mirror of
https://github.com/Azure/MachineLearningNotebooks.git
synced 2025-12-20 09:37:04 -05:00
Compare commits
1 Commits
master
...
release_up
| Author | SHA1 | Date | |
|---|---|---|---|
|
584ed9ae74 |
@@ -4,10 +4,6 @@ This repository contains example notebooks demonstrating the [Azure Machine Lear
|
||||
|
||||
|
||||
|
||||
## News
|
||||
|
||||
* [Try Azure Machine Learning with MLflow](./how-to-use-azureml/using-mlflow)
|
||||
|
||||
## Quick installation
|
||||
```sh
|
||||
pip install azureml-sdk
|
||||
@@ -56,7 +52,6 @@ The [How to use Azure ML](./how-to-use-azureml) folder contains specific example
|
||||
|
||||
Visit following repos to see projects contributed by Azure ML users:
|
||||
|
||||
- [AMLSamples](https://github.com/Azure/AMLSamples) Number of end-to-end examples, including face recognition, predictive maintenance, customer churn and sentiment analysis.
|
||||
- [Fine tune natural language processing models using Azure Machine Learning service](https://github.com/Microsoft/AzureML-BERT)
|
||||
- [Fashion MNIST with Azure ML SDK](https://github.com/amynic/azureml-sdk-fashion)
|
||||
|
||||
|
||||
@@ -103,7 +103,7 @@
|
||||
"source": [
|
||||
"import azureml.core\n",
|
||||
"\n",
|
||||
"print(\"This notebook was created using version 1.0.43 of the Azure ML SDK\")\n",
|
||||
"print(\"This notebook was created using version of the Azure ML SDK\")\n",
|
||||
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
|
||||
]
|
||||
},
|
||||
|
||||
4
configuration.yml
Normal file
4
configuration.yml
Normal file
@@ -0,0 +1,4 @@
|
||||
name: configuration
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
@@ -20,7 +20,7 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The [RAPIDS](https://www.developer.nvidia.com/rapids) suite of software libraries from NVIDIA enables the execution of end-to-end data science and analytics pipelines entirely on GPUs. In many machine learning projects, a significant portion of the model training time is spent in setting up the data; this stage of the process is known as Extraction, Transformation and Loading, or ETL. By using the DataFrame API for ETLÂ and GPU-capable ML algorithms in RAPIDS, data preparation and training models can be done in GPU-accelerated end-to-end pipelines without incurring serialization costs between the pipeline stages. This notebook demonstrates how to use NVIDIA RAPIDS to prepare data and train model in Azure.\n",
|
||||
"The [RAPIDS](https://www.developer.nvidia.com/rapids) suite of software libraries from NVIDIA enables the execution of end-to-end data science and analytics pipelines entirely on GPUs. In many machine learning projects, a significant portion of the model training time is spent in setting up the data; this stage of the process is known as Extraction, Transformation and Loading, or ETL. By using the DataFrame API for ETL\u00c3\u201a\u00c2\u00a0and GPU-capable ML algorithms in RAPIDS, data preparation and training models can be done in GPU-accelerated end-to-end pipelines without incurring serialization costs between the pipeline stages. This notebook demonstrates how to use NVIDIA RAPIDS to prepare data and train model\u00c2\u00a0in Azure.\n",
|
||||
" \n",
|
||||
"In this notebook, we will do the following:\n",
|
||||
" \n",
|
||||
|
||||
709
contrib/datadrift/azure-ml-datadrift.ipynb
Normal file
709
contrib/datadrift/azure-ml-datadrift.ipynb
Normal file
@@ -0,0 +1,709 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Track Data Drift between Training and Inference Data in Production \n",
|
||||
"\n",
|
||||
"With this notebook, you will learn how to enable the DataDrift service to automatically track and determine whether your inference data is drifting from the data your model was initially trained on. The DataDrift service provides metrics and visualizations to help stakeholders identify which specific features cause the concept drift to occur.\n",
|
||||
"\n",
|
||||
"Please email driftfeedback@microsoft.com with any issues. A member from the DataDrift team will respond shortly. \n",
|
||||
"\n",
|
||||
"The DataDrift Public Preview API can be found [here](https://docs.microsoft.com/en-us/python/api/azureml-contrib-datadrift/?view=azure-ml-py). "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Prerequisites and Setup"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Install the DataDrift package\n",
|
||||
"\n",
|
||||
"Install the azureml-contrib-datadrift, azureml-contrib-opendatasets and lightgbm packages before running this notebook.\n",
|
||||
"```\n",
|
||||
"pip install azureml-contrib-datadrift\n",
|
||||
"pip install azureml-contrib-datasets\n",
|
||||
"pip install lightgbm\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Import Dependencies"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import json\n",
|
||||
"import os\n",
|
||||
"import time\n",
|
||||
"from datetime import datetime, timedelta\n",
|
||||
"\n",
|
||||
"import numpy as np\n",
|
||||
"import pandas as pd\n",
|
||||
"import requests\n",
|
||||
"from azureml.contrib.datadrift import DataDriftDetector, AlertConfiguration\n",
|
||||
"from azureml.contrib.opendatasets import NoaaIsdWeather\n",
|
||||
"from azureml.core import Dataset, Workspace, Run\n",
|
||||
"from azureml.core.compute import AksCompute, ComputeTarget\n",
|
||||
"from azureml.core.conda_dependencies import CondaDependencies\n",
|
||||
"from azureml.core.experiment import Experiment\n",
|
||||
"from azureml.core.image import ContainerImage\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"from azureml.core.webservice import Webservice, AksWebservice\n",
|
||||
"from azureml.widgets import RunDetails\n",
|
||||
"from sklearn.externals import joblib\n",
|
||||
"from sklearn.model_selection import train_test_split\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Set up Configuraton and Create Azure ML Workspace\n",
|
||||
"\n",
|
||||
"If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, go through the [configuration notebook](../../../configuration.ipynb) first if you haven't already to establish your connection to the AzureML Workspace."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Please type in your initials/alias. The prefix is prepended to the names of resources created by this notebook. \n",
|
||||
"prefix = \"dd\"\n",
|
||||
"\n",
|
||||
"# NOTE: Please do not change the model_name, as it's required by the score.py file\n",
|
||||
"model_name = \"driftmodel\"\n",
|
||||
"image_name = \"{}driftimage\".format(prefix)\n",
|
||||
"service_name = \"{}driftservice\".format(prefix)\n",
|
||||
"\n",
|
||||
"# optionally, set email address to receive an email alert for DataDrift\n",
|
||||
"email_address = \"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Generate Train/Testing Data\n",
|
||||
"\n",
|
||||
"For this demo, we will use NOAA weather data from [Azure Open Datasets](https://azure.microsoft.com/services/open-datasets/). You may replace this step with your own dataset. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"usaf_list = ['725724', '722149', '723090', '722159', '723910', '720279',\n",
|
||||
" '725513', '725254', '726430', '720381', '723074', '726682',\n",
|
||||
" '725486', '727883', '723177', '722075', '723086', '724053',\n",
|
||||
" '725070', '722073', '726060', '725224', '725260', '724520',\n",
|
||||
" '720305', '724020', '726510', '725126', '722523', '703333',\n",
|
||||
" '722249', '722728', '725483', '722972', '724975', '742079',\n",
|
||||
" '727468', '722193', '725624', '722030', '726380', '720309',\n",
|
||||
" '722071', '720326', '725415', '724504', '725665', '725424',\n",
|
||||
" '725066']\n",
|
||||
"\n",
|
||||
"columns = ['usaf', 'wban', 'datetime', 'latitude', 'longitude', 'elevation', 'windAngle', 'windSpeed', 'temperature', 'stationName', 'p_k']\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def enrich_weather_noaa_data(noaa_df):\n",
|
||||
" hours_in_day = 23\n",
|
||||
" week_in_year = 52\n",
|
||||
" \n",
|
||||
" noaa_df[\"hour\"] = noaa_df[\"datetime\"].dt.hour\n",
|
||||
" noaa_df[\"weekofyear\"] = noaa_df[\"datetime\"].dt.week\n",
|
||||
" \n",
|
||||
" noaa_df[\"sine_weekofyear\"] = noaa_df['datetime'].transform(lambda x: np.sin((2*np.pi*x.dt.week-1)/week_in_year))\n",
|
||||
" noaa_df[\"cosine_weekofyear\"] = noaa_df['datetime'].transform(lambda x: np.cos((2*np.pi*x.dt.week-1)/week_in_year))\n",
|
||||
"\n",
|
||||
" noaa_df[\"sine_hourofday\"] = noaa_df['datetime'].transform(lambda x: np.sin(2*np.pi*x.dt.hour/hours_in_day))\n",
|
||||
" noaa_df[\"cosine_hourofday\"] = noaa_df['datetime'].transform(lambda x: np.cos(2*np.pi*x.dt.hour/hours_in_day))\n",
|
||||
" \n",
|
||||
" return noaa_df\n",
|
||||
"\n",
|
||||
"def add_window_col(input_df):\n",
|
||||
" shift_interval = pd.Timedelta('-7 days') # your X days interval\n",
|
||||
" df_shifted = input_df.copy()\n",
|
||||
" df_shifted['datetime'] = df_shifted['datetime'] - shift_interval\n",
|
||||
" df_shifted.drop(list(input_df.columns.difference(['datetime', 'usaf', 'wban', 'sine_hourofday', 'temperature'])), axis=1, inplace=True)\n",
|
||||
"\n",
|
||||
" # merge, keeping only observations where -1 lag is present\n",
|
||||
" df2 = pd.merge(input_df,\n",
|
||||
" df_shifted,\n",
|
||||
" on=['datetime', 'usaf', 'wban', 'sine_hourofday'],\n",
|
||||
" how='inner', # use 'left' to keep observations without lags\n",
|
||||
" suffixes=['', '-7'])\n",
|
||||
" return df2\n",
|
||||
"\n",
|
||||
"def get_noaa_data(start_time, end_time, cols, station_list):\n",
|
||||
" isd = NoaaIsdWeather(start_time, end_time, cols=cols)\n",
|
||||
" # Read into Pandas data frame.\n",
|
||||
" noaa_df = isd.to_pandas_dataframe()\n",
|
||||
" noaa_df = noaa_df.rename(columns={\"stationName\": \"station_name\"})\n",
|
||||
" \n",
|
||||
" df_filtered = noaa_df[noaa_df[\"usaf\"].isin(station_list)]\n",
|
||||
" df_filtered.reset_index(drop=True)\n",
|
||||
" \n",
|
||||
" # Enrich with time features\n",
|
||||
" df_enriched = enrich_weather_noaa_data(df_filtered)\n",
|
||||
" \n",
|
||||
" return df_enriched\n",
|
||||
"\n",
|
||||
"def get_featurized_noaa_df(start_time, end_time, cols, station_list):\n",
|
||||
" df_1 = get_noaa_data(start_time - timedelta(days=7), start_time - timedelta(seconds=1), cols, station_list)\n",
|
||||
" df_2 = get_noaa_data(start_time, end_time, cols, station_list)\n",
|
||||
" noaa_df = pd.concat([df_1, df_2])\n",
|
||||
" \n",
|
||||
" print(\"Adding window feature\")\n",
|
||||
" df_window = add_window_col(noaa_df)\n",
|
||||
" \n",
|
||||
" cat_columns = df_window.dtypes == object\n",
|
||||
" cat_columns = cat_columns[cat_columns == True]\n",
|
||||
" \n",
|
||||
" print(\"Encoding categorical columns\")\n",
|
||||
" df_encoded = pd.get_dummies(df_window, columns=cat_columns.keys().tolist())\n",
|
||||
" \n",
|
||||
" print(\"Dropping unnecessary columns\")\n",
|
||||
" df_featurized = df_encoded.drop(['windAngle', 'windSpeed', 'datetime', 'elevation'], axis=1).dropna().drop_duplicates()\n",
|
||||
" \n",
|
||||
" return df_featurized"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Train model on Jan 1 - 14, 2009 data\n",
|
||||
"df = get_featurized_noaa_df(datetime(2009, 1, 1), datetime(2009, 1, 14, 23, 59, 59), columns, usaf_list)\n",
|
||||
"df.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"label = \"temperature\"\n",
|
||||
"x_df = df.drop(label, axis=1)\n",
|
||||
"y_df = df[[label]]\n",
|
||||
"x_train, x_test, y_train, y_test = train_test_split(df, y_df, test_size=0.2, random_state=223)\n",
|
||||
"print(x_train.shape, x_test.shape, y_train.shape, y_test.shape)\n",
|
||||
"\n",
|
||||
"training_dir = 'outputs/training'\n",
|
||||
"training_file = \"training.csv\"\n",
|
||||
"\n",
|
||||
"# Generate training dataframe to register as Training Dataset\n",
|
||||
"os.makedirs(training_dir, exist_ok=True)\n",
|
||||
"training_df = pd.merge(x_train.drop(label, axis=1), y_train, left_index=True, right_index=True)\n",
|
||||
"training_df.to_csv(training_dir + \"/\" + training_file)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Create/Register Training Dataset"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"dataset_name = \"dataset\"\n",
|
||||
"name_suffix = datetime.utcnow().strftime(\"%Y-%m-%d-%H-%M-%S\")\n",
|
||||
"snapshot_name = \"snapshot-{}\".format(name_suffix)\n",
|
||||
"\n",
|
||||
"dstore = ws.get_default_datastore()\n",
|
||||
"dstore.upload(training_dir, \"data/training\", show_progress=True)\n",
|
||||
"dpath = dstore.path(\"data/training/training.csv\")\n",
|
||||
"trainingDataset = Dataset.auto_read_files(dpath, include_path=True)\n",
|
||||
"trainingDataset = trainingDataset.register(workspace=ws, name=dataset_name, description=\"dset\", exist_ok=True)\n",
|
||||
"\n",
|
||||
