run_config.target = compute_target\n",
+        "conda_run_config.environment.docker.enabled = True\n",
+        "conda_run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
+        "\n",
+        "# set the data reference of the run coonfiguration\n",
+        "conda_run_config.data_references = {ds.name: dr}\n",
+        "\n",
+        "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy'])\n",
+        "conda_run_config.environment.python.conda_dependencies = cd"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%writefile $project_folder/get_data.py\n",
+        "\n",
+        "import pandas as pd\n",
+        "\n",
+        "def get_data():\n",
+        "    X_train = pd.read_csv(\"/tmp/azureml_runs/bai_data/X_train.tsv\", delimiter=\"\\t\", header=None, quotechar='\"')\n",
+        "    y_train = pd.read_csv(\"/tmp/azureml_runs/bai_data/y_train.tsv\", delimiter=\"\\t\", header=None, quotechar='\"')\n",
+        "\n",
+        "    return { \"X\" : X_train.values, \"y\" : y_train[0].values }\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train\n",
+        "\n",
+        "You can specify `automl_settings` as `**kwargs` as well. Also note that you can use a `get_data()` function for local excutions too.\n",
+        "\n",
+        "**Note:** When using AmlCompute, you can't pass Numpy arrays directly to the fit method.\n",
+        "\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
+        "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+        "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
+        "|**n_cross_validations**|Number of cross validation splits.|\n",
+        "|**max_concurrent_iterations**|Maximum number of iterations that would be executed in parallel. This should be less than the number of cores on the DSVM.|"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "automl_settings = {\n",
+        "    \"iteration_timeout_minutes\": 2,\n",
+        "    \"iterations\": 20,\n",
+        "    \"n_cross_validations\": 5,\n",
+        "    \"primary_metric\": 'AUC_weighted',\n",
+        "    \"preprocess\": False,\n",
+        "    \"max_concurrent_iterations\": 5,\n",
+        "    \"verbosity\": logging.INFO\n",
+        "}\n",
+        "\n",
+        "automl_config = AutoMLConfig(task = 'classification',\n",
+        "                             debug_log = 'automl_errors.log',\n",
+        "                             path = project_folder,\n",
+        "                             run_configuration=conda_run_config,\n",
+        "                             data_script = project_folder + \"/get_data.py\",\n",
+        "                             **automl_settings\n",
+        "                            )\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Call the `submit` method on the experiment object and pass the run configuration. For remote runs the execution is asynchronous, so you will see the iterations get populated as they complete. You can interact with the widgets and models even when the experiment is running to retrieve the best model up to that point. Once you are satisfied with the model, you can cancel a particular iteration or the whole run.\n",
+        "In this example, we specify `show_output = False` to suppress console output while the run is in progress."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run = experiment.submit(automl_config, show_output = False)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Results\n",
+        "\n",
+        "#### Loading executed runs\n",
+        "In case you need to load a previously executed run, enable the cell below and replace the `run_id` value."
+      ]
+    },
+    {
+      "cell_type": "raw",
+      "metadata": {},
+      "source": [
+        "remote_run = AutoMLRun(experiment = experiment, run_id = 'AutoML_5db13491-c92a-4f1d-b622-8ab8d973a058')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Widget for Monitoring Runs\n",
+        "\n",
+        "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
+        "\n",
+        "You can click on a pipeline to see run properties and output logs.  Logs are also available on the DSVM under `/tmp/azureml_run/{iterationid}/azureml-logs`\n",
+        "\n",
+        "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.widgets import RunDetails\n",
+        "RunDetails(remote_run).show() "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Wait until the run finishes.\n",
+        "remote_run.wait_for_completion(show_output = True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "\n",
+        "#### Retrieve All Child Runs\n",
+        "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "children = list(remote_run.get_children())\n",
+        "metricslist = {}\n",
+        "for run in children:\n",
+        "    properties = run.get_properties()\n",
+        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
+        "    metricslist[int(properties['iteration'])] = metrics\n",
+        "\n",
+        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+        "rundata"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Cancelling Runs\n",
+        "\n",
+        "You can cancel ongoing remote runs using the `cancel` and `cancel_iteration` functions."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Cancel the ongoing experiment and stop scheduling new iterations.\n",
+        "# remote_run.cancel()\n",
+        "\n",
+        "# Cancel iteration 1 and move onto iteration 2.\n",
+        "# remote_run.cancel_iteration(1)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Retrieve the Best Model\n",
+        "\n",
+        "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run, fitted_model = remote_run.get_output()\n",
+        "print(best_run)\n",
+        "print(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Best Model Based on Any Other Metric\n",
+        "Show the run and the model which has the smallest `log_loss` value:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "lookup_metric = \"log_loss\"\n",
+        "best_run, fitted_model = remote_run.get_output(metric = lookup_metric)\n",
+        "print(best_run)\n",
+        "print(fitted_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Model from a Specific Iteration\n",
+        "Show the run and the model from the third iteration:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "iteration = 3\n",
+        "third_run, third_model = remote_run.get_output(iteration=iteration)\n",
+        "print(third_run)\n",
+        "print(third_model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Test\n",
+        "\n",
+        "#### Load Test Data"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "digits = datasets.load_digits()\n",
+        "X_test = digits.data[:10, :]\n",
+        "y_test = digits.target[:10]\n",
+        "images = digits.images[:10]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Testing Our Best Fitted Model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Randomly select digits and test.\n",
+        "for index in np.random.choice(len(y_test), 2, replace = False):\n",
+        "    print(index)\n",
+        "    predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
+        "    label = y_test[index]\n",
+        "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
+        "    fig = plt.figure(1, figsize=(3,3))\n",
+        "    ax1 = fig.add_axes((0,0,.8,.8))\n",
+        "    ax1.set_title(title)\n",
+        "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
+        "    plt.show()"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "savitam"
+      }
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "python",
+      "name": "python36"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.6"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

