update samples from Release-174 as a part of SDK release

update samples from Release-166 as a part of 1.49.0 SDK stable release

SECURITY.md

@@ -0,0 +1,41 @@
+<!-- BEGIN MICROSOFT SECURITY.MD V0.0.7 BLOCK -->
+
+## Security
+
+Microsoft takes the security of our software products and services seriously, which includes all source code repositories managed through our GitHub organizations, which include [Microsoft](https://github.com/Microsoft), [Azure](https://github.com/Azure), [DotNet](https://github.com/dotnet), [AspNet](https://github.com/aspnet), [Xamarin](https://github.com/xamarin), and [our GitHub organizations](https://opensource.microsoft.com/).
+
+If you believe you have found a security vulnerability in any Microsoft-owned repository that meets [Microsoft's definition of a security vulnerability](https://aka.ms/opensource/security/definition), please report it to us as described below.
+
+## Reporting Security Issues
+
+**Please do not report security vulnerabilities through public GitHub issues.**
+
+Instead, please report them to the Microsoft Security Response Center (MSRC) at [https://msrc.microsoft.com/create-report](https://aka.ms/opensource/security/create-report).
+
+If you prefer to submit without logging in, send email to [secure@microsoft.com](mailto:secure@microsoft.com).  If possible, encrypt your message with our PGP key; please download it from the [Microsoft Security Response Center PGP Key page](https://aka.ms/opensource/security/pgpkey).
+
+You should receive a response within 24 hours. If for some reason you do not, please follow up via email to ensure we received your original message. Additional information can be found at [microsoft.com/msrc](https://aka.ms/opensource/security/msrc). 
+
+Please include the requested information listed below (as much as you can provide) to help us better understand the nature and scope of the possible issue:
+
+  * Type of issue (e.g. buffer overflow, SQL injection, cross-site scripting, etc.)
+  * Full paths of source file(s) related to the manifestation of the issue
+  * The location of the affected source code (tag/branch/commit or direct URL)
+  * Any special configuration required to reproduce the issue
+  * Step-by-step instructions to reproduce the issue
+  * Proof-of-concept or exploit code (if possible)
+  * Impact of the issue, including how an attacker might exploit the issue
+
+This information will help us triage your report more quickly.
+
+If you are reporting for a bug bounty, more complete reports can contribute to a higher bounty award. Please visit our [Microsoft Bug Bounty Program](https://aka.ms/opensource/security/bounty) page for more details about our active programs.
+
+## Preferred Languages
+
+We prefer all communications to be in English.
+
+## Policy
+
+Microsoft follows the principle of [Coordinated Vulnerability Disclosure](https://aka.ms/opensource/security/cvd).
+
+<!-- END MICROSOFT SECURITY.MD BLOCK -->

configuration.ipynb

@@ -103,7 +103,7 @@
       "source": [
         "import azureml.core\n",
         "\n",
-        "print(\"This notebook was created using version 1.43.0 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version Latest of the Azure ML SDK\")\n",
         "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },
@@ -367,9 +367,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -398,7 +398,7 @@
         "# run_config.target = gpu_cluster_name\n",
         "# run_config.environment.docker.enabled = True\n",
         "# run_config.environment.docker.gpu_support = True\n",
-        "# run_config.environment.docker.base_image = \"rapidsai/rapidsai:cuda9.2-runtime-ubuntu18.04\"\n",
+        "# run_config.environment.docker.base_image = \"rapidsai/rapidsai:cuda9.2-runtime-ubuntu20.04\"\n",
         "# # run_config.environment.docker.base_image_registry.address = '<registry_url>' # not required if the base_image is in Docker hub\n",
         "# # run_config.environment.docker.base_image_registry.username = '<user_name>' # needed only for private images\n",
         "# # run_config.environment.docker.base_image_registry.password = '<password>' # needed only for private images\n",
@@ -525,9 +525,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

contrib/fairness/fairlearn-azureml-mitigation.ipynb

@@ -599,9 +599,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

contrib/fairness/fairlearn-azureml-mitigation.yml

@@ -6,7 +6,8 @@ dependencies:
   - fairlearn>=0.6.2
   - joblib
   - liac-arff
-  - raiwidgets~=0.19.0
+  - raiwidgets~=0.24.0
   - itsdangerous==2.0.1
   - markupsafe<2.1.0
   - protobuf==3.20.0
+  - numpy<1.24.0

contrib/fairness/upload-fairness-dashboard.ipynb

@@ -523,9 +523,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

contrib/fairness/upload-fairness-dashboard.yml

@@ -6,7 +6,8 @@ dependencies:
   - fairlearn>=0.6.2
   - joblib
   - liac-arff
-  - raiwidgets~=0.19.0
+  - raiwidgets~=0.24.0
   - itsdangerous==2.0.1
   - markupsafe<2.1.0
   - protobuf==3.20.0
+  - numpy<1.24.0

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

@@ -5,27 +5,21 @@ channels:
   - main
 dependencies:
   # The python interpreter version.
-  # Currently Azure ML only supports 3.6.0 and later.
-- pip==20.2.4
-- python>=3.6,<3.9
-- matplotlib==3.2.1
-- py-xgboost==1.3.3
-- pytorch::pytorch=1.4.0
+  # Azure ML only supports 3.7.0 and later.
+- pip==22.3.1
+- python>=3.7,<3.9
 - conda-forge::fbprophet==0.7.1
-- cudatoolkit=10.1.243
+- pandas==1.1.5
 - scipy==1.5.3
-- notebook
-- pywin32==227
-- PySocks==1.7.1
-- jsonschema==4.6.0
-- conda-forge::pyqt==5.12.3
+- Cython==0.29.14
+- tqdm==4.64.1
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
-  - azureml-widgets~=1.43.0
-  - pytorch-transformers==1.0.0
-  - spacy==2.2.4
-  - pystan==2.19.1.1
-  - https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz
-  - -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.43.0/validated_win32_requirements.txt [--no-deps]
-  - arch==4.14
+  - azureml-widgets~=Latest
+  - azureml-defaults~=Latest
+  - -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/Latest/validated_win32_requirements.txt [--no-deps]
+  - matplotlib==3.6.2
+  - xgboost==1.3.3
+  - cmdstanpy==0.9.5
+  - setuptools-git==1.2

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

@@ -5,13 +5,11 @@ channels:
   - main
 dependencies:
   # The python interpreter version.
-  # Currently Azure ML only supports 3.6.0 and later.
-- pip==20.2.4
-- python>=3.6,<3.9
-- boto3==1.20.19
-- botocore<=1.23.19
+  # Azure ML only supports 3.7 and later.
+- pip==22.3.1
+- python>=3.7,<3.9
 - matplotlib==3.2.1
-- numpy==1.19.5
+- numpy>=1.21.6,<=1.22.3
 - cython==0.29.14
 - urllib3==1.26.7
 - scipy>=1.4.1,<=1.5.3
@@ -19,15 +17,16 @@ dependencies:
 - py-xgboost<=1.3.3
 - holidays==0.10.3
 - conda-forge::fbprophet==0.7.1
-- pytorch::pytorch=1.4.0
+- pytorch::pytorch=1.11.0
 - cudatoolkit=10.1.243
+- notebook
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
-  - azureml-widgets~=1.43.0
+  - azureml-widgets~=Latest
+  - azureml-defaults~=Latest
   - pytorch-transformers==1.0.0
   - spacy==2.2.4
   - pystan==2.19.1.1
   - https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz
-  - -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.43.0/validated_linux_requirements.txt [--no-deps]
-  - arch==4.14
+  - -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/Latest/validated_linux_requirements.txt [--no-deps]

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

@@ -5,14 +5,11 @@ channels:
   - main
 dependencies:
   # The python interpreter version.
-  # Currently Azure ML only supports 3.6.0 and later.
-- pip==20.2.4
-- nomkl
-- python>=3.6,<3.9
-- boto3==1.20.19
-- botocore<=1.23.19
+  # Currently Azure ML only supports 3.7 and later.
+- pip==22.3.1
+- python>=3.7,<3.9
 - matplotlib==3.2.1
-- numpy==1.19.5
+- numpy>=1.21.6,<=1.22.3
 - cython==0.29.14
 - urllib3==1.26.7
 - scipy>=1.4.1,<=1.5.3
@@ -20,15 +17,16 @@ dependencies:
 - py-xgboost<=1.3.3
 - holidays==0.10.3
 - conda-forge::fbprophet==0.7.1
-- pytorch::pytorch=1.4.0
+- pytorch::pytorch=1.11.0
 - cudatoolkit=9.0
+- notebook
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
-  - azureml-widgets~=1.43.0
+  - azureml-widgets~=Latest
+  - azureml-defaults~=Latest
   - pytorch-transformers==1.0.0
   - spacy==2.2.4
   - pystan==2.19.1.1
   - https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz
-  - -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.43.0/validated_darwin_requirements.txt [--no-deps]
-  - arch==4.14
+  - -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/Latest/validated_darwin_requirements.txt [--no-deps]

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

@@ -33,6 +33,8 @@ if not errorlevel 1 (
   call conda env create -f %automl_env_file% -n %conda_env_name%
 )
 
+python "%conda_prefix%\scripts\pywin32_postinstall.py" -install
+
 call conda activate %conda_env_name% 2>nul:
 if errorlevel 1 goto ErrorExit
 

how-to-use-azureml/automated-machine-learning/check_conda_version.py

@@ -1,4 +1,4 @@
-from distutils.version import LooseVersion
+from setuptools._vendor.packaging import version
 import platform
 
 try:
@@ -17,7 +17,7 @@ if architecture != "64bit":
 
 minimumVersion = "4.7.8"
 
-versionInvalid = (LooseVersion(conda.__version__) < LooseVersion(minimumVersion))
+versionInvalid = (version.parse(conda.__version__) < version.parse(minimumVersion))
 
 if versionInvalid:
     print('Setup requires conda version ' + minimumVersion + ' or higher.')

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

@@ -228,8 +228,8 @@
         "n_missing_samples = int(np.floor(data.shape[0] * missing_rate))\n",
         "missing_samples = np.hstack(\n",
         "    (\n",
-        "        np.zeros(data.shape[0] - n_missing_samples, dtype=np.bool),\n",
-        "        np.ones(n_missing_samples, dtype=np.bool),\n",
+        "        np.zeros(data.shape[0] - n_missing_samples, dtype=bool),\n",
+        "        np.ones(n_missing_samples, dtype=bool),\n",
         "    )\n",
         ")\n",
         "rng = np.random.RandomState(0)\n",
@@ -1060,9 +1060,9 @@
       "name": "python3-azureml"
     },
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {
@@ -1074,7 +1074,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.9"
+      "version": "3.8.12"
     },
     "nteract": {
       "version": "nteract-front-end@1.0.0"

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

@@ -456,9 +456,9 @@
     "friendly_name": "Classification of credit card fraudulent transactions using Automated ML",
     "index_order": 5,
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -207,11 +207,11 @@
         "\n",
         "def remove_blanks_20news(data, feature_column_name, target_column_name):\n",
         "\n",
-        "    data[feature_column_name] = (\n",
-        "        data[feature_column_name]\n",
-        "        .replace(r\"\\n\", \" \", regex=True)\n",
-        "        .apply(lambda x: x.strip())\n",
+        "    for index, row in data.iterrows():\n",
+        "        data.at[index, feature_column_name] = (\n",
+        "            row[feature_column_name].replace(\"\\n\", \" \").strip()\n",
         "        )\n",
+        "\n",
         "    data = data[data[feature_column_name] != \"\"]\n",
         "\n",
         "    return data"
@@ -567,9 +567,9 @@
     "friendly_name": "DNN Text Featurization",
     "index_order": 2,
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

how-to-use-azureml/automated-machine-learning/classification-text-dnn/helper.py

@@ -1,6 +1,5 @@
 import pandas as pd
-from azureml.core import Environment
-from azureml.train.estimator import Estimator
+from azureml.core import Environment, ScriptRunConfig
 from azureml.core.run import Run
 
 
@@ -16,16 +15,19 @@ def run_inference(
 
     inference_env = train_run.get_environment()
 
-    est = Estimator(
+    est = ScriptRunConfig(
         source_directory=script_folder,
-        entry_script="infer.py",
-        script_params={
-            "--target_column_name": target_column_name,
-            "--model_name": model_name,
-        },
-        inputs=[test_dataset.as_named_input("test_data")],
+        script="infer.py",
+        arguments=[
+            "--target_column_name",
+            target_column_name,
+            "--model_name",
+            model_name,
+            "--input-data",
+            test_dataset.as_named_input("data"),
+        ],
         compute_target=compute_target,
-        environment_definition=inference_env,
+        environment=inference_env,
     )
 
     run = test_experiment.submit(

how-to-use-azureml/automated-machine-learning/classification-text-dnn/infer.py

@@ -6,7 +6,7 @@ import numpy as np
 from sklearn.externals import joblib
 
 from azureml.automl.runtime.shared.score import scoring, constants
-from azureml.core import Run
+from azureml.core import Run, Dataset
 from azureml.core.model import Model
 
 
@@ -21,6 +21,8 @@ parser.add_argument(
     "--model_name", type=str, dest="model_name", help="Name of registered model"
 )
 
+parser.add_argument("--input-data", type=str, dest="input_data", help="Dataset")
+
 args = parser.parse_args()
 target_column_name = args.target_column_name
 model_name = args.model_name
@@ -34,8 +36,8 @@ model_path = Model.get_model_path(model_name)
 model = joblib.load(model_path)
 
 run = Run.get_context()
-# get input dataset by name
-test_dataset = run.input_datasets["test_data"]
+
+test_dataset = Dataset.get_by_id(run.experiment.workspace, id=args.input_data)
 
 X_test_df = test_dataset.drop_columns(
     columns=[target_column_name]

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

@@ -564,9 +564,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

how-to-use-azureml/automated-machine-learning/continuous-retraining/upload_weather_data.py

@@ -120,9 +120,13 @@ except Exception:
     end_time = datetime(2021, 5, 1, 0, 0)
     end_time_last_slice = end_time - relativedelta(weeks=2)
 
+try:
     train_df = get_noaa_data(end_time_last_slice, end_time)
+except Exception as ex:
+    print("get_noaa_data failed:", ex)
+    train_df = None
 
-if train_df.size > 0:
+if train_df is not None and train_df.size > 0:
     print(
         "Received {0} rows of new data after {1}.".format(
             train_df.shape[0], end_time_last_slice

how-to-use-azureml/automated-machine-learning/experimental/autofeaturization-codegen/codegen-for-autofeaturization.ipynb

@@ -0,0 +1,346 @@
+{
+  "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/custom-model-training-from-autofeaturization-run.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning - Codegen for AutoFeaturization \n",
+        "_**Autofeaturization of credit card fraudulent transactions dataset on remote compute and codegen functionality**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Data](#Data)\n",
+        "1. [Autofeaturization](#Autofeaturization)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id='Introduction'></a>\n",
+        "## Introduction"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "**Autofeaturization** lets you run an AutoML experiment to only featurize the datasets. These datasets along with the transformer are stored in AML Storage and linked to the run which can later be retrieved and used to train models. \n",
+        "\n",
+        "**To run Autofeaturization, set the number of iterations to zero and featurization as auto.**\n",
+        "\n",
+        "Please refer to [Autofeaturization and custom model training](../autofeaturization-custom-model-training/custom-model-training-from-autofeaturization-run.ipynb) for more details on the same.\n",
+        "\n",
+        "[Codegen](https://github.com/Azure/automl-codegen-preview) is a feature, which when enabled, provides a user with the script of the underlying functionality and a notebook to tweak inputs or code and rerun the same.\n",
+        "\n",
+        "In this example we use the credit card fraudulent transactions dataset to showcase how you can use AutoML for autofeaturization and further how you can enable the `Codegen` feature.\n",
+        "\n",
+        "This notebook is using remote compute to complete the featurization.\n",
+        "\n",
+        "If you are using an Azure Machine Learning Compute Instance, 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",
+        "Here you will learn how to create an autofeaturization experiment using an existing workspace with codegen feature enabled."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id='Setup'></a>\n",
+        "## Setup\n",
+        "\n",
+        "As part of the setup you have already created an Azure ML `Workspace` object. For Automated ML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import logging\n",
+        "import pandas as pd\n",
+        "import azureml.core\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "from azureml.core.dataset import Dataset\n",
+        "from azureml.train.automl import AutoMLConfig"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"This notebook was created using version Latest of the Azure ML SDK\")\n",
+        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "# choose a name for experiment\n",
+        "experiment_name = 'automl-autofeaturization-ccard-codegen-remote'\n",
+        "\n",
+        "experiment=Experiment(ws, experiment_name)\n",
+        "\n",
+        "output = {}\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['Experiment Name'] = experiment.name\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
+        "outputDf.T"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create or Attach existing AmlCompute\n",
+        "A compute target is required to execute the Automated ML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
+        "\n",
+        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
+        "\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](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
+        "from azureml.core.compute_target import ComputeTargetException\n",
+        "\n",
+        "# Choose a name for your CPU cluster\n",
+        "cpu_cluster_name = \"cpu-cluster\"\n",
+        "\n",
+        "# Verify that cluster does not exist already\n",
+        "try:\n",
+        "    compute_target = ComputeTarget(workspace=ws, name=cpu_cluster_name)\n",
+        "    print('Found existing cluster, use it.')\n",
+        "except ComputeTargetException:\n",
+        "    compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_DS12_V2',\n",
+        "                                                           max_nodes=6)\n",
+        "    compute_target = ComputeTarget.create(ws, cpu_cluster_name, compute_config)\n",
+        "\n",
+        "compute_target.wait_for_completion(show_output=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id='Data'></a>\n",
+        "## Data"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Load Data\n",
+        "\n",
+        "Load the credit card fraudulent transactions dataset from a CSV file, containing both training features and labels. The features are inputs to the model, while the training labels represent the expected output of the model. \n",
+        "\n",
+        "Here the autofeaturization run will featurize the training data passed in."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "##### Training Dataset"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "training_data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/creditcard_train.csv\"\n",
+        "training_dataset = Dataset.Tabular.from_delimited_files(training_data) # Tabular dataset\n",
+        "\n",
+        "label_column_name = 'Class' # output label"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id='Autofeaturization'></a>\n",
+        "## AutoFeaturization\n",
+        "\n",
+        "Instantiate an AutoMLConfig object. This defines the settings and data used to run the autofeaturization experiment.\n",
+        "\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**task**|classification or regression or forecasting|\n",
+        "|**training_data**|Input training dataset, containing both features and label column.|\n",
+        "|**iterations**|For an autofeaturization run, iterations will be 0.|\n",
+        "|**featurization**|For an autofeaturization run, featurization can be 'auto' or 'custom'.|\n",
+        "|**label_column_name**|The name of the label column.|\n",
+        "|**enable_code_generation**|For enabling codegen for the run, value would be True|\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_config = AutoMLConfig(task = 'classification',\n",
+        "                             debug_log = 'automl_errors.log',\n",
+        "                             iterations = 0, # autofeaturization run can be triggered by setting iterations to 0\n",
+        "                             compute_target = compute_target,\n",
+        "                             training_data = training_dataset,\n",
+        "                             label_column_name = label_column_name,\n",
+        "                             featurization = 'auto',\n",
+        "                             verbosity = logging.INFO,\n",
+        "                             enable_code_generation = True # enable codegen\n",
+        "                            )"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Call the `submit` method on the experiment object and pass the run configuration. Depending on the data this can run for a while. Validation errors and current status will be shown when setting `show_output=True` and the execution will be synchronous."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run = experiment.submit(automl_config, show_output = False)"
+      ]
+    },
+    {
+      "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": [
+        "remote_run.wait_for_completion(show_output=False)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Codegen Script and Notebook"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Codegen script and notebook can be found under the `Outputs + logs` section from the details page of the remote run. Please check for the `autofeaturization_notebook.ipynb` under `/outputs/generated_code`. To modify the featurization code, open `script.py` and make changes. The codegen notebook can be run with the same environment configuration as the above AutoML run."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Experiment Complete!"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "bhavanatumma"
+      }
+    ],
+    "interpreter": {
+      "hash": "adb464b67752e4577e3dc163235ced27038d19b7d88def00d75d1975bde5d9ab"
+    },
+    "kernelspec": {
+      "display_name": "Python 3.8 - AzureML",
+      "language": "python",
+      "name": "python38-azureml"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.9"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/experimental/autofeaturization-codegen/codegen-for-autofeaturization.yml

@@ -0,0 +1,4 @@
+name: codegen-for-autofeaturization
+dependencies:
+- pip:
+  - azureml-sdk

how-to-use-azureml/automated-machine-learning/experimental/autofeaturization-custom-model-training/custom-model-training-from-autofeaturization-run.ipynb