"trainingDataSnapshot = trainingDataset.create_snapshot(snapshot_name=snapshot_name, compute_target=None, create_data_snapshot=True)\n",
|
||||
"datasets = [(Dataset.Scenario.TRAINING, trainingDataSnapshot)]\n",
|
||||
"print(\"dataset registration done.\\n\")\n",
|
||||
"datasets"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Train and Save Model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import lightgbm as lgb\n",
|
||||
"\n",
|
||||
"train = lgb.Dataset(data=x_train, \n",
|
||||
" label=y_train)\n",
|
||||
"\n",
|
||||
"test = lgb.Dataset(data=x_test, \n",
|
||||
" label=y_test,\n",
|
||||
" reference=train)\n",
|
||||
"\n",
|
||||
"params = {'learning_rate' : 0.1,\n",
|
||||
" 'boosting' : 'gbdt',\n",
|
||||
" 'metric' : 'rmse',\n",
|
||||
" 'feature_fraction' : 1,\n",
|
||||
" 'bagging_fraction' : 1,\n",
|
||||
" 'max_depth': 6,\n",
|
||||
" 'num_leaves' : 31,\n",
|
||||
" 'objective' : 'regression',\n",
|
||||
" 'bagging_freq' : 1,\n",
|
||||
" \"verbose\": -1,\n",
|
||||
" 'min_data_per_leaf': 100}\n",
|
||||
"\n",
|
||||
"model = lgb.train(params, \n",
|
||||
" num_boost_round=500,\n",
|
||||
" train_set=train,\n",
|
||||
" valid_sets=[train, test],\n",
|
||||
" verbose_eval=50,\n",
|
||||
" early_stopping_rounds=25)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"model_file = 'outputs/{}.pkl'.format(model_name)\n",
|
||||
"\n",
|
||||
"os.makedirs('outputs', exist_ok=True)\n",
|
||||
"joblib.dump(model, model_file)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Register Model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"model = Model.register(model_path=model_file,\n",
|
||||
" model_name=model_name,\n",
|
||||
" workspace=ws,\n",
|
||||
" datasets=datasets)\n",
|
||||
"\n",
|
||||
"print(model_name, image_name, service_name, model)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Deploy Model To AKS"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Prepare Environment"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn', 'joblib', 'lightgbm', 'pandas'],\n",
|
||||
" pip_packages=['azureml-monitoring', 'azureml-sdk[automl]'])\n",
|
||||
"\n",
|
||||
"with open(\"myenv.yml\",\"w\") as f:\n",
|
||||
" f.write(myenv.serialize_to_string())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Create Image"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Image creation may take up to 15 minutes.\n",
|
||||
"\n",
|
||||
"image_name = image_name + str(model.version)\n",
|
||||
"\n",
|
||||
"if not image_name in ws.images:\n",
|
||||
" # Use the score.py defined in this directory as the execution script\n",
|
||||
" # NOTE: The Model Data Collector must be enabled in the execution script for DataDrift to run correctly\n",
|
||||
" image_config = ContainerImage.image_configuration(execution_script=\"score.py\",\n",
|
||||
" runtime=\"python\",\n",
|
||||
" conda_file=\"myenv.yml\",\n",
|
||||
" description=\"Image with weather dataset model\")\n",
|
||||
" image = ContainerImage.create(name=image_name,\n",
|
||||
" models=[model],\n",
|
||||
" image_config=image_config,\n",
|
||||
" workspace=ws)\n",
|
||||
"\n",
|
||||
" image.wait_for_creation(show_output=True)\n",
|
||||
"else:\n",
|
||||
" image = ws.images[image_name]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Create Compute Target"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"aks_name = 'dd-demo-e2e'\n",
|
||||
"prov_config = AksCompute.provisioning_configuration()\n",
|
||||
"\n",
|
||||
"if not aks_name in ws.compute_targets:\n",
|
||||
" aks_target = ComputeTarget.create(workspace=ws,\n",
|
||||
" name=aks_name,\n",
|
||||
" provisioning_configuration=prov_config)\n",
|
||||
"\n",
|
||||
" aks_target.wait_for_completion(show_output=True)\n",
|
||||
" print(aks_target.provisioning_state)\n",
|
||||
" print(aks_target.provisioning_errors)\n",
|
||||
"else:\n",
|
||||
" aks_target=ws.compute_targets[aks_name]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Deploy Service"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"aks_service_name = service_name\n",
|
||||
"\n",
|
||||
"if not aks_service_name in ws.webservices:\n",
|
||||
" aks_config = AksWebservice.deploy_configuration(collect_model_data=True, enable_app_insights=True)\n",
|
||||
" aks_service = Webservice.deploy_from_image(workspace=ws,\n",
|
||||
" name=aks_service_name,\n",
|
||||
" image=image,\n",
|
||||
" deployment_config=aks_config,\n",
|
||||
" deployment_target=aks_target)\n",
|
||||
" aks_service.wait_for_deployment(show_output=True)\n",
|
||||
" print(aks_service.state)\n",
|
||||
"else:\n",
|
||||
" aks_service = ws.webservices[aks_service_name]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Run DataDrift Analysis"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Send Scoring Data to Service"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Download Scoring Data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Score Model on March 15, 2016 data\n",
|
||||
"scoring_df = get_noaa_data(datetime(2016, 3, 15) - timedelta(days=7), datetime(2016, 3, 16), columns, usaf_list)\n",
|
||||
"# Add the window feature column\n",
|
||||
"scoring_df = add_window_col(scoring_df)\n",
|
||||
"\n",
|
||||
"# Drop features not used by the model\n",
|
||||
"print(\"Dropping unnecessary columns\")\n",
|
||||
"scoring_df = scoring_df.drop(['windAngle', 'windSpeed', 'datetime', 'elevation'], axis=1).dropna()\n",
|
||||
"scoring_df.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# One Hot Encode the scoring dataset to match the training dataset schema\n",
|
||||
"columns_dict = model.datasets[\"training\"][0].get_profile().columns\n",
|
||||
"extra_cols = ('Path', 'Column1')\n",
|
||||
"for k in extra_cols:\n",
|
||||
" columns_dict.pop(k, None)\n",
|
||||
"training_columns = list(columns_dict.keys())\n",
|
||||
"\n",
|
||||
"categorical_columns = scoring_df.dtypes == object\n",
|
||||
"categorical_columns = categorical_columns[categorical_columns == True]\n",
|
||||
"\n",
|
||||
"test_df = pd.get_dummies(scoring_df[categorical_columns.keys().tolist()])\n",
|
||||
"encoded_df = scoring_df.join(test_df)\n",
|
||||
"\n",
|
||||
"# Populate missing OHE columns with 0 values to match traning dataset schema\n",
|
||||
"difference = list(set(training_columns) - set(encoded_df.columns.tolist()))\n",
|
||||
"for col in difference:\n",
|
||||
" encoded_df[col] = 0\n",
|
||||
"encoded_df.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Serialize dataframe to list of row dictionaries\n",
|
||||
"encoded_dict = encoded_df.to_dict('records')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Submit Scoring Data to Service"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"\n",
|
||||
"# retreive the API keys. AML generates two keys.\n",
|
||||
"key1, key2 = aks_service.get_keys()\n",
|
||||
"\n",
|
||||
"total_count = len(scoring_df)\n",
|
||||
"i = 0\n",
|
||||
"load = []\n",
|
||||
"for row in encoded_dict:\n",
|
||||
" load.append(row)\n",
|
||||
" i = i + 1\n",
|
||||
" if i % 100 == 0:\n",
|
||||
" payload = json.dumps({\"data\": load})\n",
|
||||
" \n",
|
||||
" # construct raw HTTP request and send to the service\n",
|
||||
" payload_binary = bytes(payload,encoding = 'utf8')\n",
|
||||
" headers = {'Content-Type':'application/json', 'Authorization': 'Bearer ' + key1}\n",
|
||||
" resp = requests.post(aks_service.scoring_uri, payload_binary, headers=headers)\n",
|
||||
" \n",
|
||||
" print(\"prediction:\", resp.content, \"Progress: {}/{}\".format(i, total_count)) \n",
|
||||
"\n",
|
||||
" load = []\n",
|
||||
" time.sleep(3)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Configure DataDrift"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"services = [service_name]\n",
|
||||
"start = datetime.now() - timedelta(days=2)\n",
|
||||
"end = datetime(year=2020, month=1, day=22, hour=15, minute=16)\n",
|
||||
"feature_list = ['usaf', 'wban', 'latitude', 'longitude', 'station_name', 'p_k', 'sine_hourofday', 'cosine_hourofday', 'temperature-7']\n",
|
||||
"alert_config = AlertConfiguration([email_address]) if email_address else None\n",
|
||||
"\n",
|
||||
"# there will be an exception indicating using get() method if DataDrift object already exist\n",
|
||||
"try:\n",
|
||||
" datadrift = DataDriftDetector.create(ws, model.name, model.version, services, frequency=\"Day\", alert_config=alert_config)\n",
|
||||
"except KeyError:\n",
|
||||
" datadrift = DataDriftDetector.get(ws, model.name, model.version)\n",
|
||||
" \n",
|
||||
"print(\"Details of DataDrift Object:\\n{}\".format(datadrift))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Run an Adhoc DataDriftDetector Run"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"target_date = datetime.today()\n",
|
||||
"run = datadrift.run(target_date, services, feature_list=feature_list, create_compute_target=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"exp = Experiment(ws, datadrift._id)\n",
|
||||
"dd_run = Run(experiment=exp, run_id=run)\n",
|
||||
"RunDetails(dd_run).show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Get Drift Analysis Results"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"children = list(dd_run.get_children())\n",
|
||||
"for child in children:\n",
|
||||
" child.wait_for_completion()\n",
|
||||
"\n",
|
||||
"drift_metrics = datadrift.get_output(start_time=start, end_time=end)\n",
|
||||
"drift_metrics"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Show all drift figures, one per serivice.\n",
|
||||
"# If setting with_details is False (by default), only drift will be shown; if it's True, all details will be shown.\n",
|
||||
"\n",
|
||||
"drift_figures = datadrift.show(with_details=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Enable DataDrift Schedule"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"datadrift.enable_schedule()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "rafarmah"
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
8
contrib/datadrift/azure-ml-datadrift.yml
Normal file
8
contrib/datadrift/azure-ml-datadrift.yml
Normal file
@@ -0,0 +1,8 @@
|
||||
name: azure-ml-datadrift
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-contrib-datadrift
|
||||
- azureml-contrib-opendatasets
|
||||
- lightgbm
|
||||
- azureml-widgets
|
||||
58
contrib/datadrift/score.py
Normal file
58
contrib/datadrift/score.py
Normal file
@@ -0,0 +1,58 @@
|
||||
import pickle
|
||||
import json
|
||||
import numpy
|
||||
import azureml.train.automl
|
||||
from sklearn.externals import joblib
|
||||
from sklearn.linear_model import Ridge
|
||||
from azureml.core.model import Model
|
||||
from azureml.core.run import Run
|
||||
from azureml.monitoring import ModelDataCollector
|
||||
import time
|
||||
import pandas as pd
|
||||
|
||||
|
||||
def init():
|
||||
global model, inputs_dc, prediction_dc, feature_names, categorical_features
|
||||
|
||||
print("Model is initialized" + time.strftime("%H:%M:%S"))
|
||||
model_path = Model.get_model_path(model_name="driftmodel")
|
||||
model = joblib.load(model_path)
|
||||
|
||||
feature_names = ["usaf", "wban", "latitude", "longitude", "station_name", "p_k",
|
||||
"sine_weekofyear", "cosine_weekofyear", "sine_hourofday", "cosine_hourofday",
|
||||
"temperature-7"]
|
||||
|
||||
categorical_features = ["usaf", "wban", "p_k", "station_name"]
|
||||
|
||||
inputs_dc = ModelDataCollector(model_name="driftmodel",
|
||||
identifier="inputs",
|
||||
feature_names=feature_names)
|
||||
|
||||
prediction_dc = ModelDataCollector("driftmodel",
|
||||
identifier="predictions",
|
||||
feature_names=["temperature"])
|
||||
|
||||
|
||||
def run(raw_data):
|
||||
global inputs_dc, prediction_dc
|
||||
|
||||
try:
|
||||
data = json.loads(raw_data)["data"]
|
||||
data = pd.DataFrame(data)
|
||||
|
||||
# Remove the categorical features as the model expects OHE values
|
||||
input_data = data.drop(categorical_features, axis=1)
|
||||
|
||||
result = model.predict(input_data)
|
||||
|
||||
# Collect the non-OHE dataframe
|
||||
collected_df = data[feature_names]
|
||||
|
||||
inputs_dc.collect(collected_df.values)
|
||||
prediction_dc.collect(result)
|
||||
return result.tolist()
|
||||
except Exception as e:
|
||||
error = str(e)
|
||||
|
||||
print(error + time.strftime("%H:%M:%S"))
|
||||
return error
|
||||
@@ -179,6 +179,26 @@ jupyter notebook
|
||||
- Simple example of using automated ML for classification with ONNX models
|
||||
- Uses local compute for training
|
||||
|
||||
- [auto-ml-bank-marketing-subscribers-with-deployment.ipynb](bank-marketing-subscribers-with-deployment/auto-ml-bank-marketing-with-deployment.ipynb)
|
||||
- Dataset: UCI's [bank marketing dataset](https://www.kaggle.com/janiobachmann/bank-marketing-dataset)
|
||||
- Simple example of using automated ML for classification to predict term deposit subscriptions for a bank