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

@@ -0,0 +1,586 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "_**Remote Execution with DataStore**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Data](#Data)\n",
+        "1. [Train](#Train)\n",
+        "1. [Results](#Results)\n",
+        "1. [Test](#Test)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "This sample accesses a data file on a remote DSVM through DataStore. Advantages of using data store are:\n",
+        "1. DataStore secures the access details.\n",
+        "2. DataStore supports read, write to blob and file store\n",
+        "3. AutoML natively supports copying data from DataStore to DSVM\n",
+        "\n",
+        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+        "\n",
+        "In this notebook you would see\n",
+        "1. Storing data in DataStore.\n",
+        "2. get_data returning data from DataStore."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup\n",
+        "\n",
+        "As part of the setup you have already created a <b>Workspace</b>. For AutoML you would need to create an <b>Experiment</b>. An <b>Experiment</b> is a named object in a <b>Workspace</b>, which is used to run experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import logging\n",
+        "import os\n",
+        "import time\n",
+        "\n",
+        "import numpy as np\n",
+        "import pandas as pd\n",
+        "\n",
+        "import azureml.core\n",
+        "from azureml.core.compute import DsvmCompute\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "from azureml.train.automl import AutoMLConfig"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "# choose a name for experiment\n",
+        "experiment_name = 'automl-remote-datastore-file'\n",
+        "# project folder\n",
+        "project_folder = './sample_projects/automl-remote-datastore-file'\n",
+        "\n",
+        "experiment=Experiment(ws, experiment_name)\n",
+        "\n",
+        "output = {}\n",
+        "output['SDK version'] = azureml.core.VERSION\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace'] = ws.name\n",
+        "output['Resource Group'] = ws.resource_group\n",
+        "output['Location'] = ws.location\n",
+        "output['Project Directory'] = project_folder\n",
+        "output['Experiment Name'] = experiment.name\n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
+        "outputDf.T"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create a Remote Linux DSVM\n",
+        "Note: If creation fails with a message about Marketplace purchase eligibilty, go to portal.azure.com, start creating DSVM there, and select \"Want to create programmatically\" to enable programmatic creation. Once you've enabled it, you can exit without actually creating VM.\n",
+        "\n",
+        "**Note**: By default SSH runs on port 22 and you don't need to specify it. But if for security reasons you can switch to a different port (such as 5022), you can append the port number to the address. [Read more](https://docs.microsoft.com/en-us/azure/virtual-machines/troubleshooting/detailed-troubleshoot-ssh-connection) on this."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "compute_target_name = 'mydsvmc'\n",
+        "\n",
+        "try:\n",
+        "    while ws.compute_targets[compute_target_name].provisioning_state == 'Creating':\n",
+        "        time.sleep(1)\n",
+        "        \n",
+        "    dsvm_compute = DsvmCompute(workspace=ws, name=compute_target_name)\n",
+        "    print('found existing:', dsvm_compute.name)\n",
+        "except:\n",
+        "    dsvm_config = DsvmCompute.provisioning_configuration(vm_size=\"Standard_D2_v2\")\n",
+        "    dsvm_compute = DsvmCompute.create(ws, name=compute_target_name, provisioning_configuration=dsvm_config)\n",
+        "    dsvm_compute.wait_for_completion(show_output=True)\n",
+        "    print(\"Waiting one minute for ssh to be accessible\")\n",
+        "    time.sleep(90) # Wait for ssh to be accessible"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Data\n",
+        "\n",
+        "### Copy data file to local\n",
+        "\n",
+        "Download the data file.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "if not os.path.isdir('data'):\n",
+        "    os.mkdir('data')    "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from sklearn.datasets import fetch_20newsgroups\n",
+        "import csv\n",
+        "\n",
+        "remove = ('headers', 'footers', 'quotes')\n",
+        "categories = [\n",
+        "        'alt.atheism',\n",
+        "        'talk.religion.misc',\n",
+        "        'comp.graphics',\n",
+        "        'sci.space',\n",
+        "    ]\n",
+        "data_train = fetch_20newsgroups(subset = 'train', categories = categories,\n",
+        "                                    shuffle = True, random_state = 42,\n",
+        "                                    remove = remove)\n",
+        "    \n",
+        "pd.DataFrame(data_train.data).to_csv(\"data/X_train.tsv\", index=False, header=False, quoting=csv.QUOTE_ALL, sep=\"\\t\")\n",
+        "pd.DataFrame(data_train.target).to_csv(\"data/y_train.tsv\", index=False, header=False, sep=\"\\t\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Upload data to the cloud"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Now make the data accessible remotely by uploading that data from your local machine into Azure so it can be accessed for remote training. The datastore is a convenient construct associated with your workspace for you to upload/download data, and interact with it from your remote compute targets. It is backed by Azure blob storage account.\n",
+        "\n",
+        "The data.tsv files are uploaded into a directory named data at the root of the datastore."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "#blob_datastore = Datastore(ws, blob_datastore_name)\n",
+        "ds = ws.get_default_datastore()\n",
+        "print(ds.datastore_type, ds.account_name, ds.container_name)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# ds.upload_files(\"data.tsv\")\n",
+        "ds.upload(src_dir='./data', target_path='data', overwrite=True, show_progress=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Configure & Run\n",
+        "\n",
+        "First let's create a DataReferenceConfigruation object to inform the system what data folder to download to the compute target.\n",
+        "The path_on_compute should be an absolute path to ensure that the data files are downloaded only once.   The get_data method should use this same path to access the data files."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.runconfig import DataReferenceConfiguration\n",
+        "dr = DataReferenceConfiguration(datastore_name=ds.name, \n",
+        "                   path_on_datastore='data', \n",
+        "                   path_on_compute='/tmp/azureml_runs',\n",
+        "                   mode='download', # download files from datastore to compute target\n",
+        "                   overwrite=False)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.runconfig import RunConfiguration\n",
+        "from azureml.core.conda_dependencies import CondaDependencies\n",
+        "import pkg_resources\n",
+        "\n",
+        "# create a new RunConfig object\n",
+        "conda_run_config = RunConfiguration(framework=\"python\")\n",
+        "\n",
+        "# Set compute target to the Linux DSVM\n",
+        "conda_run_config.target = dsvm_compute\n",
+        "# set the data reference of the run coonfiguration\n",
+        "conda_run_config.data_references = {ds.name: dr}\n",
+        "\n",
+        "pandas_dependency = 'pandas==' + pkg_resources.get_distribution(\"pandas\").version\n",
+        "\n",
+        "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy','py-xgboost<=0.80',pandas_dependency])\n",
+        "conda_run_config.environment.python.conda_dependencies = cd"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create Get Data File\n",
+        "For remote executions you should author a get_data.py file containing a get_data() function. This file should be in the root directory of the project. You can encapsulate code to read data either from a blob storage or local disk in this file.\n",
+        "\n",
+        "The *get_data()* function returns a [dictionary](README.md#getdata).\n",
+        "\n",
+        "The read_csv uses the path_on_compute value specified in the DataReferenceConfiguration call plus the path_on_datastore folder and then the actual file name."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "if not os.path.exists(project_folder):\n",
+        "    os.makedirs(project_folder)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%writefile $project_folder/get_data.py\n",
+        "\n",
+        "import pandas as pd\n",
+        "\n",
+        "def get_data():\n",
+        "    X_train = pd.read_csv(\"/tmp/azureml_runs/data/X_train.tsv\", delimiter=\"\\t\", header=None, quotechar='\"')\n",
+        "    y_train = pd.read_csv(\"/tmp/azureml_runs/data/y_train.tsv\", delimiter=\"\\t\", header=None, quotechar='\"')\n",
+        "\n",
+        "    return { \"X\" : X_train.values, \"y\" : y_train[0].values }"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train\n",
+        "\n",
+        "You can specify automl_settings as **kwargs** as well. Also note that you can use the get_data() symantic for local excutions too. \n",
+        "\n",
+        "<i>Note: For Remote DSVM and Batch AI you cannot pass Numpy arrays directly to AutoMLConfig.</i>\n",
+        "\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
+        "|**iteration_timeout_minutes**|Time limit in minutes for each iteration|\n",
+        "|**iterations**|Number of iterations. In each iteration Auto ML trains a specific pipeline with the data|\n",
+        "|**n_cross_validations**|Number of cross validation splits|\n",
+        "|**max_concurrent_iterations**|Max number of iterations that would be executed in parallel.  This should be less than the number of cores on the DSVM\n",
+        "|**preprocess**| *True/False* <br>Setting this to *True* enables Auto ML to perform preprocessing <br>on the input to handle *missing data*, and perform some common *feature extraction*|\n",
+        "|**enable_cache**|Setting this to *True* enables preprocess done once and reuse the same preprocessed data for all the iterations. Default value is True.|\n",
+        "|**max_cores_per_iteration**| Indicates how many cores on the compute target would be used to train a single pipeline.<br> Default is *1*, you can set it to *-1* to use all cores|"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "automl_settings = {\n",
+        "    \"iteration_timeout_minutes\": 60,\n",
+        "    \"iterations\": 4,\n",
+        "    \"n_cross_validations\": 5,\n",
+        "    \"primary_metric\": 'AUC_weighted',\n",
+        "    \"preprocess\": True,\n",
+        "    \"max_cores_per_iteration\": 1,\n",
+        "    \"verbosity\": logging.INFO\n",
+        "}\n",
+        "automl_config = AutoMLConfig(task = 'classification',\n",
+        "                             debug_log = 'automl_errors.log',\n",
+        "                             path=project_folder,\n",
+        "                             run_configuration=conda_run_config,\n",
+        "                             #compute_target = dsvm_compute,\n",
+        "                             data_script = project_folder + \"/get_data.py\",\n",
+        "                             **automl_settings\n",
+        "                            )"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "For remote runs the execution is asynchronous, so you will see the iterations get populated as they complete. You can interact with the widgets/models even when the experiment is running to retreive the best model up to that point. Once you are satisfied with the model you can cancel a particular iteration or the whole run."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run = experiment.submit(automl_config, show_output=False)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Results\n",
+        "#### Widget for monitoring runs\n",
+        "\n",
+        "The widget will sit on \"loading\" until the first iteration completed, then you will see an auto-updating graph and table show up. It refreshed once per minute, so you should see the graph update as child runs complete.\n",
+        "\n",
+        "You can click on a pipeline to see run properties and output logs. Logs are also available on the DSVM under /tmp/azureml_run/{iterationid}/azureml-logs\n",
+        "\n",
+        "NOTE: The widget displays a link at the bottom. This links to a web-ui to explore the individual run details."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.widgets import RunDetails\n",
+        "RunDetails(remote_run).show() "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Wait until the run finishes.\n",
+        "remote_run.wait_for_completion(show_output = True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "\n",
+        "#### Retrieve All Child Runs\n",
+        "You can also use sdk methods to fetch all the child runs and see individual metrics that we log. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "children = list(remote_run.get_children())\n",
+        "metricslist = {}\n",
+        "for run in children:\n",
+        "    properties = run.get_properties()\n",
+        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}    \n",
+        "    metricslist[int(properties['iteration'])] = metrics\n",
+        "\n",
+        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
+        "rundata"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Canceling Runs\n",
+        "You can cancel ongoing remote runs using the *cancel()* and *cancel_iteration()* functions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Cancel the ongoing experiment and stop scheduling new iterations\n",
+        "# remote_run.cancel()\n",
+        "\n",
+        "# Cancel iteration 1 and move onto iteration 2\n",
+        "# remote_run.cancel_iteration(1)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Pre-process cache cleanup\n",
+        "The preprocess data gets cache at user default file store. When the run is completed the cache can be cleaned by running below cell"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run.clean_preprocessor_cache()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Retrieve the Best Model\n",
+        "\n",
+        "Below we select the best pipeline from our iterations. The *get_output* method returns the best run and the fitted model. There are overloads on *get_output* that allow you to retrieve the best run and fitted model for *any* logged metric or a particular *iteration*."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run, fitted_model = remote_run.get_output()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Best Model based on any other metric"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# lookup_metric = \"accuracy\"\n",
+        "# best_run, fitted_model = remote_run.get_output(metric=lookup_metric)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Model from a specific iteration"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# iteration = 1\n",
+        "# best_run, fitted_model = remote_run.get_output(iteration=iteration)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Test\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Load test data.\n",
+        "from pandas_ml import ConfusionMatrix\n",
+        "\n",
+        "data_test = fetch_20newsgroups(subset = 'test', categories = categories,\n",
+        "                               shuffle = True, random_state = 42,\n",
+        "                               remove = remove)\n",
+        "\n",
+        "X_test = np.array(data_test.data).reshape((len(data_test.data),1))\n",
+        "y_test = data_test.target\n",
+        "\n",
+        "# Test our best pipeline.\n",
+        "\n",
+        "y_pred = fitted_model.predict(X_test)\n",
+        "y_pred_strings = [data_test.target_names[i] for i in y_pred]\n",
+        "y_test_strings = [data_test.target_names[i] for i in y_test]\n",
+        "\n",
+        "cm = ConfusionMatrix(y_test_strings, y_pred_strings)\n",
+        "print(cm)\n",
+        "cm.plot()"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "savitam"
+      }
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "python",
+      "name": "python36"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.6"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

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

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

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

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/sample-weight/auto-ml-sample-weight.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

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

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/sparse-data-train-test-split/auto-ml-sparse-data-train-test-split.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

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

@@ -1,113 +0,0 @@
-# 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

@@ -1,10 +0,0 @@
--- 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

@@ -1,17 +0,0 @@
--- 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

@@ -1,21 +0,0 @@
--- 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

@@ -1,141 +0,0 @@
-{
- "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

@@ -1,70 +0,0 @@
--- 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

@@ -1,41 +0,0 @@
--- 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

@@ -1,234 +0,0 @@
--- 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

@@ -1,18 +0,0 @@
--- 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

@@ -1,22 +0,0 @@
--- 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

@@ -1,562 +0,0 @@
-{
- "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/automated-machine-learning/subsampling/auto-ml-subsampling-local.ipynb

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/subsampling/auto-ml-subsampling-local.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

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

@@ -26,8 +26,4 @@ You can use Azure Databricks as a compute target from [Azure Machine Learning Pi
 
 For more on SDK concepts, please refer to [notebooks](https://github.com/Azure/MachineLearningNotebooks).
 