@@ -0,0 +1,735 @@
+{
+  "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/custom-model-training-from-autofeaturization-run.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning - AutoFeaturization (Part 1)\n",
+        "_**Autofeaturization of credit card fraudulent transactions dataset on remote compute**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Data](#Data)\n",
+        "1. [Autofeaturization](#Autofeaturization)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id='Introduction'></a>\n",
+        "## Introduction"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Autofeaturization is a new feature to let you as the user run an AutoML experiment to only featurize the datasets. These datasets along with the transformer will be stored in the experiment which can later be retrieved and used to train models, either via AutoML or custom training. \n",
+        "\n",
+        "**To run Autofeaturization, pass in zero iterations and featurization as auto. This will featurize the datasets and terminate the experiment. Training will not occur.**\n",
+        "\n",
+        "*Limitations - Sparse data cannot be supported at the moment. Any dataset that has extensive categorical data might be featurized into sparse data which will not be allowed as input to AutoML. Efforts are underway to support sparse data and will be updated soon.* \n",
+        "\n",
+        "In this example we use the credit card fraudulent transactions dataset to showcase how you can use AutoML for autofeaturization. The goal is to clean and featurize the training dataset.\n",
+        "\n",
+        "This notebook is using remote compute to complete the featurization.\n",
+        "\n",
+        "If you are using an Azure Machine Learning Compute Instance, 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 the below steps, you will learn how to:\n",
+        "1. Create an autofeaturization experiment using an existing workspace.\n",
+        "2. View the featurized datasets and transformer"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id='Setup'></a>\n",
+        "## Setup\n",
+        "\n",
+        "As part of the setup you have already created an Azure ML `Workspace` object. For Automated ML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import logging\n",
+        "import pandas as pd\n",
+        "import azureml.core\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "from azureml.core.dataset import Dataset\n",
+        "from azureml.train.automl import AutoMLConfig"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"This notebook was created using version Latest of the Azure ML SDK\")\n",
+        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "# choose a name for experiment\n",
+        "experiment_name = 'automl-autofeaturization-ccard-remote'\n",
+        "\n",
+        "experiment=Experiment(ws, experiment_name)\n",
+        "\n",
+        "output = {}\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['Experiment Name'] = experiment.name\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
+        "outputDf.T"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create or Attach existing AmlCompute\n",
+        "A compute target is required to execute the Automated ML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
+        "\n",
+        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
+        "\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](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
+        "from azureml.core.compute_target import ComputeTargetException\n",
+        "\n",
+        "# Choose a name for your CPU cluster\n",
+        "cpu_cluster_name = \"cpu-cluster\"\n",
+        "\n",
+        "# Verify that cluster does not exist already\n",
+        "try:\n",
+        "    compute_target = ComputeTarget(workspace=ws, name=cpu_cluster_name)\n",
+        "    print('Found existing cluster, use it.')\n",
+        "except ComputeTargetException:\n",
+        "    compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_DS12_V2',\n",
+        "                                                           max_nodes=6)\n",
+        "    compute_target = ComputeTarget.create(ws, cpu_cluster_name, compute_config)\n",
+        "\n",
+        "compute_target.wait_for_completion(show_output=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id='Data'></a>\n",
+        "## Data"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Load Data\n",
+        "\n",
+        "Load the credit card fraudulent transactions dataset from a CSV file, containing both training features and labels. The features are inputs to the model, while the training labels represent the expected output of the model. \n",
+        "\n",
+        "Here the autofeaturization run will featurize the training data passed in."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "##### Training Dataset"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "training_data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/creditcard_train.csv\"\n",
+        "training_dataset = Dataset.Tabular.from_delimited_files(training_data) # Tabular dataset\n",
+        "\n",
+        "label_column_name = 'Class' # output label"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id='Autofeaturization'></a>\n",
+        "## AutoFeaturization\n",
+        "\n",
+        "Instantiate an AutoMLConfig object. This defines the settings and data used to run the autofeaturization experiment.\n",
+        "\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**task**|classification or regression|\n",
+        "|**training_data**|Input training dataset, containing both features and label column.|\n",
+        "|**iterations**|For an autofeaturization run, iterations will be 0.|\n",
+        "|**featurization**|For an autofeaturization run, featurization will be 'auto'.|\n",
+        "|**label_column_name**|The name of the label column.|\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_config = AutoMLConfig(task = 'classification',\n",
+        "                             debug_log = 'automl_errors.log',\n",
+        "                             iterations = 0, # autofeaturization run can be triggered by setting iterations to 0\n",
+        "                             compute_target = compute_target,\n",
+        "                             training_data = training_dataset,\n",
+        "                             label_column_name = label_column_name,\n",
+        "                             featurization = 'auto',\n",
+        "                             verbosity = logging.INFO\n",
+        "                            )"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Call the `submit` method on the experiment object and pass the run configuration. Depending on the data this can run for a while. Validation errors and current status will be shown when setting `show_output=True` and the execution will be synchronous."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run = experiment.submit(automl_config, show_output = False)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Transformer and Featurized Datasets\n",
+        "The given datasets have been featurized and stored under `Outputs + logs` from the details page of the remote run. The structure is shown below. The featurized dataset is stored under `/outputs/featurization/data` and the transformer is saved under `/outputs/featurization/pipeline` \n",
+        "\n",
+        "Below you will learn how to refer to the data saved in your run and retrieve the same."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Featurized Data](https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/autofeaturization_img.png)"
+      ]
+    },
+    {
+      "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": [
+        "remote_run.wait_for_completion(show_output=False)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning - AutoFeaturization (Part 2)\n",
+        "_**Training using a custom model with the featurized data from Autofeaturization run of credit card fraudulent transactions dataset**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Data Setup](#DataSetup)\n",
+        "1. [Autofeaturization Data](#AutofeaturizationData)\n",
+        "1. [Train](#Train)\n",
+        "1. [Results](#Results)\n",
+        "1. [Test](#Test)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id='Introduction'></a>\n",
+        "## Introduction\n",
+        "\n",
+        "Here we use the featurized dataset saved in the above run to showcase how you can perform custom training by using the transformer from an autofeaturization run to transform validation / test datasets. \n",
+        "\n",
+        "The goal is to use autofeaturized run data and transformer to transform and run a custom training experiment independently\n",
+        "\n",
+        "In the below steps, you will learn how to:\n",
+        "1. Read transformer from a completed autofeaturization run and transform data\n",
+        "2. Pull featurized data from a completed autofeaturization run\n",
+        "3. Run a custom training experiment with the above data\n",
+        "4. Check results"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id='DataSetup'></a>\n",
+        "## Data Setup"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We will load the featurized training data and also load the transformer from the above autofeaturized run. This transformer can then be used to transform the test data to check the accuracy of the custom model after training."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Load Test Data"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "load test dataset from CSV and split into X and y columns to featurize with the transformer going forward."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "test_data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/creditcard_test.csv\"\n",
+        "\n",
+        "test_dataset = pd.read_csv(test_data)\n",
+        "label_column_name = 'Class'\n",
+        "\n",
+        "X_test_data = test_dataset[test_dataset.columns.difference([label_column_name])]\n",
+        "y_test_data = test_dataset[label_column_name].values\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Load data_transformer from the above remote run artifact"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### (Method 1)\n",
+        "\n",
+        "Method 1 allows you to read the transformer from the remote storage."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import mlflow\n",
+        "mlflow.set_tracking_uri(ws.get_mlflow_tracking_uri())\n",
+        "\n",
+        "# Set uri to fetch data transformer from remote parent run.\n",
+        "artifact_path = \"/outputs/featurization/pipeline/\"\n",
+        "uri = \"runs:/\" + remote_run.id + artifact_path\n",
+        "\n",
+        "print(uri)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### (Method 2)\n",
+        "\n",
+        "Method 2 downloads the transformer to the local directory and then can be used to transform the data. Uncomment to use."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "''' import pathlib\n",
+        "\n",
+        "# Download the transformer to the local directory\n",
+        "transformers_file_path = \"/outputs/featurization/pipeline/\"\n",
+        "local_path = \"./transformer\"\n",
+        "remote_run.download_files(prefix=transformers_file_path, output_directory=local_path, batch_size=500)\n",
+        "\n",
+        "path = pathlib.Path(\"transformer\") \n",
+        "path = str(path.absolute()) + transformers_file_path\n",
+        "str_uri = \"file:///\" + path\n",
+        "\n",
+        "print(str_uri) '''"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Transform Data"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "**Note:** Not all datasets produce a y_transformer. The dataset used in the current notebook requires a transformer as the y column data is categorical."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.automl.core.shared.constants import Transformers\n",
+        "\n",
+        "transformers = mlflow.sklearn.load_model(uri) # Using method 1\n",
+        "data_transformers = transformers.get_transformers()\n",
+        "x_transformer = data_transformers[Transformers.X_TRANSFORMER]\n",
+        "y_transformer = data_transformers[Transformers.Y_TRANSFORMER]\n",
+        "\n",
+        "X_test = x_transformer.transform(X_test_data)\n",
+        "y_test = y_transformer.transform(y_test_data)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Run the following cell to see the featurization summary of X and y transformers.  "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X_data_summary = x_transformer.get_featurization_summary(is_user_friendly=False)\n",
+        "\n",
+        "summary_df = pd.DataFrame.from_records(X_data_summary)\n",
+        "summary_df"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Load Datastore\n",
+        "\n",
+        "The below data store holds the featurized datasets, hence we load and access the data. Check the path and file names according to the saved structure in your experiment `Outputs + logs` as seen in <i>Autofeaturization Part 1</i>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.datastore import Datastore\n",
+        "\n",
+        "ds = Datastore.get(ws, \"workspaceartifactstore\")\n",
+        "experiment_loc = \"ExperimentRun/dcid.\" + remote_run.id\n",
+        "\n",
+        "remote_data_path = \"/outputs/featurization/data/\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id='AutofeaturizationData'></a>\n",
+        "## Autofeaturization Data\n",
+        "\n",
+        "We will load the training data from the previously completed Autofeaturization experiment. The resulting featurized dataframe can be passed into the custom model for training. Here we are saving the file to local from the experiment storage and reading the data."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "train_data_file_path = \"full_training_dataset.df.parquet\"\n",
+        "local_data_path = \"./data/\" + train_data_file_path\n",
+        "\n",
+        "remote_run.download_file(remote_data_path + train_data_file_path, local_data_path)\n",
+        "\n",
+        "full_training_data = pd.read_parquet(local_data_path)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Another way to load the data is to go to the above autofeaturization experiment and check for the featurized dataset ids under `Output datasets`. Uncomment and replace them accordingly below to use."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# train_data = Dataset.get_by_id(ws, 'cb4418ee-bac4-45ac-b055-600653bdf83a') # replace the featurized full_training_dataset id\n",
+        "# full_training_data = train_data.to_pandas_dataframe()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Training Data"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We are dropping the y column and weights column from the featurized training dataset."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "Y_COLUMN = \"automl_y\"\n",
+        "SW_COLUMN = \"automl_weights\"\n",
+        "\n",
+        "X_train = full_training_data[full_training_data.columns.difference([Y_COLUMN, SW_COLUMN])]\n",
+        "y_train = full_training_data[Y_COLUMN].values\n",
+        "sample_weight = full_training_data[SW_COLUMN].values"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id='Train'></a>\n",
+        "## Train"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Here we are passing our training data to the lightgbm classifier, any custom model can be used with your data."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import lightgbm as lgb\n",
+        "\n",
+        "model = lgb.LGBMClassifier(learning_rate=0.08,max_depth=-5,random_state=42)\n",
+        "model.fit(X_train, y_train, sample_weight=sample_weight, eval_set=[(X_test, y_test),(X_train, y_train)],\n",
+        "          verbose=20,eval_metric='logloss')\n",
+        "\n",
+        "print('Training accuracy {:.4f}'.format(model.score(X_train, y_train)))\n",
+        "print('Testing accuracy {:.4f}'.format(model.score(X_test, y_test)))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id='Results'></a>\n",
+        "## Analyze results\n",
+        "\n",
+        "### Retrieve the Model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "model"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id='Test'></a>\n",
+        "## Test the fitted model\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": [
+        "y_pred = model.predict(X_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": [
+        "from sklearn.metrics import confusion_matrix\n",
+        "from matplotlib import pyplot as plt\n",
+        "import numpy as np\n",
+        "import itertools\n",
+        "\n",
+        "cf =confusion_matrix(y_test,y_pred)\n",
+        "plt.imshow(cf,cmap=plt.cm.Blues,interpolation='nearest')\n",
+        "plt.colorbar()\n",
+        "plt.title('Confusion Matrix')\n",
+        "plt.xlabel('Predicted')\n",
+        "plt.ylabel('Actual')\n",
+        "class_labels = ['False','True']\n",
+        "tick_marks = np.arange(len(class_labels))\n",
+        "plt.xticks(tick_marks,class_labels)\n",
+        "plt.yticks([-0.5,0,1,1.5],['','False','True',''])\n",
+        "# plotting text value inside cells\n",
+        "thresh = cf.max() / 2.\n",
+        "for i,j in itertools.product(range(cf.shape[0]),range(cf.shape[1])):\n",
+        "    plt.text(j,i,format(cf[i,j],'d'),horizontalalignment='center',color='white' if cf[i,j] >thresh else 'black')\n",
+        "plt.show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Experiment Complete!"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "bhavanatumma"
+      }
+    ],
+    "interpreter": {
+      "hash": "adb464b67752e4577e3dc163235ced27038d19b7d88def00d75d1975bde5d9ab"
+    },
+    "kernelspec": {
+      "display_name": "Python 3.8 - AzureML",
+      "language": "python",
+      "name": "python38-azureml"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.9"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/experimental/autofeaturization-custom-model-training/custom-model-training-from-autofeaturization-run.yml

@@ -0,0 +1,4 @@
+name: custom-model-training-from-autofeaturization-run
+dependencies:
+- pip:
+  - azureml-sdk

how-to-use-azureml/automated-machine-learning/experimental/automl_thin_client_env.yml

@@ -1,22 +1,15 @@
 name: azure_automl_experimental
 dependencies:
   # The python interpreter version.
-  # Currently Azure ML only supports 3.6.0 and later.
-- pip<=20.2.4
-- python>=3.6.0,<3.9
-- cython==0.29.14
-- urllib3==1.26.7
-- PyJWT < 2.0.0
-- numpy==1.18.5
-- pywin32==227
-- cryptography<37.0.0
+  # Currently Azure ML only supports 3.7.0 and later.
+- pip<=22.3.1
+- python>=3.7.0,<3.11
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
-  - azure-mgmt-core==1.3.0
-  - azure-core==1.21.1
-  - azure-identity==1.7.0
   - azureml-defaults
   - azureml-sdk
   - azureml-widgets
+  - azureml-mlflow
   - pandas
+  - mlflow

how-to-use-azureml/automated-machine-learning/experimental/automl_thin_client_env_mac.yml

@@ -4,21 +4,21 @@ channels:
   - main
 dependencies:
   # The python interpreter version.
-  # Currently Azure ML only supports 3.6.0 and later.
+  # Currently Azure ML only supports 3.7.0 and later.
 - pip<=20.2.4
 - nomkl
-- python>=3.6.0,<3.9
+- python>=3.7.0,<3.11
 - urllib3==1.26.7
 - PyJWT < 2.0.0
-- numpy==1.19.5
-- cryptography<37.0.0
+- numpy>=1.21.6,<=1.22.3
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
-  - azure-mgmt-core==1.3.0
-  - azure-core==1.21.1
+  - azure-core==1.24.1
   - azure-identity==1.7.0
   - azureml-defaults
   - azureml-sdk
   - azureml-widgets
+  - azureml-mlflow
   - pandas
+  - mlflow

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

@@ -92,7 +92,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "print(\"This notebook was created using version 1.43.0 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version Latest of the Azure ML SDK\")\n",
         "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },
@@ -354,7 +354,7 @@
         "This Credit Card fraud Detection dataset is made available under the Open Database License: http://opendatacommons.org/licenses/odbl/1.0/. Any rights in individual contents of the database are licensed under the Database Contents License: http://opendatacommons.org/licenses/dbcl/1.0/ and is available at: https://www.kaggle.com/mlg-ulb/creditcardfraud\n",
         "\n",
         "\n",
-        "The dataset has been collected and analysed during a research collaboration of Worldline and the Machine Learning Group (http://mlg.ulb.ac.be) of ULB (Universit\u00c3\u0192\u00c2\u00a9 Libre de Bruxelles) on big data mining and fraud detection. More details on current and past projects on related topics are available on https://www.researchgate.net/project/Fraud-detection-5 and the page of the DefeatFraud project\n",
+        "The dataset has been collected and analysed during a research collaboration of Worldline and the Machine Learning Group (http://mlg.ulb.ac.be) of ULB (Universit\u00c3\u0192\u00c2\u00a9 Libre de Bruxelles) on big data mining and fraud detection. More details on current and past projects on related topics are available on https://www.researchgate.net and the page of the DefeatFraud project\n",
         "Please cite the following works: \n",
         "\u00c3\u00a2\u00e2\u201a\u00ac\u00c2\u00a2\tAndrea Dal Pozzolo, Olivier Caelen, Reid A. Johnson and Gianluca Bontempi. Calibrating Probability with Undersampling for Unbalanced Classification. In Symposium on Computational Intelligence and Data Mining (CIDM), IEEE, 2015\n",
         "\u00c3\u00a2\u00e2\u201a\u00ac\u00c2\u00a2\tDal Pozzolo, Andrea; Caelen, Olivier; Le Borgne, Yann-Ael; Waterschoot, Serge; Bontempi, Gianluca. Learned lessons in credit card fraud detection from a practitioner perspective, Expert systems with applications,41,10,4915-4928,2014, Pergamon\n",
@@ -389,9 +389,9 @@
     "friendly_name": "Classification of credit card fraudulent transactions using Automated ML",
     "index_order": 5,
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -91,7 +91,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "print(\"This notebook was created using version 1.43.0 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version Latest of the Azure ML SDK\")\n",
         "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },
@@ -448,9 +448,9 @@
       "automated-machine-learning"
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

how-to-use-azureml/automated-machine-learning/forecasting-backtest-many-models/assets/score.py

@@ -122,7 +122,10 @@ def calculate_scores_and_build_plots(
     input_dir: str, output_dir: str, automl_settings: Dict[str, Any]
 ):
     os.makedirs(output_dir, exist_ok=True)
-    grains = automl_settings.get(constants.TimeSeries.TIME_SERIES_ID_COLUMN_NAMES)
+    grains = automl_settings.get(
+        constants.TimeSeries.TIME_SERIES_ID_COLUMN_NAMES,
+        automl_settings.get(constants.TimeSeries.GRAIN_COLUMN_NAMES, None),
+    )
     time_column_name = automl_settings.get(constants.TimeSeries.TIME_COLUMN_NAME)
     if grains is None:
         grains = []

how-to-use-azureml/automated-machine-learning/forecasting-backtest-many-models/auto-ml-forecasting-backtest-many-models.ipynb