|
||||
- Uses azure compute for training
|
||||
|
||||
- [auto-ml-creditcard-with-deployment.ipynb](credit-card-fraud-detection-with-deployment/auto-ml-creditcard-with-deployment.ipynb)
|
||||
- Dataset: Kaggle's [credit card fraud detection dataset](https://www.kaggle.com/mlg-ulb/creditcardfraud)
|
||||
- Simple example of using automated ML for classification to fraudulent credit card transactions
|
||||
- Uses azure compute for training
|
||||
|
||||
- [auto-ml-hardware-performance-with-deployment.ipynb](hardware-performance-prediction-with-deployment/auto-ml-hardware-performance-with-deployment.ipynb)
|
||||
- Dataset: UCI's [computer hardware dataset](https://archive.ics.uci.edu/ml/datasets/Computer+Hardware)
|
||||
- Simple example of using automated ML for regression to predict the performance of certain combinations of hardware components
|
||||
- Uses azure compute for training
|
||||
|
||||
- [auto-ml-concrete-strength-with-deployment.ipynb](predicting-concrete-strength-with-deployment/auto-ml-concrete-strength-with-deployment.ipynb)
|
||||
- Dataset: UCI's [concrete compressive strength dataset](https://www.kaggle.com/pavanraj159/concrete-compressive-strength-data-set)
|
||||
- Simple example of using automated ML for regression to predict the strength predict the compressive strength of concrete based off of different ingredient combinations and quantities of those ingredients
|
||||
- Uses azure compute for training
|
||||
|
||||
<a name="documentation"></a>
|
||||
See [Configure automated machine learning experiments](https://docs.microsoft.com/azure/machine-learning/service/how-to-configure-auto-train) to learn how more about the the settings and features available for automated machine learning experiments.
|
||||
|
||||
|
||||
@@ -9,6 +9,8 @@ IF "%automl_env_file%"=="" SET automl_env_file="automl_env.yml"
|
||||
|
||||
IF NOT EXIST %automl_env_file% GOTO YmlMissing
|
||||
|
||||
IF "%CONDA_EXE%"=="" GOTO CondaMissing
|
||||
|
||||
call conda activate %conda_env_name% 2>nul:
|
||||
|
||||
if not errorlevel 1 (
|
||||
@@ -42,6 +44,15 @@ IF NOT "%options%"=="nolaunch" (
|
||||
|
||||
goto End
|
||||
|
||||
:CondaMissing
|
||||
echo Please run this script from an Anaconda Prompt window.
|
||||
echo You can start an Anaconda Prompt window by
|
||||
echo typing Anaconda Prompt on the Start menu.
|
||||
echo If you don't see the Anaconda Prompt app, install Miniconda.
|
||||
echo If you are running an older version of Miniconda or Anaconda,
|
||||
echo you can upgrade using the command: conda update conda
|
||||
goto End
|
||||
|
||||
:YmlMissing
|
||||
echo File %automl_env_file% not found.
|
||||
|
||||
|
||||
@@ -0,0 +1,729 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Automated Machine Learning\n",
|
||||
"_**Classification with Deployment using a Bank Marketing Dataset**_\n",
|
||||
"\n",
|
||||
"## Contents\n",
|
||||
"1. [Introduction](#Introduction)\n",
|
||||
"1. [Setup](#Setup)\n",
|
||||
"1. [Train](#Train)\n",
|
||||
"1. [Results](#Results)\n",
|
||||
"1. [Deploy](#Deploy)\n",
|
||||
"1. [Test](#Test)\n",
|
||||
"1. [Acknowledgements](#Acknowledgements)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Introduction\n",
|
||||
"\n",
|
||||
"In this example we use the UCI Bank Marketing dataset to showcase how you can use AutoML for a classification problem and deploy it to an Azure Container Instance (ACI). The classification goal is to predict if the client will subscribe to a term deposit with the bank.\n",
|
||||
"\n",
|
||||
"If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, go through the [configuration](../../../configuration.ipynb) notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
|
||||
"\n",
|
||||
"In this notebook you will learn how to:\n",
|
||||
"1. Create an experiment using an existing workspace.\n",
|
||||
"2. Configure AutoML using `AutoMLConfig`.\n",
|
||||
"3. Train the model using local compute.\n",
|
||||
"4. Explore the results.\n",
|
||||
"5. Register the model.\n",
|
||||
"6. Create a container image.\n",
|
||||
"7. Create an Azure Container Instance (ACI) service.\n",
|
||||
"8. Test the ACI service."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setup\n",
|
||||
"\n",
|
||||
"As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import json\n",
|
||||
"import logging\n",
|
||||
"\n",
|
||||
"from matplotlib import pyplot as plt\n",
|
||||
"import numpy as np\n",
|
||||
"import pandas as pd\n",
|
||||
"import os\n",
|
||||
"from sklearn import datasets\n",
|
||||
"import azureml.dataprep as dprep\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"\n",
|
||||
"import azureml.core\n",
|
||||
"from azureml.core.experiment import Experiment\n",
|
||||
"from azureml.core.workspace import Workspace\n",
|
||||
"from azureml.train.automl import AutoMLConfig\n",
|
||||
"from azureml.train.automl.run import AutoMLRun"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ws = Workspace.from_config()\n",
|
||||
"\n",
|
||||
"# choose a name for experiment\n",
|
||||
"experiment_name = 'automl-classification-bmarketing'\n",
|
||||
"# project folder\n",
|
||||
"project_folder = './sample_projects/automl-classification-bankmarketing'\n",
|
||||
"\n",
|
||||
"experiment=Experiment(ws, experiment_name)\n",
|
||||
"\n",
|
||||
"output = {}\n",
|
||||
"output['SDK version'] = azureml.core.VERSION\n",
|
||||
"output['Subscription ID'] = ws.subscription_id\n",
|
||||
"output['Workspace'] = ws.name\n",
|
||||
"output['Resource Group'] = ws.resource_group\n",
|
||||
"output['Location'] = ws.location\n",
|
||||
"output['Project Directory'] = project_folder\n",
|
||||
"output['Experiment Name'] = experiment.name\n",
|
||||
"pd.set_option('display.max_colwidth', -1)\n",
|
||||
"outputDf = pd.DataFrame(data = output, index = [''])\n",
|
||||
"outputDf.T"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Create or Attach existing AmlCompute\n",
|
||||
"You will need to create a compute target for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
|
||||
"#### Creation of AmlCompute takes approximately 5 minutes. \n",
|
||||
"If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
|
||||
"As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read this article on the default limits and how to request more quota."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.compute import AmlCompute\n",
|
||||
"from azureml.core.compute import ComputeTarget\n",
|
||||
"\n",
|
||||
"# Choose a name for your cluster.\n",
|
||||
"amlcompute_cluster_name = \"automlcl\"\n",
|
||||
"\n",
|
||||
"found = False\n",
|
||||
"# Check if this compute target already exists in the workspace.\n",
|
||||
"cts = ws.compute_targets\n",
|
||||
"if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
|
||||
" found = True\n",
|
||||
" print('Found existing compute target.')\n",
|
||||
" compute_target = cts[amlcompute_cluster_name]\n",
|
||||
" \n",
|
||||
"if not found:\n",
|
||||
" print('Creating a new compute target...')\n",
|
||||
" provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
|
||||
" #vm_priority = 'lowpriority', # optional\n",
|
||||
" max_nodes = 6)\n",
|
||||
"\n",
|
||||
" # Create the cluster.\n",
|
||||
" compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
|
||||
" \n",
|
||||
" # Can poll for a minimum number of nodes and for a specific timeout.\n",
|
||||
" # If no min_node_count is provided, it will use the scale settings for the cluster.\n",
|
||||
" compute_target.wait_for_completion(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
|
||||
" \n",
|
||||
" # For a more detailed view of current AmlCompute status, use get_status()."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Data\n",
|
||||
"\n",
|
||||
"Here load the data in the get_data() script to be utilized in azure compute. To do this first load all the necessary libraries and dependencies to set up paths for the data and to create the conda_Run_config."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if not os.path.isdir('data'):\n",
|
||||
" os.mkdir('data')\n",
|
||||
" \n",
|
||||
"if not os.path.exists(project_folder):\n",
|
||||
" os.makedirs(project_folder)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.runconfig import RunConfiguration\n",
|
||||
"from azureml.core.conda_dependencies import CondaDependencies\n",
|
||||
"\n",
|
||||
"# create a new RunConfig object\n",
|
||||
"conda_run_config = RunConfiguration(framework=\"python\")\n",
|
||||
"\n",
|
||||
"# Set compute target to AmlCompute\n",
|
||||
"conda_run_config.target = compute_target\n",
|
||||
"conda_run_config.environment.docker.enabled = True\n",
|
||||
"conda_run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy','py-xgboost<=0.80'])\n",
|
||||
"conda_run_config.environment.python.conda_dependencies = cd"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Load Data\n",
|
||||
"\n",
|
||||
"Here we create the script to be run in azure comput for loading the data, we load the bank marketing dataset into X_train and y_train. Next X_train and y_train is returned for training the model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_train.csv\"\n",
|
||||
"dflow = dprep.auto_read_file(data)\n",
|
||||
"dflow.get_profile()\n",
|
||||
"X_train = dflow.drop_columns(columns=['y'])\n",
|
||||
"y_train = dflow.keep_columns(columns=['y'], validate_column_exists=True)\n",
|
||||
"dflow.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Train\n",
|
||||
"\n",
|
||||
"Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
|
||||
"\n",
|
||||
"|Property|Description|\n",
|
||||
"|-|-|\n",
|
||||
"|**task**|classification or regression|\n",
|
||||
"|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
|
||||
"|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
|
||||
"|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
|
||||
"|**n_cross_validations**|Number of cross validation splits.|\n",
|
||||
"|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
|
||||
"|**y**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|\n",
|
||||
"|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|\n",
|
||||
"\n",
|
||||
"**_You can find more information about primary metrics_** [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#primary-metric)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"automl_settings = {\n",
|
||||
" \"iteration_timeout_minutes\": 5,\n",
|
||||
" \"iterations\": 10,\n",
|
||||
" \"n_cross_validations\": 2,\n",
|
||||
" \"primary_metric\": 'AUC_weighted',\n",
|
||||
" \"preprocess\": True,\n",
|
||||
" \"max_concurrent_iterations\": 5,\n",
|
||||
" \"verbosity\": logging.INFO,\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"automl_config = AutoMLConfig(task = 'classification',\n",
|
||||
" debug_log = 'automl_errors.log',\n",
|
||||
" path = project_folder,\n",
|
||||
" run_configuration=conda_run_config,\n",
|
||||
" X = X_train,\n",
|
||||
" y = y_train,\n",
|
||||
" **automl_settings\n",
|
||||
" )"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
|
||||
"In this example, we specify `show_output = True` to print currently running iterations to the console."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"remote_run = experiment.submit(automl_config, show_output = True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"remote_run"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Results"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Widget for Monitoring Runs\n",
|
||||
"\n",
|
||||
"The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
|
||||
"\n",
|
||||
"**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.widgets import RunDetails\n",
|
||||
"RunDetails(remote_run).show() "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Deploy\n",
|
||||
"\n",
|
||||
"### Retrieve the Best Model\n",
|
||||
"\n",
|
||||
"Below we select the best pipeline from our iterations. The `get_output` method on `automl_classifier` returns the best run and the fitted model for the last invocation. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"best_run, fitted_model = remote_run.get_output()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Register the Fitted Model for Deployment\n",
|
||||
"If neither `metric` nor `iteration` are specified in the `register_model` call, the iteration with the best primary metric is registered."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"description = 'AutoML Model trained on bank marketing data to predict if a client will subscribe to a term deposit'\n",
|
||||
"tags = None\n",
|
||||
"model = remote_run.register_model(description = description, tags = tags)\n",
|
||||
"\n",
|
||||
"print(remote_run.model_id) # This will be written to the script file later in the notebook."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create Scoring Script\n",