-**Please let us know your feedback.**
-
- 
-
-![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/azure-databricks/README.png) 
+**Please let us know your feedback.**

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

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

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

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

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

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

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

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

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

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

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

@@ -660,13 +660,6 @@
       "metadata": {},
       "outputs": [],
       "source": []
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/azure-databricks/automl/automl-databricks-local-01.png)"
-      ]
     }
   ],
   "metadata": {

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

@@ -796,13 +796,6 @@
       "source": [
         "myservice.delete()"
       ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/azure-databricks/automl/automl-databricks-local-with-deployment.png)"
-      ]
     }
   ],
   "metadata": {

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

@@ -677,13 +677,6 @@
         "# Next: ADLA as a Compute Target\n",
         "To use ADLA as a compute target from Azure Machine Learning Pipeline, a AdlaStep is used. This [notebook](./aml-pipelines-use-adla-as-compute-target.ipynb) demonstrates the use of AdlaStep in Azure Machine Learning Pipeline."
       ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/azure-databricks/databricks-as-remote-compute-target/aml-pipelines-use-databricks-as-compute-target.png)"
-      ]
     }
   ],
   "metadata": {

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

@@ -1,709 +0,0 @@
-{
- "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

@@ -1,3 +0,0 @@
-## 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

@@ -1,58 +0,0 @@
-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/deploy-to-cloud/README.md

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

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

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

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

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

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

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

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

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

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

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

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

@@ -9,20 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/deploy-to-cloud/model-register-and-deploy.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/deploy-to-cloud/model-register-and-deploy.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -40,7 +26,7 @@
       "metadata": {},
       "source": [
         "## Prerequisites\n",
-        "If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, make sure you go through the [configuration](../../../configuration.ipynb) Notebook first if you haven't."
+        "Make sure you go through the [configuration](../../../configuration.ipynb) Notebook first if you haven't."
       ]
     },
     {

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

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

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

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

how-to-use-azureml/deploy-to-local/register-model-deploy-local-advanced.ipynb

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/deploy-to-local/register-model-deploy-local-advanced.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -35,7 +28,7 @@
       "metadata": {},
       "source": [
         "## Prerequisites\n",
-        "If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, make sure you go through the [configuration](../../../configuration.ipynb) Notebook first if you haven't."
+        "Make sure you go through the [configuration](../../../configuration.ipynb) Notebook first if you haven't."
       ]
     },
     {

how-to-use-azureml/deploy-to-local/register-model-deploy-local.ipynb

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/deploy-to-local/register-model-deploy-local.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -35,7 +28,7 @@
       "metadata": {},
       "source": [
         "## Prerequisites\n",
-        "If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, make sure you go through the [configuration](../../../configuration.ipynb) Notebook first if you haven't."
+        "Make sure you go through the [configuration](../../../configuration.ipynb) Notebook first if you haven't."
       ]
     },
     {

how-to-use-azureml/deployment/accelerated-models/README.md

@@ -1,102 +0,0 @@
-
-# Notebooks for Microsoft Azure Machine Learning Hardware Accelerated Models SDK
-
-Easily create and train a model using various deep neural networks (DNNs) as a featurizer for deployment to Azure or a Data Box Edge device for ultra-low latency inferencing using FPGA's. These models are currently available:
-
-* ResNet 50
-* ResNet 152
-* DenseNet-121
-* VGG-16
-* SSD-VGG  
-
-To learn more about the azureml-accel-model classes, see the section [Model Classes](#model-classes) below or the [Azure ML Accel Models SDK documentation](https://docs.microsoft.com/en-us/python/api/azureml-accel-models/azureml.accel?view=azure-ml-py).
-
-### Step 1: Create an Azure ML workspace
-Follow [these instructions](https://docs.microsoft.com/en-us/azure/machine-learning/service/quickstart-create-workspace-with-python) to install the Azure ML SDK on your local machine, create an Azure ML workspace, and set up your notebook environment, which is required for the next step.
-
-### Step 2: Check your FPGA quota
-Use the Azure CLI to check whether you have quota.
-
-```shell
-az vm list-usage --location "eastus" -o table
-```
-
-The other locations are ``southeastasia``, ``westeurope``, and ``westus2``.
-
-Under the "Name" column, look for "Standard PBS Family vCPUs" and ensure you have at least 6 vCPUs under "CurrentValue."
-
-If you do not have quota, then submit a request form [here](https://aka.ms/accelerateAI).
-
-### Step 3: Install the Azure ML Accelerated Models SDK
-Once you have set up your environment, install the Azure ML Accel Models SDK. This package requires tensorflow >= 1.6,<2.0 to be installed. 
-
-If you already have tensorflow >= 1.6,<2.0 installed in your development environment, you can install the SDK package using: 
-
-```
-pip install azureml-accel-models
-```
-
-If you do not have tensorflow >= 1.6,<2.0 and are using a CPU-only development environment, our SDK with tensorflow can be installed using:
-
-```
-pip install azureml-accel-models[cpu]
-```
-
-If your machine supports GPU (for example, on an [Azure DSVM](https://docs.microsoft.com/en-us/azure/machine-learning/data-science-virtual-machine/overview)), then you can leverage the tensorflow-gpu functionality using:
-
-```
-pip install azureml-accel-models[gpu]
-```
-
-### Step 4: Follow our notebooks
-
-The notebooks in this repo walk through the following scenarios: 
-* [Quickstart](accelerated-models-quickstart.ipynb), deploy and inference a ResNet50 model trained on ImageNet
-* [Object Detection](accelerated-models-object-detection.ipynb), deploy and inference an SSD-VGG model that can do object detection
-* [Training models](accelerated-models-training.ipynb), train one of our accelerated models on the Kaggle Cats and Dogs dataset to see how to improve accuracy on custom datasets
-
-<a name="model-classes"></a>
-## Model Classes
-As stated above, we support 5 Accelerated Models. Here's more information on their input and output tensors.
-
-**Available models and output tensors**
-
-The available models and the corresponding default classifier output tensors are below. This is the value that you would use during inferencing if you used the default classifier.
-* Resnet50, QuantizedResnet50 
-``
-output_tensors = "classifier_1/resnet_v1_50/predictions/Softmax:0"
-``
-* Resnet152, QuantizedResnet152 
-``
-output_tensors = "classifier/resnet_v1_152/predictions/Softmax:0"
-``
-* Densenet121, QuantizedDensenet121
-``
-output_tensors = "classifier/densenet121/predictions/Softmax:0"
-``
-* Vgg16, QuantizedVgg16 
-``
-output_tensors = "classifier/vgg_16/fc8/squeezed:0"
-``
-* SsdVgg, QuantizedSsdVgg
-``
-output_tensors = ['ssd_300_vgg/block4_box/Reshape_1:0', 'ssd_300_vgg/block7_box/Reshape_1:0', 'ssd_300_vgg/block8_box/Reshape_1:0', 'ssd_300_vgg/block9_box/Reshape_1:0', 'ssd_300_vgg/block10_box/Reshape_1:0', 'ssd_300_vgg/block11_box/Reshape_1:0', 'ssd_300_vgg/block4_box/Reshape:0', 'ssd_300_vgg/block7_box/Reshape:0', 'ssd_300_vgg/block8_box/Reshape:0', 'ssd_300_vgg/block9_box/Reshape:0', 'ssd_300_vgg/block10_box/Reshape:0', 'ssd_300_vgg/block11_box/Reshape:0']
-``
-
-For more information, please reference the azureml.accel.models package in the [Azure ML Python SDK documentation](https://docs.microsoft.com/en-us/python/api/azureml-accel-models/azureml.accel.models?view=azure-ml-py).
-
-**Input tensors**
-
-The input_tensors value defaults to "Placeholder:0" and is created in the [Image Preprocessing](#construct-model) step in the line: 
-``
-in_images = tf.placeholder(tf.string)
-``
-
-You can change the input_tensors name by doing this: 
-``
-in_images = tf.placeholder(tf.string, name="images")
-``
-
-
-## Resources
-*  [Read more about FPGAs](https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-accelerate-with-fpgas)

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

@@ -1,494 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# 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()"
-      ]
-    }
-  ],
-  "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"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

how-to-use-azureml/deployment/accelerated-models/accelerated-models-quickstart.ipynb