@@ -33,6 +33,7 @@
         "For this notebook we are using a synthetic dataset to demonstrate the back testing in many model scenario. This allows us to check historical performance of AutoML on a historical data. To do that we step back on the backtesting period by the data set several times and split the data to train and test sets. Then these data sets are used for training and evaluation of model.<br>\n",
         "\n",
         "Thus, it is a quick way of evaluating AutoML as if it was in production. Here, we do not test historical performance of a particular model, for this see the [notebook](../forecasting-backtest-single-model/auto-ml-forecasting-backtest-single-model.ipynb). Instead, the best model for every backtest iteration can be different since AutoML chooses the best model for a given training set.\n",
+        "\n",
         "![Backtesting](Backtesting.png)\n",
         "\n",
         "**NOTE: There are limits on how many runs we can do in parallel per workspace, and we currently recommend to set the parallelism to maximum of 320 runs per experiment per workspace. If users want to have more parallelism and increase this limit they might encounter Too Many Requests errors (HTTP 429).**"
@@ -43,7 +44,7 @@
       "metadata": {},
       "source": [
         "### Prerequisites\n",
-        "You'll need to create a compute Instance by following the instructions in the [EnvironmentSetup.md](../Setup_Resources/EnvironmentSetup.md)."
+        "You'll need to create a compute Instance by following [these](https://learn.microsoft.com/en-us/azure/machine-learning/v1/how-to-create-manage-compute-instance?tabs=python) instructions."
       ]
     },
     {
@@ -313,21 +314,37 @@
       "source": [
         "### Set up training parameters\n",
         "\n",
-        "This dictionary defines the AutoML and many models settings. For this forecasting task we need to define several settings including the name of the time column, the maximum forecast horizon, and the partition column name definition. Please note, that in this case we are setting grain_column_names to be the time series ID column plus iteration, because we want to train a separate model for each time series and iteration.\n",
+        "We need to provide ``ForecastingParameters``, ``AutoMLConfig`` and ``ManyModelsTrainParameters`` objects. For the forecasting task we also need to define several settings including the name of the time column, the maximum forecast horizon, and the partition column name(s) definition.\n",
         "\n",
+        "#### ``ForecastingParameters`` arguments\n",
+        "| Property                           | Description|\n",
+        "| :---------------                   | :------------------- |\n",
+        "| **forecast_horizon**               | The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly). Periods are inferred from your data. |\n",
+        "| **time_column_name**               | The name of your time column. |\n",
+        "| **time_series_id_column_names**    | The column names used to uniquely identify timeseries in data that has multiple rows with the same timestamp. |\n",
+        "| **cv_step_size**                   | Number of periods between two consecutive cross-validation folds. The default value is \\\"auto\\\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value. |\n",
+        "\n",
+        "#### ``AutoMLConfig`` arguments\n",
         "| Property                           | Description|\n",
         "| :---------------                   | :------------------- |\n",
         "| **task**                           | forecasting |\n",
-        "| **primary_metric**                 | This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>normalized_root_mean_squared_error</i><br><i>normalized_mean_absolute_error</i> |\n",
+        "| **primary_metric**                 | This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i> |\n",
+        "| **blocked_models**                 | Blocked models won't be used by AutoML. |\n",
         "| **iteration_timeout_minutes**      | Maximum amount of time in minutes that the model can train. This is optional but provides customers with greater control on exit criteria. |\n",
         "| **iterations**                     | Number of models to train. This is optional but provides customers with greater control on exit criteria. |\n",
-        "| **experiment_timeout_hours**       | Maximum amount of time in hours that the experiment can take before it terminates. This is optional but provides customers with greater control on exit criteria. |\n",
+        "| **experiment_timeout_hours**       | Maximum amount of time in hours that each experiment can take before it terminates. This is optional but provides customers with greater control on exit criteria. **It does not control the overall timeout for the pipeline run, instead controls the timeout for each training run per partitioned time series.** |\n",
         "| **label_column_name**              | The name of the label column. |\n",
-        "| **forecast_horizon**               | The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly). Periods are inferred from your data. |\n",
-        "| **n_cross_validations**            | Number of cross validation splits. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
-        "| **time_column_name**               | The name of your time column. |\n",
-        "| **time_series_id_column_names**     | The column names used to uniquely identify timeseries in data that has multiple rows with the same timestamp. |\n",
+        "| **n_cross_validations**            | Number of cross validation splits. The default value is \\\"auto\\\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
+        "| **enable_early_stopping**          | Flag to enable early termination if the primary metric is no longer improving. |\n",
+        "| **enable_engineered_explanations** | Engineered feature explanations will be downloaded if enable_engineered_explanations flag is set to True. By default it is set to False to save storage space. |\n",
         "| **track_child_runs**               | Flag to disable tracking of child runs. Only best run is tracked if the flag is set to False (this includes the model and metrics of the run). |\n",
+        "| **pipeline_fetch_max_batch_size**  | Determines how many pipelines (training algorithms) to fetch at a time for training, this helps reduce throttling when training at large scale. |\n",
+        "\n",
+        "\n",
+        "#### ``ManyModelsTrainParameters`` arguments\n",
+        "| Property                           | Description|\n",
+        "| :---------------                   | :------------------- |\n",
+        "| **automl_settings**                | The ``AutoMLConfig`` object defined above. |\n",
         "| **partition_column_names**         | The names of columns used to group your models. For timeseries, the groups must not split up individual time-series. That is, each group must contain one or more whole time-series. |"
       ]
     },
@@ -344,21 +361,30 @@
         "from azureml.train.automl.runtime._many_models.many_models_parameters import (\n",
         "    ManyModelsTrainParameters,\n",
         ")\n",
+        "from azureml.automl.core.forecasting_parameters import ForecastingParameters\n",
+        "from azureml.train.automl.automlconfig import AutoMLConfig\n",
         "\n",
         "partition_column_names = [TIME_SERIES_ID_COLNAME, \"backtest_iteration\"]\n",
-        "automl_settings = {\n",
-        "    \"task\": \"forecasting\",\n",
-        "    \"primary_metric\": \"normalized_root_mean_squared_error\",\n",
-        "    \"iteration_timeout_minutes\": 10,  # This needs to be changed based on the dataset. We ask customer to explore how long training is taking before settings this value\n",
-        "    \"iterations\": 15,\n",
-        "    \"experiment_timeout_hours\": 0.25,  # This also needs to be changed based on the dataset. For larger data set this number needs to be bigger.\n",
-        "    \"label_column_name\": TARGET_COLNAME,\n",
-        "    \"n_cross_validations\": 3,\n",
-        "    \"time_column_name\": TIME_COLNAME,\n",
-        "    \"forecast_horizon\": 6,\n",
-        "    \"time_series_id_column_names\": partition_column_names,\n",
-        "    \"track_child_runs\": False,\n",
-        "}\n",
+        "\n",
+        "forecasting_parameters = ForecastingParameters(\n",
+        "    time_column_name=TIME_COLNAME,\n",
+        "    forecast_horizon=6,\n",
+        "    time_series_id_column_names=partition_column_names,\n",
+        "    cv_step_size=\"auto\",\n",
+        ")\n",
+        "\n",
+        "automl_settings = AutoMLConfig(\n",
+        "    task=\"forecasting\",\n",
+        "    primary_metric=\"normalized_root_mean_squared_error\",\n",
+        "    iteration_timeout_minutes=10,\n",
+        "    iterations=15,\n",
+        "    experiment_timeout_hours=0.25,\n",
+        "    label_column_name=TARGET_COLNAME,\n",
+        "    n_cross_validations=\"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
+        "    track_child_runs=False,\n",
+        "    forecasting_parameters=forecasting_parameters,\n",
+        ")\n",
+        "\n",
         "\n",
         "mm_paramters = ManyModelsTrainParameters(\n",
         "    automl_settings=automl_settings, partition_column_names=partition_column_names\n",
@@ -385,8 +411,16 @@
         "| **node_count**                     | The number of compute nodes to be used for running the user script. We recommend to start with 3 and increase the node_count if the training time is taking too long. |\n",
         "| **process_count_per_node**         | Process count per node, we recommend 2:1 ratio for number of cores: number of processes per node. eg. If node has 16 cores then configure 8 or less process count per node or optimal performance. |\n",
         "| **train_pipeline_parameters**      | The set of configuration parameters defined in the previous section. |\n",
+        "| **run_invocation_timeout**         | Maximum amount of time in seconds that the ``ParallelRunStep`` class is allowed. This is optional but provides customers with greater control on exit criteria. This must be greater than ``experiment_timeout_hours`` by at least 300 seconds. |\n",
         "\n",
-        "Calling this method will create a new aggregated dataset which is generated dynamically on pipeline execution."
+        "Calling this method will create a new aggregated dataset which is generated dynamically on pipeline execution.\n",
+        "\n",
+        "**Note**: Total time taken for the **training step** in the pipeline to complete = $ \\frac{t}{ p \\times n } \\times ts $\n",
+        "where,\n",
+        "- $ t $ is time taken for training one partition (can be viewed in the training logs)\n",
+        "- $ p $ is ``process_count_per_node``\n",
+        "- $ n $ is ``node_count``\n",
+        "- $ ts $ is total number of partitions in time series based on ``partition_column_names``"
       ]
     },
     {
@@ -404,7 +438,7 @@
         "    compute_target=compute_target,\n",
         "    node_count=2,\n",
         "    process_count_per_node=2,\n",
-        "    run_invocation_timeout=920,\n",
+        "    run_invocation_timeout=1200,\n",
         "    train_pipeline_parameters=mm_paramters,\n",
         ")"
       ]
@@ -489,25 +523,31 @@
       "source": [
         "For many models we need to provide the ManyModelsInferenceParameters object.\n",
         "\n",
-        "#### ManyModelsInferenceParameters arguments\n",
+        "#### ``ManyModelsInferenceParameters`` arguments\n",
         "| Property                           | Description|\n",
         "| :---------------                   | :------------------- |\n",
         "| **partition_column_names**         | List of column names that identifies groups. |\n",
-        "| **target_column_name**             | \\[Optional\\] Column name only if the inference dataset has the target. |\n",
-        "| **time_column_name**               | Column name only if it is timeseries. |\n",
-        "| **many_models_run_id**             | \\[Optional\\] Many models pipeline run id where models were trained. |\n",
+        "| **target_column_name**             | \\[Optional] Column name only if the inference dataset has the target. |\n",
+        "| **time_column_name**               | \\[Optional] Time column name only if it is timeseries. |\n",
+        "| **inference_type**                 | \\[Optional] Which inference method to use on the model. Possible values are 'forecast', 'predict_proba', and 'predict'. |\n",
+        "| **forecast_mode**                  | \\[Optional] The type of forecast to be used, either 'rolling' or 'recursive'; defaults to 'recursive'. |\n",
+        "| **step**                           | \\[Optional] Number of periods to advance the forecasting window in each iteration **(for rolling forecast only)**; defaults to 1. |\n",
         "\n",
-        "#### get_many_models_batch_inference_steps arguments\n",
+        "#### ``get_many_models_batch_inference_steps`` arguments\n",
         "| Property                           | Description|\n",
         "| :---------------                   | :------------------- |\n",
         "| **experiment**                     | The experiment used for inference run. |\n",
         "| **inference_data**                 | The data to use for inferencing. It should be the same schema as used for training.\n",
         "| **compute_target**                 | The compute target that runs the inference pipeline. |\n",
         "| **node_count**                     | The number of compute nodes to be used for running the user script. We recommend to start with the number of cores per node (varies by compute sku). |\n",
-        "| **process_count_per_node**         | The number of processes per node.\n",
-        "| **train_run_id**                   | \\[Optional\\] The run id of the hierarchy training, by default it is the latest successful training many model run in the experiment. |\n",
-        "| **train_experiment_name**          | \\[Optional\\] The train experiment that contains the train pipeline. This one is only needed when the train pipeline is not in the same experiement as the inference pipeline. |\n",
-        "| **process_count_per_node**         | \\[Optional\\] The number of processes per node, by default it's 4. |"
+        "| **process_count_per_node**         | \\[Optional] The number of processes per node. By default it's 2 (should be at most half of the number of cores in a single node of the compute cluster that will be used for the experiment).\n",
+        "| **inference_pipeline_parameters**  | \\[Optional] The ``ManyModelsInferenceParameters`` object defined above. |\n",
+        "| **append_row_file_name**           | \\[Optional] The name of the output file (optional, default value is 'parallel_run_step.txt'). Supports 'txt' and 'csv' file extension. A 'txt' file extension generates the output in 'txt' format with space as separator without column names. A 'csv' file extension generates the output in 'csv' format with comma as separator and with column names. |\n",
+        "| **train_run_id**                   | \\[Optional] The run id of the **training pipeline**. By default it is the latest successful training pipeline run in the experiment. |\n",
+        "| **train_experiment_name**          | \\[Optional] The train experiment that contains the train pipeline. This one is only needed when the train pipeline is not in the same experiement as the inference pipeline. |\n",
+        "| **run_invocation_timeout**         | \\[Optional] Maximum amount of time in seconds that the ``ParallelRunStep`` class is allowed. This is optional but provides customers with greater control on exit criteria. |\n",
+        "| **output_datastore**               | \\[Optional] The ``Datastore`` or ``OutputDatasetConfig`` to be used for output. If specified any pipeline output will be written to that location. If unspecified the default datastore will be used. |\n",
+        "| **arguments**                      | \\[Optional] Arguments to be passed to inference script. Possible argument is '--forecast_quantiles' followed by quantile values. |"
       ]
     },
     {
@@ -527,6 +567,8 @@
         "    target_column_name=TARGET_COLNAME,\n",
         ")\n",
         "\n",
+        "output_file_name = \"parallel_run_step.csv\"\n",
+        "\n",
         "inference_steps = AutoMLPipelineBuilder.get_many_models_batch_inference_steps(\n",
         "    experiment=experiment,\n",
         "    inference_data=test_data,\n",
@@ -538,6 +580,7 @@
         "    train_run_id=training_run.id,\n",
         "    train_experiment_name=training_run.experiment.name,\n",
         "    inference_pipeline_parameters=mm_parameters,\n",
+        "    append_row_file_name=output_file_name,\n",
         ")"
       ]
     },
@@ -585,18 +628,21 @@
       "source": [
         "from azureml.contrib.automl.pipeline.steps.utilities import get_output_from_mm_pipeline\n",
         "\n",
+        "PREDICTION_COLNAME = \"Predictions\"\n",
         "forecasting_results_name = \"forecasting_results\"\n",
         "forecasting_output_name = \"many_models_inference_output\"\n",
         "forecast_file = get_output_from_mm_pipeline(\n",
-        "    inference_run, forecasting_results_name, forecasting_output_name\n",
+        "    inference_run, forecasting_results_name, forecasting_output_name, output_file_name\n",
         ")\n",
-        "df = pd.read_csv(forecast_file, delimiter=\" \", header=None, parse_dates=[0])\n",
-        "df.columns = list(X_train.columns) + [\"predicted_level\"]\n",
+        "df = pd.read_csv(forecast_file, parse_dates=[0])\n",
         "print(\n",
         "    \"Prediction has \", df.shape[0], \" rows. Here the first 10 rows are being displayed.\"\n",
         ")\n",
-        "# Save the scv file with header to read it in the next step.\n",
-        "df.rename(columns={TARGET_COLNAME: \"actual_level\"}, inplace=True)\n",
+        "# Save the csv file to read it in the next step.\n",
+        "df.rename(\n",
+        "    columns={TARGET_COLNAME: \"actual_level\", PREDICTION_COLNAME: \"predicted_level\"},\n",
+        "    inplace=True,\n",
+        ")\n",
         "df.to_csv(os.path.join(forecasting_results_name, \"forecast.csv\"), index=False)\n",
         "df.head(10)"
       ]
@@ -620,7 +666,9 @@
         "backtesting_results = \"backtesting_mm_results\"\n",
         "os.makedirs(backtesting_results, exist_ok=True)\n",
         "calculate_scores_and_build_plots(\n",
-        "    forecasting_results_name, backtesting_results, automl_settings\n",
+        "    forecasting_results_name,\n",
+        "    backtesting_results,\n",
+        "    automl_settings.as_serializable_dict(),\n",
         ")\n",
         "pd.DataFrame({\"File\": os.listdir(backtesting_results)})"
       ]
@@ -704,9 +752,9 @@
       "automated-machine-learning"
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {
@@ -718,7 +766,12 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.9"
+      "version": "3.8.5"
+    },
+    "vscode": {
+      "interpreter": {
+        "hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
+      }
     }
   },
   "nbformat": 4,

how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/assets/retrain_models.py

@@ -43,11 +43,20 @@ def init():
     global output_dir
     global automl_settings
     global model_uid
+    global forecast_quantiles
+
     logger.info("Initialization of the run.")
     parser = argparse.ArgumentParser("Parsing input arguments.")
     parser.add_argument("--output-dir", dest="out", required=True)
     parser.add_argument("--model-name", dest="model", default=None)
     parser.add_argument("--model-uid", dest="model_uid", default=None)
+    parser.add_argument(
+        "--forecast_quantiles",
+        nargs="*",
+        type=float,
+        help="forecast quantiles list",
+        default=None,
+    )
 
     parsed_args, _ = parser.parse_known_args()
     model_name = parsed_args.model
@@ -55,6 +64,7 @@ def init():
     target_column_name = automl_settings.get("label_column_name")
     output_dir = parsed_args.out
     model_uid = parsed_args.model_uid
+    forecast_quantiles = parsed_args.forecast_quantiles
     os.makedirs(output_dir, exist_ok=True)
     os.environ["AUTOML_IGNORE_PACKAGE_VERSION_INCOMPATIBILITIES".lower()] = "True"
 
@@ -126,23 +136,18 @@ def run_backtest(data_input_name: str, file_name: str, experiment: Experiment):
         )
         print(f"The model {best_run.properties['model_name']} was registered.")
 
-    _, x_pred = fitted_model.forecast(X_test)
-    x_pred.reset_index(inplace=True, drop=False)
-    columns = [automl_settings[constants.TimeSeries.TIME_COLUMN_NAME]]
-    if automl_settings.get(constants.TimeSeries.GRAIN_COLUMN_NAMES):
-        # We know that fitted_model.grain_column_names is a list.
-        columns.extend(fitted_model.grain_column_names)
-    columns.append(constants.TimeSeriesInternal.DUMMY_TARGET_COLUMN)
-    # Remove featurized columns.
-    x_pred = x_pred[columns]
-    x_pred.rename(
-        {constants.TimeSeriesInternal.DUMMY_TARGET_COLUMN: "predicted_level"},
-        axis=1,
-        inplace=True,
-    )
+    # By default we will have forecast quantiles of 0.5, which is our target
+    if forecast_quantiles:
+        if 0.5 not in forecast_quantiles:
+            forecast_quantiles.append(0.5)
+        fitted_model.quantiles = forecast_quantiles
+
+    x_pred = fitted_model.forecast_quantiles(X_test)
     x_pred["actual_level"] = y_test
     x_pred["backtest_iteration"] = f"iteration_{last_training_date}"
+    x_pred.rename({0.5: "predicted_level"}, axis=1, inplace=True)
     date_safe = RE_INVALID_SYMBOLS.sub("_", last_training_date)
+
     x_pred.to_csv(os.path.join(output_dir, f"iteration_{date_safe}.csv"), index=False)
     return x_pred
 

how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/auto-ml-forecasting-backtest-single-model.ipynb

@@ -283,7 +283,8 @@
         "| **experiment_timeout_hours**       | Maximum amount of time in hours that the experiment can take before it terminates. This is optional but provides customers with greater control on exit criteria. |\n",
         "| **label_column_name**              | The name of the label column. |\n",
         "| **max_horizon**               | The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly). Periods are inferred from your data. |\n",
-        "| **n_cross_validations**            | Number of cross validation splits. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
+        "| **n_cross_validations**            | Number of cross validation splits. The default value is \"auto\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
+        "|**cv_step_size**|Number of periods between two consecutive cross-validation folds. The default value is \"auto\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value.\n",
         "| **time_column_name**               | The name of your time column. |\n",
         "| **grain_column_names**     | The column names used to uniquely identify timeseries in data that has multiple rows with the same timestamp. |"
       ]
@@ -301,7 +302,8 @@
         "    \"iterations\": 15,\n",
         "    \"experiment_timeout_hours\": 1,  # This also needs to be changed based on the dataset. For larger data set this number needs to be bigger.\n",
         "    \"label_column_name\": LABEL_COLUMN_NAME,\n",
-        "    \"n_cross_validations\": 3,\n",
+        "    \"n_cross_validations\": \"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
+        "    \"cv_step_size\": \"auto\",\n",
         "    \"time_column_name\": TIME_COLUMN_NAME,\n",
         "    \"max_horizon\": FORECAST_HORIZON,\n",
         "    \"track_child_runs\": False,\n",
@@ -363,6 +365,7 @@
         "    step_size=BACKTESTING_PERIOD,\n",
         "    step_number=NUMBER_OF_BACKTESTS,\n",
         "    model_uid=model_uid,\n",
+        "    forecast_quantiles=[0.025, 0.975],  # Optional\n",
         ")"
       ]
     },
@@ -524,7 +527,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "model_list = Model.list(ws, tags={\"experiment\": \"automl-backtesting\"})\n",
+        "model_list = Model.list(ws, tags=[[\"experiment\", \"automl-backtesting\"]])\n",
         "model_data = {\"name\": [], \"last_training_date\": []}\n",
         "for model in model_list:\n",
         "    if (\n",
@@ -588,6 +591,7 @@
         "    step_size=BACKTESTING_PERIOD,\n",
         "    step_number=NUMBER_OF_BACKTESTS,\n",
         "    model_name=model_name,\n",
+        "    forecast_quantiles=[0.025, 0.975],\n",
         ")"
       ]
     },
@@ -698,9 +702,9 @@
       "Azure ML AutoML"
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {
@@ -712,7 +716,12 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.9"
+      "version": "3.8.5"
+    },
+    "vscode": {
+      "interpreter": {
+        "hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
+      }
     }
   },
   "nbformat": 4,

how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/pipeline_helper.py

@@ -31,6 +31,7 @@ def get_backtest_pipeline(
     step_number: int,
     model_name: Optional[str] = None,
     model_uid: Optional[str] = None,
+    forecast_quantiles: Optional[list] = None,
 ) -> Pipeline:
     """
     :param experiment: The experiment used to run the pipeline.
@@ -44,6 +45,7 @@ def get_backtest_pipeline(
     :param step_size: The number of periods to step back in backtesting.
     :param step_number: The number of backtesting iterations.
     :param model_uid: The uid to mark models from this run of the experiment.
+    :param forecast_quantiles: The forecast quantiles that are required in the inference.
     :return: The pipeline to be used for model retraining.
              **Note:** The output will be uploaded in the pipeline output
              called 'score'.
@@ -72,6 +74,8 @@ def get_backtest_pipeline(
     run_config.docker.use_docker = True
     run_config.environment = env
 
+    utilities.set_environment_variables_for_run(run_config)
+
     split_data = PipelineData(name="split_data_output", datastore=None).as_dataset()
     split_step = PythonScriptStep(
         name="split_data_for_backtest",
@@ -114,6 +118,7 @@ def get_backtest_pipeline(
         run_invocation_timeout=3600,
         node_count=node_count,
     )
+    utilities.set_environment_variables_for_run(back_test_config)
     forecasts = PipelineData(name="forecasts", datastore=None)
     if model_name:
         parallel_step_name = "{}-backtest".format(model_name.replace("_", "-"))
@@ -132,6 +137,9 @@ def get_backtest_pipeline(
     if model_uid is not None:
         prs_args.append("--model-uid")
         prs_args.append(model_uid)
+    if forecast_quantiles:
+        prs_args.append("--forecast_quantiles")
+        prs_args.extend(forecast_quantiles)
     backtest_prs = ParallelRunStep(
         name=parallel_step_name,
         parallel_run_config=back_test_config,