|
||||
"The scoring script is required to generate the image for deployment. It contains the code to do the predictions on input data."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import pickle\n",
|
||||
"import json\n",
|
||||
"import numpy\n",
|
||||
"import azureml.train.automl\n",
|
||||
"from sklearn.externals import joblib\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global model\n",
|
||||
" model_path = Model.get_model_path(model_name = '<<modelid>>') # this name is model.id of model that we want to deploy\n",
|
||||
" # deserialize the model file back into a sklearn model\n",
|
||||
" model = joblib.load(model_path)\n",
|
||||
"\n",
|
||||
"def run(rawdata):\n",
|
||||
" try:\n",
|
||||
" data = json.loads(rawdata)['data']\n",
|
||||
" data = numpy.array(data)\n",
|
||||
" result = model.predict(data)\n",
|
||||
" except Exception as e:\n",
|
||||
" result = str(e)\n",
|
||||
" return json.dumps({\"error\": result})\n",
|
||||
" return json.dumps({\"result\":result.tolist()})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create a YAML File for the Environment"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To ensure the fit results are consistent with the training results, the SDK dependency versions need to be the same as the environment that trains the model. Details about retrieving the versions can be found in notebook [12.auto-ml-retrieve-the-training-sdk-versions](12.auto-ml-retrieve-the-training-sdk-versions.ipynb)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"dependencies = remote_run.get_run_sdk_dependencies(iteration = 1)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"for p in ['azureml-train-automl', 'azureml-sdk', 'azureml-core']:\n",
|
||||
" print('{}\\t{}'.format(p, dependencies[p]))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.conda_dependencies import CondaDependencies\n",
|
||||
"\n",
|
||||
"myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn','py-xgboost<=0.80'],\n",
|
||||
" pip_packages=['azureml-sdk[automl]'])\n",
|
||||
"\n",
|
||||
"conda_env_file_name = 'myenv.yml'\n",
|
||||
"myenv.save_to_file('.', conda_env_file_name)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Substitute the actual version number in the environment file.\n",
|
||||
"# This is not strictly needed in this notebook because the model should have been generated using the current SDK version.\n",
|
||||
"# However, we include this in case this code is used on an experiment from a previous SDK version.\n",
|
||||
"\n",
|
||||
"with open(conda_env_file_name, 'r') as cefr:\n",
|
||||
" content = cefr.read()\n",
|
||||
"\n",
|
||||
"with open(conda_env_file_name, 'w') as cefw:\n",
|
||||
" cefw.write(content.replace(azureml.core.VERSION, dependencies['azureml-sdk']))\n",
|
||||
"\n",
|
||||
"# Substitute the actual model id in the script file.\n",
|
||||
"\n",
|
||||
"script_file_name = 'score.py'\n",
|
||||
"\n",
|
||||
"with open(script_file_name, 'r') as cefr:\n",
|
||||
" content = cefr.read()\n",
|
||||
"\n",
|
||||
"with open(script_file_name, 'w') as cefw:\n",
|
||||
" cefw.write(content.replace('<<modelid>>', remote_run.model_id))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create a Container Image\n",
|
||||
"\n",
|
||||
"Next use Azure Container Instances for deploying models as a web service for quickly deploying and validating your model\n",
|
||||
"or when testing a model that is under development."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.image import Image, ContainerImage\n",
|
||||
"\n",
|
||||
"image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
|
||||
" execution_script = script_file_name,\n",
|
||||
" conda_file = conda_env_file_name,\n",
|
||||
" tags = {'area': \"bmData\", 'type': \"automl_classification\"},\n",
|
||||
" description = \"Image for automl classification sample\")\n",
|
||||
"\n",
|
||||
"image = Image.create(name = \"automlsampleimage\",\n",
|
||||
" # this is the model object \n",
|
||||
" models = [model],\n",
|
||||
" image_config = image_config, \n",
|
||||
" workspace = ws)\n",
|
||||
"\n",
|
||||
"image.wait_for_creation(show_output = True)\n",
|
||||
"\n",
|
||||
"if image.creation_state == 'Failed':\n",
|
||||
" print(\"Image build log at: \" + image.image_build_log_uri)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Deploy the Image as a Web Service on Azure Container Instance\n",
|
||||
"\n",
|
||||
"Deploy an image that contains the model and other assets needed by the service."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import AciWebservice\n",
|
||||
"\n",
|
||||
"aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
|
||||
" memory_gb = 1, \n",
|
||||
" tags = {'area': \"bmData\", 'type': \"automl_classification\"}, \n",
|
||||
" description = 'sample service for Automl Classification')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import Webservice\n",
|
||||
"\n",
|
||||
"aci_service_name = 'automl-sample-bankmarketing'\n",
|
||||
"print(aci_service_name)\n",
|
||||
"aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
|
||||
" image = image,\n",
|
||||
" name = aci_service_name,\n",
|
||||
" workspace = ws)\n",
|
||||
"aci_service.wait_for_deployment(True)\n",
|
||||
"print(aci_service.state)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Delete a Web Service\n",
|
||||
"\n",
|
||||
"Deletes the specified web service."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#aci_service.delete()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Get Logs from a Deployed Web Service\n",
|
||||
"\n",
|
||||
"Gets logs from a deployed web service."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#aci_service.get_logs()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Test\n",
|
||||
"\n",
|
||||
"Now that the model is trained split our data in the same way the data was split for training (The difference here is the data is being split locally) and then run the test data through the trained model to get the predicted values."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Load the bank marketing datasets.\n",
|
||||
"from sklearn.datasets import load_diabetes\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"from numpy import array"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_validate.csv\"\n",
|
||||
"dflow = dprep.auto_read_file(data)\n",
|
||||
"dflow.get_profile()\n",
|
||||
"X_test = dflow.drop_columns(columns=['y'])\n",
|
||||
"y_test = dflow.keep_columns(columns=['y'], validate_column_exists=True)\n",
|
||||
"dflow.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X_test = X_test.to_pandas_dataframe()\n",
|
||||
"y_test = y_test.to_pandas_dataframe()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"y_pred = fitted_model.predict(X_test)\n",
|
||||
"actual = array(y_test)\n",
|
||||
"actual = actual[:,0]\n",
|
||||
"print(y_pred.shape, \" \", actual.shape)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Calculate metrics for the prediction\n",
|
||||
"\n",
|
||||
"Now visualize the data on a scatter plot to show what our truth (actual) values are compared to the predicted values \n",
|
||||
"from the trained model that was returned."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%matplotlib notebook\n",
|
||||
"test_pred = plt.scatter(actual, y_pred, color='b')\n",
|
||||
"test_test = plt.scatter(actual, actual, color='g')\n",
|
||||
"plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Acknowledgements"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"This Bank Marketing dataset is made available under the Creative Commons (CCO: Public Domain) License: https://creativecommons.org/publicdomain/zero/1.0/. Any rights in individual contents of the database are licensed under the Database Contents License: https://creativecommons.org/publicdomain/zero/1.0/ and is available at: https://www.kaggle.com/janiobachmann/bank-marketing-dataset .\n",
|
||||
"\n",
|
||||
"_**Acknowledgements**_\n",
|
||||
"This data set is originally available within the UCI Machine Learning Database: https://archive.ics.uci.edu/ml/datasets/bank+marketing\n",
|
||||
"\n",
|
||||
"[Moro et al., 2014] S. Moro, P. Cortez and P. Rita. A Data-Driven Approach to Predict the Success of Bank Telemarketing. Decision Support Systems, Elsevier, 62:22-31, June 2014"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "v-rasav"
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.7"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-classification-bank-marketing
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,712 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Automated Machine Learning\n",
|
||||
"_**Classification with Deployment using Credit Card Dataset**_\n",
|
||||
"\n",
|
||||
"## Contents\n",
|
||||
"1. [Introduction](#Introduction)\n",
|
||||
"1. [Setup](#Setup)\n",
|
||||
"1. [Train](#Train)\n",
|
||||
"1. [Results](#Results)\n",
|
||||
"1. [Deploy](#Deploy)\n",
|
||||
"1. [Test](#Test)\n",
|
||||
"1. [Acknowledgements](#Acknowledgements)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Introduction\n",
|
||||
"\n",
|
||||
"In this example we use the associated credit card dataset to showcase how you can use AutoML for a simple classification problem and deploy it to an Azure Container Instance (ACI). The classification goal is to predict if a creditcard transaction is or is not considered a fraudulent charge.\n",
|
||||
"\n",
|
||||
"If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, go through the [configuration](../../../configuration.ipynb) notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
|
||||
"\n",
|
||||
"In this notebook you will learn how to:\n",
|
||||
"1. Create an experiment using an existing workspace.\n",
|
||||
"2. Configure AutoML using `AutoMLConfig`.\n",
|
||||
"3. Train the model using local compute.\n",
|
||||
"4. Explore the results.\n",
|
||||
"5. Register the model.\n",
|
||||
"6. Create a container image.\n",
|
||||
"7. Create an Azure Container Instance (ACI) service.\n",
|
||||
"8. Test the ACI service."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setup\n",
|
||||
"\n",
|
||||
"As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import logging\n",
|
||||
"\n",
|
||||
"from matplotlib import pyplot as plt\n",
|
||||
"import pandas as pd\n",
|
||||
"import os\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"import azureml.dataprep as dprep\n",
|
||||
"\n",
|
||||
"import azureml.core\n",
|
||||
"from azureml.core.experiment import Experiment\n",
|
||||
"from azureml.core.workspace import Workspace\n",
|
||||
"from azureml.train.automl import AutoMLConfig\n",
|
||||
"from azureml.train.automl.run import AutoMLRun"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ws = Workspace.from_config()\n",
|
||||
"\n",
|
||||
"# choose a name for experiment\n",
|
||||
"experiment_name = 'automl-classification-ccard'\n",
|
||||
"# project folder\n",
|
||||
"project_folder = './sample_projects/automl-classification-creditcard'\n",
|
||||
"\n",
|
||||
"experiment=Experiment(ws, experiment_name)\n",
|
||||
"\n",
|
||||
"output = {}\n",
|
||||
"output['SDK version'] = azureml.core.VERSION\n",
|
||||
"output['Subscription ID'] = ws.subscription_id\n",
|
||||
"output['Workspace'] = ws.name\n",
|
||||
"output['Resource Group'] = ws.resource_group\n",
|
||||
"output['Location'] = ws.location\n",
|
||||
"output['Project Directory'] = project_folder\n",
|
||||
"output['Experiment Name'] = experiment.name\n",
|
||||
"pd.set_option('display.max_colwidth', -1)\n",
|
||||
"outputDf = pd.DataFrame(data = output, index = [''])\n",
|
||||
"outputDf.T"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Create or Attach existing AmlCompute\n",
|
||||
"You will need to create a compute target for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
|
||||
"#### Creation of AmlCompute takes approximately 5 minutes. \n",
|
||||
"If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
|
||||
"As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read this article on the default limits and how to request more quota."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.compute import AmlCompute\n",
|
||||
"from azureml.core.compute import ComputeTarget\n",
|
||||
"\n",
|
||||
"# Choose a name for your cluster.\n",
|
||||
"amlcompute_cluster_name = \"automlcl\"\n",
|
||||
"\n",
|
||||
"found = False\n",
|
||||
"# Check if this compute target already exists in the workspace.\n",
|
||||
"cts = ws.compute_targets\n",
|
||||
"if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
|
||||
" found = True\n",
|
||||
" print('Found existing compute target.')\n",
|
||||
" compute_target = cts[amlcompute_cluster_name]\n",
|
||||
" \n",
|
||||
"if not found:\n",
|
||||
" print('Creating a new compute target...')\n",