@@ -1,548 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Azure ML Hardware Accelerated Models Quickstart"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "This tutorial will show you how to deploy an image recognition service based on the ResNet 50 classifier using the Azure Machine Learning Accelerated Models service.  Get more information about our service from our [documentation](https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-accelerate-with-fpgas), [API reference](https://docs.microsoft.com/en-us/python/api/azureml-accel-models/azureml.accel?view=azure-ml-py), or [forum](https://aka.ms/aml-forum).\n",
-        "\n",
-        "We will use an accelerated ResNet50 featurizer running on an FPGA. Our Accelerated Models Service handles translating deep neural networks (DNN) into an FPGA program.\n",
-        "\n",
-        "For more information about using other models besides Resnet50, see the [README](./README.md).\n",
-        "\n",
-        "The steps covered in this notebook are: \n",
-        "1. [Set up environment](#set-up-environment)\n",
-        "* [Construct model](#construct-model)\n",
-        "    * Image Preprocessing\n",
-        "    * Featurizer (Resnet50)\n",
-        "    * Classifier\n",
-        "    * Save Model\n",
-        "* [Register Model](#register-model)\n",
-        "* [Convert into Accelerated Model](#convert-model)\n",
-        "* [Create Image](#create-image)\n",
-        "* [Deploy](#deploy-image)\n",
-        "* [Test service](#test-service)\n",
-        "* [Clean-up](#clean-up)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id=\"set-up-environment\"></a>\n",
-        "## 1. Set up environment"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "import tensorflow as tf"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Retrieve Workspace\n",
-        "If you haven't created a Workspace, please follow [this notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/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",
-        "\n",
-        "There are three parts to the model we are deploying: pre-processing, featurizer with ResNet50, and classifier with ImageNet dataset. Then we will save this complete Tensorflow model graph locally before registering it to your Azure ML Workspace.\n",
-        "\n",
-        "### 2.a. Image preprocessing\n",
-        "We'd like our service to accept JPEG images as input. However the input to ResNet50 is a tensor. So we need code that decodes JPEG images and does the preprocessing required by ResNet50. 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 strings) and produces a tensor that is ready to be featurized by ResNet50.\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)\n",
-        "print(image_tensors.shape)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### 2.b. Featurizer\n",
-        "We use ResNet50 as a featurizer. In this step we initialize the model. This downloads a TensorFlow checkpoint of the quantized ResNet50."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.accel.models import QuantizedResnet50\n",
-        "save_path = os.path.expanduser('~/models')\n",
-        "model_graph = QuantizedResnet50(save_path, is_frozen = True)\n",
-        "feature_tensor = model_graph.import_graph_def(image_tensors)\n",
-        "print(model_graph.version)\n",
-        "print(feature_tensor.name)\n",
-        "print(feature_tensor.shape)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### 2.c. Classifier\n",
-        "The model we downloaded includes a classifier which takes the output of the ResNet50 and identifies an image. This classifier is trained on the ImageNet dataset. We are going to use this classifier for our service. The next [notebook](./accelerated-models-training.ipynb) shows how to train a classifier for a different data set. The input to the classifier is a tensor matching the output of our ResNet50 featurizer."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "classifier_output = model_graph.get_default_classifier(feature_tensor)\n",
-        "print(classifier_output)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### 2.d. Save Model\n",
-        "Now that we loaded all three parts of the tensorflow graph (preprocessor, resnet50 featurizer, and the classifier), 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 must be lowercase\n",
-        "model_name = \"resnet50\"\n",
-        "model_save_path = os.path.join(save_path, model_name)\n",
-        "print(\"Saving model in {}\".format(model_save_path))\n",
-        "\n",
-        "with tf.Session() as sess:\n",
-        "    model_graph.restore_weights(sess)\n",
-        "    tf.saved_model.simple_save(sess, model_save_path,\n",
-        "                                   inputs={'images': in_images},\n",
-        "                                   outputs={'output_alias': classifier_output})"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### 2.e. 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! You can see our defaults for all the models in the [README](./README.md).\n",
-        "\n",
-        "By default for Resnet50, these are the values you should see when running the cell below: \n",
-        "* input_tensors = \"Placeholder:0\"\n",
-        "* output_tensors = \"classifier/resnet_v1_50/predictions/Softmax:0\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "tags": [
-          "register model from file"
-        ]
-      },
-      "outputs": [],
-      "source": [
-        "input_tensors = in_images.name\n",
-        "output_tensors = classifier_output.name\n",
-        "\n",
-        "print(input_tensors)\n",
-        "print(output_tensors)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id=\"register-model\"></a>\n",
-        "## 3. Register Model"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "You can add tags and descriptions to your models. Using tags, you can track useful information such as the name and version of the machine learning library used to train the model. Note that tags must be alphanumeric."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "tags": [
-          "register model from file"
-        ]
-      },
-      "outputs": [],
-      "source": [
-        "from azureml.core.model import Model\n",
-        "\n",
-        "registered_model = Model.register(workspace = ws,\n",
-        "                                  model_path = model_save_path,\n",
-        "                                  model_name = model_name)\n",
-        "\n",
-        "print(\"Successfully registered: \", registered_model.name, registered_model.description, registered_model.version, sep = '\\t')"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id=\"convert-model\"></a>\n",
-        "## 4. Convert Model"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "For conversion you need to provide names of input and output tensors. This information can be found from the model_graph you saved in step 2.e. above.\n",
-        "\n",
-        "**Note**: Conversion may take a while and on average for FPGA model it is about 1-3 minutes and it depends on model type."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "tags": [
-          "register model from file"
-        ]
-      },
-      "outputs": [],
-      "source": [
-        "from azureml.accel import AccelOnnxConverter\n",
-        "\n",
-        "convert_request = AccelOnnxConverter.convert_tf_model(ws, registered_model, input_tensors, output_tensors)\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",
-        "# If the above call succeeded, get the converted model\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')"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id=\"create-image\"></a>\n",
-        "## 5. Package the model into an Image"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "You can add tags and descriptions to image. Also, for FPGA model an image can only contain **single** model.\n",
-        "\n",
-        "**Note**: The following command can take few minutes. "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.image import Image\n",
-        "from azureml.accel import AccelContainerImage\n",
-        "\n",
-        "image_config = AccelContainerImage.image_configuration()\n",
-        "# Image name must be lowercase\n",
-        "image_name = \"{}-image\".format(model_name)\n",
-        "\n",
-        "image = Image.create(name = image_name,\n",
-        "                     models = [converted_model],\n",
-        "                     image_config = image_config, \n",
-        "                     workspace = ws)\n",
-        "image.wait_for_creation(show_output = False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id=\"deploy-image\"></a>\n",
-        "## 6. Deploy\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",
-        "### 6.a. 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",
-        "### 6.b. Azure Kubernetes Service (AKS) using Azure ML Service\n",
-        "We are going to create an AKS cluster with FPGA-enabled machines, then deploy our service to it. For more information, see [AKS official docs](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-deploy-and-where#aks).\n",
-        "\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 = 'my-aks-pb6'\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 also 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",
-        "## 7. Test the service"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### 7.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, 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": [
-        "### 7.b. Serve the model\n",
-        "To understand the results we need a mapping to the human readable imagenet classes"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import requests\n",
-        "classes_entries = requests.get(\"https://raw.githubusercontent.com/Lasagne/Recipes/master/examples/resnet50/imagenet_classes.txt\").text.splitlines()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Score image with input and output tensor names\n",
-        "results = client.score_file(path=\"./snowleopardgaze.jpg\", \n",
-        "                             input_name=input_tensors, \n",
-        "                             outputs=output_tensors)\n",
-        "\n",
-        "# map results [class_id] => [confidence]\n",
-        "results = enumerate(results)\n",
-        "# sort results by confidence\n",
-        "sorted_results = sorted(results, key=lambda x: x[1], reverse=True)\n",
-        "# print top 5 results\n",
-        "for top in sorted_results[:5]:\n",
-        "    print(classes_entries[top[0]], 'confidence:', top[1])"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id=\"clean-up\"></a>\n",
-        "## 8. Clean-up\n",
-        "Run the cell below to delete your webservice, image, and model (must be done in that order). In the [next notebook](./accelerated-models-training.ipynb) you will learn how to train a classfier on a new dataset using transfer learning and finetune the weights."
-      ]
-    },
-    {
-      "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": "aibhalla"
-      }
-    ],
-    "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"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

how-to-use-azureml/deployment/accelerated-models/accelerated-models-training.ipynb