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

@@ -42,7 +42,7 @@
         "\n",
         "AutoML highlights here include built-in holiday featurization, accessing engineered feature names, and working with the `forecast` function. Please also look at the additional forecasting notebooks, which document lagging, rolling windows, forecast quantiles, other ways to use the forecast function, and forecaster deployment.\n",
         "\n",
-        "Make sure you have executed the [configuration notebook](../../../configuration.ipynb) before running this notebook.\n",
+        "Make sure you have executed the [configuration notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/configuration.ipynb) before running this notebook.\n",
         "\n",
         "Notebook synopsis:\n",
         "1. Creating an Experiment in an existing Workspace\n",
@@ -265,7 +265,8 @@
         "|**forecast_horizon**|The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly).|\n",
         "|**country_or_region_for_holidays**|The country/region used to generate holiday features. These should be ISO 3166 two-letter country/region codes (i.e. 'US', 'GB').|\n",
         "|**target_lags**|The target_lags specifies how far back we will construct the lags of the target variable.|\n",
-        "|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information."
+        "|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information.\n",
+        "|**cv_step_size**|Number of periods between two consecutive cross-validation folds. The default value is \"auto\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value."
       ]
     },
     {
@@ -285,7 +286,7 @@
         "|**training_data**|Input dataset, containing both features and label column.|\n",
         "|**label_column_name**|The name of the label column.|\n",
         "|**compute_target**|The remote compute for training.|\n",
-        "|**n_cross_validations**|Number of cross validation splits.|\n",
+        "|**n_cross_validations**|Number of cross-validation folds to use for model/pipeline selection. The default value is \"auto\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value.\n",
         "|**enable_early_stopping**|If early stopping is on, training will stop when the primary metric is no longer improving.|\n",
         "|**forecasting_parameters**|A class that holds all the forecasting related parameters.|\n",
         "\n",
@@ -350,6 +351,7 @@
         "    country_or_region_for_holidays=\"US\",  # set country_or_region will trigger holiday featurizer\n",
         "    target_lags=\"auto\",  # use heuristic based lag setting\n",
         "    freq=\"D\",  # Set the forecast frequency to be daily\n",
+        "    cv_step_size=\"auto\",\n",
         ")\n",
         "\n",
         "automl_config = AutoMLConfig(\n",
@@ -362,7 +364,7 @@
         "    label_column_name=target_column_name,\n",
         "    compute_target=compute_target,\n",
         "    enable_early_stopping=True,\n",
-        "    n_cross_validations=3,\n",
+        "    n_cross_validations=\"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
         "    max_concurrent_iterations=4,\n",
         "    max_cores_per_iteration=-1,\n",
         "    verbosity=logging.INFO,\n",
@@ -573,7 +575,32 @@
       "outputs": [],
       "source": [
         "remote_run.download_file(\"outputs/predictions.csv\", \"predictions.csv\")\n",
-        "df_all = pd.read_csv(\"predictions.csv\")"
+        "fcst_df = pd.read_csv(\"predictions.csv\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Note that the rolling forecast can contain multiple predictions for each date, each from a different forecast origin. For example, consider 2012-09-05:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "fcst_df[fcst_df.date == \"2012-09-05\"]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Here, the forecast origin refers to the latest date of actuals available for a given forecast. The earliest origin in the rolling forecast, 2012-08-31, is the last day in the training data. For origin date 2012-09-01, the forecasts use actual recorded counts from the training data *and* the actual count recorded on 2012-09-01. Note that the model is not retrained for origin dates later than 2012-08-31, but the values for model features, such as lagged values of daily count, are updated.\n",
+        "\n",
+        "Let's calculate the metrics over all rolling forecasts:"
       ]
     },
     {
@@ -585,29 +612,17 @@
         "from azureml.automl.core.shared import constants\n",
         "from azureml.automl.runtime.shared.score import scoring\n",
         "from sklearn.metrics import mean_absolute_error, mean_squared_error\n",
-        "from matplotlib import pyplot as plt\n",
         "\n",
         "# use automl metrics module\n",
         "scores = scoring.score_regression(\n",
-        "    y_test=df_all[target_column_name],\n",
-        "    y_pred=df_all[\"predicted\"],\n",
+        "    y_test=fcst_df[target_column_name],\n",
+        "    y_pred=fcst_df[\"predicted\"],\n",
         "    metrics=list(constants.Metric.SCALAR_REGRESSION_SET),\n",
         ")\n",
         "\n",
         "print(\"[Test data scores]\\n\")\n",
         "for key, value in scores.items():\n",
-        "    print(\"{}:   {:.3f}\".format(key, value))\n",
-        "\n",
-        "# Plot outputs\n",
-        "%matplotlib inline\n",
-        "test_pred = plt.scatter(df_all[target_column_name], df_all[\"predicted\"], color=\"b\")\n",
-        "test_test = plt.scatter(\n",
-        "    df_all[target_column_name], df_all[target_column_name], color=\"g\"\n",
-        ")\n",
-        "plt.legend(\n",
-        "    (test_pred, test_test), (\"prediction\", \"truth\"), loc=\"upper left\", fontsize=8\n",
-        ")\n",
-        "plt.show()"
+        "    print(\"{}:   {:.3f}\".format(key, value))"
       ]
     },
     {
@@ -616,36 +631,15 @@
       "source": [
         "For more details on what metrics are included and how they are calculated, please refer to [supported metrics](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#regressionforecasting-metrics). You could also calculate residuals, like described [here](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#residuals).\n",
         "\n",
-        "\n",
-        "Since we did a rolling evaluation on the test set, we can analyze the predictions by their forecast horizon relative to the rolling origin. The model was initially trained at a forecast horizon of 14, so each prediction from the model is associated with a horizon value from 1 to 14. The horizon values are in a column named, \"horizon_origin,\" in the prediction set. For example, we can calculate some of the error metrics grouped by the horizon:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from metrics_helper import MAPE, APE\n",
-        "\n",
-        "df_all.groupby(\"horizon_origin\").apply(\n",
-        "    lambda df: pd.Series(\n",
-        "        {\n",
-        "            \"MAPE\": MAPE(df[target_column_name], df[\"predicted\"]),\n",
-        "            \"RMSE\": np.sqrt(\n",
-        "                mean_squared_error(df[target_column_name], df[\"predicted\"])\n",
-        "            ),\n",
-        "            \"MAE\": mean_absolute_error(df[target_column_name], df[\"predicted\"]),\n",
-        "        }\n",
-        "    )\n",
-        ")"
+        "The rolling forecast metric values are very high in comparison to the validation metrics reported by the AutoML job. What's going on here? We will investigate in the following cells!"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "To drill down more, we can look at the distributions of APE (absolute percentage error) by horizon. From the chart, it is clear that the overall MAPE is being skewed by one particular point where the actual value is of small absolute value."
+        "### Forecast versus actuals plot\n",
+        "We will plot predictions and actuals on a time series plot. Since there are many forecasts for each date, we select the 14-day-ahead forecast from each forecast origin for our comparison."
       ]
     },
     {
@@ -654,21 +648,55 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "df_all_APE = df_all.assign(APE=APE(df_all[target_column_name], df_all[\"predicted\"]))\n",
-        "APEs = [\n",
-        "    df_all_APE[df_all[\"horizon_origin\"] == h].APE.values\n",
-        "    for h in range(1, forecast_horizon + 1)\n",
-        "]\n",
+        "from matplotlib import pyplot as plt\n",
         "\n",
         "%matplotlib inline\n",
-        "plt.boxplot(APEs)\n",
-        "plt.yscale(\"log\")\n",
-        "plt.xlabel(\"horizon\")\n",
-        "plt.ylabel(\"APE (%)\")\n",
-        "plt.title(\"Absolute Percentage Errors by Forecast Horizon\")\n",
         "\n",
+        "fcst_df_h14 = (\n",
+        "    fcst_df.groupby(\"forecast_origin\", as_index=False)\n",
+        "    .last()\n",
+        "    .drop(columns=[\"forecast_origin\"])\n",
+        ")\n",
+        "fcst_df_h14.set_index(time_column_name, inplace=True)\n",
+        "plt.plot(fcst_df_h14[[target_column_name, \"predicted\"]])\n",
+        "plt.xticks(rotation=45)\n",
+        "plt.title(f\"Predicted vs. Actuals\")\n",
+        "plt.legend([\"actual\", \"14-day-ahead forecast\"])\n",
         "plt.show()"
       ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Looking at the plot, there are two clear issues:\n",
+        "1. An anomalously low count value on October 29th, 2012.\n",
+        "2. End-of-year holidays (Thanksgiving and Christmas) in late November and late December.\n",
+        "\n",
+        "What happened on Oct. 29th, 2012? That day, Hurricane Sandy brought severe storm surge flooding to the east coast of the United States, particularly around New York City. This is certainly an anomalous event that the model did not account for!\n",
+        "\n",
+        "As for the late year holidays, the model apparently did not learn to account for the full reduction of bike share rentals on these major holidays. The training data covers 2011 and early 2012, so the model fit only had access to a single occurrence of these holidays. This makes it challenging to resolve holiday effects; however, a larger AutoML model search may result in a better model that is more holiday-aware.\n",
+        "\n",
+        "If we filter the predictions prior to the Thanksgiving holiday and remove the anomalous day of 2012-10-29, the metrics are closer to validation levels:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "date_filter = (fcst_df.date != \"2012-10-29\") & (fcst_df.date < \"2012-11-22\")\n",
+        "scores = scoring.score_regression(\n",
+        "    y_test=fcst_df[date_filter][target_column_name],\n",
+        "    y_pred=fcst_df[date_filter][\"predicted\"],\n",
+        "    metrics=list(constants.Metric.SCALAR_REGRESSION_SET),\n",
+        ")\n",
+        "\n",
+        "print(\"[Test data scores (filtered)]\\n\")\n",
+        "for key, value in scores.items():\n",
+        "    print(\"{}:   {:.3f}\".format(key, value))"
+      ]
     }
   ],
   "metadata": {
@@ -695,9 +723,9 @@
     "friendly_name": "Forecasting BikeShare Demand",
     "index_order": 1,
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {
@@ -709,7 +737,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.7"
+      "version": "3.7.13"
     },
     "mimetype": "text/x-python",
     "name": "python",
@@ -719,7 +747,12 @@
       "Forecasting"
     ],
     "task": "Forecasting",
-    "version": 3
+    "version": 3,
+    "vscode": {
+      "interpreter": {
+        "hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
+      }
+    }
   },
   "nbformat": 4,
   "nbformat_minor": 4

how-to-use-azureml/automated-machine-learning/forecasting-bike-share/forecasting_script.py

@@ -36,18 +36,18 @@ y_test_df = (
 
 fitted_model = joblib.load("model.pkl")
 
-y_pred, X_trans = fitted_model.rolling_evaluation(X_test_df, y_test_df.values)
+X_rf = fitted_model.rolling_forecast(X_test_df, y_test_df.values, step=1)
 
 # Add predictions, actuals, and horizon relative to rolling origin to the test feature data
 assign_dict = {
-    "horizon_origin": X_trans["horizon_origin"].values,
-    "predicted": y_pred,
-    target_column_name: y_test_df[target_column_name].values,
+    fitted_model.forecast_origin_column_name: "forecast_origin",
+    fitted_model.forecast_column_name: "predicted",
+    fitted_model.actual_column_name: target_column_name,
 }
-df_all = X_test_df.assign(**assign_dict)
+X_rf.rename(columns=assign_dict, inplace=True)
 
 file_name = "outputs/predictions.csv"
-export_csv = df_all.to_csv(file_name, header=True)
+export_csv = X_rf.to_csv(file_name, header=True)
 
 # Upload the predictions into artifacts
 run.upload_file(name=file_name, path_or_stream=file_name)

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

@@ -43,7 +43,7 @@
         "\n",
         "In this example we use the associated New York City energy demand dataset to showcase how you can use AutoML for a simple forecasting problem and explore the results. The goal is predict the energy demand for the next 48 hours based on historic time-series data.\n",
         "\n",
-        "If you are using an Azure Machine Learning Compute Instance, 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.\n",
+        "If you are using an Azure Machine Learning Compute Instance, you are all set. Otherwise, go through the [configuration notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/configuration.ipynb) 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. Creating an Experiment using an existing Workspace\n",
@@ -308,7 +308,8 @@
         "|-|-|\n",
         "|**time_column_name**|The name of your time column.|\n",
         "|**forecast_horizon**|The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly).|\n",
-        "|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information."
+        "|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information.\n",
+        "|**cv_step_size**|Number of periods between two consecutive cross-validation folds. The default value is \"auto\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value."
       ]
     },
     {
@@ -328,7 +329,7 @@
         "|**training_data**|The training data to be used within the experiment.|\n",
         "|**label_column_name**|The name of the label column.|\n",
         "|**compute_target**|The remote compute for training.|\n",
-        "|**n_cross_validations**|Number of cross validation splits. Rolling Origin Validation is used to split time-series in a temporally consistent way.|\n",
+        "|**n_cross_validations**|Number of cross-validation folds to use for model/pipeline selection. The default value is \"auto\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value.\n",
         "|**enable_early_stopping**|Flag to enble early termination if the score is not improving in the short term.|\n",
         "|**forecasting_parameters**|A class holds all the forecasting related parameters.|\n"
       ]
@@ -352,6 +353,7 @@
         "    time_column_name=time_column_name,\n",
         "    forecast_horizon=forecast_horizon,\n",
         "    freq=\"H\",  # Set the forecast frequency to be hourly\n",
+        "    cv_step_size=\"auto\",\n",
         ")\n",
         "\n",
         "automl_config = AutoMLConfig(\n",
@@ -363,7 +365,7 @@
         "    label_column_name=target_column_name,\n",
         "    compute_target=compute_target,\n",
         "    enable_early_stopping=True,\n",
-        "    n_cross_validations=3,\n",
+        "    n_cross_validations=\"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
         "    verbosity=logging.INFO,\n",
         "    forecasting_parameters=forecasting_parameters,\n",
         ")"
@@ -609,6 +611,7 @@
         "    forecast_horizon=forecast_horizon,\n",
         "    target_lags=12,\n",
         "    target_rolling_window_size=4,\n",
+        "    cv_step_size=\"auto\",\n",
         ")\n",
         "\n",
         "automl_config = AutoMLConfig(\n",
@@ -628,7 +631,7 @@
         "    label_column_name=target_column_name,\n",
         "    compute_target=compute_target,\n",
         "    enable_early_stopping=True,\n",
-        "    n_cross_validations=3,\n",
+        "    n_cross_validations=\"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
         "    verbosity=logging.INFO,\n",
         "    forecasting_parameters=advanced_forecasting_parameters,\n",
         ")"
@@ -764,9 +767,9 @@
       "automated-machine-learning"
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {
@@ -778,7 +781,12 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.9"
+      "version": "3.8.5"
+    },
+    "vscode": {
+      "interpreter": {
+        "hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
+      }
     }
   },
   "nbformat": 4,

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

@@ -52,7 +52,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Please make sure you have followed the `configuration.ipynb` notebook so that your ML workspace information is saved in the config file."
+        "Please make sure you have followed the [configuration notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/configuration.ipynb) so that your ML workspace information is saved in the config file."
       ]
     },
     {
@@ -335,7 +335,8 @@
         "    forecast_horizon=forecast_horizon,\n",
         "    time_series_id_column_names=[TIME_SERIES_ID_COLUMN_NAME],\n",
         "    target_lags=lags,\n",
-        "    freq=\"H\",  # Set the forecast frequency to be hourly\n",
+        "    freq=\"H\",  # Set the forecast frequency to be hourly,\n",
+        "    cv_step_size=\"auto\",\n",
         ")"
       ]
     },
@@ -365,7 +366,7 @@
         "    enable_early_stopping=True,\n",
         "    training_data=train_data,\n",
         "    compute_target=compute_target,\n",
-        "    n_cross_validations=3,\n",
+        "    n_cross_validations=\"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
         "    verbosity=logging.INFO,\n",
         "    max_concurrent_iterations=4,\n",
         "    max_cores_per_iteration=-1,\n",
@@ -647,13 +648,11 @@
         "        & (fulldata[time_column_name] <= forecast_origin + horizon)\n",
         "    ]\n",
         "\n",
-        "    y_past = X_past.pop(target_column_name).values.astype(np.float)\n",
-        "    y_future = X_future.pop(target_column_name).values.astype(np.float)\n",
+        "    y_past = X_past.pop(target_column_name).values.astype(float)\n",
+        "    y_future = X_future.pop(target_column_name).values.astype(float)\n",
         "\n",
         "    # Now take y_future and turn it into question marks\n",
-        "    y_query = y_future.copy().astype(\n",
-        "        np.float\n",
-        "    )  # because sometimes life hands you an int\n",
+        "    y_query = y_future.copy().astype(float)  # because sometimes life hands you an int\n",
         "    y_query.fill(np.NaN)\n",
         "\n",
         "    print(\"X_past is \" + str(X_past.shape) + \" - shaped\")\n",
@@ -759,7 +758,15 @@
       "metadata": {},
       "source": [
         "## Forecasting farther than the forecast horizon <a id=\"recursive forecasting\"></a>\n",
-        "When the forecast destination, or the latest date in the prediction data frame, is farther into the future than the specified forecast horizon, the `forecast()` function will still make point predictions out to the later date using a recursive operation mode. Internally, the method recursively applies the regular forecaster to generate context so that we can forecast further into the future. \n",
+        "When the forecast destination, or the latest date in the prediction data frame, is farther into the future than the specified forecast horizon, the forecaster must be iteratively applied. Here, we advance the forecast origin on each iteration over the prediction window, predicting `max_horizon` periods ahead on each iteration. There are two choices for the context data to use as the forecaster advances into the prediction window:\n",
+        "\n",
+        "1. We can use forecasted values from previous iterations (recursive forecast),\n",
+        "2. We can use known, actual values of the target if they are available (rolling forecast).\n",
+        "\n",
+        "The first method is useful in a true forecasting scenario when we do not yet know the actual target values while the second is useful in an evaluation scenario where we want to compute accuracy metrics for the `max_horizon`-period-ahead forecaster over a long test set. We refer to the first as a **recursive forecast** since we apply the forecaster recursively over the prediction window and the second as a **rolling forecast** since we roll forward over known actuals.\n",
+        "\n",
+        "### Recursive forecasting\n",
+        "By default, the `forecast()` function will make point predictions out to the later date using a recursive operation mode. Internally, the method recursively applies the regular forecaster to generate context so that we can forecast further into the future. \n",
         "\n",
         "To illustrate the use-case and operation of recursive forecasting, we'll consider an example with a single time-series where the forecasting period directly follows the training period and is twice as long as the forecasting horizon given at training time.\n",
         "\n",
@@ -819,6 +826,35 @@
         "np.array_equal(y_pred_all, y_pred_long)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Rolling forecasts\n",
+        "A rolling forecast is a similar concept to the recursive forecasts described above except that we use known actual values of the target for our context data. We have provided a different, public method for this called `rolling_forecast`. In addition to test data and actuals (`X_test` and `y_test`), `rolling_forecast` also accepts an optional `step` parameter that controls how far the origin advances on each iteration. The recursive forecast mode uses a fixed step of `max_horizon` while `rolling_forecast` defaults to a step size of 1, but can be set to any integer from 1 to `max_horizon`, inclusive.\n",
+        "\n",
+        "Let's see what the rolling forecast looks like on the long test set with the step set to 1:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X_rf = fitted_model.rolling_forecast(X_test_long, y_test_long, step=1)\n",
+        "X_rf.head(n=12)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Notice that `rolling_forecast` has returned a single DataFrame containing all results and has generated some new columns: `_automl_forecast_origin`, `_automl_forecast_y`, and `_automl_actual_y`. These are the origin date for each forecast, the forecasted value and the actual value, respectively. Note that \"y\" in the forecast and actual column names will generally be replaced by the target column name supplied to AutoML.\n",
+        "\n",
+        "The output above shows forecasts for two prediction windows, the first with origin at the end of the training set and the second including the first observation in the test set (2000-01-01 06:00:00). Since the forecast windows overlap, there are multiple forecasts for most dates which are associated with different origin dates."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -867,9 +903,9 @@
     "friendly_name": "Forecasting away from training data",
     "index_order": 3,
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {
@@ -881,14 +917,19 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.8"
+      "version": "3.7.13"
     },
     "tags": [
       "Forecasting",
       "Confidence Intervals"
     ],
-    "task": "Forecasting"
+    "task": "Forecasting",
+    "vscode": {
+      "interpreter": {
+        "hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
+      }
+    }
   },
   "nbformat": 4,
-  "nbformat_minor": 2
+  "nbformat_minor": 4
 }

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

@@ -52,7 +52,7 @@
         "\n",
         "AutoML highlights here include using Deep Learning forecasts, Arima, Prophet,  Remote Execution and Remote Inferencing, and working with the `forecast` function. Please also look at the additional forecasting notebooks, which document lagging, rolling windows, forecast quantiles, other ways to use the forecast function, and forecaster deployment.\n",
         "\n",
-        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+        "Make sure you have executed the [configuration](https://github.com/Azure/MachineLearningNotebooks/blob/master/configuration.ipynb) before running this notebook.\n",
         "\n",
         "Notebook synopsis:\n",
         "\n",
@@ -325,7 +325,7 @@
       "source": [
         "### Setting forecaster maximum horizon \n",
         "\n",
-        "The forecast horizon is the number of periods into the future that the model should predict. Here, we set the horizon to 12 periods (i.e. 12 months). Notice that this is much shorter than the number of months in the test set; we will need to use a rolling test to evaluate the performance on the whole test set. For more discussion of forecast horizons and guiding principles for setting them, please see the [energy demand notebook](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand).  "
+        "The forecast horizon is the number of periods into the future that the model should predict. Here, we set the horizon to 14 periods (i.e. 14 days). Notice that this is much shorter than the number of months in the test set; we will need to use a rolling test to evaluate the performance on the whole test set. For more discussion of forecast horizons and guiding principles for setting them, please see the [energy demand notebook](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand).  "
       ]
     },
     {
@@ -337,7 +337,7 @@
       },
       "outputs": [],
       "source": [
-        "forecast_horizon = 12"
+        "forecast_horizon = 14"
       ]
     },
     {
@@ -681,9 +681,9 @@
     ],
     "hide_code_all_hidden": false,
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {
@@ -699,5 +699,5 @@
     }
   },
   "nbformat": 4,
-  "nbformat_minor": 2
+  "nbformat_minor": 4
 }

how-to-use-azureml/automated-machine-learning/forecasting-github-dau/infer.py

@@ -4,7 +4,6 @@ import os
 import numpy as np
 import pandas as pd
 
-from pandas.tseries.frequencies import to_offset
 from sklearn.externals import joblib
 from sklearn.metrics import mean_absolute_error, mean_squared_error
 