|
||||
" provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
|
||||
" #vm_priority = 'lowpriority', # optional\n",
|
||||
" max_nodes = 6)\n",
|
||||
"\n",
|
||||
" # Create the cluster.\n",
|
||||
" compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
|
||||
" \n",
|
||||
" # Can poll for a minimum number of nodes and for a specific timeout.\n",
|
||||
" # If no min_node_count is provided, it will use the scale settings for the cluster.\n",
|
||||
" compute_target.wait_for_completion(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
|
||||
" \n",
|
||||
" # For a more detailed view of current AmlCompute status, use get_status()."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Data\n",
|
||||
"\n",
|
||||
"Here load the data in the get_data script to be utilized in azure compute. To do this, first load all the necessary libraries and dependencies to set up paths for the data and to create the conda_run_config."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if not os.path.isdir('data'):\n",
|
||||
" os.mkdir('data')\n",
|
||||
" \n",
|
||||
"if not os.path.exists(project_folder):\n",
|
||||
" os.makedirs(project_folder)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.runconfig import RunConfiguration\n",
|
||||
"from azureml.core.conda_dependencies import CondaDependencies\n",
|
||||
"\n",
|
||||
"# create a new RunConfig object\n",
|
||||
"conda_run_config = RunConfiguration(framework=\"python\")\n",
|
||||
"\n",
|
||||
"# Set compute target to AmlCompute\n",
|
||||
"conda_run_config.target = compute_target\n",
|
||||
"conda_run_config.environment.docker.enabled = True\n",
|
||||
"conda_run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy','py-xgboost<=0.80'])\n",
|
||||
"conda_run_config.environment.python.conda_dependencies = cd"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Load Data\n",
|
||||
"\n",
|
||||
"Here create the script to be run in azure compute for loading the data, load the credit card dataset into cards and store the Class column (y) in the y variable and store the remaining data in the x variable. Next split the data using train_test_split and return X_train and y_train for training the model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/creditcard.csv\"\n",
|
||||
"dflow = dprep.auto_read_file(data)\n",
|
||||
"dflow.get_profile()\n",
|
||||
"X = dflow.drop_columns(columns=['Class'])\n",
|
||||
"y = dflow.keep_columns(columns=['Class'], validate_column_exists=True)\n",
|
||||
"X_train, X_test = X.random_split(percentage=0.8, seed=223)\n",
|
||||
"y_train, y_test = y.random_split(percentage=0.8, seed=223)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Train\n",
|
||||
"\n",
|
||||
"Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
|
||||
"\n",
|
||||
"|Property|Description|\n",
|
||||
"|-|-|\n",
|
||||
"|**task**|classification or regression|\n",
|
||||
"|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
|
||||
"|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
|
||||
"|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
|
||||
"|**n_cross_validations**|Number of cross validation splits.|\n",
|
||||
"|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
|
||||
"|**y**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|\n",
|
||||
"|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|\n",
|
||||
"\n",
|
||||
"**_You can find more information about primary metrics_** [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#primary-metric)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"##### If you would like to see even better results increase \"iteration_time_out minutes\" to 10+ mins and increase \"iterations\" to a minimum of 30"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"automl_settings = {\n",
|
||||
" \"iteration_timeout_minutes\": 5,\n",
|
||||
" \"iterations\": 10,\n",
|
||||
" \"n_cross_validations\": 2,\n",
|
||||
" \"primary_metric\": 'average_precision_score_weighted',\n",
|
||||
" \"preprocess\": True,\n",
|
||||
" \"max_concurrent_iterations\": 5,\n",
|
||||
" \"verbosity\": logging.INFO,\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"automl_config = AutoMLConfig(task = 'classification',\n",
|
||||
" debug_log = 'automl_errors_20190417.log',\n",
|
||||
" path = project_folder,\n",
|
||||
" run_configuration=conda_run_config,\n",
|
||||
" X = X_train,\n",
|
||||
" y = y_train,\n",
|
||||
" **automl_settings\n",
|
||||
" )"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
|
||||
"In this example, we specify `show_output = True` to print currently running iterations to the console."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"remote_run = experiment.submit(automl_config, show_output = True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"remote_run"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Results"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Widget for Monitoring Runs\n",
|
||||
"\n",
|
||||
"The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
|
||||
"\n",
|
||||
"**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.widgets import RunDetails\n",
|
||||
"RunDetails(remote_run).show() "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Deploy\n",
|
||||
"\n",
|
||||
"### Retrieve the Best Model\n",
|
||||
"\n",
|
||||
"Below we select the best pipeline from our iterations. The `get_output` method on `automl_classifier` returns the best run and the fitted model for the last invocation. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"best_run, fitted_model = remote_run.get_output()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Register the Fitted Model for Deployment\n",
|
||||
"If neither `metric` nor `iteration` are specified in the `register_model` call, the iteration with the best primary metric is registered."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"description = 'AutoML Model'\n",
|
||||
"tags = None\n",
|
||||
"model = remote_run.register_model(description = description, tags = tags)\n",
|
||||
"\n",
|
||||
"print(remote_run.model_id) # This will be written to the script file later in the notebook."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create Scoring Script\n",
|
||||
"The scoring script is required to generate the image for deployment. It contains the code to do the predictions on input data."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import pickle\n",
|
||||
"import json\n",
|
||||
"import numpy\n",
|
||||
"import azureml.train.automl\n",
|
||||
"from sklearn.externals import joblib\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global model\n",
|
||||
" model_path = Model.get_model_path(model_name = '<<modelid>>') # this name is model.id of model that we want to deploy\n",
|
||||
" # deserialize the model file back into a sklearn model\n",
|
||||
" model = joblib.load(model_path)\n",
|
||||
"\n",
|
||||
"def run(rawdata):\n",
|
||||
" try:\n",
|
||||
" data = json.loads(rawdata)['data']\n",
|
||||
" data = numpy.array(data)\n",
|
||||
" result = model.predict(data)\n",
|
||||
" except Exception as e:\n",
|
||||
" result = str(e)\n",
|
||||
" return json.dumps({\"error\": result})\n",
|
||||
" return json.dumps({\"result\":result.tolist()})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create a YAML File for the Environment"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To ensure the fit results are consistent with the training results, the SDK dependency versions need to be the same as the environment that trains the model. Details about retrieving the versions can be found in notebook [12.auto-ml-retrieve-the-training-sdk-versions](12.auto-ml-retrieve-the-training-sdk-versions.ipynb)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"dependencies = remote_run.get_run_sdk_dependencies(iteration = 1)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"for p in ['azureml-train-automl', 'azureml-sdk', 'azureml-core']:\n",
|
||||
" print('{}\\t{}'.format(p, dependencies[p]))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn','py-xgboost<=0.80'],\n",
|
||||
" pip_packages=['azureml-sdk[automl]'])\n",
|
||||
"\n",
|
||||
"conda_env_file_name = 'myenv.yml'\n",
|
||||
"myenv.save_to_file('.', conda_env_file_name)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Substitute the actual version number in the environment file.\n",
|
||||
"# This is not strictly needed in this notebook because the model should have been generated using the current SDK version.\n",
|
||||
"# However, we include this in case this code is used on an experiment from a previous SDK version.\n",
|
||||
"\n",
|
||||
"with open(conda_env_file_name, 'r') as cefr:\n",
|
||||
" content = cefr.read()\n",
|
||||
"\n",
|
||||
"with open(conda_env_file_name, 'w') as cefw:\n",
|
||||
" cefw.write(content.replace(azureml.core.VERSION, dependencies['azureml-sdk']))\n",
|
||||
"\n",
|
||||
"# Substitute the actual model id in the script file.\n",
|
||||
"\n",
|
||||
"script_file_name = 'score.py'\n",
|
||||
"\n",
|
||||
"with open(script_file_name, 'r') as cefr:\n",
|
||||
" content = cefr.read()\n",
|
||||
"\n",
|
||||
"with open(script_file_name, 'w') as cefw:\n",
|
||||
" cefw.write(content.replace('<<modelid>>', remote_run.model_id))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create a Container Image\n",
|
||||
"\n",
|
||||
"Next use Azure Container Instances for deploying models as a web service for quickly deploying and validating your model\n",
|
||||
"or when testing a model that is under development."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.image import Image, ContainerImage\n",
|
||||
"\n",
|
||||
"image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
|
||||
" execution_script = script_file_name,\n",
|
||||
" conda_file = conda_env_file_name,\n",
|
||||
" tags = {'area': \"cards\", 'type': \"automl_classification\"},\n",
|
||||
" description = \"Image for automl classification sample\")\n",
|
||||
"\n",
|
||||
"image = Image.create(name = \"automlsampleimage\",\n",
|
||||
" # this is the model object \n",
|
||||
" models = [model],\n",
|
||||
" image_config = image_config, \n",
|
||||
" workspace = ws)\n",
|
||||
"\n",
|
||||
"image.wait_for_creation(show_output = True)\n",
|
||||
"\n",
|
||||
"if image.creation_state == 'Failed':\n",
|
||||
" print(\"Image build log at: \" + image.image_build_log_uri)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Deploy the Image as a Web Service on Azure Container Instance\n",
|
||||
"\n",
|
||||
"Deploy an image that contains the model and other assets needed by the service."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import AciWebservice\n",
|
||||
"\n",
|
||||
"aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
|
||||
" memory_gb = 1, \n",
|
||||
" tags = {'area': \"cards\", 'type': \"automl_classification\"}, \n",
|
||||
" description = 'sample service for Automl Classification')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import Webservice\n",
|
||||
"\n",
|
||||
"aci_service_name = 'automl-sample-creditcard'\n",
|
||||
"print(aci_service_name)\n",
|
||||
"aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
|
||||
" image = image,\n",
|
||||
" name = aci_service_name,\n",
|
||||
" workspace = ws)\n",
|
||||
"aci_service.wait_for_deployment(True)\n",
|
||||
"print(aci_service.state)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Delete a Web Service\n",
|
||||
"\n",
|
||||
"Deletes the specified web service."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#aci_service.delete()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Get Logs from a Deployed Web Service\n",
|
||||
"\n",
|
||||
"Gets logs from a deployed web service."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#aci_service.get_logs()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Test\n",
|
||||
"\n",
|
||||
"Now that the model is trained, split the data in the same way the data was split for training (The difference here is the data is being split locally) and then run the test data through the trained model to get the predicted values."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Randomly select and test\n",
|
||||
"X_test = X_test.to_pandas_dataframe()\n",
|
||||
"y_test = y_test.to_pandas_dataframe()\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"y_pred = fitted_model.predict(X_test)\n",
|
||||
"y_pred"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Calculate metrics for the prediction\n",
|
||||
"\n",
|
||||
"Now visualize the data on a scatter plot to show what our truth (actual) values are compared to the predicted values \n",
|
||||
"from the trained model that was returned."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Randomly select and test\n",
|
||||
"# Plot outputs\n",
|
||||
"%matplotlib notebook\n",
|
||||