@@ -1,862 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Training with the Azure Machine Learning Accelerated Models Service"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "This notebook will introduce how to apply common machine learning techniques, like transfer learning, custom weights, and unquantized vs. quantized models, when working with our Azure Machine Learning Accelerated Models Service (Azure ML Accel Models).\n",
-        "\n",
-        "We will use Tensorflow for the preprocessing steps, ResNet50 for the featurizer, and the Keras API (built on Tensorflow backend) to build the classifier layers instead of the default ImageNet classifier used in Quickstart. Then we will train the model, evaluate it, and deploy it to run on an FPGA.\n",
-        "\n",
-        "#### Transfer Learning and Custom weights\n",
-        "We will walk you through two ways to build and train a ResNet50 model on the Kaggle Cats and Dogs dataset: transfer learning only and then transfer learning with custom weights.\n",
-        "\n",
-        "In using transfer learning, our goal is to re-purpose the ResNet50 model already trained on the [ImageNet image dataset](http://www.image-net.org/) as a basis for our training of the Kaggle Cats and Dogs dataset. The ResNet50 featurizer will be imported as frozen, so only the Keras classifier will be trained.\n",
-        "\n",
-        "With the addition of custom weights, we will build the model so that the ResNet50 featurizer weights as not frozen. This will let us retrain starting with custom weights trained with ImageNet on ResNet50 and then use the Kaggle Cats and Dogs dataset to retrain and fine-tune the quantized version of the model.\n",
-        "\n",
-        "#### Unquantized vs. Quantized models\n",
-        "The unquantized version of our models (ie. Resnet50, Resnet152, Densenet121, Vgg16, SsdVgg) uses native float precision (32-bit floats), which will be faster at training. We will use this for our first run through, then fine-tune the weights with the quantized version. The quantized version of our models (i.e. QuantizedResnet50, QuantizedResnet152, QuantizedDensenet121, QuantizedVgg16, QuantizedSsdVgg) will have the same node names as the unquantized version, but use quantized operations and will match the performance of the model when running on an FPGA.\n",
-        "\n",
-        "#### Contents\n",
-        "1. [Setup Environment](#setup)\n",
-        "* [Prepare Data](#prepare-data)\n",
-        "* [Construct Model](#construct-model)\n",
-        "    * Preprocessor\n",
-        "    * Classifier\n",
-        "    * Model construction\n",
-        "* [Train Model](#train-model)\n",
-        "* [Test Model](#test-model)\n",
-        "* [Execution](#execution)\n",
-        "    * [Transfer Learning](#transfer-learning)\n",
-        "    * [Transfer Learning with Custom Weights](#custom-weights)\n",
-        "* [Create Image](#create-image)\n",
-        "* [Deploy Image](#deploy-image)\n",
-        "* [Test the service](#test-service)\n",
-        "* [Clean-up](#cleanup)\n",
-        "* [Appendix](#appendix)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id=\"setup\"></a>\n",
-        "## 1. Setup Environment\n",
-        "#### 1.a. Please set up your environment as described in the [Quickstart](./accelerated-models-quickstart.ipynb), meaning:\n",
-        "* Make sure your Workspace config.json exists and has the correct info\n",
-        "* Install Tensorflow\n",
-        "\n",
-        "#### 1.b. Download dataset into ~/catsanddogs \n",
-        "The dataset we will be using for training can be downloaded [here](https://www.microsoft.com/en-us/download/details.aspx?id=54765). Download the zip and extract to a directory named 'catsanddogs' under your user directory (\"~/catsanddogs\"). \n",
-        "\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### 1.c. Import packages"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "import sys\n",
-        "import tensorflow as tf\n",
-        "import numpy as np\n",
-        "from keras import backend as K\n",
-        "import sklearn\n",
-        "import tqdm"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### 1.d. Create directories for later use\n",
-        "After you train your model in float32, you'll write the weights to a place on disk. We also need a location to store the models that get downloaded."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "custom_weights_dir = os.path.expanduser(\"~/custom-weights\")\n",
-        "saved_model_dir = os.path.expanduser(\"~/models\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id=\"prepare-data\"></a>\n",
-        "## 2. Prepare Data\n",
-        "Load the files we are going to use for training and testing. By default this notebook uses only a very small subset of the Cats and Dogs dataset. That makes it run relatively quickly."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import glob\n",
-        "import imghdr\n",
-        "datadir = os.path.expanduser(\"~/catsanddogs\")\n",
-        "\n",
-        "cat_files = glob.glob(os.path.join(datadir, 'PetImages', 'Cat', '*.jpg'))\n",
-        "dog_files = glob.glob(os.path.join(datadir, 'PetImages', 'Dog', '*.jpg'))\n",
-        "\n",
-        "# Limit the data set to make the notebook execute quickly.\n",
-        "cat_files = cat_files[:64]\n",
-        "dog_files = dog_files[:64]\n",
-        "\n",
-        "# The data set has a few images that are not jpeg. Remove them.\n",
-        "cat_files = [f for f in cat_files if imghdr.what(f) == 'jpeg']\n",
-        "dog_files = [f for f in dog_files if imghdr.what(f) == 'jpeg']\n",
-        "\n",
-        "if(not len(cat_files) or not len(dog_files)):\n",
-        "    print(\"Please download the Kaggle Cats and Dogs dataset form https://www.microsoft.com/en-us/download/details.aspx?id=54765 and extract the zip to \" + datadir)    \n",
-        "    raise ValueError(\"Data not found\")\n",
-        "else:\n",
-        "    print(cat_files[0])\n",
-        "    print(dog_files[0])"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Construct a numpy array as labels\n",
-        "image_paths = cat_files + dog_files\n",
-        "total_files = len(cat_files) + len(dog_files)\n",
-        "labels = np.zeros(total_files)\n",
-        "labels[len(cat_files):] = 1"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Split images data as training data and test data\n",
-        "from sklearn.model_selection import train_test_split\n",
-        "onehot_labels = np.array([[0,1] if i else [1,0] for i in labels])\n",
-        "img_train, img_test, label_train, label_test = train_test_split(image_paths, onehot_labels, random_state=42, shuffle=True)\n",
-        "\n",
-        "print(len(img_train), len(img_test), label_train.shape, label_test.shape)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id=\"construct-model\"></a>\n",
-        "## 3. Construct Model\n",
-        "We will define the functions to handle creating the preprocessor and the classifier first, and then run them together to actually construct the model with the Resnet50 featurizer in a single Tensorflow session in a separate cell.\n",
-        "\n",
-        "We use ResNet50 for the featurizer and build our own classifier using Keras layers. We train the featurizer and the classifier as one model. We will provide parameters to determine whether we are using the quantized version and whether we are using custom weights in training or not."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### 3.a. Define image preprocessing step\n",
-        "Same as in the Quickstart, before passing image dataset to the ResNet50 featurizer, we need to preprocess the input file to get it into the form expected by ResNet50. ResNet50 expects float tensors representing the images in BGR, channel last order. We've provided a default implementation of the preprocessing that you can use.\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": [
-        "import azureml.accel.models.utils as utils\n",
-        "\n",
-        "def preprocess_images(scaling_factor=1.0):\n",
-        "    # Convert images to 3D tensors [width,height,channel] - channels are in BGR order.\n",
-        "    in_images = tf.placeholder(tf.string)\n",
-        "    image_tensors = utils.preprocess_array(in_images, 'RGB', scaling_factor)\n",
-        "    return in_images, image_tensors"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### 3.b. Define classifier\n",
-        "We use Keras layer APIs to construct the classifier. Because we're using the tensorflow backend, we can train this classifier in one session with our Resnet50 model."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "def construct_classifier(in_tensor, seed=None):\n",
-        "    from keras.layers import Dropout, Dense, Flatten\n",
-        "    from keras.initializers import glorot_uniform\n",
-        "    K.set_session(tf.get_default_session())\n",
-        "\n",
-        "    FC_SIZE = 1024\n",
-        "    NUM_CLASSES = 2\n",
-        "\n",
-        "    x = Dropout(0.2, input_shape=(1, 1, int(in_tensor.shape[3]),), seed=seed)(in_tensor)\n",
-        "    x = Dense(FC_SIZE, activation='relu', input_dim=(1, 1, int(in_tensor.shape[3]),),\n",
-        "              kernel_initializer=glorot_uniform(seed=seed), bias_initializer='zeros')(x)\n",
-        "    x = Flatten()(x)\n",
-        "    preds = Dense(NUM_CLASSES, activation='softmax', input_dim=FC_SIZE, name='classifier_output',\n",
-        "                  kernel_initializer=glorot_uniform(seed=seed), bias_initializer='zeros')(x)\n",
-        "    return preds"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### 3.c. Define model construction\n",
-        "Now that the preprocessor and classifier for the model are defined, we can define how we want to construct the model. \n",
-        "\n",
-        "Constructing the model has these steps: \n",
-        "1. Get preprocessing steps\n",
-        "* Get featurizer using the Azure ML Accel Models SDK:\n",
-        "    * import the graph definition\n",
-        "    * restore the weights of the model into a Tensorflow session\n",
-        "* Get classifier\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "def construct_model(quantized, starting_weights_directory = None):\n",
-        "    from azureml.accel.models import Resnet50, QuantizedResnet50\n",
-        "    \n",
-        "    # Convert images to 3D tensors [width,height,channel]\n",
-        "    in_images, image_tensors = preprocess_images(1.0)\n",
-        "\n",
-        "    # Construct featurizer using quantized or unquantized ResNet50 model\n",
-        "    if not quantized:\n",
-        "        featurizer = Resnet50(saved_model_dir)\n",
-        "    else:\n",
-        "        featurizer = QuantizedResnet50(saved_model_dir, custom_weights_directory = starting_weights_directory)\n",
-        "\n",
-        "    features = featurizer.import_graph_def(input_tensor=image_tensors)\n",
-        "    \n",
-        "    # Construct classifier\n",
-        "    preds = construct_classifier(features)\n",
-        "    \n",
-        "    # Initialize weights\n",
-        "    sess = tf.get_default_session()\n",
-        "    tf.global_variables_initializer().run()\n",
-        "\n",
-        "    featurizer.restore_weights(sess)\n",
-        "\n",
-        "    return in_images, image_tensors, features, preds, featurizer"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id=\"train-model\"></a>\n",
-        "## 4. Train Model"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "def read_files(files):\n",
-        "    \"\"\" Read files to array\"\"\"\n",
-        "    contents = []\n",
-        "    for path in files:\n",
-        "        with open(path, 'rb') as f:\n",
-        "            contents.append(f.read())\n",
-        "    return contents"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "def train_model(preds, in_images, img_train, label_train, is_retrain = False, train_epoch = 10, learning_rate=None):\n",
-        "    \"\"\" training model \"\"\"\n",
-        "    from keras.objectives import binary_crossentropy\n",
-        "    from tqdm import tqdm\n",
-        "    \n",
-        "    learning_rate = learning_rate if learning_rate else 0.001 if is_retrain else 0.01\n",
-        "        \n",
-        "    # Specify the loss function\n",
-        "    in_labels = tf.placeholder(tf.float32, shape=(None, 2))   \n",
-        "    cross_entropy = tf.reduce_mean(binary_crossentropy(in_labels, preds))\n",
-        "    optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cross_entropy)\n",
-        "\n",
-        "    def chunks(a, b, n):\n",
-        "        \"\"\"Yield successive n-sized chunks from a and b.\"\"\"\n",
-        "        if (len(a) != len(b)):\n",
-        "            print(\"a and b are not equal in chunks(a,b,n)\")\n",
-        "            raise ValueError(\"Parameter error\")\n",
-        "\n",
-        "        for i in range(0, len(a), n):\n",
-        "            yield a[i:i + n], b[i:i + n]\n",
-        "\n",
-        "    chunk_size = 16\n",
-        "    chunk_num = len(label_train) / chunk_size\n",
-        "\n",
-        "    sess = tf.get_default_session()\n",
-        "    for epoch in range(train_epoch):\n",
-        "        avg_loss = 0\n",
-        "        for img_chunk, label_chunk in tqdm(chunks(img_train, label_train, chunk_size)):\n",
-        "            contents = read_files(img_chunk)\n",
-        "            _, loss = sess.run([optimizer, cross_entropy],\n",
-        "                                feed_dict={in_images: contents,\n",
-        "                                           in_labels: label_chunk,\n",
-        "                                           K.learning_phase(): 1})\n",
-        "            avg_loss += loss / chunk_num\n",
-        "        print(\"Epoch:\", (epoch + 1), \"loss = \", \"{:.3f}\".format(avg_loss))\n",
-        "            \n",
-        "        # Reach desired performance\n",
-        "        if (avg_loss < 0.001):\n",
-        "            break"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id=\"test-model\"></a>"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id=\"test-model\"></a>\n",
-        "## 5. Test Model"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "def test_model(preds, in_images, img_test, label_test):\n",
-        "    \"\"\"Test the model\"\"\"\n",
-        "    from keras.metrics import categorical_accuracy\n",
-        "\n",
-        "    in_labels = tf.placeholder(tf.float32, shape=(None, 2))\n",
-        "    accuracy = tf.reduce_mean(categorical_accuracy(in_labels, preds))\n",
-        "    contents = read_files(img_test)\n",
-        "\n",
-        "    accuracy = accuracy.eval(feed_dict={in_images: contents,\n",
-        "                                        in_labels: label_test,\n",
-        "                                        K.learning_phase(): 0})\n",
-        "    return accuracy"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id=\"execution\"></a>\n",
-        "## 6. Execute steps\n",
-        "You can run through the Transfer Learning section, then skip to Create AccelContainerImage. By default, because the custom weights section takes much longer for training twice, it is not saved as executable cells. You can copy the code or change cell type to 'Code'.\n",
-        "\n",
-        "<a id=\"transfer-learning\"></a>\n",
-        "### 6.a. Training using Transfer Learning"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Launch the training\n",
-        "tf.reset_default_graph()\n",
-        "sess = tf.Session(graph=tf.get_default_graph())\n",
-        "\n",
-        "with sess.as_default():\n",
-        "    in_images, image_tensors, features, preds, featurizer = construct_model(quantized=True)\n",
-        "    train_model(preds, in_images, img_train, label_train, is_retrain=False, train_epoch=10, learning_rate=0.01)    \n",
-        "    accuracy = test_model(preds, in_images, img_test, label_test)  \n",
-        "    print(\"Accuracy:\", accuracy)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Save Model"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "model_name = 'resnet50-catsanddogs-tl'\n",
-        "model_save_path = os.path.join(saved_model_dir, model_name)\n",
-        "\n",
-        "tf.saved_model.simple_save(sess, model_save_path,\n",
-        "                               inputs={'images': in_images},\n",
-        "                               outputs={'output_alias': preds})\n",
-        "\n",
-        "input_tensors = in_images.name\n",
-        "output_tensors = preds.name\n",
-        "\n",
-        "print(input_tensors)\n",
-        "print(output_tensors)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id=\"custom-weights\"></a>\n",
-        "### 6.b. Traning using Custom Weights\n",
-        "\n",
-        "Because the quantized graph defintion and the float32 graph defintion share the same node names in the graph definitions, we can initally train the weights in float32, and then reload them with the quantized operations (which take longer) to fine-tune the model.\n",
-        "\n",
-        "First we train the model with custom weights but without quantization. Training is done with native float precision (32-bit floats). We load the training data set and batch the training with 10 epochs. When the performance reaches desired level or starts decredation, we stop the training iteration and save the weights as tensorflow checkpoint files. "
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Launch the training\n",
-        "```\n",
-        "tf.reset_default_graph()\n",
-        "sess = tf.Session(graph=tf.get_default_graph())\n",
-        "\n",
-        "with sess.as_default():\n",
-        "    in_images, image_tensors, features, preds, featurizer = construct_model(quantized=False)\n",
-        "    train_model(preds, in_images, img_train, label_train, is_retrain=False, train_epoch=10)    \n",
-        "    accuracy = test_model(preds, in_images, img_test, label_test)  \n",
-        "    print(\"Accuracy:\", accuracy)\n",
-        "    featurizer.save_weights(custom_weights_dir + \"/rn50\", tf.get_default_session())\n",
-        "```"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Test Model\n",
-        "After training, we evaluate the trained model's accuracy on test dataset with quantization. So that we know the model's performance if it is deployed on the FPGA."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "```\n",
-        "tf.reset_default_graph()\n",
-        "sess = tf.Session(graph=tf.get_default_graph())\n",
-        "\n",
-        "with sess.as_default():\n",
-        "    print(\"Testing trained model with quantization\")\n",
-        "    in_images, image_tensors, features, preds, quantized_featurizer = construct_model(quantized=True, starting_weights_directory=custom_weights_dir)\n",
-        "    accuracy = test_model(preds, in_images, img_test, label_test)      \n",
-        "    print(\"Accuracy:\", accuracy)\n",
-        "```"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Fine-Tune Model\n",
-        "Sometimes, the model's accuracy can drop significantly after quantization. In those cases, we need to retrain the model enabled with quantization to get better model accuracy."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "```\n",
-        "if (accuracy < 0.93):\n",
-        "    with sess.as_default():\n",
-        "        print(\"Fine-tuning model with quantization\")\n",
-        "        train_model(preds, in_images, img_train, label_train, is_retrain=True, train_epoch=10)\n",
-        "        accuracy = test_model(preds, in_images, img_test, label_test)        \n",
-        "        print(\"Accuracy:\", accuracy)\n",
-        "```"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Save Model"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "```\n",
-        "model_name = 'resnet50-catsanddogs-cw'\n",
-        "model_save_path = os.path.join(saved_model_dir, model_name)\n",
-        "\n",
-        "tf.saved_model.simple_save(sess, model_save_path,\n",
-        "                               inputs={'images': in_images},\n",
-        "                               outputs={'output_alias': preds})\n",
-        "\n",
-        "input_tensors = in_images.name\n",
-        "output_tensors = preds.name\n",
-        "```"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id=\"create-image\"></a>\n",
-        "## 7. Create AccelContainerImage\n",
-        "\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)\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",
-        "## 8. 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",
-        "### 8.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",
-        "### 8.b. Deploy to AKS Cluster"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### 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-tl'\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",
-        "## 9. Test the service\n",
-        "\n",
-        "<a id=\"create-client\"></a>\n",
-        "### 9.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": [
-        "<a id=\"serve-model\"></a>\n",
-        "### 9.b. Serve the model\n",
-        "Let's see how our service does on a few images. It may get a few wrong."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Specify an image to classify\n",
-        "print('CATS')\n",
-        "for image_file in cat_files[:8]:\n",
-        "    results = client.score_file(path=image_file, \n",
-        "                                 input_name=input_tensors, \n",
-        "                                 outputs=output_tensors)\n",
-        "    result = 'CORRECT ' if results[0] > results[1] else 'WRONG '\n",
-        "    print(result + str(results))\n",
-        "print('DOGS')\n",
-        "for image_file in dog_files[:8]:\n",
-        "    results = client.score_file(path=image_file, \n",
-        "                                 input_name=input_tensors, \n",
-        "                                 outputs=output_tensors)\n",
-        "    result = 'CORRECT ' if results[1] > results[0] else 'WRONG '\n",
-        "    print(result + str(results))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id=\"cleanup\"></a>\n",
-        "## 10. Cleanup\n",
-        "It's important to clean up your resources, so that you won't incur unnecessary costs."
-      ]
-    },
-    {
-      "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()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "<a id=\"appendix\"></a>\n",
-        "## 11. Appendix"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "License for plot_confusion_matrix:\n",
-        "\n",
-        "New BSD License\n",
-        "\n",
-        "Copyright (c) 2007-2018 The scikit-learn developers.\n",
-        "All rights reserved.\n",
-        "\n",
-        "\n",
-        "Redistribution and use in source and binary forms, with or without\n",
-        "modification, are permitted provided that the following conditions are met:\n",
-        "\n",
-        "  a. Redistributions of source code must retain the above copyright notice,\n",
-        "     this list of conditions and the following disclaimer.\n",
-        "  b. Redistributions in binary form must reproduce the above copyright\n",
-        "     notice, this list of conditions and the following disclaimer in the\n",
-        "     documentation and/or other materials provided with the distribution.\n",
-        "  c. Neither the name of the Scikit-learn Developers  nor the names of\n",
-        "     its contributors may be used to endorse or promote products\n",
-        "     derived from this software without specific prior written\n",
-        "     permission. \n",
-        "\n",
-        "\n",
-        "THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS \"AS IS\"\n",
-        "AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE\n",
-        "IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE\n",
-        "ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE FOR\n",
-        "ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL\n",
-        "DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR\n",
-        "SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER\n",
-        "CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT\n",
-        "LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY\n",
-        "OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH\n",
-        "DAMAGE.\n"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "coverste"
-      },
-      {
-        "name": "paledger"
-      }
-    ],
-    "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"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