@@ -19,219 +18,8 @@ except ImportError:
     _torch_present = False
 
 
-def align_outputs(
-    y_predicted,
-    X_trans,
-    X_test,
-    y_test,
-    predicted_column_name="predicted",
-    horizon_colname="horizon_origin",
-):
-    """
-    Demonstrates how to get the output aligned to the inputs
-    using pandas indexes. Helps understand what happened if
-    the output's shape differs from the input shape, or if
-    the data got re-sorted by time and grain during forecasting.
-
-    Typical causes of misalignment are:
-    * we predicted some periods that were missing in actuals -> drop from eval
-    * model was asked to predict past max_horizon -> increase max horizon
-    * data at start of X_test was needed for lags -> provide previous periods
-    """
-    if horizon_colname in X_trans:
-        df_fcst = pd.DataFrame(
-            {
-                predicted_column_name: y_predicted,
-                horizon_colname: X_trans[horizon_colname],
-            }
-        )
-    else:
-        df_fcst = pd.DataFrame({predicted_column_name: y_predicted})
-
-    # y and X outputs are aligned by forecast() function contract
-    df_fcst.index = X_trans.index
-
-    # align original X_test to y_test
-    X_test_full = X_test.copy()
-    X_test_full[target_column_name] = y_test
-
-    # X_test_full's index does not include origin, so reset for merge
-    df_fcst.reset_index(inplace=True)
-    X_test_full = X_test_full.reset_index().drop(columns="index")
-    together = df_fcst.merge(X_test_full, how="right")
-
-    # drop rows where prediction or actuals are nan
-    # happens because of missing actuals
-    # or at edges of time due to lags/rolling windows
-    clean = together[
-        together[[target_column_name, predicted_column_name]].notnull().all(axis=1)
-    ]
-    return clean
-
-
-def do_rolling_forecast_with_lookback(
-    fitted_model, X_test, y_test, max_horizon, X_lookback, y_lookback, freq="D"
-):
-    """
-    Produce forecasts on a rolling origin over the given test set.
-
-    Each iteration makes a forecast for the next 'max_horizon' periods
-    with respect to the current origin, then advances the origin by the
-    horizon time duration. The prediction context for each forecast is set so
-    that the forecaster uses the actual target values prior to the current
-    origin time for constructing lag features.
-
-    This function returns a concatenated DataFrame of rolling forecasts.
-    """
-    print("Using lookback of size: ", y_lookback.size)
-    df_list = []
-    origin_time = X_test[time_column_name].min()
-    X = X_lookback.append(X_test)
-    y = np.concatenate((y_lookback, y_test), axis=0)
-    while origin_time <= X_test[time_column_name].max():
-        # Set the horizon time - end date of the forecast
-        horizon_time = origin_time + max_horizon * to_offset(freq)
-
-        # Extract test data from an expanding window up-to the horizon
-        expand_wind = X[time_column_name] < horizon_time
-        X_test_expand = X[expand_wind]
-        y_query_expand = np.zeros(len(X_test_expand)).astype(np.float)
-        y_query_expand.fill(np.NaN)
-
-        if origin_time != X[time_column_name].min():
-            # Set the context by including actuals up-to the origin time
-            test_context_expand_wind = X[time_column_name] < origin_time
-            context_expand_wind = X_test_expand[time_column_name] < origin_time
-            y_query_expand[context_expand_wind] = y[test_context_expand_wind]
-
-        # Print some debug info
-        print(
-            "Horizon_time:",
-            horizon_time,
-            " origin_time: ",
-            origin_time,
-            " max_horizon: ",
-            max_horizon,
-            " freq: ",
-            freq,
-        )
-        print("expand_wind: ", expand_wind)
-        print("y_query_expand")
-        print(y_query_expand)
-        print("X_test")
-        print(X)
-        print("X_test_expand")
-        print(X_test_expand)
-        print("Type of X_test_expand: ", type(X_test_expand))
-        print("Type of y_query_expand: ", type(y_query_expand))
-
-        print("y_query_expand")
-        print(y_query_expand)
-
-        # Make a forecast out to the maximum horizon
-        # y_fcst, X_trans = y_query_expand, X_test_expand
-        y_fcst, X_trans = fitted_model.forecast(X_test_expand, y_query_expand)
-
-        print("y_fcst")
-        print(y_fcst)
-
-        # Align forecast with test set for dates within
-        # the current rolling window
-        trans_tindex = X_trans.index.get_level_values(time_column_name)
-        trans_roll_wind = (trans_tindex >= origin_time) & (trans_tindex < horizon_time)
-        test_roll_wind = expand_wind & (X[time_column_name] >= origin_time)
-        df_list.append(
-            align_outputs(
-                y_fcst[trans_roll_wind],
-                X_trans[trans_roll_wind],
-                X[test_roll_wind],
-                y[test_roll_wind],
-            )
-        )
-
-        # Advance the origin time
-        origin_time = horizon_time
-
-    return pd.concat(df_list, ignore_index=True)
-
-
-def do_rolling_forecast(fitted_model, X_test, y_test, max_horizon, freq="D"):
-    """
-    Produce forecasts on a rolling origin over the given test set.
-
-    Each iteration makes a forecast for the next 'max_horizon' periods
-    with respect to the current origin, then advances the origin by the
-    horizon time duration. The prediction context for each forecast is set so
-    that the forecaster uses the actual target values prior to the current
-    origin time for constructing lag features.
-
-    This function returns a concatenated DataFrame of rolling forecasts.
-    """
-    df_list = []
-    origin_time = X_test[time_column_name].min()
-    while origin_time <= X_test[time_column_name].max():
-        # Set the horizon time - end date of the forecast
-        horizon_time = origin_time + max_horizon * to_offset(freq)
-
-        # Extract test data from an expanding window up-to the horizon
-        expand_wind = X_test[time_column_name] < horizon_time
-        X_test_expand = X_test[expand_wind]
-        y_query_expand = np.zeros(len(X_test_expand)).astype(np.float)
-        y_query_expand.fill(np.NaN)
-
-        if origin_time != X_test[time_column_name].min():
-            # Set the context by including actuals up-to the origin time
-            test_context_expand_wind = X_test[time_column_name] < origin_time
-            context_expand_wind = X_test_expand[time_column_name] < origin_time
-            y_query_expand[context_expand_wind] = y_test[test_context_expand_wind]
-
-        # Print some debug info
-        print(
-            "Horizon_time:",
-            horizon_time,
-            " origin_time: ",
-            origin_time,
-            " max_horizon: ",
-            max_horizon,
-            " freq: ",
-            freq,
-        )
-        print("expand_wind: ", expand_wind)
-        print("y_query_expand")
-        print(y_query_expand)
-        print("X_test")
-        print(X_test)
-        print("X_test_expand")
-        print(X_test_expand)
-        print("Type of X_test_expand: ", type(X_test_expand))
-        print("Type of y_query_expand: ", type(y_query_expand))
-        print("y_query_expand")
-        print(y_query_expand)
-
-        # Make a forecast out to the maximum horizon
-        y_fcst, X_trans = fitted_model.forecast(X_test_expand, y_query_expand)
-
-        print("y_fcst")
-        print(y_fcst)
-
-        # Align forecast with test set for dates within the
-        # current rolling window
-        trans_tindex = X_trans.index.get_level_values(time_column_name)
-        trans_roll_wind = (trans_tindex >= origin_time) & (trans_tindex < horizon_time)
-        test_roll_wind = expand_wind & (X_test[time_column_name] >= origin_time)
-        df_list.append(
-            align_outputs(
-                y_fcst[trans_roll_wind],
-                X_trans[trans_roll_wind],
-                X_test[test_roll_wind],
-                y_test[test_roll_wind],
-            )
-        )
-
-        # Advance the origin time
-        origin_time = horizon_time
-
-    return pd.concat(df_list, ignore_index=True)
+def map_location_cuda(storage, loc):
+    return storage.cuda()
 
 
 def APE(actual, pred):
@@ -254,10 +42,6 @@ def MAPE(actual, pred):
     return np.mean(APE(actual_safe, pred_safe))
 
 
-def map_location_cuda(storage, loc):
-    return storage.cuda()
-
-
 parser = argparse.ArgumentParser()
 parser.add_argument(
     "--max_horizon",
@@ -303,7 +87,6 @@ print(model_path)
 run = Run.get_context()
 # get input dataset by name
 test_dataset = run.input_datasets["test_data"]
-lookback_dataset = run.input_datasets["lookback_data"]
 
 grain_column_names = []
 
@@ -312,15 +95,8 @@ df = test_dataset.to_pandas_dataframe()
 print("Read df")
 print(df)
 
-X_test_df = test_dataset.drop_columns(columns=[target_column_name])
-y_test_df = test_dataset.with_timestamp_columns(None).keep_columns(
-    columns=[target_column_name]
-)
-
-X_lookback_df = lookback_dataset.drop_columns(columns=[target_column_name])
-y_lookback_df = lookback_dataset.with_timestamp_columns(None).keep_columns(
-    columns=[target_column_name]
-)
+X_test_df = df
+y_test = df.pop(target_column_name).to_numpy()
 
 _, ext = os.path.splitext(model_path)
 if ext == ".pt":
@@ -336,37 +112,20 @@ else:
     # Load the sklearn pipeline.
     fitted_model = joblib.load(model_path)
 
-if hasattr(fitted_model, "get_lookback"):
-    lookback = fitted_model.get_lookback()
-    df_all = do_rolling_forecast_with_lookback(
-        fitted_model,
-        X_test_df.to_pandas_dataframe(),
-        y_test_df.to_pandas_dataframe().values.T[0],
-        max_horizon,
-        X_lookback_df.to_pandas_dataframe()[-lookback:],
-        y_lookback_df.to_pandas_dataframe().values.T[0][-lookback:],
-        freq,
-    )
-else:
-    df_all = do_rolling_forecast(
-        fitted_model,
-        X_test_df.to_pandas_dataframe(),
-        y_test_df.to_pandas_dataframe().values.T[0],
-        max_horizon,
-        freq,
-    )
+X_rf = fitted_model.rolling_forecast(X_test_df, y_test, step=1)
+assign_dict = {
+    fitted_model.forecast_origin_column_name: "forecast_origin",
+    fitted_model.forecast_column_name: "predicted",
+    fitted_model.actual_column_name: target_column_name,
+}
+X_rf.rename(columns=assign_dict, inplace=True)
 
-print(df_all)
-
-print("target values:::")
-print(df_all[target_column_name])
-print("predicted values:::")
-print(df_all["predicted"])
+print(X_rf.head())
 
 # Use the AutoML scoring module
 regression_metrics = list(constants.REGRESSION_SCALAR_SET)
-y_test = np.array(df_all[target_column_name])
-y_pred = np.array(df_all["predicted"])
+y_test = np.array(X_rf[target_column_name])
+y_pred = np.array(X_rf["predicted"])
 scores = scoring.score_regression(y_test, y_pred, regression_metrics)
 
 print("scores:")
@@ -376,11 +135,11 @@ for key, value in scores.items():
     run.log(key, value)
 
 print("Simple forecasting model")
-rmse = np.sqrt(mean_squared_error(df_all[target_column_name], df_all["predicted"]))
+rmse = np.sqrt(mean_squared_error(X_rf[target_column_name], X_rf["predicted"]))
 print("[Test Data] \nRoot Mean squared error: %.2f" % rmse)
-mae = mean_absolute_error(df_all[target_column_name], df_all["predicted"])
+mae = mean_absolute_error(X_rf[target_column_name], X_rf["predicted"])
 print("mean_absolute_error score: %.2f" % mae)
-print("MAPE: %.2f" % MAPE(df_all[target_column_name], df_all["predicted"]))
+print("MAPE: %.2f" % MAPE(X_rf[target_column_name], X_rf["predicted"]))
 
 run.log("rmse", rmse)
 run.log("mae", mae)

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

@@ -40,7 +40,7 @@
       "metadata": {},
       "source": [
         "### Prerequisites\n",
-        "You'll need to create a compute Instance by following the instructions in the [EnvironmentSetup.md](../Setup_Resources/EnvironmentSetup.md)."
+        "You'll need to create a compute Instance by following [these](https://learn.microsoft.com/en-us/azure/machine-learning/v1/how-to-create-manage-compute-instance?tabs=python) instructions."
       ]
     },
     {
@@ -251,8 +251,17 @@
       "source": [
         "### Set up training parameters\n",
         "\n",
-        "This dictionary defines the AutoML and hierarchy settings. For this forecasting task we need to define several settings inncluding the name of the time column, the maximum forecast horizon, the hierarchy definition, and the level of the hierarchy at which to train.\n",
+        "We need to provide ``ForecastingParameters``, ``AutoMLConfig`` and ``HTSTrainParameters`` objects. For the forecasting task we need to define several settings including the name of the time column, the maximum forecast horizon, the hierarchy definition, and the level of the hierarchy at which to train.\n",
         "\n",
+        "#### ``ForecastingParameters`` arguments\n",
+        "| Property                           | Description|\n",
+        "| :---------------                   | :------------------- |\n",
+        "| **forecast_horizon**               | The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly). Periods are inferred from your data. |\n",
+        "| **time_column_name**               | The name of your time column. |\n",
+        "| **time_series_id_column_names**    | The column names used to uniquely identify timeseries in data that has multiple rows with the same timestamp. |\n",
+        "| **cv_step_size**                   | Number of periods between two consecutive cross-validation folds. The default value is \\\"auto\\\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value. |\n",
+        "\n",
+        "#### ``AutoMLConfig`` arguments\n",
         "| Property                           | Description|\n",
         "| :---------------                   | :------------------- |\n",
         "| **task**                           | forecasting |\n",
@@ -260,19 +269,22 @@
         "| **blocked_models**                 | Blocked models won't be used by AutoML. |\n",
         "| **iteration_timeout_minutes**      | Maximum amount of time in minutes that the model can train. This is optional but provides customers with greater control on exit criteria. |\n",
         "| **iterations**                     | Number of models to train. This is optional but provides customers with greater control on exit criteria. |\n",
-        "| **experiment_timeout_hours**       | Maximum amount of time in hours that the experiment can take before it terminates. This is optional but provides customers with greater control on exit criteria. |\n",
+        "| **experiment_timeout_hours**       | Maximum amount of time in hours that each experiment can take before it terminates. This is optional but provides customers with greater control on exit criteria. **It does not control the overall timeout for the pipeline run, instead controls the timeout for each training run per partitioned time series.** |\n",
         "| **label_column_name**              | The name of the label column. |\n",
-        "| **forecast_horizon**               | The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly). Periods are inferred from your data. |\n",
-        "| **n_cross_validations**            | Number of cross validation splits. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
-        "| **enable_early_stopping**          | Flag to enable early termination if the score is not improving in the short term. |\n",
-        "| **time_column_name**               | The name of your time column. |\n",
-        "| **hierarchy_column_names**         | The names of columns that define the hierarchical structure of the data from highest level to most granular. |\n",
-        "| **training_level**                 | The level of the hierarchy to be used for training models. |\n",
+        "| **n_cross_validations**            | Number of cross validation splits. The default value is \\\"auto\\\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
+        "| **enable_early_stopping**          | Flag to enable early termination if the primary metric is no longer improving. |\n",
         "| **enable_engineered_explanations** | Engineered feature explanations will be downloaded if enable_engineered_explanations flag is set to True. By default it is set to False to save storage space. |\n",
-        "| **time_series_id_column_name**     | The column names used to uniquely identify timeseries in data that has multiple rows with the same timestamp. |\n",
         "| **track_child_runs**               | Flag to disable tracking of child runs. Only best run is tracked if the flag is set to False (this includes the model and metrics of the run). |\n",
         "| **pipeline_fetch_max_batch_size**  | Determines how many pipelines (training algorithms) to fetch at a time for training, this helps reduce throttling when training at large scale. |\n",
-        "| **model_explainability**           | Flag to disable explaining the best automated ML model at the end of all training iterations. The default is True and will block non-explainable models which may impact the forecast accuracy. For more information, see [Interpretability: model explanations in automated machine learning](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-machine-learning-interpretability-automl). |"
+        "| **model_explainability**           | Flag to disable explaining the best automated ML model at the end of all training iterations. The default is True and will block non-explainable models which may impact the forecast accuracy. For more information, see [Interpretability: model explanations in automated machine learning](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-machine-learning-interpretability-automl). |\n",
+        "\n",
+        "#### ``HTSTrainParameters`` arguments\n",
+        "| Property                           | Description|\n",
+        "| :---------------                   | :------------------- |\n",
+        "| **automl_settings**                | The ``AutoMLConfig`` object defined above. |\n",
+        "| **hierarchy_column_names**         | The names of columns that define the hierarchical structure of the data from highest level to most granular. |\n",
+        "| **training_level**                 | The level of the hierarchy to be used for training models. |\n",
+        "| **enable_engineered_explanations** | The switch controls engineered explanations. |"
       ]
     },
     {
@@ -286,6 +298,9 @@
       "outputs": [],
       "source": [
         "from azureml.train.automl.runtime._hts.hts_parameters import HTSTrainParameters\n",
+        "from azureml.automl.core.forecasting_parameters import ForecastingParameters\n",
+        "from azureml.train.automl.automlconfig import AutoMLConfig\n",
+        "\n",
         "\n",
         "model_explainability = True\n",
         "\n",
@@ -299,23 +314,26 @@
         "label_column_name = \"quantity\"\n",
         "forecast_horizon = 7\n",
         "\n",
+        "forecasting_parameters = ForecastingParameters(\n",
+        "    time_column_name=time_column_name,\n",
+        "    forecast_horizon=forecast_horizon,\n",
+        ")\n",
         "\n",
-        "automl_settings = {\n",
-        "    \"task\": \"forecasting\",\n",
-        "    \"primary_metric\": \"normalized_root_mean_squared_error\",\n",
-        "    \"label_column_name\": label_column_name,\n",
-        "    \"time_column_name\": time_column_name,\n",
-        "    \"forecast_horizon\": forecast_horizon,\n",
-        "    \"hierarchy_column_names\": hierarchy,\n",
-        "    \"hierarchy_training_level\": training_level,\n",
-        "    \"track_child_runs\": False,\n",
-        "    \"pipeline_fetch_max_batch_size\": 15,\n",
-        "    \"model_explainability\": model_explainability,\n",
+        "automl_settings = AutoMLConfig(\n",
+        "    task=\"forecasting\",\n",
+        "    primary_metric=\"normalized_root_mean_squared_error\",\n",
+        "    experiment_timeout_hours=1,\n",
+        "    label_column_name=label_column_name,\n",
+        "    track_child_runs=False,\n",
+        "    forecasting_parameters=forecasting_parameters,\n",
+        "    pipeline_fetch_max_batch_size=15,\n",
+        "    model_explainability=model_explainability,\n",
+        "    n_cross_validations=\"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
+        "    cv_step_size=\"auto\",\n",
         "    # The following settings are specific to this sample and should be adjusted according to your own needs.\n",
-        "    \"iteration_timeout_minutes\": 10,\n",
-        "    \"iterations\": 10,\n",
-        "    \"n_cross_validations\": 2,\n",
-        "}\n",
+        "    iteration_timeout_minutes=10,\n",
+        "    iterations=15,\n",
+        ")\n",
         "\n",
         "hts_parameters = HTSTrainParameters(\n",
         "    automl_settings=automl_settings,\n",
@@ -336,15 +354,25 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Parallel run step is leveraged to train the hierarchy. To configure the ParallelRunConfig you will need to determine the appropriate number of workers and nodes for your use case. The `process_count_per_node` is based off the number of cores of the compute VM. The node_count will determine the number of master nodes to use, increasing the node count will speed up the training process.\n",
+        "Parallel run step is leveraged to train multiple models at once. To configure the ParallelRunConfig you will need to determine the appropriate number of workers and nodes for your use case. The ``process_count_per_node`` is based off the number of cores of the compute VM. The node_count will determine the number of master nodes to use, increasing the node count will speed up the training process.\n",
         "\n",
-        "* **experiment:** The experiment used for training.\n",
-        "* **train_data:** The tabular dataset to be used as input to the training run.\n",
-        "* **node_count:** The number of compute nodes to be used for running the user script. We recommend to start with 3 and increase the node_count if the training time is taking too long.\n",
-        "* **process_count_per_node:** Process count per node, we recommend 2:1 ratio for number of cores: number of processes per node. eg. If node has 16 cores then configure 8 or less process count per node or optimal performance.\n",
-        "* **train_pipeline_parameters:** The set of configuration parameters defined in the previous section. \n",
+        "| Property                           | Description|\n",
+        "| :---------------                   | :------------------- |\n",
+        "| **experiment**                     | The experiment used for training. |\n",
+        "| **train_data**                     | The file dataset to be used as input to the training run. |\n",
+        "| **node_count**                     | The number of compute nodes to be used for running the user script. We recommend to start with 3 and increase the node_count if the training time is taking too long. |\n",
+        "| **process_count_per_node**         | Process count per node, we recommend 2:1 ratio for number of cores: number of processes per node. eg. If node has 16 cores then configure 8 or less process count per node for optimal performance. |\n",
+        "| **train_pipeline_parameters**      | The set of configuration parameters defined in the previous section. |\n",
+        "| **run_invocation_timeout**         | Maximum amount of time in seconds that the ``ParallelRunStep`` class is allowed. This is optional but provides customers with greater control on exit criteria. This must be greater than ``experiment_timeout_hours`` by at least 300 seconds. |\n",
         "\n",
-        "Calling this method will create a new aggregated dataset which is generated dynamically on pipeline execution."
+        "Calling this method will create a new aggregated dataset which is generated dynamically on pipeline execution.\n",
+        "\n",
+        "**Note**: Total time taken for the **training step** in the pipeline to complete = $ \\frac{t}{ p \\times n } \\times ts $\n",
+        "where,\n",
+        "- $ t $ is time taken for training one partition (can be viewed in the training logs)\n",
+        "- $ p $ is ``process_count_per_node``\n",
+        "- $ n $ is ``node_count``\n",
+        "- $ ts $ is total number of partitions in time series based on ``partition_column_names``"
       ]
     },
     {
@@ -363,6 +391,7 @@
         "    node_count=2,\n",
         "    process_count_per_node=8,\n",
         "    train_pipeline_parameters=hts_parameters,\n",
+        "    run_invocation_timeout=3900,\n",
         ")"
       ]
     },
@@ -507,19 +536,24 @@
       "source": [
         "## 5.0 Forecasting\n",
         "For hierarchical forecasting we need to provide the HTSInferenceParameters object.\n",
-        "#### HTSInferenceParameters arguments\n",
-        "* **hierarchy_forecast_level:** The default level of the hierarchy to produce prediction/forecast on.\n",
-        "* **allocation_method:** \\[Optional] The disaggregation method to use if the hierarchy forecast level specified is below the define hierarchy training level. <br><i>(average historical proportions) 'average_historical_proportions'</i><br><i>(proportions of the historical averages) 'proportions_of_historical_average'</i>\n",
+        "#### ``HTSInferenceParameters`` arguments\n",
+        "| Property                           | Description|\n",
+        "| :---------------                   | :------------------- |\n",
+        "| **hierarchy_forecast_level:**      | The default level of the hierarchy to produce prediction/forecast on. |\n",
+        "| **allocation_method:**             | \\[Optional] The disaggregation method to use if the hierarchy forecast level specified is below the define hierarchy training level. <br><i>(average historical proportions) 'average_historical_proportions'</i><br><i>(proportions of the historical averages) 'proportions_of_historical_average'</i> |\n",
         "\n",
-        "#### get_many_models_batch_inference_steps arguments\n",
-        "* **experiment:** The experiment used for inference run.\n",
-        "* **inference_data:** The data to use for inferencing. It should be the same schema as used for training.\n",
-        "* **compute_target:** The compute target that runs the inference pipeline.\n",
-        "* **node_count:** The number of compute nodes to be used for running the user script. We recommend to start with the number of cores per node (varies by compute sku).\n",
-        "* **process_count_per_node:** The number of processes per node.\n",
-        "* **train_run_id:** \\[Optional] The run id of the hierarchy training, by default it is the latest successful training hts run in the experiment.\n",
-        "* **train_experiment_name:** \\[Optional] The train experiment that contains the train pipeline. This one is only needed when the train pipeline is not in the same experiement as the inference pipeline.\n",
-        "* **process_count_per_node:** \\[Optional] The number of processes per node, by default it's 4."
+        "#### ``get_many_models_batch_inference_steps`` arguments\n",
+        "| Property                           | Description|\n",
+        "| :---------------                   | :------------------- |\n",
+        "| **experiment**                     | The experiment used for inference run. |\n",
+        "| **inference_data**                 | The data to use for inferencing. It should be the same schema as used for training.\n",
+        "| **compute_target**                 | The compute target that runs the inference pipeline. |\n",
+        "| **node_count**                     | The number of compute nodes to be used for running the user script. We recommend to start with the number of cores per node (varies by compute sku). |\n",
+        "| **process_count_per_node**         | \\[Optional] The number of processes per node. By default it's 2 (should be at most half of the number of cores in a single node of the compute cluster that will be used for the experiment).\n",
+        "| **inference_pipeline_parameters**  | \\[Optional] The ``HTSInferenceParameters`` object defined above. |\n",
+        "| **train_run_id**                   | \\[Optional] The run id of the **training pipeline**. By default it is the latest successful training pipeline run in the experiment. |\n",
+        "| **train_experiment_name**          | \\[Optional] The train experiment that contains the train pipeline. This one is only needed when the train pipeline is not in the same experiement as the inference pipeline. |\n",
+        "| **run_invocation_timeout**         | \\[Optional] Maximum amount of time in seconds that the ``ParallelRunStep`` class is allowed. This is optional but provides customers with greater control on exit criteria. |"
       ]
     },
     {
@@ -618,9 +652,9 @@
       "automated-machine-learning"
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -0,0 +1,122 @@
+---
+page_type: sample
+languages:
+- python
+products:
+- azure-machine-learning
+description: Tutorial showing how to solve a complex machine learning time series forecasting problems at scale by using Azure Automated ML and Many Models solution accelerator.
+---
+
+![Many Models Solution Accelerator Banner](images/mmsa.png)
+# Many Models Solution Accelerator
+
+<!-- 
+Guidelines on README format: https://review.docs.microsoft.com/help/onboard/admin/samples/concepts/readme-template?branch=master
+
+Guidance on onboarding samples to docs.microsoft.com/samples: https://review.docs.microsoft.com/help/onboard/admin/samples/process/onboarding?branch=master
+
+Taxonomies for products and languages: https://review.docs.microsoft.com/new-hope/information-architecture/metadata/taxonomies?branch=master
+-->
+
+In the real world, many problems can be too complex to be solved by a single machine learning model. Whether that be predicting sales for each individual store, building a predictive maintanence model for hundreds of oil wells, or tailoring an experience to individual users, building a model for each instance can lead to improved results on many machine learning problems.
+
+This Pattern is very common across a wide variety of industries and applicable to many real world use cases. Below are some examples we have seen where this pattern is being used.
+
+- Energy and utility companies building predictive maintenance models for thousands of oil wells, hundreds of wind turbines or hundreds of smart meters
+
+- Retail organizations building workforce optimization models for thousands of stores, campaign promotion propensity models, Price optimization models for hundreds of thousands of products they sell
+
+- Restaurant chains building demand forecasting models across thousands of restaurants  
+
+- Banks and financial institutes building models for cash replenishment for ATM Machine and for several ATMs or building personalized models for individuals
+
+- Enterprises building revenue forecasting models at each division level
+
+- Document management companies building text analytics and legal document search models per each state
+
+Azure Machine Learning (AML) makes it easy to train, operate, and manage hundreds or even thousands of models. This repo will walk you through the end to end process of creating a many models solution from training to scoring to monitoring.
+
+## Prerequisites
+
+To use this solution accelerator, all you need is access to an [Azure subscription](https://azure.microsoft.com/free/) and an [Azure Machine Learning Workspace](https://docs.microsoft.com/azure/machine-learning/how-to-manage-workspace) that you'll create below.
+
+While it's not required, a basic understanding of Azure Machine Learning will be helpful for understanding the solution. The following resources can help introduce you to AML:
+
+1. [Azure Machine Learning Overview](https://azure.microsoft.com/services/machine-learning/)
+2. [Azure Machine Learning Tutorials](https://docs.microsoft.com/azure/machine-learning/tutorial-1st-experiment-sdk-setup)
+3. [Azure Machine Learning Sample Notebooks on Github](https://github.com/Azure/azureml-examples)
+
+## Getting started
+
+### 1. Deploy Resources
+
+Start by deploying the resources to Azure. The button below will deploy Azure Machine Learning and its related resources:
+
+<a href="https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.githubusercontent.com%2Fmicrosoft%2Fsolution-accelerator-many-models%2Fmaster%2Fazuredeploy.json" target="_blank">
+    <img src="http://azuredeploy.net/deploybutton.png"/>
+</a>
+
+### 2. Configure Development Environment
+
+Next you'll need to configure your [development environment](https://docs.microsoft.com/azure/machine-learning/how-to-configure-environment) for Azure Machine Learning. We recommend using a [Compute Instance](https://docs.microsoft.com/azure/machine-learning/how-to-configure-environment#compute-instance) as it's the fastest way to get up and running.
+
+### 3. Run Notebooks
+
+Once your development environment is set up, run through the Jupyter Notebooks sequentially following the steps outlined. By the end, you'll know how to train, score, and make predictions using the many models pattern on Azure Machine Learning.
+
+![Sequence of Notebooks](./images/mmsa-overview.png)
+
+
+## Contents
+
+In this repo, you'll train and score a forecasting model for each orange juice brand and for each store at a (simulated) grocery chain. By the end, you'll have forecasted sales by using up to 11,973 models to predict sales for the next few weeks.
+
+The data used in this sample is simulated based on the [Dominick's Orange Juice Dataset](http://www.cs.unitn.it/~taufer/QMMA/L10-OJ-Data.html#(1)), sales data from a Chicago area grocery store.
+
+<img src="images/Flow_map.png" width="1000">
+
+### Using Automated ML to train the models:
+
+The [`auto-ml-forecasting-many-models.ipynb`](./auto-ml-forecasting-many-models.ipynb) noteboook is a guided solution accelerator that demonstrates steps from data preparation, to model training, and forecasting on train models as well as operationalizing the solution.
+
+## How-to-videos
+
+Watch these how-to-videos for a step by step walk-through of the many model solution accelerator to learn how to setup your models using Automated ML.
+
+### Automated ML
+
+[![Watch the video](https://media.giphy.com/media/dWUKfameudyNGRnp1t/giphy.gif)](https://channel9.msdn.com/Shows/Docs-AI/Building-Large-Scale-Machine-Learning-Forecasting-Models-using-Azure-Machine-Learnings-Automated-ML)
+
+## Key concepts
+
+### ParallelRunStep
+
+[ParallelRunStep](https://docs.microsoft.com/en-us/python/api/azureml-pipeline-steps/azureml.pipeline.steps.parallel_run_step.parallelrunstep?view=azure-ml-py) enables the parallel training of models and is commonly used for batch inferencing. This [document](https://docs.microsoft.com/azure/machine-learning/how-to-use-parallel-run-step) walks through some of the key concepts around ParallelRunStep.
+
+### Pipelines
+
+[Pipelines](https://docs.microsoft.com/azure/machine-learning/concept-ml-pipelines) allow you to create workflows in your machine learning projects. These workflows have a number of benefits including speed, simplicity, repeatability, and modularity.
+
+### Automated Machine Learning
+
+[Automated Machine Learning](https://docs.microsoft.com/azure/machine-learning/concept-automated-ml) also referred to as automated ML or AutoML, is the process of automating the time consuming, iterative tasks of machine learning model development. It allows data scientists, analysts, and developers to build ML models with high scale, efficiency, and productivity all while sustaining model quality.
+
+### Other Concepts
+
+In additional to ParallelRunStep, Pipelines and Automated Machine Learning, you'll also be working with the following concepts including [workspace](https://docs.microsoft.com/azure/machine-learning/concept-workspace), [datasets](https://docs.microsoft.com/azure/machine-learning/concept-data#datasets), [compute targets](https://docs.microsoft.com/azure/machine-learning/concept-compute-target#train), [python script steps](https://docs.microsoft.com/python/api/azureml-pipeline-steps/azureml.pipeline.steps.python_script_step.pythonscriptstep?view=azure-ml-py), and [Azure Open Datasets](https://azure.microsoft.com/services/open-datasets/).
+
+## Contributing
+
+This project welcomes contributions and suggestions. To learn more visit the [contributing](../../../CONTRIBUTING.md) section.
+
+Most contributions require you to agree to a Contributor License Agreement (CLA)
+declaring that you have the right to, and actually do, grant us
+the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.
+
+When you submit a pull request, a CLA bot will automatically determine whether you need to provide
+a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions
+provided by the bot. You will only need to do this once across all repos using our CLA.
+
+This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
+For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or
+contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.