"test_pred = plt.scatter(y_test, y_pred, color='b')\n",
|
||||
"test_test = plt.scatter(y_test, y_test, color='g')\n",
|
||||
"plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
|
||||
"plt.show()\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Acknowledgements"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"This Credit Card fraud Detection dataset is made available under the Open Database License: http://opendatacommons.org/licenses/odbl/1.0/. Any rights in individual contents of the database are licensed under the Database Contents License: http://opendatacommons.org/licenses/dbcl/1.0/ and is available at: https://www.kaggle.com/mlg-ulb/creditcardfraud\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"The dataset has been collected and analysed during a research collaboration of Worldline and the Machine Learning Group (http://mlg.ulb.ac.be) of ULB (Universit\u00c3\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",
|
||||
"Please cite the following works: \n",
|
||||
"\u00e2\u20ac\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",
|
||||
"\u00e2\u20ac\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",
|
||||
"\u00e2\u20ac\u00a2\tDal Pozzolo, Andrea; Boracchi, Giacomo; Caelen, Olivier; Alippi, Cesare; Bontempi, Gianluca. Credit card fraud detection: a realistic modeling and a novel learning strategy, IEEE transactions on neural networks and learning systems,29,8,3784-3797,2018,IEEE\n",
|
||||
"o\tDal Pozzolo, Andrea Adaptive Machine learning for credit card fraud detection ULB MLG PhD thesis (supervised by G. Bontempi)\n",
|
||||
"\u00e2\u20ac\u00a2\tCarcillo, Fabrizio; Dal Pozzolo, Andrea; Le Borgne, Yann-A\u00c3\u00abl; Caelen, Olivier; Mazzer, Yannis; Bontempi, Gianluca. Scarff: a scalable framework for streaming credit card fraud detection with Spark, Information fusion,41, 182-194,2018,Elsevier\n",
|
||||
"\u00e2\u20ac\u00a2\tCarcillo, Fabrizio; Le Borgne, Yann-A\u00c3\u00abl; Caelen, Olivier; Bontempi, Gianluca. Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization, International Journal of Data Science and Analytics, 5,4,285-300,2018,Springer International Publishing"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "v-rasav"
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.7"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-classification-credit-card-fraud
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-classification-with-deployment
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -129,6 +129,22 @@
|
||||
" test_size=0.2, \n",
|
||||
" random_state=0)\n",
|
||||
"\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Ensure the x_train and x_test are pandas DataFrame."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Convert the X_train and X_test to pandas DataFrame and set column names,\n",
|
||||
"# This is needed for initializing the input variable names of ONNX model, \n",
|
||||
"# and the prediction with the ONNX model using the inference helper.\n",
|
||||
@@ -158,6 +174,13 @@
|
||||
"|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Set the preprocess=True, currently the InferenceHelper only supports this mode."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
@@ -299,7 +322,7 @@
|
||||
" onnxrt_present = False\n",
|
||||
"\n",
|
||||
"def get_onnx_res(run):\n",
|
||||
" res_path = '_debug_y_trans_converter.json'\n",
|
||||
" res_path = 'onnx_resource.json'\n",
|
||||
" run.download_file(name=constants.MODEL_RESOURCE_PATH_ONNX, output_file_path=res_path)\n",
|
||||
" with open(res_path) as f:\n",
|
||||
" onnx_res = json.load(f)\n",
|
||||
@@ -316,7 +339,7 @@
|
||||
" print(pred_prob_onnx)\n",
|
||||
"else:\n",
|
||||
" if not python_version_compatible:\n",
|
||||
" print('Please use Python version 3.6 to run the inference helper.') \n",
|
||||
" print('Please use Python version 3.6 or 3.7 to run the inference helper.') \n",
|
||||
" if not onnxrt_present:\n",
|
||||
" print('Please install the onnxruntime package to do the prediction with ONNX model.')"
|
||||
]
|
||||
|
||||
@@ -0,0 +1,9 @@
|
||||
name: auto-ml-classification-with-onnx
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
- onnxruntime
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-classification-with-whitelisting
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-classification
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -21,7 +21,7 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Automated Machine Learning\n",
|
||||
"_**Prepare Data using `azureml.dataprep` for Remote Execution (DSVM)**_\n",
|
||||
"_**Prepare Data using `azureml.dataprep` for Remote Execution (AmlCompute)**_\n",
|
||||
"\n",
|
||||
"## Contents\n",
|
||||
"1. [Introduction](#Introduction)\n",
|
||||
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-dataprep-remote-execution
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-dataprep
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-exploring-previous-runs
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -36,19 +36,17 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Introduction\n",
|
||||
"In this example, we show how AutoML can be used for bike share forecasting.\n",
|
||||
"This notebook demonstrates demand forecasting for a bike-sharing service using AutoML.\n",
|
||||
"\n",
|
||||
"The purpose is to demonstrate how to take advantage of the built-in holiday featurization, access the feature names, and further demonstrate how to work 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",
|
||||
"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](../../../configuration.ipynb) before running this notebook.\n",
|
||||
"\n",
|
||||
"In this notebook you would see\n",
|
||||
"Notebook synopsis:\n",
|
||||
"1. Creating an Experiment in an existing Workspace\n",
|
||||
"2. Instantiating AutoMLConfig with new task type \"forecasting\" for timeseries data training, and other timeseries related settings: for this dataset we use the basic one: \"time_column_name\" \n",
|
||||
"3. Training the Model using local compute\n",
|
||||
"4. Exploring the results\n",
|
||||
"5. Viewing the engineered names for featurized data and featurization summary for all raw features\n",
|
||||
"6. Testing the fitted model"
|
||||
"2. Configuration and local run of AutoML for a time-series model with lag and holiday features \n",
|
||||
"3. Viewing the engineered names for featurized data and featurization summary for all raw features\n",
|
||||
"4. Evaluating the fitted model using a rolling test "
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -69,10 +67,12 @@
|
||||
"import numpy as np\n",
|
||||
"import logging\n",
|
||||
"import warnings\n",
|
||||
"\n",
|
||||
"from pandas.tseries.frequencies import to_offset\n",
|
||||
"\n",
|
||||
"# Squash warning messages for cleaner output in the notebook\n",
|
||||
"warnings.showwarning = lambda *args, **kwargs: None\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"from azureml.core.workspace import Workspace\n",
|
||||
"from azureml.core.experiment import Experiment\n",
|
||||
"from azureml.train.automl import AutoMLConfig\n",
|
||||
@@ -84,7 +84,7 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"As part of the setup you have already created a <b>Workspace</b>. For AutoML you would need to create an <b>Experiment</b>. An <b>Experiment</b> is a named object in a <b>Workspace</b>, which is used to run experiments."
|
||||
"As part of the setup you have already created a <b>Workspace</b>. To run AutoML, you also need to create an <b>Experiment</b>. An Experiment corresponds to a prediction problem you are trying to solve, while a Run corresponds to a specific approach to the problem."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -129,14 +129,15 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"data = pd.read_csv('bike-no.csv', parse_dates=['date'])"
|
||||
"data = pd.read_csv('bike-no.csv', parse_dates=['date'])\n",
|
||||
"data.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Let's set up what we know abou the dataset. \n",
|
||||
"Let's set up what we know about the dataset. \n",
|
||||
"\n",
|
||||
"**Target column** is what we want to forecast.\n",
|
||||
"\n",
|
||||
@@ -194,8 +195,7 @@
|
||||
"source": [
|
||||
"### Setting forecaster maximum horizon \n",
|
||||
"\n",
|
||||
"Assuming your test data forms a full and regular time series(regular time intervals and no holes), \n",
|
||||
"the maximum horizon you will need to forecast is the length of the longest grain in your test set."
|
||||
"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 days 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). "
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -204,10 +204,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if len(grain_column_names) == 0:\n",
|
||||
" max_horizon = len(X_test)\n",
|
||||
"else:\n",
|
||||
" max_horizon = X_test.groupby(grain_column_names)[time_column_name].count().max()"
|
||||
"max_horizon = 14"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -237,26 +234,25 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"time_column_name = 'date'\n",
|
||||
"automl_settings = {\n",
|
||||
" \"time_column_name\": time_column_name,\n",
|
||||
" # these columns are a breakdown of the total and therefore a leak\n",
|
||||
" \"drop_column_names\": ['casual', 'registered'],\n",
|
||||
" 'time_column_name': time_column_name,\n",
|
||||
" 'max_horizon': max_horizon,\n",
|
||||
" # knowing the country/region allows Automated ML to bring in holidays\n",
|
||||
" \"country_or_region\" : 'US',\n",
|
||||
" \"max_horizon\" : max_horizon,\n",
|
||||
" \"target_lags\": 1 \n",
|
||||
" 'country_or_region': 'US',\n",
|
||||
" 'target_lags': 1,\n",
|
||||
" # these columns are a breakdown of the total and therefore a leak\n",
|
||||
" 'drop_column_names': ['casual', 'registered']\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"automl_config = AutoMLConfig(task = 'forecasting', \n",
|
||||
"automl_config = AutoMLConfig(task='forecasting', \n",
|
||||
" primary_metric='normalized_root_mean_squared_error',\n",
|
||||
" iterations = 10,\n",
|
||||
" iteration_timeout_minutes = 5,\n",
|
||||
" X = X_train,\n",
|
||||
" y = y_train,\n",
|
||||
" n_cross_validations = 3, \n",
|
||||
" iterations=10,\n",
|
||||
" iteration_timeout_minutes=5,\n",
|
||||
" X=X_train,\n",
|
||||
" y=y_train,\n",
|
||||
" n_cross_validations=3, \n",
|
||||
" path=project_folder,\n",
|
||||
" verbosity = logging.INFO,\n",
|
||||
" verbosity=logging.INFO,\n",
|
||||
" **automl_settings)"
|
||||
]
|
||||
},
|
||||
@@ -264,7 +260,7 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We will now run the experiment, starting with 10 iterations of model search. Experiment can be continued for more iterations if the results are not yet good. You will see the currently running iterations printing to the console."
|
||||
"We will now run the experiment, starting with 10 iterations of model search. The experiment can be continued for more iterations if more accurate results are required. You will see the currently running iterations printing to the console."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -356,11 +352,16 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Test the Best Fitted Model\n",
|
||||
"## Evaluate"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We now use the best fitted model from the AutoML Run to make forecasts for the test set. \n",
|
||||
"\n",
|
||||
"Predict on training and test set, and calculate residual values.\n",
|
||||
"\n",
|
||||
"We always score on the original dataset whose schema matches the scheme of the training dataset."
|
||||
"We always score on the original dataset whose schema matches the training set schema."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -372,21 +373,12 @@
|
||||
"X_test.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"y_query = y_test.copy().astype(np.float)\n",
|
||||
"y_query.fill(np.NaN)\n",
|
||||
"y_fcst, X_trans = fitted_model.forecast(X_test, y_query)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We now define some functions for aligning output to input and for producing rolling forecasts over the full test set. As previously stated, the forecast horizon of 14 days is shorter than the length of the test set - which is about 120 days. To get predictions over the full test set, we iterate over the test set, making forecasts 14 days at a time and combining the results. We also make sure that each 14-day forecast uses up-to-date actuals - the current context - to construct lag features. \n",
|
||||
"\n",
|
||||
"It is a good practice to always align the output explicitly to the input, as the count and order of the rows may have changed during transformations that span multiple rows."