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

@@ -25,13 +25,6 @@
         "3. Build new image and deploy it. "
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/deployment/enable-app-insights-in-production-service/enable-app-insights-in-production-service.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

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

@@ -1,12 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/deployment/enable-data-collection-for-models-in-aks/enable-data-collection-for-models-in-aks.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

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

@@ -4,7 +4,7 @@ These tutorials show how to create and deploy Open Neural Network eXchange ([ONN
 
 ## Tutorials
 
-0. If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, [Configure your Azure Machine Learning Workspace](../../../configuration.ipynb)
+0. [Configure your Azure Machine Learning Workspace](../../../configuration.ipynb)
 
 #### Obtain pretrained models from the [ONNX Model Zoo](https://github.com/onnx/models) and deploy with ONNX Runtime
 1. [MNIST - Handwritten Digit Classification with ONNX Runtime](onnx-inference-mnist-deploy.ipynb)
@@ -34,6 +34,3 @@ Licensed under the MIT License.
 
 ## Acknowledgements
 These tutorials were developed by Vinitra Swamy and Prasanth Pulavarthi of the Microsoft AI Frameworks team and adapted for presentation at Microsoft Ignite 2018.
-
-
- ![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/deployment/onnx/README.png)

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

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/deployment/onnx/onnx-convert-aml-deploy-tinyyolo.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -40,7 +33,7 @@
         "To make the best use of your time, make sure you have done the following:\n",
         "\n",
         "* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning\n",
-        "* If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, go through the [configuration](../../../configuration.ipynb) notebook to:\n",
+        "* Go through the [configuration](../../../configuration.ipynb) notebook to:\n",
         "    * install the AML SDK\n",
         "    * create a workspace and its configuration file (config.json)"
       ]
@@ -255,7 +248,7 @@
       "source": [
         "from azureml.core.conda_dependencies import CondaDependencies \n",
         "\n",
-        "myenv = CondaDependencies.create(pip_packages=[\"numpy\",\"onnxruntime==0.4.0\",\"azureml-core\"])\n",
+        "myenv = CondaDependencies.create(pip_packages=[\"numpy\",\"onnxruntime\",\"azureml-core\"])\n",
         "\n",
         "with open(\"myenv.yml\",\"w\") as f:\n",
         "    f.write(myenv.serialize_to_string())"

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

@@ -8,13 +8,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/deployment/onnx/onnx-inference-facial-expression-recognition-deploy.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -41,7 +34,7 @@
         "## Prerequisites\n",
         "\n",
         "### 1. Install Azure ML SDK and create a new workspace\n",
-        "If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, please follow [Azure ML configuration notebook](../../../configuration.ipynb) to set up your environment.\n",
+        "Please follow [Azure ML configuration notebook](../../../configuration.ipynb) to set up your environment.\n",
         "\n",
         "### 2. Install additional packages needed for this Notebook\n",
         "You need to install the popular plotting library `matplotlib`, the image manipulation library `opencv`, and the `onnx` library in the conda environment where Azure Maching Learning SDK is installed.\n",

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

@@ -8,13 +8,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/deployment/onnx/onnx-inference-mnist-deploy.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -41,7 +34,7 @@
         "## Prerequisites\n",
         "\n",
         "### 1. Install Azure ML SDK and create a new workspace\n",
-        "If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, please follow [Azure ML configuration notebook](../../../configuration.ipynb) to set up your environment.\n",
+        "Please follow [Azure ML configuration notebook](../../../configuration.ipynb) to set up your environment.\n",
         "\n",
         "### 2. Install additional packages needed for this tutorial notebook\n",
         "You need to install the popular plotting library `matplotlib`, the image manipulation library `opencv`, and the `onnx` library in the conda environment where Azure Maching Learning SDK is installed. \n",

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

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/deployment/onnx/onnx-modelzoo-aml-deploy-resnet50.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -40,7 +33,7 @@
         "To make the best use of your time, make sure you have done the following:\n",
         "\n",
         "* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning\n",
-        "* If you are using an Azure Machine Learning Notebook VM, you are all set.  Otherwise, go through the [configuration notebook](../../../configuration.ipynb) to:\n",
+        "* Go through the [configuration notebook](../../../configuration.ipynb) to:\n",
         "    * install the AML SDK\n",
         "    * create a workspace and its configuration file (config.json)"
       ]

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

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/deployment/onnx/onnx-train-pytorch-aml-deploy-mnist.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -37,7 +30,7 @@
       "source": [
         "## Prerequisites\n",
         "* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning\n",
-        "* If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, go through the [configuration notebook](../../../configuration.ipynb) to:\n",
+        "* Go through the [configuration notebook](../../../configuration.ipynb) to:\n",
         "    * install the AML SDK\n",
         "    * create a workspace and its configuration file (`config.json`)"
       ]
@@ -98,7 +91,7 @@
         "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# choose a name for your cluster\n",
-        "cluster_name = \"gpu-cluster\"\n",
+        "cluster_name = \"gpucluster\"\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 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# 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"
-      }
-    ],
-    "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"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

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

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/deployment/production-deploy-to-aks/production-deploy-to-aks.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

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

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/deployment/register-model-create-image-deploy-service/register-model-create-image-deploy-service.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -41,7 +34,7 @@
       "metadata": {},
       "source": [
         "## Prerequisites\n",
-        "If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, make sure you go through the [configuration](../../../configuration.ipynb) Notebook first if you haven't."
+        "Make sure you go through the [configuration](../../../configuration.ipynb) Notebook first if you haven't."
       ]
     },
     {

how-to-use-azureml/explain-model/README.md

@@ -2,7 +2,10 @@
 
 Follow these sample notebooks to learn:
 
-1. [Explain tabular data locally](explain-tabular-data-local): Basic example of explaining model trained on tabular data.
+1. [Explain tabular data](explain-tabular-data): Basic example of explaining model trained on tabular data.
+2. [Explain local classification](explain-local-sklearn-classification): Explain a scikit-learn classification model.
+3. [Explain local regression](explain-local-sklearn-regression): Explain a scikit-learn regression model.
 4. [Explain on remote AMLCompute](explain-on-amlcompute): Explain a model on a remote AMLCompute target.
-5. [Explain tabular data with Run History](explain-tabular-data-run-history): Explain a model with Run History.
-7. [Explain raw features](explain-tabular-data-raw-features): Explain the raw features of a trained model.
+5. [Explain classification using Run History](explain-run-history-sklearn-classification): Explain a scikit-learn classification model with Run History.
+6. [Explain regression using Run History](explain-run-history-sklearn-regression): Explain a scikit-learn regression model with Run History.
+7. [Explain scikit-learn raw features](explain-sklearn-raw-features): Explain the raw features of a trained scikit-learn model.

how-to-use-azureml/explain-model/explain-local-sklearn-classification/explain-local-sklearn-classification.ipynb