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

@@ -40,7 +40,7 @@
       "metadata": {},
       "source": [
         "### Prerequisites\n",
-        "You'll need to create a compute Instance by following the instructions in the [EnvironmentSetup.md](../Setup_Resources/EnvironmentSetup.md)."
+        "You'll need to create a compute Instance by following [these](https://learn.microsoft.com/en-us/azure/machine-learning/v1/how-to-create-manage-compute-instance?tabs=python) instructions."
       ]
     },
     {
@@ -379,8 +379,17 @@
       "source": [
         "### Set up training parameters\n",
         "\n",
-        "This dictionary defines the AutoML and many models settings. For this forecasting task we need to define several settings inncluding the name of the time column, the maximum forecast horizon, and the partition column name definition.\n",
+        "We need to provide ``ForecastingParameters``, ``AutoMLConfig`` and ``ManyModelsTrainParameters`` objects. For the forecasting task we also need to define several settings including the name of the time column, the maximum forecast horizon, and the partition column name(s) definition.\n",
         "\n",
+        "#### ``ForecastingParameters`` arguments\n",
+        "| Property                           | Description|\n",
+        "| :---------------                   | :------------------- |\n",
+        "| **forecast_horizon**               | The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly). Periods are inferred from your data. |\n",
+        "| **time_column_name**               | The name of your time column. |\n",
+        "| **time_series_id_column_names**    | The column names used to uniquely identify timeseries in data that has multiple rows with the same timestamp. |\n",
+        "| **cv_step_size**                   | Number of periods between two consecutive cross-validation folds. The default value is \\\"auto\\\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value. |\n",
+        "\n",
+        "#### ``AutoMLConfig`` arguments\n",
         "| Property                           | Description|\n",
         "| :---------------                   | :------------------- |\n",
         "| **task**                           | forecasting |\n",
@@ -388,16 +397,19 @@
         "| **blocked_models**                 | Blocked models won't be used by AutoML. |\n",
         "| **iteration_timeout_minutes**      | Maximum amount of time in minutes that the model can train. This is optional but provides customers with greater control on exit criteria. |\n",
         "| **iterations**                     | Number of models to train. This is optional but provides customers with greater control on exit criteria. |\n",
-        "| **experiment_timeout_hours**       | Maximum amount of time in hours that the experiment can take before it terminates. This is optional but provides customers with greater control on exit criteria. |\n",
+        "| **experiment_timeout_hours**       | Maximum amount of time in hours that each experiment can take before it terminates. This is optional but provides customers with greater control on exit criteria. **It does not control the overall timeout for the pipeline run, instead controls the timeout for each training run per partitioned time series.** |\n",
         "| **label_column_name**              | The name of the label column. |\n",
-        "| **forecast_horizon**               | The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly). Periods are inferred from your data. |\n",
-        "| **n_cross_validations**            | Number of cross validation splits. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
-        "| **enable_early_stopping**          | Flag to enable early termination if the score is not improving in the short term. |\n",
-        "| **time_column_name**               | The name of your time column. |\n",
+        "| **n_cross_validations**            | Number of cross validation splits. The default value is \\\"auto\\\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
+        "| **enable_early_stopping**          | Flag to enable early termination if the primary metric is no longer improving. |\n",
         "| **enable_engineered_explanations** | Engineered feature explanations will be downloaded if enable_engineered_explanations flag is set to True. By default it is set to False to save storage space. |\n",
-        "| **time_series_id_column_names**     | The column names used to uniquely identify timeseries in data that has multiple rows with the same timestamp. |\n",
         "| **track_child_runs**               | Flag to disable tracking of child runs. Only best run is tracked if the flag is set to False (this includes the model and metrics of the run). |\n",
         "| **pipeline_fetch_max_batch_size**  | Determines how many pipelines (training algorithms) to fetch at a time for training, this helps reduce throttling when training at large scale. |\n",
+        "\n",
+        "\n",
+        "#### ``ManyModelsTrainParameters`` arguments\n",
+        "| Property                           | Description|\n",
+        "| :---------------                   | :------------------- |\n",
+        "| **automl_settings**                | The ``AutoMLConfig`` object defined above. |\n",
         "| **partition_column_names**         | The names of columns used to group your models. For timeseries, the groups must not split up individual time-series. That is, each group must contain one or more whole time-series. |"
       ]
     },
@@ -414,22 +426,29 @@
         "from azureml.train.automl.runtime._many_models.many_models_parameters import (\n",
         "    ManyModelsTrainParameters,\n",
         ")\n",
+        "from azureml.automl.core.forecasting_parameters import ForecastingParameters\n",
+        "from azureml.train.automl.automlconfig import AutoMLConfig\n",
         "\n",
         "partition_column_names = [\"Store\", \"Brand\"]\n",
-        "automl_settings = {\n",
-        "    \"task\": \"forecasting\",\n",
-        "    \"primary_metric\": \"normalized_root_mean_squared_error\",\n",
-        "    \"iteration_timeout_minutes\": 10,  # This needs to be changed based on the dataset. We ask customer to explore how long training is taking before settings this value\n",
-        "    \"iterations\": 15,\n",
-        "    \"experiment_timeout_hours\": 0.25,\n",
-        "    \"label_column_name\": \"Quantity\",\n",
-        "    \"n_cross_validations\": 3,\n",
-        "    \"time_column_name\": \"WeekStarting\",\n",
-        "    \"drop_column_names\": \"Revenue\",\n",
-        "    \"forecast_horizon\": 6,\n",
-        "    \"time_series_id_column_names\": partition_column_names,\n",
-        "    \"track_child_runs\": False,\n",
-        "}\n",
+        "\n",
+        "forecasting_parameters = ForecastingParameters(\n",
+        "    time_column_name=\"WeekStarting\",\n",
+        "    forecast_horizon=6,\n",
+        "    time_series_id_column_names=partition_column_names,\n",
+        "    cv_step_size=\"auto\",\n",
+        ")\n",
+        "\n",
+        "automl_settings = AutoMLConfig(\n",
+        "    task=\"forecasting\",\n",
+        "    primary_metric=\"normalized_root_mean_squared_error\",\n",
+        "    iteration_timeout_minutes=10,\n",
+        "    iterations=15,\n",
+        "    experiment_timeout_hours=0.25,\n",
+        "    label_column_name=\"Quantity\",\n",
+        "    n_cross_validations=\"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
+        "    track_child_runs=False,\n",
+        "    forecasting_parameters=forecasting_parameters,\n",
+        ")\n",
         "\n",
         "mm_paramters = ManyModelsTrainParameters(\n",
         "    automl_settings=automl_settings, partition_column_names=partition_column_names\n",
@@ -449,7 +468,9 @@
         "\n",
         "Reuse of previous results (``allow_reuse``) is key when using pipelines in a collaborative environment since eliminating unnecessary reruns offers agility. Reuse is the default behavior when the ``script_name``, ``inputs``, and the parameters of a step remain the same. When reuse is allowed, results from the previous run are immediately sent to the next step. If ``allow_reuse`` is set to False, a new run will always be generated for this step during pipeline execution.\n",
         "\n",
-        "> Note that we only support partitioned FileDataset and TabularDataset without partition when using such output as input."
+        "> Note that we only support partitioned FileDataset and TabularDataset without partition when using such output as input.\n",
+        "\n",
+        "> Note that we **drop column** \"Revenue\" from the dataset in this step to avoid information leak as \"Quantity\" = \"Revenue\" / \"Price\". **Please modify the logic based on your data**."
       ]
     },
     {
@@ -487,17 +508,25 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Parallel run step is leveraged to train multiple models at once. To configure the ParallelRunConfig you will need to determine the appropriate number of workers and nodes for your use case. The process_count_per_node is based off the number of cores of the compute VM. The node_count will determine the number of master nodes to use, increasing the node count will speed up the training process.\n",
+        "Parallel run step is leveraged to train multiple models at once. To configure the ParallelRunConfig you will need to determine the appropriate number of workers and nodes for your use case. The ``process_count_per_node`` is based off the number of cores of the compute VM. The node_count will determine the number of master nodes to use, increasing the node count will speed up the training process.\n",
         "\n",
         "| Property                           | Description|\n",
         "| :---------------                   | :------------------- |\n",
         "| **experiment**                     | The experiment used for training. |\n",
         "| **train_data**                     | The file dataset to be used as input to the training run. |\n",
         "| **node_count**                     | The number of compute nodes to be used for running the user script. We recommend to start with 3 and increase the node_count if the training time is taking too long. |\n",
-        "| **process_count_per_node**         | Process count per node, we recommend 2:1 ratio for number of cores: number of processes per node. eg. If node has 16 cores then configure 8 or less process count per node or optimal performance. |\n",
+        "| **process_count_per_node**         | Process count per node, we recommend 2:1 ratio for number of cores: number of processes per node. eg. If node has 16 cores then configure 8 or less process count per node for optimal performance. |\n",
         "| **train_pipeline_parameters**      | The set of configuration parameters defined in the previous section. |\n",
+        "| **run_invocation_timeout**         | Maximum amount of time in seconds that the ``ParallelRunStep`` class is allowed. This is optional but provides customers with greater control on exit criteria. This must be greater than ``experiment_timeout_hours`` by at least 300 seconds. |\n",
         "\n",
-        "Calling this method will create a new aggregated dataset which is generated dynamically on pipeline execution."
+        "Calling this method will create a new aggregated dataset which is generated dynamically on pipeline execution.\n",
+        "\n",
+        "**Note**: Total time taken for the **training step** in the pipeline to complete = $ \\frac{t}{ p \\times n } \\times ts $\n",
+        "where,\n",
+        "- $ t $ is time taken for training one partition (can be viewed in the training logs)\n",
+        "- $ p $ is ``process_count_per_node``\n",
+        "- $ n $ is ``node_count``\n",
+        "- $ ts $ is total number of partitions in time series based on ``partition_column_names``"
       ]
     },
     {
@@ -515,7 +544,7 @@
         "    compute_target=compute_target,\n",
         "    node_count=2,\n",
         "    process_count_per_node=8,\n",
-        "    run_invocation_timeout=920,\n",
+        "    run_invocation_timeout=1200,\n",
         "    train_pipeline_parameters=mm_paramters,\n",
         ")"
       ]
@@ -596,7 +625,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### 7.2 Schedule the pipeline\n",
+        "### 5.2 Schedule the pipeline\n",
         "You can also [schedule the pipeline](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-schedule-pipelines) to run on a time-based or change-based schedule. This could be used to automatically retrain models every month or based on another trigger such as data drift."
       ]
     },
@@ -652,25 +681,31 @@
       "source": [
         "For many models we need to provide the ManyModelsInferenceParameters object.\n",
         "\n",
-        "#### ManyModelsInferenceParameters arguments\n",
+        "#### ``ManyModelsInferenceParameters`` arguments\n",
         "| Property                           | Description|\n",
         "| :---------------                   | :------------------- |\n",
         "| **partition_column_names**         | List of column names that identifies groups. |\n",
         "| **target_column_name**             | \\[Optional] Column name only if the inference dataset has the target. |\n",
-        "| **time_column_name**               | \\[Optional] Column name only if it is timeseries. |\n",
-        "| **many_models_run_id**             | \\[Optional] Many models run id where models were trained. |\n",
+        "| **time_column_name**               | \\[Optional] Time column name only if it is timeseries. |\n",
+        "| **inference_type**                 | \\[Optional] Which inference method to use on the model. Possible values are 'forecast', 'predict_proba', and 'predict'. |\n",
+        "| **forecast_mode**                  | \\[Optional] The type of forecast to be used, either 'rolling' or 'recursive'; defaults to 'recursive'. |\n",
+        "| **step**                           | \\[Optional] Number of periods to advance the forecasting window in each iteration **(for rolling forecast only)**; defaults to 1. |\n",
         "\n",
-        "#### get_many_models_batch_inference_steps arguments\n",
+        "#### ``get_many_models_batch_inference_steps`` arguments\n",
         "| Property                           | Description|\n",
         "| :---------------                   | :------------------- |\n",
         "| **experiment**                     | The experiment used for inference run. |\n",
         "| **inference_data**                 | The data to use for inferencing. It should be the same schema as used for training.\n",
-        "| **compute_target** The compute target that runs the inference pipeline.|\n",
+        "| **compute_target**                 | The compute target that runs the inference pipeline. |\n",
         "| **node_count**                     | The number of compute nodes to be used for running the user script. We recommend to start with the number of cores per node (varies by compute sku). |\n",
-        "| **process_count_per_node** The number of processes per node.\n",
-        "| **train_run_id**                   | \\[Optional] The run id of the hierarchy training, by default it is the latest successful training many model run in the experiment. |\n",
+        "| **process_count_per_node**         | \\[Optional] The number of processes per node. By default it's 2 (should be at most half of the number of cores in a single node of the compute cluster that will be used for the experiment).\n",
+        "| **inference_pipeline_parameters**  | \\[Optional] The ``ManyModelsInferenceParameters`` object defined above. |\n",
+        "| **append_row_file_name**           | \\[Optional] The name of the output file (optional, default value is 'parallel_run_step.txt'). Supports 'txt' and 'csv' file extension. A 'txt' file extension generates the output in 'txt' format with space as separator without column names. A 'csv' file extension generates the output in 'csv' format with comma as separator and with column names. |\n",
+        "| **train_run_id**                   | \\[Optional] The run id of the **training pipeline**. By default it is the latest successful training pipeline run in the experiment. |\n",
         "| **train_experiment_name**          | \\[Optional] The train experiment that contains the train pipeline. This one is only needed when the train pipeline is not in the same experiement as the inference pipeline. |\n",
-        "| **process_count_per_node**         | \\[Optional] The number of processes per node, by default it's 4. |"
+        "| **run_invocation_timeout**         | \\[Optional] Maximum amount of time in seconds that the ``ParallelRunStep`` class is allowed. This is optional but provides customers with greater control on exit criteria. |\n",
+        "| **output_datastore**               | \\[Optional] The ``Datastore`` or ``OutputDatasetConfig`` to be used for output. If specified any pipeline output will be written to that location. If unspecified the default datastore will be used. |\n",
+        "| **arguments**                      | \\[Optional] Arguments to be passed to inference script. Possible argument is '--forecast_quantiles' followed by quantile values. |"
       ]
     },
     {
@@ -690,6 +725,8 @@
         "    target_column_name=\"Quantity\",\n",
         ")\n",
         "\n",
+        "output_file_name = \"parallel_run_step.csv\"\n",
+        "\n",
         "inference_steps = AutoMLPipelineBuilder.get_many_models_batch_inference_steps(\n",
         "    experiment=experiment,\n",
         "    inference_data=inference_ds_small,\n",
@@ -701,6 +738,8 @@
         "    train_run_id=training_run.id,\n",
         "    train_experiment_name=training_run.experiment.name,\n",
         "    inference_pipeline_parameters=mm_parameters,\n",
+        "    append_row_file_name=output_file_name,\n",
+        "    arguments=[\"--forecast_quantiles\", 0.1, 0.9],\n",
         ")"
       ]
     },
@@ -735,7 +774,7 @@
         "\n",
         "The following code snippet:\n",
         "1. Downloads the contents of the output folder that is passed in the parallel run step \n",
-        "2. Reads the parallel_run_step.txt file that has the predictions as pandas dataframe and \n",
+        "2. Reads the output file that has the predictions as pandas dataframe and \n",
         "3. Displays the top 10 rows of the predictions"
       ]
     },
@@ -750,19 +789,9 @@
         "forecasting_results_name = \"forecasting_results\"\n",
         "forecasting_output_name = \"many_models_inference_output\"\n",
         "forecast_file = get_output_from_mm_pipeline(\n",
-        "    inference_run, forecasting_results_name, forecasting_output_name\n",
+        "    inference_run, forecasting_results_name, forecasting_output_name, output_file_name\n",
         ")\n",
-        "df = pd.read_csv(forecast_file, delimiter=\" \", header=None)\n",
-        "df.columns = [\n",
-        "    \"Week Starting\",\n",
-        "    \"Store\",\n",
-        "    \"Brand\",\n",
-        "    \"Quantity\",\n",
-        "    \"Advert\",\n",
-        "    \"Price\",\n",
-        "    \"Revenue\",\n",
-        "    \"Predicted\",\n",
-        "]\n",
+        "df = pd.read_csv(forecast_file)\n",
         "print(\n",
         "    \"Prediction has \", df.shape[0], \" rows. Here the first 10 rows are being displayed.\"\n",
         ")\n",
@@ -835,9 +864,9 @@
       "automated-machine-learning"
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {
@@ -849,7 +878,12 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.8"
+      "version": "3.8.5"
+    },
+    "vscode": {
+      "interpreter": {
+        "hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
+      }
     }
   },
   "nbformat": 4,