|
||||
]
|
||||
},
|
||||
@@ -396,7 +388,8 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def align_outputs(y_predicted, X_trans, X_test, y_test, predicted_column_name = 'predicted'):\n",
|
||||
"def align_outputs(y_predicted, X_trans, X_test, y_test, predicted_column_name='predicted',\n",
|
||||
" horizon_colname='horizon_origin'):\n",
|
||||
" \"\"\"\n",
|
||||
" Demonstrates how to get the output aligned to the inputs\n",
|
||||
" using pandas indexes. Helps understand what happened if\n",
|
||||
@@ -408,7 +401,8 @@
|
||||
" * model was asked to predict past max_horizon -> increase max horizon\n",
|
||||
" * data at start of X_test was needed for lags -> provide previous periods\n",
|
||||
" \"\"\"\n",
|
||||
" df_fcst = pd.DataFrame({predicted_column_name : y_predicted})\n",
|
||||
" df_fcst = pd.DataFrame({predicted_column_name : y_predicted,\n",
|
||||
" horizon_colname: X_trans[horizon_colname]})\n",
|
||||
" # y and X outputs are aligned by forecast() function contract\n",
|
||||
" df_fcst.index = X_trans.index\n",
|
||||
" \n",
|
||||
@@ -427,7 +421,49 @@
|
||||
" clean = together[together[[target_column_name, predicted_column_name]].notnull().all(axis=1)]\n",
|
||||
" return(clean)\n",
|
||||
"\n",
|
||||
"df_all = align_outputs(y_fcst, X_trans, X_test, y_test)\n"
|
||||
"def do_rolling_forecast(fitted_model, X_test, y_test, max_horizon, freq='D'):\n",
|
||||
" \"\"\"\n",
|
||||
" Produce forecasts on a rolling origin over the given test set.\n",
|
||||
" \n",
|
||||
" Each iteration makes a forecast for the next 'max_horizon' periods \n",
|
||||
" with respect to the current origin, then advances the origin by the horizon time duration. \n",
|
||||
" The prediction context for each forecast is set so that the forecaster uses \n",
|
||||
" the actual target values prior to the current origin time for constructing lag features.\n",
|
||||
" \n",
|
||||
" This function returns a concatenated DataFrame of rolling forecasts.\n",
|
||||
" \"\"\"\n",
|
||||
" df_list = []\n",
|
||||
" origin_time = X_test[time_column_name].min()\n",
|
||||
" while origin_time <= X_test[time_column_name].max():\n",
|
||||
" # Set the horizon time - end date of the forecast\n",
|
||||
" horizon_time = origin_time + max_horizon * to_offset(freq)\n",
|
||||
" \n",
|
||||
" # Extract test data from an expanding window up-to the horizon \n",
|
||||
" expand_wind = (X_test[time_column_name] < horizon_time)\n",
|
||||
" X_test_expand = X_test[expand_wind]\n",
|
||||
" y_query_expand = np.zeros(len(X_test_expand)).astype(np.float)\n",
|
||||
" y_query_expand.fill(np.NaN)\n",
|
||||
" \n",
|
||||
" if origin_time != X_test[time_column_name].min():\n",
|
||||
" # Set the context by including actuals up-to the origin time\n",
|
||||
" test_context_expand_wind = (X_test[time_column_name] < origin_time)\n",
|
||||
" context_expand_wind = (X_test_expand[time_column_name] < origin_time)\n",
|
||||
" y_query_expand[context_expand_wind] = y_test[test_context_expand_wind]\n",
|
||||
" \n",
|
||||
" # Make a forecast out to the maximum horizon\n",
|
||||
" y_fcst, X_trans = fitted_model.forecast(X_test_expand, y_query_expand)\n",
|
||||
" \n",
|
||||
" # Align forecast with test set for dates within the current rolling window \n",
|
||||
" trans_tindex = X_trans.index.get_level_values(time_column_name)\n",
|
||||
" trans_roll_wind = (trans_tindex >= origin_time) & (trans_tindex < horizon_time)\n",
|
||||
" test_roll_wind = expand_wind & (X_test[time_column_name] >= origin_time)\n",
|
||||
" df_list.append(align_outputs(y_fcst[trans_roll_wind], X_trans[trans_roll_wind],\n",
|
||||
" X_test[test_roll_wind], y_test[test_roll_wind]))\n",
|
||||
" \n",
|
||||
" # Advance the origin time\n",
|
||||
" origin_time = horizon_time\n",
|
||||
" \n",
|
||||
" return pd.concat(df_list, ignore_index=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -436,6 +472,30 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"df_all = do_rolling_forecast(fitted_model, X_test, y_test, max_horizon)\n",
|
||||
"df_all"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We now calculate some error metrics for the forecasts and vizualize the predictions vs. the actuals."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def APE(actual, pred):\n",
|
||||
" \"\"\"\n",
|
||||
" Calculate absolute percentage error.\n",
|
||||
" Returns a vector of APE values with same length as actual/pred.\n",
|
||||
" \"\"\"\n",
|
||||
" return 100*np.abs((actual - pred)/actual)\n",
|
||||
"\n",
|
||||
"def MAPE(actual, pred):\n",
|
||||
" \"\"\"\n",
|
||||
" Calculate mean absolute percentage error.\n",
|
||||
@@ -445,8 +505,7 @@
|
||||
" not_zero = ~np.isclose(actual, 0.0)\n",
|
||||
" actual_safe = actual[not_na & not_zero]\n",
|
||||
" pred_safe = pred[not_na & not_zero]\n",
|
||||
" APE = 100*np.abs((actual_safe - pred_safe)/actual_safe)\n",
|
||||
" return np.mean(APE)"
|
||||
" return np.mean(APE(actual_safe, pred_safe))"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -469,12 +528,57 @@
|
||||
"plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The MAPE seems high; it is being skewed by an actual with a small absolute value. For a more informative evaluation, we can calculate the metrics by forecast horizon:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"df_all.groupby('horizon_origin').apply(\n",
|
||||
" lambda df: pd.Series({'MAPE': MAPE(df[target_column_name], df['predicted']),\n",
|
||||
" 'RMSE': np.sqrt(mean_squared_error(df[target_column_name], df['predicted'])),\n",
|
||||
" 'MAE': mean_absolute_error(df[target_column_name], df['predicted'])}))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"It's also interesting to see the distributions of APE (absolute percentage error) by horizon. On a log scale, the outlying APE in the horizon-3 group is clear."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"df_all_APE = df_all.assign(APE=APE(df_all[target_column_name], df_all['predicted']))\n",
|
||||
"APEs = [df_all_APE[df_all['horizon_origin'] == h].APE.values for h in range(1, max_horizon + 1)]\n",
|
||||
"\n",
|
||||
"%matplotlib notebook\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",
|
||||
"plt.show()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "xiaga@microsoft.com, tosingli@microsoft.com"
|
||||
"name": "xiaga@microsoft.com, tosingli@microsoft.com, erwright@microsoft.com"
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
@@ -492,7 +596,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.7"
|
||||
"version": "3.6.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -0,0 +1,9 @@
|
||||
name: auto-ml-forecasting-bike-share
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
- statsmodels
|
||||
@@ -35,17 +35,16 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Introduction\n",
|
||||
"In this example, we show how AutoML can be used for energy demand forecasting.\n",
|
||||
"In this example, we show how AutoML can be used to forecast a single time-series in the energy demand application area. \n",
|
||||
"\n",
|
||||
"Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
|
||||
"\n",
|
||||
"In this notebook you would see\n",
|
||||
"Notebook synopsis:\n",
|
||||
"1. Creating an Experiment in an existing Workspace\n",
|
||||
"2. Instantiating AutoMLConfig with new task type \"forecasting\" for timeseries data training, and other timeseries related settings: for this dataset we use the basic one: \"time_column_name\" \n",
|
||||
"3. Training the Model using local compute\n",
|
||||
"4. Exploring the results\n",
|
||||
"5. Viewing the engineered names for featurized data and featurization summary for all raw features\n",
|
||||
"6. Testing the fitted model"
|
||||
"2. Configuration and local run of AutoML for a simple time-series model\n",
|
||||
"3. View engineered features and prediction results\n",
|
||||
"4. Configuration and local run of AutoML for a time-series model with lag and rolling window features\n",
|
||||
"5. Estimate feature importance"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -66,10 +65,10 @@
|
||||
"import numpy as np\n",
|
||||
"import logging\n",
|
||||
"import warnings\n",
|
||||
"\n",
|
||||
"# Squash warning messages for cleaner output in the notebook\n",
|
||||
"warnings.showwarning = lambda *args, **kwargs: None\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"from azureml.core.workspace import Workspace\n",
|
||||
"from azureml.core.experiment import Experiment\n",
|
||||
"from azureml.train.automl import AutoMLConfig\n",
|
||||
@@ -81,7 +80,7 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"As part of the setup you have already created a <b>Workspace</b>. For AutoML you would need to create an <b>Experiment</b>. An <b>Experiment</b> is a named object in a <b>Workspace</b>, which is used to run experiments."
|
||||
"As part of the setup you have already created a <b>Workspace</b>. To run AutoML, you also need to create an <b>Experiment</b>. An Experiment corresponds to a prediction problem you are trying to solve, while a Run corresponds to a specific approach to the problem."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -117,7 +116,7 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Data\n",
|
||||
"Read energy demanding data from file, and preview data."