@@ -7,13 +7,6 @@
         "# Breast cancer diagnosis classification with scikit-learn (run model explainer locally)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/explain-model/explain-tabular-data-local/explain-local-sklearn-binary-classification.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -31,8 +24,7 @@
         "\n",
         "1. Train a SVM classification model using Scikit-learn\n",
         "2. Run 'explain_model' with full data in local mode, which doesn't contact any Azure services\n",
-        "3. Run 'explain_model' with summarized data in local mode, which doesn't contact any Azure services\n",
-        "4. Visualize the global and local explanations with the visualization dashboard."
+        "3. Run 'explain_model' with summarized data in local mode, which doesn't contact any Azure services"
       ]
     },
     {
@@ -189,9 +181,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "# explain the first member of the test set\n",
-        "instance_num = 0\n",
-        "local_explanation = tabular_explainer.explain_local(x_test[instance_num,:])"
+        "local_explanation = tabular_explainer.explain_local(x_test[0,:])"
       ]
     },
     {
@@ -200,21 +190,9 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "# get the prediction for the first member of the test set and explain why model made that prediction\n",
-        "prediction_value = clf.predict(x_test)[instance_num]\n",
-        "\n",
-        "sorted_local_importance_values = local_explanation.get_ranked_local_values()[prediction_value]\n",
-        "sorted_local_importance_names = local_explanation.get_ranked_local_names()[prediction_value]\n",
-        "\n",
-        "\n",
-        "dict(zip(sorted_local_importance_names, sorted_local_importance_values))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# 2. Load visualization dashboard"
+        "# local feature importance information\n",
+        "local_importance_values = local_explanation.local_importance_values\n",
+        "print('local importance for first instance: {}'.format(local_importance_values[y_test[0]]))"
       ]
     },
     {
@@ -223,12 +201,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "# Note you will need to have extensions enabled prior to jupyter kernel starting\n",
-        "!jupyter nbextension install --py --sys-prefix azureml.contrib.explain.model.visualize\n",
-        "!jupyter nbextension enable --py --sys-prefix azureml.contrib.explain.model.visualize\n",
-        "# Or, in Jupyter Labs, uncomment below\n",
-        "# jupyter labextension install @jupyter-widgets/jupyterlab-manager\n",
-        "# jupyter labextension install microsoft-mli-widget"
+        "print('local importance feature names: {}'.format(list(local_explanation.features)))"
       ]
     },
     {
@@ -237,23 +210,14 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.contrib.explain.model.visualize import ExplanationDashboard"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ExplanationDashboard(global_explanation, model, x_test)"
+        "dict(zip(local_explanation.features, local_explanation.local_importance_values[y_test[0]]))"
       ]
     }
   ],
   "metadata": {
     "authors": [
       {
-        "name": "mesameki"
+        "name": "wamartin"
       }
     ],
     "kernelspec": {

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

@@ -7,13 +7,6 @@
         "# Boston Housing Price Prediction with scikit-learn (run model explainer locally)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/explain-model/explain-tabular-data-local/explain-local-sklearn-regression.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -31,8 +24,7 @@
         "\n",
         "1. Train a GradientBoosting regression model using Scikit-learn\n",
         "2. Run 'explain_model' with full dataset in local mode, which doesn't contact any Azure services.\n",
-        "3. Run 'explain_model' with summarized dataset in local mode, which doesn't contact any Azure services.\n",
-        "4. Visualize the global and local explanations with the visualization dashboard."
+        "3. Run 'explain_model' with summarized dataset in local mode, which doesn't contact any Azure services."
       ]
     },
     {
@@ -93,10 +85,10 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "reg = GradientBoostingRegressor(n_estimators=100, max_depth=4,\n",
+        "clf = GradientBoostingRegressor(n_estimators=100, max_depth=4,\n",
         "                                learning_rate=0.1, loss='huber',\n",
         "                                random_state=1)\n",
-        "model = reg.fit(x_train, y_train)"
+        "model = clf.fit(x_train, y_train)"
       ]
     },
     {
@@ -133,6 +125,15 @@
         "global_explanation = tabular_explainer.explain_global(x_test)"
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "help(global_explanation)"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -195,58 +196,16 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "# sorted local feature importance information; reflects the original feature order\n",
-        "sorted_local_importance_names = local_explanation.get_ranked_local_names()\n",
-        "sorted_local_importance_values = local_explanation.get_ranked_local_values()\n",
-        "\n",
-        "print('sorted local importance names: {}'.format(sorted_local_importance_names))\n",
-        "print('sorted local importance values: {}'.format(sorted_local_importance_values))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Load visualization dashboard"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Note you will need to have extensions enabled prior to jupyter kernel starting\n",
-        "!jupyter nbextension install --py --sys-prefix azureml.contrib.explain.model.visualize\n",
-        "!jupyter nbextension enable --py --sys-prefix azureml.contrib.explain.model.visualize\n",
-        "# Or, in Jupyter Labs, uncomment below\n",
-        "# jupyter labextension install @jupyter-widgets/jupyterlab-manager\n",
-        "# jupyter labextension install microsoft-mli-widget"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.contrib.explain.model.visualize import ExplanationDashboard"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ExplanationDashboard(global_explanation, model, x_test)"
+        "# local feature importance information\n",
+        "local_importance_values = local_explanation.local_importance_values\n",
+        "print('local importance values: {}'.format(local_importance_values))"
       ]
     }
   ],
   "metadata": {
     "authors": [
       {
-        "name": "mesameki"
+        "name": "wamartin"
       }
     ],
     "kernelspec": {

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

@@ -9,13 +9,6 @@
         "Licensed under the MIT License."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/explain-model/explain-on-amlcompute/regression-sklearn-on-amlcompute.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -39,7 +32,7 @@
       "metadata": {},
       "source": [
         "## Prerequisites\n",
-        "If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, make sure you go through the [configuration notebook](../../../configuration.ipynb) first if you haven't."
+        "Make sure you go through the [configuration notebook](../../../configuration.ipynb) first if you haven't."
       ]
     },
     {
@@ -203,6 +196,9 @@
         "# use conda_dependencies.yml to create a conda environment in the Docker image for execution\n",
         "run_config.environment.python.user_managed_dependencies = False\n",
         "\n",
+        "# auto-prepare the Docker image when used for execution (if it is not already prepared)\n",
+        "run_config.auto_prepare_environment = True\n",
+        "\n",
         "azureml_pip_packages = [\n",
         "    'azureml-defaults', 'azureml-contrib-explain-model', 'azureml-core', 'azureml-telemetry',\n",
         "    'azureml-explain-model'\n",
@@ -265,7 +261,7 @@
         "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# Choose a name for your CPU cluster\n",
-        "cpu_cluster_name = \"cpu-cluster\"\n",
+        "cpu_cluster_name = \"cpucluster\"\n",
         "\n",
         "# Verify that cluster does not exist already\n",
         "try:\n",
@@ -370,7 +366,7 @@
         "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# Choose a name for your CPU cluster\n",
-        "cpu_cluster_name = \"cpu-cluster\"\n",
+        "cpu_cluster_name = \"cpucluster\"\n",
         "\n",
         "# Verify that cluster does not exist already\n",
         "try:\n",
@@ -506,7 +502,7 @@
       "outputs": [],
       "source": [
         "# Delete () is used to deprovision and delete the AmlCompute target. Useful if you want to re-use the compute name \n",
-        "# 'cpu-cluster' in this case but use a different VM family for instance.\n",
+        "# 'cpucluster' in this case but use a different VM family for instance.\n",
         "\n",
         "# cpu_cluster.delete()"
       ]
@@ -580,7 +576,7 @@
   "metadata": {
     "authors": [
       {
-        "name": "mesameki"
+        "name": "wamartin"
       }
     ],
     "kernelspec": {

how-to-use-azureml/explain-model/explain-run-history-sklearn-classification/explain-run-history-sklearn-classification.ipynb

@@ -7,13 +7,6 @@
         "# Breast cancer diagnosis classification with scikit-learn (save model explanations via AML Run History)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/explain-model/explain-tabular-data-run-history/explain-run-history-sklearn-classification.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -236,7 +229,7 @@
   "metadata": {
     "authors": [
       {
-        "name": "mesameki"
+        "name": "wamartin"
       }
     ],
     "kernelspec": {

how-to-use-azureml/explain-model/explain-run-history-sklearn-regression/explain-run-history-sklearn-regression.ipynb

@@ -7,13 +7,6 @@
         "# Boston Housing Price Prediction with scikit-learn (save model explanations via AML Run History)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/explain-model/explain-tabular-data-run-history/explain-run-history-sklearn-regression.png)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -250,7 +243,7 @@
   "metadata": {
     "authors": [
       {
-        "name": "mesameki"
+        "name": "wamartin"
       }
     ],
     "kernelspec": {

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

@@ -0,0 +1,221 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Summary\n",
+        "From raw data that is a mixture of categoricals and numeric, featurize the categoricals using one hot encoding. Use tabular explainer to get explain object and then get raw feature importances"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Load titanic dataset. Impute missing values by filling both backward and forward since some data is at the first/last row. This is just for illustration and not a recommended way to impute missing data."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import pandas as pd\n",
+        "\n",
+        "titanic_url = ('https://raw.githubusercontent.com/amueller/'\n",
+        "               'scipy-2017-sklearn/091d371/notebooks/datasets/titanic3.csv')\n",
+        "data = pd.read_csv(titanic_url)\n",
+        "# fill missing values\n",
+        "data = data.fillna(method=\"ffill\")\n",
+        "data = data.fillna(method=\"bfill\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "data.columns"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Similar to example [here](https://scikit-learn.org/stable/auto_examples/compose/plot_column_transformer_mixed_types.html#sphx-glr-auto-examples-compose-plot-column-transformer-mixed-types-py), use a subset of columns"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from sklearn.model_selection import train_test_split\n",
+        "\n",
+        "numeric_features = ['age', 'fare']\n",
+        "categorical_features = ['embarked', 'sex', 'pclass']\n",
+        "\n",
+        "y = data['survived'].values\n",
+        "X = data[categorical_features + numeric_features]\n",
+        "\n",
+        "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": [
+        "One hot encode the categorical features"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from sklearn.preprocessing import OneHotEncoder\n",
+        "one_enc = OneHotEncoder()\n",
+        "one_enc.fit(X_train[categorical_features])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Columnwise concatenate one hot encoded categoricals and numerical features."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import numpy as np\n",
+        "from scipy import sparse\n",
+        "def get_feats(X):\n",
+        "    a = one_enc.transform(X[categorical_features])\n",
+        "    b = X[numeric_features]\n",
+        "    return sparse.hstack((one_enc.transform(X[categorical_features]), X[numeric_features].values))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Train a logistic regression model on featurized training data."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from sklearn.linear_model import LogisticRegression\n",
+        "\n",
+        "X_train_transformed = get_feats(X_train)\n",
+        "X_test_transformed = get_feats(X_test)\n",
+        "\n",
+        "clf = LogisticRegression(solver='lbfgs', max_iter=200)\n",
+        "clf.fit(X_train_transformed, y_train)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Get feature mapping between raw and generated features. Using the order in which features are concatenated in `get_feats` and using `categories_` in `OneHotEncoder` we are able to compute this mapping."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "raw_feat_mapping = []\n",
+        "start_index = 0\n",
+        "for cat_list in one_enc.categories_:\n",
+        "    raw_feat_mapping.append([start_index + i for i in range(len(cat_list))])\n",
+        "    start_index += len(cat_list)\n",
+        "for i in range(len(numeric_features)):\n",
+        "    raw_feat_mapping.append([start_index])\n",
+        "    start_index += 1    "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.explain.model.tabular_explainer import TabularExplainer\n",
+        "\n",
+        "explainer = TabularExplainer(clf, X_train_transformed)\n",
+        "global_explanation = explainer.explain_global(X_test_transformed)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "raw_feat_imps = global_explanation.get_raw_feature_importances(raw_feat_mapping)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "feature_names = categorical_features + numeric_features\n",
+        "sorted_indices = np.argsort(raw_feat_imps)[::-1]\n",
+        "\n",
+        "for i in sorted_indices:\n",
+        "    print(\"{}: {}\".format(feature_names[i], raw_feat_imps[i]))"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "hichando"
+      }
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "python",
+      "name": "python36"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.8"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/explain-model/explain-tabular-data-local/explain-local-sklearn-multiclass-classification.ipynb