how-to-use-azureml/automated-machine-learning/forecasting-many-models/scripts/data_preprocessing_file.py

@@ -0,0 +1,39 @@
+from pathlib import Path
+from azureml.core import Run
+
+import argparse
+import os
+
+
+def main(args):
+    output = Path(args.output)
+    output.mkdir(parents=True, exist_ok=True)
+
+    run_context = Run.get_context()
+    input_path = run_context.input_datasets["train_10_models"]
+
+    for file_name in os.listdir(input_path):
+        input_file = os.path.join(input_path, file_name)
+        with open(input_file, "r") as f:
+            content = f.read()
+
+            # Apply any data pre-processing techniques here
+
+            output_file = os.path.join(output, file_name)
+            with open(output_file, "w") as f:
+                f.write(content)
+
+
+def my_parse_args():
+    parser = argparse.ArgumentParser("Test")
+
+    parser.add_argument("--input", type=str)
+    parser.add_argument("--output", type=str)
+
+    args = parser.parse_args()
+    return args
+
+
+if __name__ == "__main__":
+    args = my_parse_args()
+    main(args)

how-to-use-azureml/automated-machine-learning/forecasting-many-models/scripts/data_preprocessing_tabular.py

@@ -0,0 +1,37 @@
+from pathlib import Path
+from azureml.core import Run
+import argparse
+
+
+def main(args):
+    output = Path(args.output)
+    output.mkdir(parents=True, exist_ok=True)
+
+    run_context = Run.get_context()
+    dataset = run_context.input_datasets["train_10_models"]
+    df = dataset.to_pandas_dataframe()
+
+    # Drop the column "Revenue" from the dataset to avoid information leak as
+    # "Quantity" = "Revenue" / "Price". Please modify the logic based on your data.
+    drop_column_name = "Revenue"
+    if drop_column_name in df.columns:
+        df.drop(drop_column_name, axis=1, inplace=True)
+
+    # Apply any data pre-processing techniques here
+
+    df.to_parquet(output / "data_prepared_result.parquet", compression=None)
+
+
+def my_parse_args():
+    parser = argparse.ArgumentParser("Test")
+
+    parser.add_argument("--input", type=str)
+    parser.add_argument("--output", type=str)
+
+    args = parser.parse_args()
+    return args
+
+
+if __name__ == "__main__":
+    args = my_parse_args()
+    main(args)

how-to-use-azureml/automated-machine-learning/forecasting-many-models/update_env.yml

@@ -0,0 +1,3 @@
+dependencies:
+- pip:
+  - azureml-contrib-automl-pipeline-steps

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

@@ -40,7 +40,7 @@
         "## Introduction<a id=\"introduction\"></a>\n",
         "In this example, we use AutoML to train, select, and operationalize a time-series forecasting model for multiple time-series.\n",
         "\n",
-        "Make sure you have executed the [configuration notebook](../../../configuration.ipynb) before running this notebook.\n",
+        "Make sure you have executed the [configuration notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/configuration.ipynb) before running this notebook.\n",
         "\n",
         "The examples in the follow code samples use the University of Chicago's Dominick's Finer Foods dataset to forecast orange juice sales. Dominick's was a grocery chain in the Chicago metropolitan area."
       ]
@@ -368,7 +368,8 @@
         "|**time_column_name**|The name of your time column.|\n",
         "|**forecast_horizon**|The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly).|\n",
         "|**time_series_id_column_names**|The column names used to uniquely identify the time series in data that has multiple rows with the same timestamp. If the time series identifiers are not defined, the data set is assumed to be one time series.|\n",
-        "|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information."
+        "|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information.\n",
+        "|**cv_step_size**|Number of periods between two consecutive cross-validation folds. The default value is \"auto\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value."
       ]
     },
     {
@@ -390,7 +391,7 @@
         "In the first case, AutoML loops over all time-series in your dataset and trains one model (e.g. AutoArima or Prophet, as the case may be) for each series. This can result in long runtimes to train these models if there are a lot of series in the data. One way to mitigate this problem is to fit models for different series in parallel if you have multiple compute cores available. To enable this behavior, set the `max_cores_per_iteration` parameter in your AutoMLConfig as shown in the example in the next cell. \n",
         "\n",
         "\n",
-        "Finally, a note about the cross-validation (CV) procedure for time-series data. AutoML uses out-of-sample error estimates to select a best pipeline/model, so it is important that the CV fold splitting is done correctly. Time-series can violate the basic statistical assumptions of the canonical K-Fold CV strategy, so AutoML implements a [rolling origin validation](https://robjhyndman.com/hyndsight/tscv/) procedure to create CV folds for time-series data. To use this procedure, you just need to specify the desired number of CV folds in the AutoMLConfig object. It is also possible to bypass CV and use your own validation set by setting the *validation_data* parameter of AutoMLConfig.\n",
+        "Finally, a note about the cross-validation (CV) procedure for time-series data. AutoML uses out-of-sample error estimates to select a best pipeline/model, so it is important that the CV fold splitting is done correctly. Time-series can violate the basic statistical assumptions of the canonical K-Fold CV strategy, so AutoML implements a [rolling origin validation](https://robjhyndman.com/hyndsight/tscv/) procedure to create CV folds for time-series data. To use this procedure, you could specify the desired number of CV folds and the number of periods between two consecutive folds in the AutoMLConfig object, or AutoMl could set them automatically if you don't specify them. It is also possible to bypass CV and use your own validation set by setting the *validation_data* parameter of AutoMLConfig.\n",
         "\n",
         "Here is a summary of AutoMLConfig parameters used for training the OJ model:\n",
         "\n",
@@ -403,7 +404,7 @@
         "|**training_data**|Input dataset, containing both features and label column.|\n",
         "|**label_column_name**|The name of the label column.|\n",
         "|**compute_target**|The remote compute for training.|\n",
-        "|**n_cross_validations**|Number of cross-validation folds to use for model/pipeline selection|\n",
+        "|**n_cross_validations**|Number of cross-validation folds to use for model/pipeline selection. The default value is \"auto\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value.\n",
         "|**enable_voting_ensemble**|Allow AutoML to create a Voting ensemble of the best performing models|\n",
         "|**enable_stack_ensemble**|Allow AutoML to create a Stack ensemble of the best performing models|\n",
         "|**debug_log**|Log file path for writing debugging information|\n",
@@ -424,6 +425,7 @@
         "    forecast_horizon=n_test_periods,\n",
         "    time_series_id_column_names=time_series_id_column_names,\n",
         "    freq=\"W-THU\",  # Set the forecast frequency to be weekly (start on each Thursday)\n",
+        "    cv_step_size=\"auto\",\n",
         ")\n",
         "\n",
         "automl_config = AutoMLConfig(\n",
@@ -436,7 +438,7 @@
         "    compute_target=compute_target,\n",
         "    enable_early_stopping=True,\n",
         "    featurization=featurization_config,\n",
-        "    n_cross_validations=3,\n",
+        "    n_cross_validations=\"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
         "    verbosity=logging.INFO,\n",
         "    max_cores_per_iteration=-1,\n",
         "    forecasting_parameters=forecasting_parameters,\n",
@@ -819,9 +821,9 @@
     "friendly_name": "Forecasting orange juice sales with deployment",
     "index_order": 1,
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {
@@ -833,12 +835,17 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.9"
+      "version": "3.8.5"
     },
     "tags": [
       "None"
     ],
-    "task": "Forecasting"
+    "task": "Forecasting",
+    "vscode": {
+      "interpreter": {
+        "hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
+      }
+    }
   },
   "nbformat": 4,
   "nbformat_minor": 4

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

@@ -13,7 +13,7 @@
       "source": [
         "## Introduction\n",
         "\n",
-        "In this notebook, we demonstrate how to use piplines to train and inference on AutoML Forecasting model. Two pipelines will be created: one for training AutoML model, and the other is for inference on AutoML model. We'll also demonstrate how to schedule the inference pipeline so you can get inference results periodically (with refreshed test dataset). Make sure you have executed the configuration notebook before running this notebook. In this notebook you will learn how to:\n",
+        "In this notebook, we demonstrate how to use piplines to train and inference on AutoML Forecasting model. Two pipelines will be created: one for training AutoML model, and the other is for inference on AutoML model. We'll also demonstrate how to schedule the inference pipeline so you can get inference results periodically (with refreshed test dataset). Make sure you have executed the [configuration notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/configuration.ipynb) before running this notebook. In this notebook you will learn how to:\n",
         "\n",
         "- Configure AutoML using AutoMLConfig for forecasting tasks using pipeline AutoMLSteps.\n",
         "- Create and register an AutoML model using AzureML pipeline.\n",
@@ -237,11 +237,11 @@
         "\n",
         "datastore = ws.get_default_datastore()\n",
         "train_dataset = TabularDatasetFactory.register_pandas_dataframe(\n",
-        "    train, target=(datastore, \"dataset/\"), name=\"dominicks_OJ_train\"\n",
+        "    train, target=(datastore, \"dataset/\"), name=\"dominicks_OJ_train_pipeline\"\n",
         ")\n",
         "\n",
         "test_dataset = TabularDatasetFactory.register_pandas_dataframe(\n",
-        "    test, target=(datastore, \"dataset/\"), name=\"dominicks_OJ_test\"\n",
+        "    test, target=(datastore, \"dataset/\"), name=\"dominicks_OJ_test_pipeline\"\n",
         ")"
       ]
     },
@@ -292,7 +292,8 @@
         "|**time_column_name**|The name of your time column.|\n",
         "|**forecast_horizon**|The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly).|\n",
         "|**time_series_id_column_names**|The column names used to uniquely identify the time series in data that has multiple rows with the same timestamp. If the time series identifiers are not defined, the data set is assumed to be one time series.|\n",
-        "|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information."
+        "|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information.\n",
+        "|**cv_step_size**|Number of periods between two consecutive cross-validation folds. The default value is \"auto\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value."
       ]
     },
     {
@@ -307,7 +308,8 @@
         "    time_column_name=time_column_name,\n",
         "    forecast_horizon=n_test_periods,\n",
         "    time_series_id_column_names=time_series_id_column_names,\n",
-        "    freq=\"W-THU\",  # Set the forecast frequency to be weekly (start on each Thursday)\n",
+        "    freq=\"W-THU\",  # Set the forecast frequency to be weekly (start on each Thursday),\n",
+        "    cv_step_size=\"auto\",\n",
         ")\n",
         "\n",
         "automl_config = AutoMLConfig(\n",
@@ -319,7 +321,7 @@
         "    label_column_name=target_column_name,\n",
         "    compute_target=compute_target,\n",
         "    enable_early_stopping=True,\n",
-        "    n_cross_validations=5,\n",
+        "    n_cross_validations=\"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
         "    verbosity=logging.INFO,\n",
         "    max_cores_per_iteration=-1,\n",
         "    forecasting_parameters=forecasting_parameters,\n",
@@ -797,9 +799,9 @@
     "friendly_name": "Forecasting orange juice sales with deployment",
     "index_order": 1,
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {
@@ -811,12 +813,17 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.9"
+      "version": "3.8.5"
     },
     "tags": [
       "None"
     ],
-    "task": "Forecasting"
+    "task": "Forecasting",
+    "vscode": {
+      "interpreter": {
+        "hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
+      }
+    }
   },
   "nbformat": 4,
   "nbformat_minor": 4

how-to-use-azureml/automated-machine-learning/forecasting-pipelines/scripts/infer.py

@@ -107,7 +107,7 @@ def get_data(run, fitted_model, target_column_name, test_dataset_name):
     test_dataset = Dataset.get_by_name(run.experiment.workspace, test_dataset_name)
     test_df = test_dataset.to_pandas_dataframe()
     if target_column_name in test_df:
-        y_test = test_df.pop(target_column_name)
+        y_test = test_df.pop(target_column_name).values
     else:
         y_test = np.full(test_df.shape[0], np.nan)
 

how-to-use-azureml/automated-machine-learning/forecasting-recipes-univariate/auto-ml-forecasting-univariate-recipe-experiment-settings.ipynb

@@ -472,9 +472,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

how-to-use-azureml/automated-machine-learning/forecasting-recipes-univariate/auto-ml-forecasting-univariate-recipe-run-experiment.ipynb

@@ -358,7 +358,8 @@
         "    enable_early_stopping=True,\n",
         "    training_data=train_dataset,\n",
         "    label_column_name=TARGET_COLNAME,\n",
-        "    n_cross_validations=5,\n",
+        "    n_cross_validations=\"auto\",  # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
+        "    cv_step_size=\"auto\",\n",
         "    verbosity=logging.INFO,\n",
         "    max_cores_per_iteration=-1,\n",
         "    compute_target=compute_target,\n",
@@ -571,9 +572,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {
@@ -585,7 +586,12 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.9"
+      "version": "3.8.5"
+    },
+    "vscode": {
+      "interpreter": {
+        "hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
+      }
     }
   },
   "nbformat": 4,

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

@@ -870,9 +870,9 @@
     "friendly_name": "Classification of credit card fraudulent transactions using Automated ML",
     "index_order": 5,
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -859,8 +859,8 @@
       "outputs": [],
       "source": [
         "%matplotlib inline\n",
-        "test_pred = plt.scatter(y_test, y_pred_test, color=\"\")\n",
-        "test_test = plt.scatter(y_test, y_test, color=\"g\")\n",
+        "test_pred = plt.scatter(y_test, y_pred_test, c=[\"b\"])\n",
+        "test_test = plt.scatter(y_test, y_test, c=[\"g\"])\n",
         "plt.legend(\n",
         "    (test_pred, test_test), (\"prediction\", \"truth\"), loc=\"upper left\", fontsize=8\n",
         ")\n",
@@ -895,9 +895,9 @@
     "friendly_name": "Automated ML run with featurization and model explainability.",
     "index_order": 5,
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -422,8 +422,8 @@
       "outputs": [],
       "source": [
         "%matplotlib inline\n",
-        "test_pred = plt.scatter(y_test, y_pred_test, color=\"\")\n",
-        "test_test = plt.scatter(y_test, y_test, color=\"g\")\n",
+        "test_pred = plt.scatter(y_test, y_pred_test, c=[\"b\"])\n",
+        "test_test = plt.scatter(y_test, y_test, c=[\"g\"])\n",
         "plt.legend(\n",
         "    (test_pred, test_test), (\"prediction\", \"truth\"), loc=\"upper left\", fontsize=8\n",
         ")\n",
@@ -449,9 +449,9 @@
       "automated-machine-learning"
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -429,9 +429,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -557,9 +557,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

how-to-use-azureml/azure-synapse/Synapse_Job_Scala_Support.ipynb

@@ -161,9 +161,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

how-to-use-azureml/azure-synapse/Synapse_Session_Scala_Support.ipynb

@@ -215,9 +215,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

how-to-use-azureml/azure-synapse/spark_job_on_synapse_spark_pool.ipynb

@@ -482,9 +482,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

how-to-use-azureml/azure-synapse/spark_session_on_synapse_spark_pool.ipynb

@@ -302,9 +302,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -86,7 +86,7 @@
       "source": [
         "In this example, we will be using and registering two models. \n",
         "\n",
-        "First we will train two simple models on the [diabetes dataset](https://scikit-learn.org/stable/datasets/index.html#diabetes-dataset) included with scikit-learn, serializing them to files in the current directory."
+        "First we will train two simple models on the [diabetes dataset](https://scikit-learn.org/stable/datasets/toy_dataset.html#diabetes-dataset) included with scikit-learn, serializing them to files in the current directory."
       ]
     },
     {
@@ -239,7 +239,7 @@
         "\n",
         "env = Environment(\"deploytocloudenv\")\n",
         "env.python.conda_dependencies.add_pip_package(\"joblib\")\n",
-        "env.python.conda_dependencies.add_pip_package(\"numpy\")\n",
+        "env.python.conda_dependencies.add_pip_package(\"numpy==1.23\")\n",
         "env.python.conda_dependencies.add_pip_package(\"scikit-learn=={}\".format(sklearn.__version__))"
       ]
     },
@@ -373,9 +373,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -285,7 +285,7 @@
         "    'azureml-defaults',\n",
         "    'inference-schema[numpy-support]',\n",
         "    'joblib',\n",
-        "    'numpy',\n",
+        "    'numpy==1.23',\n",
         "    'scikit-learn=={}'.format(sklearn.__version__)\n",
         "])"
       ]
@@ -486,7 +486,7 @@
         "    'azureml-defaults',\n",
         "    'inference-schema[numpy-support]',\n",
         "    'joblib',\n",
-        "    'numpy',\n",
+        "    'numpy==1.23',\n",
         "    'scikit-learn=={}'.format(sklearn.__version__)\n",
         "])\n",
         "inference_config = InferenceConfig(entry_script='score.py', environment=environment)\n",
@@ -541,7 +541,7 @@
         " - To run a local web service, see the [notebook on deployment to a local Docker container](../deploy-to-local/register-model-deploy-local.ipynb).\n",
         " - For more information on datasets, see the [notebook on training with datasets](../../work-with-data/datasets-tutorial/train-with-datasets/train-with-datasets.ipynb).\n",
         " - For more information on environments, see the [notebook on using environments](../../training/using-environments/using-environments.ipynb).\n",
-        " - For information on all the available deployment targets, see [“How and where to deploy models”](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-deploy-and-where#choose-a-compute-target)."
+        " - For information on all the available deployment targets, see [“How and where to deploy models”](https://docs.microsoft.com/azure/machine-learning/v1/how-to-deploy-and-where#choose-a-compute-target)."
       ]
     }
   ],
@@ -568,9 +568,9 @@
     "friendly_name": "Register model and deploy as webservice",
     "index_order": 3,
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -473,9 +473,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -529,9 +529,9 @@
     "friendly_name": "Register a model and deploy locally",
     "index_order": 1,
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

how-to-use-azureml/deployment/deploy-with-controlled-rollout/deploy-aks-with-controlled-rollout.ipynb

@@ -110,7 +110,7 @@
         "    pip_packages=[\n",
         "    'azureml-defaults',\n",
         "    'inference-schema[numpy-support]',\n",
-        "    'numpy',\n",
+        "    'numpy==1.23',\n",
         "    'scikit-learn==0.22.1',\n",
         "    'scipy'\n",
         "])"
@@ -344,9 +344,9 @@
     "friendly_name": "Deploy models to AKS using controlled roll out",
     "index_order": 3,
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -476,9 +476,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -405,9 +405,9 @@
     "friendly_name": "Convert and deploy TinyYolo with ONNX Runtime",
     "index_order": 5,
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -773,9 +773,9 @@
     "friendly_name": "Deploy Facial Expression Recognition (FER+) with ONNX Runtime",
     "index_order": 2,
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -750,9 +750,9 @@
     "friendly_name": "Deploy MNIST digit recognition with ONNX Runtime",
     "index_order": 1,
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -206,9 +206,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -389,9 +389,9 @@
     "friendly_name": "Deploy ResNet50 with ONNX Runtime",
     "index_order": 4,
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -564,9 +564,9 @@
     "friendly_name": "Train MNIST in PyTorch, convert, and deploy with ONNX Runtime",
     "index_order": 3,
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -240,9 +240,9 @@
         "# Please see [Azure ML Containers repository](https://github.com/Azure/AzureML-Containers#featured-tags)\n",
         "# for open-sourced GPU base images.\n",
         "env.docker.base_image = DEFAULT_GPU_IMAGE\n",
-        "env.python.conda_dependencies = CondaDependencies.create(python_version=\"3.6.2\", \n",
+        "env.python.conda_dependencies = CondaDependencies.create(python_version=\"3.6.2\", pin_sdk_version=False,\n",
         "                                    conda_packages=['tensorflow-gpu==1.12.0','numpy'],\n",
-        "                                    pip_packages=['azureml-contrib-services', 'azureml-defaults'])\n",
+        "                                    pip_packages=['azureml-contrib-services==1.47.0', 'azureml-defaults==1.47.0'])\n",
         "\n",
         "inference_config = InferenceConfig(entry_script=\"score.py\", environment=env)\n",
         "aks_config = AksWebservice.deploy_configuration()\n",
@@ -329,9 +329,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {
@@ -343,7 +343,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.6"
+      "version": "3.7.0"
     }
   },
   "nbformat": 4,

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

@@ -213,7 +213,7 @@
         "\n",
         "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
         "\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"
+        "See code snippet below. Check the documentation [here](https://docs.microsoft.com/azure/machine-learning/v1/how-to-secure-web-service) for more details"
       ]
     },
     {
@@ -334,9 +334,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

how-to-use-azureml/deployment/production-deploy-to-aks/production-deploy-to-aks-ssl.yml

@@ -5,4 +5,4 @@ dependencies:
   - matplotlib
   - tqdm
   - scipy
-  - sklearn
+  - scikit-learn

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

@@ -366,7 +366,7 @@
       "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."
+        "See code snippet below. Check the documentation [here](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-network-security-overview) for more details."
       ]
     },
     {
@@ -397,7 +397,7 @@
       "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"
+        "See code snippet below. Check the documentation [here](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-network-security-overview#secure-the-inferencing-environment-v1) for more details"
       ]
     },
     {
@@ -603,9 +603,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -5,4 +5,4 @@ dependencies:
   - matplotlib
   - tqdm
   - scipy
-  - sklearn
+  - scikit-learn

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

@@ -137,7 +137,7 @@
         "myenv = Environment('my-pyspark-environment')\r\n",
         "myenv.docker.base_image = \"mcr.microsoft.com/mmlspark/release:0.15\"\r\n",
         "myenv.inferencing_stack_version = \"latest\"\r\n",
-        "myenv.python.conda_dependencies = CondaDependencies.create(pip_packages=[\"azureml-core\",\"azureml-defaults\",\"azureml-telemetry\",\"azureml-train-restclients-hyperdrive\",\"azureml-train-core\"], python_version=\"3.6.2\")\r\n",
+        "myenv.python.conda_dependencies = CondaDependencies.create(pip_packages=[\"azureml-core\",\"azureml-defaults\",\"azureml-telemetry\",\"azureml-train-restclients-hyperdrive\",\"azureml-train-core\"], python_version=\"3.7.0\")\r\n",
         "myenv.python.conda_dependencies.add_channel(\"conda-forge\")\r\n",
         "myenv.spark.packages = [SparkPackage(\"com.microsoft.ml.spark\", \"mmlspark_2.11\", \"0.15\"), SparkPackage(\"com.microsoft.azure\", \"azure-storage\", \"2.0.0\"), SparkPackage(\"org.apache.hadoop\", \"hadoop-azure\", \"2.7.0\")]\r\n",
         "myenv.spark.repositories = [\"https://mmlspark.azureedge.net/maven\"]\r\n"
@@ -327,9 +327,9 @@
     ],
     "friendly_name": "Register Spark model and deploy as webservice",
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {
@@ -341,7 +341,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.2"
+      "version": "3.7.0"
     }
   },
   "nbformat": 4,

how-to-use-azureml/explain-model/azure-integration/gpu-explanation/train-explain-model-gpu-tree-explainer.ipynb

@@ -106,7 +106,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "print(\"This notebook was created using version 1.43.0 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version Latest of the Azure ML SDK\")\n",
         "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },
@@ -235,20 +235,30 @@
         "# Note: this is to pin the pandas and xgboost versions to be same as notebook.\n",
         "# In production scenario user would choose their dependencies\n",
         "import pkg_resources\n",
+        "from distutils.version import LooseVersion\n",
         "available_packages = pkg_resources.working_set\n",
-        "xgboost_ver = None\n",
         "pandas_ver = None\n",
+        "numpy_ver = None\n",
+        "sklearn_ver = None\n",
         "for dist in list(available_packages):\n",
-        "    if dist.key == 'xgboost':\n",
-        "        xgboost_ver = dist.version\n",
-        "    elif dist.key == 'pandas':\n",
+        "    if dist.key == 'pandas':\n",
         "       pandas_ver = dist.version\n",
-        "xgboost_dep = 'xgboost'\n",
+        "    if dist.key == 'numpy':\n",
+        "       if LooseVersion(dist.version) >= LooseVersion('1.20.0'):\n",
+        "           numpy_ver = dist.version\n",
+        "       else:\n",
+        "           numpy_ver = '1.21.6'\n",
+        "    if dist.key == 'scikit-learn':\n",
+        "        sklearn_ver = dist.version\n",
         "pandas_dep = 'pandas'\n",
+        "numpy_dep = 'numpy'\n",
+        "sklearn_dep = 'scikit-learn'\n",
         "if pandas_ver:\n",
         "    pandas_dep = 'pandas=={}'.format(pandas_ver)\n",
-        "if xgboost_dep:\n",
-        "    xgboost_dep = 'xgboost=={}'.format(xgboost_ver)\n",
+        "if numpy_ver:\n",
+        "    numpy_dep = 'numpy=={}'.format(numpy_ver)\n",
+        "if sklearn_ver:\n",
+        "    sklearn_dep = 'scikit-learn=={}'.format(sklearn_ver)\n",
         "\n",
         "# Note: we build shap at commit 690245 for Tesla K80 GPUs\n",
         "env.docker.base_dockerfile = f\"\"\"\n",
@@ -269,13 +279,12 @@
         "rm -f Miniconda3-latest-Linux-x86_64.sh && \\\n",
         "conda init bash && \\\n",
         ". ~/.bashrc && \\\n",
-        "conda create -n shapgpu python=3.7 && \\\n",
+        "conda create -n shapgpu python=3.8 && \\\n",
         "conda activate shapgpu && \\\n",
         "apt-get install -y g++ && \\\n",
         "printenv && \\\n",
         "echo \"which nvcc: \" && \\\n",
         "which nvcc && \\\n",
-        "pip install numpy==1.20.3 && \\\n",
         "pip install azureml-defaults && \\\n",
         "pip install azureml-telemetry && \\\n",
         "pip install azureml-interpret && \\\n",
@@ -287,7 +296,11 @@
         "mkdir build && \\\n",
         "python setup.py install --user && \\\n",
         "pip uninstall -y xgboost && \\\n",
-        "pip install {xgboost_dep} \\\n",
+        "conda install py-xgboost==1.3.3 && \\\n",
+        "pip uninstall -y numpy && \\\n",
+        "pip install {numpy_dep} && \\\n",
+        "pip install {sklearn_dep} && \\\n",
+        "pip install chardet \\\n",
         "\"\"\"\n",
         "\n",
         "env.python.user_managed_dependencies = True\n",
@@ -482,9 +495,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

how-to-use-azureml/explain-model/azure-integration/gpu-explanation/train-explain-model-gpu-tree-explainer.yml

@@ -7,12 +7,12 @@ dependencies:
   - flask
   - flask-cors
   - gevent>=1.3.6
-  - jinja2
   - ipython
   - matplotlib
   - ipywidgets
-  - raiwidgets~=0.19.0
+  - raiwidgets~=0.24.0
   - itsdangerous==2.0.1
   - markupsafe<2.1.0
   - scipy>=1.5.3
   - protobuf==3.20.0
+  - jinja2==3.0.3

how-to-use-azureml/explain-model/azure-integration/remote-explanation/explain-model-on-amlcompute.ipynb

@@ -269,23 +269,29 @@
         "available_packages = pkg_resources.working_set\n",
         "sklearn_ver = None\n",
         "pandas_ver = None\n",
+        "joblib_ver = None\n",
         "for dist in list(available_packages):\n",
         "    if dist.key == 'scikit-learn':\n",
         "        sklearn_ver = dist.version\n",
         "    elif dist.key == 'pandas':\n",
         "        pandas_ver = dist.version\n",
+        "    elif dist.key == 'joblib':\n",
+        "        joblib_ver = dist.version\n",
         "sklearn_dep = 'scikit-learn'\n",
         "pandas_dep = 'pandas'\n",
+        "joblib_dep = 'joblib'\n",
         "if sklearn_ver:\n",
         "    sklearn_dep = 'scikit-learn=={}'.format(sklearn_ver)\n",
         "if pandas_ver:\n",
         "    pandas_dep = 'pandas=={}'.format(pandas_ver)\n",
+        "if joblib_ver:\n",
+        "    joblib_dep = 'joblib=={}'.format(joblib_ver)\n",
         "# Specify CondaDependencies obj\n",
         "# The CondaDependencies specifies the conda and pip packages that are installed in the environment\n",
         "# the submitted job is run in.  Note the remote environment(s) needs to be similar to the local\n",
         "# environment, otherwise if a model is trained or deployed in a different environment this can\n",
         "# cause errors.  Please take extra care when specifying your dependencies in a production environment.\n",
-        "azureml_pip_packages.extend([sklearn_dep, pandas_dep])\n",
+        "azureml_pip_packages.extend([sklearn_dep, pandas_dep, joblib_dep])\n",
         "run_config.environment.python.conda_dependencies = CondaDependencies.create(pip_packages=azureml_pip_packages,  python_version=python_version)\n",
         "\n",
         "from azureml.core import ScriptRunConfig\n",
@@ -490,9 +496,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

how-to-use-azureml/explain-model/azure-integration/remote-explanation/explain-model-on-amlcompute.yml

@@ -6,13 +6,13 @@ dependencies:
   - flask
   - flask-cors
   - gevent>=1.3.6
-  - jinja2
   - ipython
   - matplotlib
   - azureml-dataset-runtime
   - ipywidgets
-  - raiwidgets~=0.19.0
+  - raiwidgets~=0.24.0
   - itsdangerous==2.0.1
   - markupsafe<2.1.0
   - scipy>=1.5.3
   - protobuf==3.20.0
+  - jinja2==3.0.3

how-to-use-azureml/explain-model/azure-integration/run-history/save-retrieve-explanations-run-history.ipynb

@@ -595,9 +595,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

how-to-use-azureml/explain-model/azure-integration/run-history/save-retrieve-explanations-run-history.yml

@@ -6,13 +6,13 @@ dependencies:
   - flask
   - flask-cors
   - gevent>=1.3.6
-  - jinja2
   - ipython
   - matplotlib
   - ipywidgets
-  - raiwidgets~=0.19.0
+  - raiwidgets~=0.24.0
   - packaging>=20.9
   - itsdangerous==2.0.1
   - markupsafe<2.1.0
   - scipy>=1.5.3
   - protobuf==3.20.0
+  - jinja2==3.0.3

how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-locally-and-deploy.ipynb

@@ -340,17 +340,29 @@
         "available_packages = pkg_resources.working_set\n",
         "sklearn_ver = None\n",
         "pandas_ver = None\n",
+        "numpy_ver = None\n",
+        "numba_ver = None\n",
         "for dist in available_packages:\n",
         "    if dist.key == 'scikit-learn':\n",
         "        sklearn_ver = dist.version\n",
+        "    elif dist.key == 'numpy':\n",
+        "        numpy_ver = dist.version\n",
+        "    elif dist.key == 'numba':\n",
+        "        numba_ver = dist.version\n",
         "    elif dist.key == 'pandas':\n",
         "        pandas_ver = dist.version\n",
         "sklearn_dep = 'scikit-learn'\n",
         "pandas_dep = 'pandas'\n",
+        "numpy_dep = 'numpy'\n",
+        "numba_dep = 'numba'\n",
         "if sklearn_ver:\n",
         "    sklearn_dep = 'scikit-learn=={}'.format(sklearn_ver)\n",
         "if pandas_ver:\n",
         "    pandas_dep = 'pandas=={}'.format(pandas_ver)\n",
+        "if numpy_ver:\n",
+        "    numpy_dep = 'numpy=={}'.format(numpy_ver)\n",
+        "if numba_ver:\n",
+        "    numba_dep = 'numba=={}'.format(numba_ver)\n",
         "# Specify CondaDependencies obj\n",
         "# The CondaDependencies specifies the conda and pip packages that are installed in the environment\n",
         "# the submitted job is run in.  Note the remote environment(s) needs to be similar to the local\n",
@@ -358,8 +370,8 @@
         "# cause errors.  Please take extra care when specifying your dependencies in a production environment.\n",
         "myenv = CondaDependencies.create(\n",
         "    python_version=python_version,\n",
-        "    conda_packages=['pip==20.2.4'],\n",
-        "    pip_packages=['pyyaml', sklearn_dep, pandas_dep] + azureml_pip_packages)\n",
+        "    conda_packages=['pip==20.2.4', numpy_dep],\n",
+        "    pip_packages=['pyyaml', sklearn_dep, pandas_dep, numba_dep] + azureml_pip_packages)\n",
         "\n",
         "with open(\"myenv.yml\",\"w\") as f:\n",
         "    f.write(myenv.serialize_to_string())\n",
@@ -504,9 +516,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-locally-and-deploy.yml

@@ -6,13 +6,13 @@ dependencies:
   - flask
   - flask-cors
   - gevent>=1.3.6
-  - jinja2
   - ipython
   - matplotlib
   - ipywidgets
-  - raiwidgets~=0.19.0
+  - raiwidgets~=0.24.0
   - packaging>=20.9
   - itsdangerous==2.0.1
   - markupsafe<2.1.0
   - scipy>=1.5.3
   - protobuf==3.20.0
+  - jinja2==3.0.3

how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-on-amlcompute-and-deploy.ipynb

@@ -277,23 +277,29 @@
         "available_packages = pkg_resources.working_set\n",
         "sklearn_ver = None\n",
         "pandas_ver = None\n",
+        "joblib_ver = None\n",
         "for dist in available_packages:\n",
         "    if dist.key == 'scikit-learn':\n",
         "        sklearn_ver = dist.version\n",
         "    elif dist.key == 'pandas':\n",
         "        pandas_ver = dist.version\n",
+        "    elif dist.key == 'joblib':\n",
+        "        joblib_ver = dist.version\n",
         "sklearn_dep = 'scikit-learn'\n",
         "pandas_dep = 'pandas'\n",
+        "joblib_dep = 'joblib'\n",
         "if sklearn_ver:\n",
         "    sklearn_dep = 'scikit-learn=={}'.format(sklearn_ver)\n",
         "if pandas_ver:\n",
         "    pandas_dep = 'pandas=={}'.format(pandas_ver)\n",
+        "if joblib_ver:\n",
+        "    joblib_dep = 'joblib=={}'.format(joblib_ver)\n",
         "# Specify CondaDependencies obj\n",
         "# The CondaDependencies specifies the conda and pip packages that are installed in the environment\n",
         "# the submitted job is run in.  Note the remote environment(s) needs to be similar to the local\n",
         "# environment, otherwise if a model is trained or deployed in a different environment this can\n",
         "# cause errors.  Please take extra care when specifying your dependencies in a production environment.\n",
-        "azureml_pip_packages.extend(['pyyaml', sklearn_dep, pandas_dep])\n",
+        "azureml_pip_packages.extend(['pyyaml', sklearn_dep, pandas_dep, joblib_dep])\n",
         "run_config.environment.python.conda_dependencies = CondaDependencies.create(\n",
         "    python_version=python_version,\n",
         "    pip_packages=azureml_pip_packages)\n",
@@ -440,23 +446,29 @@
         "available_packages = pkg_resources.working_set\n",
         "sklearn_ver = None\n",
         "pandas_ver = None\n",
+        "joblib_ver = None\n",
         "for dist in available_packages:\n",
         "    if dist.key == 'scikit-learn':\n",
         "        sklearn_ver = dist.version\n",
         "    elif dist.key == 'pandas':\n",
         "        pandas_ver = dist.version\n",
+        "    elif dist.key == 'joblib':\n",
+        "        joblib_ver = dist.version\n",
         "sklearn_dep = 'scikit-learn'\n",
         "pandas_dep = 'pandas'\n",
+        "joblib_dep = 'joblib'\n",
         "if sklearn_ver:\n",
         "    sklearn_dep = 'scikit-learn=={}'.format(sklearn_ver)\n",
         "if pandas_ver:\n",
         "    pandas_dep = 'pandas=={}'.format(pandas_ver)\n",
+        "if joblib_ver:\n",
+        "    joblib_dep = 'joblib=={}'.format(joblib_ver)\n",
         "# Specify CondaDependencies obj\n",
         "# The CondaDependencies specifies the conda and pip packages that are installed in the environment\n",
         "# the submitted job is run in.  Note the remote environment(s) needs to be similar to the local\n",
         "# environment, otherwise if a model is trained or deployed in a different environment this can\n",
         "# cause errors.  Please take extra care when specifying your dependencies in a production environment.\n",
-        "azureml_pip_packages.extend(['pyyaml', sklearn_dep, pandas_dep])\n",
+        "azureml_pip_packages.extend(['pyyaml', sklearn_dep, pandas_dep, joblib_dep])\n",
         "myenv = CondaDependencies.create(python_version=python_version, pip_packages=azureml_pip_packages)\n",
         "\n",
         "with open(\"myenv.yml\",\"w\") as f:\n",
@@ -564,9 +576,9 @@
       }
     ],
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-on-amlcompute-and-deploy.yml

@@ -6,14 +6,14 @@ dependencies:
   - flask
   - flask-cors
   - gevent>=1.3.6
-  - jinja2
   - ipython
   - matplotlib
   - azureml-dataset-runtime
   - azureml-core
   - ipywidgets
-  - raiwidgets~=0.19.0
+  - raiwidgets~=0.24.0
   - itsdangerous==2.0.1
   - markupsafe<2.1.0
   - scipy>=1.5.3
   - protobuf==3.20.0
+  - jinja2==3.0.3

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

@@ -579,9 +579,9 @@
     ],
     "friendly_name": "Azure Machine Learning Pipeline with DataTranferStep",
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -632,9 +632,9 @@
     ],
     "friendly_name": "Getting Started with Azure Machine Learning Pipelines",
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -384,9 +384,9 @@
     ],
     "friendly_name": "Azure Machine Learning Pipeline with AzureBatchStep",
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -470,9 +470,9 @@
     ],
     "friendly_name": "How to use ModuleStep with AML Pipelines",
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -261,9 +261,9 @@
     ],
     "friendly_name": "How to use Pipeline Drafts to create a Published Pipeline",
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {

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

@@ -292,7 +292,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "tf_env = Environment.get(ws, name='AzureML-TensorFlow-2.0-GPU')"
+        "tf_env = Environment.get(ws, name='AzureML-tensorflow-2.6-ubuntu20.04-py38-cuda11-gpu')"
       ]
     },
     {
@@ -595,9 +595,9 @@
     ],
     "friendly_name": "Azure Machine Learning Pipeline with HyperDriveStep",
     "kernelspec": {
-      "display_name": "Python 3.6",
+      "display_name": "Python 3.8 - AzureML",
       "language": "python",
-      "name": "python36"
+      "name": "python38-azureml"
     },
     "language_info": {
       "codemirror_mode": {