@@ -1,280 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Iris flower classification with scikit-learn (run model explainer locally)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/explain-model/explain-tabular-data-local/explain-local-sklearn-multiclass-classification.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Explain a model with the AML explain-model package\n",
-        "\n",
-        "1. Train a SVM classification model using Scikit-learn\n",
-        "2. Run 'explain_model' with full data in local mode, which doesn't contact any Azure services\n",
-        "3. Run 'explain_model' with summarized data in local mode, which doesn't contact any Azure services\n",
-        "4. Visualize the global and local explanations with the visualization dashboard."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from sklearn.datasets import load_iris\n",
-        "from sklearn import svm\n",
-        "from azureml.explain.model.tabular_explainer import TabularExplainer"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# 1. Run model explainer locally with full data"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Load the breast cancer diagnosis data"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "iris = load_iris()\n",
-        "X = iris['data']\n",
-        "y = iris['target']\n",
-        "classes = iris['target_names']\n",
-        "feature_names = iris['feature_names']"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Split data into train and test\n",
-        "from sklearn.model_selection import train_test_split\n",
-        "x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Train a SVM classification model, which you want to explain"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "clf = svm.SVC(gamma=0.001, C=100., probability=True)\n",
-        "model = clf.fit(x_train, y_train)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Explain predictions on your local machine"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "tabular_explainer = TabularExplainer(model, x_train, features = feature_names, classes=classes)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Explain overall model predictions (global explanation)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "global_explanation = tabular_explainer.explain_global(x_test)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Sorted SHAP values\n",
-        "print('ranked global importance values: {}'.format(global_explanation.get_ranked_global_values()))\n",
-        "# Corresponding feature names\n",
-        "print('ranked global importance names: {}'.format(global_explanation.get_ranked_global_names()))\n",
-        "# feature ranks (based on original order of features)\n",
-        "print('global importance rank: {}'.format(global_explanation.global_importance_rank))\n",
-        "# per class feature names\n",
-        "print('ranked per class feature names: {}'.format(global_explanation.get_ranked_per_class_names()))\n",
-        "# per class feature importance values\n",
-        "print('ranked per class feature values: {}'.format(global_explanation.get_ranked_per_class_values()))"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "dict(zip(global_explanation.get_ranked_global_names(), global_explanation.get_ranked_global_values()))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Explain overall model predictions as a collection of local (instance-level) explanations"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# feature shap values for all features and all data points in the training data\n",
-        "print('local importance values: {}'.format(global_explanation.local_importance_values))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Explain local data points (individual instances)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# explain the first member of the test set\n",
-        "instance_num = 0\n",
-        "local_explanation = tabular_explainer.explain_local(x_test[instance_num,:])"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# get the prediction for the first member of the test set and explain why model made that prediction\n",
-        "prediction_value = clf.predict(x_test)[instance_num]\n",
-        "\n",
-        "sorted_local_importance_values = local_explanation.get_ranked_local_values()[prediction_value]\n",
-        "sorted_local_importance_names = local_explanation.get_ranked_local_names()[prediction_value]\n",
-        "\n",
-        "\n",
-        "dict(zip(sorted_local_importance_names, sorted_local_importance_values))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Load visualization dashboard"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Note you will need to have extensions enabled prior to jupyter kernel starting\n",
-        "!jupyter nbextension install --py --sys-prefix azureml.contrib.explain.model.visualize\n",
-        "!jupyter nbextension enable --py --sys-prefix azureml.contrib.explain.model.visualize\n",
-        "# Or, in Jupyter Labs, uncomment below\n",
-        "# jupyter labextension install @jupyter-widgets/jupyterlab-manager\n",
-        "# jupyter labextension install microsoft-mli-widget"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.contrib.explain.model.visualize import ExplanationDashboard"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ExplanationDashboard(global_explanation, model, x_test)"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "mesameki"
-      }
-    ],
-    "kernelspec": {
-      "display_name": "Python 3.6",
-      "language": "python",
-      "name": "python36"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.6.8"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

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

@@ -1,337 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Summary\n",
-        "From raw data that is a mixture of categoricals and numeric, featurize the categoricals using one hot encoding. Use tabular explainer to get explain object and then get raw feature importances"
-      ]
-    },
-    {
-      "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/explain-model/explain-tabular-data-raw-features/explain-sklearn-raw-features.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Explain a model with the AML explain-model package on raw features\n",
-        "\n",
-        "1. Train a Logistic Regression model using Scikit-learn\n",
-        "2. Run 'explain_model' with full dataset in local mode, which doesn't contact any Azure services.\n",
-        "3. Run 'explain_model' with summarized dataset in local mode, which doesn't contact any Azure services.\n",
-        "4. Visualize the global and local explanations with the visualization dashboard."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from sklearn.pipeline import Pipeline\n",
-        "from sklearn.impute import SimpleImputer\n",
-        "from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
-        "from sklearn.linear_model import LogisticRegression\n",
-        "from azureml.explain.model.tabular_explainer import TabularExplainer\n",
-        "import pandas as pd\n",
-        "import numpy as np"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "titanic_url = ('https://raw.githubusercontent.com/amueller/'\n",
-        "               'scipy-2017-sklearn/091d371/notebooks/datasets/titanic3.csv')\n",
-        "data = pd.read_csv(titanic_url)\n",
-        "# fill missing values\n",
-        "data = data.fillna(method=\"ffill\")\n",
-        "data = data.fillna(method=\"bfill\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# 1. Run model explainer locally with full data"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Similar to example [here](https://scikit-learn.org/stable/auto_examples/compose/plot_column_transformer_mixed_types.html#sphx-glr-auto-examples-compose-plot-column-transformer-mixed-types-py), use a subset of columns"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from sklearn.model_selection import train_test_split\n",
-        "\n",
-        "numeric_features = ['age', 'fare']\n",
-        "categorical_features = ['embarked', 'sex', 'pclass']\n",
-        "\n",
-        "y = data['survived'].values\n",
-        "X = data[categorical_features + numeric_features]\n",
-        "\n",
-        "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,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from sklearn.pipeline import Pipeline\n",
-        "from sklearn.impute import SimpleImputer\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",
-        "\n",
-        "transformations = [\n",
-        "    ([\"age\", \"fare\"], Pipeline(steps=[\n",
-        "        ('imputer', SimpleImputer(strategy='median')),\n",
-        "        ('scaler', StandardScaler())\n",
-        "    ])),\n",
-        "    ([\"embarked\"], Pipeline(steps=[\n",
-        "        (\"imputer\", SimpleImputer(strategy='constant', fill_value='missing')), \n",
-        "        (\"encoder\", OneHotEncoder(sparse=False))])),\n",
-        "    ([\"sex\", \"pclass\"], OneHotEncoder(sparse=False))    \n",
-        "]\n",
-        "\n",
-        "\n",
-        "# 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'))])\n",
-        "'''"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Train a Logistic Regression model, which you want to explain"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "model = clf.fit(x_train, y_train)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Explain predictions on your local machine"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "tabular_explainer = TabularExplainer(clf.steps[-1][1], initialization_examples=x_train, features=x_train.columns, transformations=transformations)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Passing in test dataset for evaluation examples - note it must be a representative sample of the original data\n",
-        "# x_train can be passed as well, but with more examples explanations will take longer although they may be more accurate\n",
-        "global_explanation = tabular_explainer.explain_global(x_test)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "sorted_global_importance_values = global_explanation.get_ranked_global_values()\n",
-        "sorted_global_importance_names = global_explanation.get_ranked_global_names()\n",
-        "dict(zip(sorted_global_importance_names, sorted_global_importance_values))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Explain overall model predictions as a collection of local (instance-level) explanations"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# explain the first member of the test set\n",
-        "local_explanation = tabular_explainer.explain_local(x_test[:1])"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# get the prediction for the first member of the test set and explain why model made that prediction\n",
-        "prediction_value = clf.predict(x_test)[0]\n",
-        "\n",
-        "sorted_local_importance_values = local_explanation.get_ranked_local_values()[prediction_value]\n",
-        "sorted_local_importance_names = local_explanation.get_ranked_local_names()[prediction_value]\n",
-        "\n",
-        "# Sorted local SHAP values\n",
-        "print('ranked local importance values: {}'.format(sorted_local_importance_values))\n",
-        "# Corresponding feature names\n",
-        "print('ranked local importance names: {}'.format(sorted_local_importance_names))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# 2. Load visualization dashboard"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Note you will need to have extensions enabled prior to jupyter kernel starting\n",
-        "!jupyter nbextension install --py --sys-prefix azureml.contrib.explain.model.visualize\n",
-        "!jupyter nbextension enable --py --sys-prefix azureml.contrib.explain.model.visualize\n",
-        "# Or, in Jupyter Labs, uncomment below\n",
-        "# jupyter labextension install @jupyter-widgets/jupyterlab-manager\n",
-        "# jupyter labextension install microsoft-mli-widget"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.contrib.explain.model.visualize import ExplanationDashboard"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ExplanationDashboard(global_explanation, model, x_test)"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "mesameki"
-      }
-    ],
-    "kernelspec": {
-      "display_name": "Python 3.6",
-      "language": "python",
-      "name": "python36"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.6.8"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}