|
||||
"We will use energy consumption data from New York City for model training. The data is stored in a tabular format and includes energy demand and basic weather data at an hourly frequency. Pandas CSV reader is used to read the file into memory. Special attention is given to the \"timeStamp\" column in the data since it contains text which should be parsed as datetime-type objects. "
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -130,13 +129,20 @@
|
||||
"data.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We must now define the schema of this dataset. Every time-series must have a time column and a target. The target quantity is what will be eventually forecasted by a trained model. In this case, the target is the \"demand\" column. The other columns, \"temp\" and \"precip,\" are implicitly designated as features."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# let's take note of what columns means what in the data\n",
|
||||
"# Dataset schema\n",
|
||||
"time_column_name = 'timeStamp'\n",
|
||||
"target_column_name = 'demand'"
|
||||
]
|
||||
@@ -145,7 +151,14 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Split the data into train and test sets\n"
|
||||
"### Forecast Horizon\n",
|
||||
"\n",
|
||||
"In addition to the data schema, we must also specify the forecast horizon. A forecast horizon is a time span into the future (or just beyond the latest date in the training data) where forecasts of the target quantity are needed. Choosing a forecast horizon is application specific, but a rule-of-thumb is that **the horizon should be the time-frame where you need actionable decisions based on the forecast.** The horizon usually has a strong relationship with the frequency of the time-series data, that is, the sampling interval of the target quantity and the features. For instance, the NYC energy demand data has an hourly frequency. A decision that requires a demand forecast to the hour is unlikely to be made weeks or months in advance, particularly if we expect weather to be a strong determinant of demand. We may have fairly accurate meteorological forecasts of the hourly temperature and precipitation on a the time-scale of a day or two, however.\n",
|
||||
"\n",
|
||||
"Given the above discussion, we generally recommend that users set forecast horizons to less than 100 time periods (i.e. less than 100 hours in the NYC energy example). Furthermore, **AutoML's memory use and computation time increase in proportion to the length of the horizon**, so the user should consider carefully how they set this value. If a long horizon forecast really is necessary, it may be good practice to aggregate the series to a coarser time scale. \n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Forecast horizons in AutoML are given as integer multiples of the time-series frequency. In this example, we set the horizon to 48 hours."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -154,8 +167,32 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X_train = data[data[time_column_name] < '2017-02-01']\n",
|
||||
"X_test = data[data[time_column_name] >= '2017-02-01']\n",
|
||||
"max_horizon = 48"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Split the data into train and test sets\n",
|
||||
"We now split the data into a train and a test set so that we may evaluate model performance. We note that the tail of the dataset contains a large number of NA values in the target column, so we designate the test set as the 48 hour window ending on the latest date of known energy demand. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Find time point to split on\n",
|
||||
"latest_known_time = data[~pd.isnull(data[target_column_name])][time_column_name].max()\n",
|
||||
"split_time = latest_known_time - pd.Timedelta(hours=max_horizon)\n",
|
||||
"\n",
|
||||
"# Split into train/test sets\n",
|
||||
"X_train = data[data[time_column_name] <= split_time]\n",
|
||||
"X_test = data[(data[time_column_name] > split_time) & (data[time_column_name] <= latest_known_time)]\n",
|
||||
"\n",
|
||||
"# Move the target values into their own arrays \n",
|
||||
"y_train = X_train.pop(target_column_name).values\n",
|
||||
"y_test = X_test.pop(target_column_name).values"
|
||||
]
|
||||
@@ -166,7 +203,7 @@
|
||||
"source": [
|
||||
"## Train\n",
|
||||
"\n",
|
||||
"Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
|
||||
"We now instantiate an AutoMLConfig object. This config defines the settings and data used to run the experiment. For forecasting tasks, we must provide extra configuration related to the time-series data schema and forecasting context. Here, only the name of the time column and the maximum forecast horizon are needed. Other settings are described below:\n",
|
||||
"\n",
|
||||
"|Property|Description|\n",
|
||||
"|-|-|\n",
|
||||
@@ -176,7 +213,7 @@
|
||||
"|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
|
||||
"|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
|
||||
"|**y**|(sparse) array-like, shape = [n_samples, ], targets values.|\n",
|
||||
"|**n_cross_validations**|Number of cross validation splits.|\n",
|
||||
"|**n_cross_validations**|Number of cross validation splits. Rolling Origin Validation is used to split time-series in a temporally consistent way.|\n",
|
||||
"|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder. "
|
||||
]
|
||||
},
|
||||
@@ -186,22 +223,22 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"automl_settings = {\n",
|
||||
" \"time_column_name\": time_column_name \n",
|
||||
"time_series_settings = {\n",
|
||||
" 'time_column_name': time_column_name,\n",
|
||||
" 'max_horizon': max_horizon\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"automl_config = AutoMLConfig(task = 'forecasting',\n",
|
||||
" debug_log = 'automl_nyc_energy_errors.log',\n",
|
||||
"automl_config = AutoMLConfig(task='forecasting',\n",
|
||||
" debug_log='automl_nyc_energy_errors.log',\n",
|
||||
" primary_metric='normalized_root_mean_squared_error',\n",
|
||||
" iterations = 10,\n",
|
||||
" iteration_timeout_minutes = 5,\n",
|
||||
" X = X_train,\n",
|
||||
" y = y_train,\n",
|
||||
" n_cross_validations = 3,\n",
|
||||
" iterations=10,\n",
|
||||
" iteration_timeout_minutes=5,\n",
|
||||
" X=X_train,\n",
|
||||
" y=y_train,\n",
|
||||
" n_cross_validations=3,\n",
|
||||
" path=project_folder,\n",
|
||||
" verbosity = logging.INFO,\n",
|
||||
" **automl_settings)"
|
||||
" **time_series_settings)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -358,7 +395,8 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Calculate accuracy metrics\n"
|
||||
"### Calculate accuracy metrics\n",
|
||||
"Finally, we calculate some accuracy metrics for the forecast and plot the predictions vs. the actuals over the time range in the test set."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -395,9 +433,12 @@
|
||||
"\n",
|
||||
"# Plot outputs\n",
|
||||
"%matplotlib notebook\n",
|
||||
"test_pred = plt.scatter(df_all[target_column_name], df_all['predicted'], color='b')\n",
|
||||
"test_test = plt.scatter(y_test, y_test, color='g')\n",
|
||||
"plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
|
||||
"pred, = plt.plot(df_all[time_column_name], df_all['predicted'], color='b')\n",
|
||||
"actual, = plt.plot(df_all[time_column_name], df_all[target_column_name], color='g')\n",
|
||||
"plt.xticks(fontsize=8)\n",
|
||||
"plt.legend((pred, actual), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
|
||||
"plt.title('Prediction vs. Actual Time-Series')\n",
|
||||
"\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
@@ -412,16 +453,16 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Using lags and rolling window features to improve the forecast"
|
||||
"### Using lags and rolling window features"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We did not use lags in the previous model specification. In effect, the prediction was the result of a simple regression on date, grain and any additional features. This is often a very good prediction as common time series patterns like seasonality and trends can be captured in this manner. Such simple regression is horizon-less: it doesn't matter how far into the future we are predicting, because we are not using past data.\n",
|
||||
"We did not use lags in the previous model specification. In effect, the prediction was the result of a simple regression on date, grain and any additional features. This is often a very good prediction as common time series patterns like seasonality and trends can be captured in this manner. Such simple regression is horizon-less: it doesn't matter how far into the future we are predicting, because we are not using past data. In the previous example, the horizon was only used to split the data for cross-validation.\n",
|
||||
"\n",
|
||||
"Now that we configured target lags, that is the previous values of the target variables, and the prediction is no longer horizon-less. We therefore must specify the `max_horizon` that the model will learn to forecast. The `target_lags` keyword specifies how far back we will construct the lags of the target variable, and the `target_rolling_window_size` specifies the size of the rolling window over which we will generate the `max`, `min` and `sum` features."
|
||||
"Now that we configured target lags, that is the previous values of the target variables, and the prediction is no longer horizon-less. We therefore must still specify the `max_horizon` that the model will learn to forecast. The `target_lags` keyword specifies how far back we will construct the lags of the target variable, and the `target_rolling_window_size` specifies the size of the rolling window over which we will generate the `max`, `min` and `sum` features."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -430,27 +471,32 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"automl_settings_lags = {\n",
|
||||
"time_series_settings_with_lags = {\n",
|
||||
" 'time_column_name': time_column_name,\n",
|
||||
" 'target_lags': 1,\n",
|
||||
" 'target_rolling_window_size': 5,\n",
|
||||
" # you MUST set the max_horizon when using lags and rolling windows\n",
|
||||
" # it is optional when looking-back features are not used \n",
|
||||
" 'max_horizon': len(y_test), # only one grain\n",
|
||||
" 'max_horizon': max_horizon,\n",
|
||||
" 'target_lags': 12,\n",
|
||||
" 'target_rolling_window_size': 4\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"automl_config_lags = AutoMLConfig(task = 'forecasting',\n",
|
||||
" debug_log = 'automl_nyc_energy_errors.log',\n",
|
||||
"automl_config_lags = AutoMLConfig(task='forecasting',\n",
|
||||
" debug_log='automl_nyc_energy_errors.log',\n",
|
||||
" primary_metric='normalized_root_mean_squared_error',\n",
|
||||
" iterations = 10,\n",
|
||||
" iteration_timeout_minutes = 5,\n",
|
||||
" X = X_train,\n",
|
||||
" y = y_train,\n",
|
||||
" n_cross_validations = 3,\n",
|
||||
" blacklist_models=['ElasticNet'],\n",
|
||||
" iterations=10,\n",
|
||||
" iteration_timeout_minutes=10,\n",
|
||||
" X=X_train,\n",
|
||||
" y=y_train,\n",
|
||||
" n_cross_validations=3,\n",
|
||||
" path=project_folder,\n",
|
||||
" verbosity = logging.INFO,\n",
|
||||
" **automl_settings_lags)"
|
||||
" verbosity=logging.INFO,\n",
|
||||
" **time_series_settings_with_lags)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We now start a new local run, this time with lag and rolling window featurization. AutoML applies featurizations in the setup stage, prior to iterating over ML models. The full training set is featurized first, followed by featurization of each of the CV splits. Lag and rolling window features introduce additional complexity, so the run will take longer than in the previous example that lacked these featurizations."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -498,9 +544,10 @@
|
||||
"\n",
|
||||
"# Plot outputs\n",
|
||||
"%matplotlib notebook\n",
|
||||
"test_pred = plt.scatter(df_lags[target_column_name], df_lags['predicted'], color='b')\n",
|
||||
"test_test = plt.scatter(y_test, y_test, color='g')\n",
|
||||
"plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
|
||||
"pred, = plt.plot(df_lags[time_column_name], df_lags['predicted'], color='b')\n",
|
||||
"actual, = plt.plot(df_lags[time_column_name], df_lags[target_column_name], color='g')\n",
|
||||
"plt.xticks(fontsize=8)\n",
|
||||
"plt.legend((pred, actual), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
@@ -520,8 +567,8 @@
|
||||
"from azureml.train.automl.automlexplainer import explain_model\n",
|
||||
"\n",
|
||||
"# feature names are everything in the transformed data except the target\n",
|
||||
"features = X_trans.columns[:-1]\n",
|
||||
"expl = explain_model(fitted_model, X_train, X_test, features = features, best_run=best_run_lags, y_train = y_train)\n",
|
||||
"features = X_trans_lags.columns[:-1]\n",
|
||||
"expl = explain_model(fitted_model_lags, X_train.copy(), X_test.copy(), features=features, best_run=best_run_lags, y_train=y_train)\n",
|
||||
"# unpack the tuple\n",
|
||||
"shap_values, expected_values, feat_overall_imp, feat_names, per_class_summary, per_class_imp = expl\n",
|
||||
"best_run_lags"
|
||||
@@ -540,7 +587,7 @@
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "xiaga, tosingli"
|
||||
"name": "xiaga, tosingli, erwright"
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
@@ -558,7 +605,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.7"
|
||||
"version": "3.6.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -0,0 +1,10 @@
|
||||
name: auto-ml-forecasting-energy-demand
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
- statsmodels
|
||||
- azureml-explain-model
|
||||
@@ -37,16 +37,10 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Introduction\n",
|
||||
"In this example, we use AutoML to find and tune a time-series forecasting model.\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",
|
||||
"\n",
|
||||
"In this notebook, you will:\n",
|
||||
"1. Create an Experiment in an existing Workspace\n",
|
||||
"2. Instantiate an AutoMLConfig \n",
|
||||
"3. Find and train a forecasting model using local compute\n",
|
||||
"4. Evaluate the performance of the model\n",
|
||||
"\n",
|
||||
"The examples in the follow code samples use the University of Chicago's Dominick's Finer Foods dataset to forecast orange juice sales. Dominick's was a grocery chain in the Chicago metropolitan area."
|
||||
]
|
||||
},
|
||||
@@ -68,10 +62,10 @@
|
||||
"import numpy as np\n",
|
||||
"import logging\n",
|
||||
"import warnings\n",
|
||||
"\n",
|
||||
"# Squash warning messages for cleaner output in the notebook\n",
|
||||
"warnings.showwarning = lambda *args, **kwargs: None\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"from azureml.core.workspace import Workspace\n",
|
||||
"from azureml.core.experiment import Experiment\n",
|
||||
"from azureml.train.automl import AutoMLConfig\n",
|
||||
@@ -82,7 +76,7 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"As part of the setup you have already created a <b>Workspace</b>. To run AutoML, you also need to create an <b>Experiment</b>. An Experiment is a named object in a Workspace which represents a predictive task, the output of which is a trained model and a set of evaluation metrics for the model. "
|
||||
"As part of the setup you have already created a <b>Workspace</b>. To run AutoML, you also need to create an <b>Experiment</b>. An Experiment corresponds to a prediction problem you are trying to solve, while a Run corresponds to a specific approach to the problem. "
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -236,7 +230,7 @@
|
||||
"\n",
|
||||
"For forecasting tasks, there are some additional parameters that can be set: the name of the column holding the date/time, the grain column names, and the maximum forecast horizon. A time column is required for forecasting, while the grain is optional. If a grain is not given, AutoML assumes that the whole dataset is a single time-series. We also pass a list of columns to drop prior to modeling. The _logQuantity_ column is completely correlated with the target quantity, so it must be removed to prevent a target leak.\n",
|
||||
"\n",
|
||||
"The forecast horizon is given in units of the time-series frequency; for instance, the OJ series frequency is weekly, so a horizon of 20 means that a trained model will estimate sales up-to 20 weeks beyond the latest date in the training data for each series. In this example, we set the maximum horizon to the number of samples per series in the test set (n_test_periods). Generally, the value of this parameter will be dictated by business needs. For example, a demand planning organizaion that needs to estimate the next month of sales would set the horizon accordingly. \n",
|
||||
"The forecast horizon is given in units of the time-series frequency; for instance, the OJ series frequency is weekly, so a horizon of 20 means that a trained model will estimate sales up-to 20 weeks beyond the latest date in the training data for each series. In this example, we set the maximum horizon to the number of samples per series in the test set (n_test_periods). Generally, the value of this parameter will be dictated by business needs. For example, a demand planning organizaion that needs to estimate the next month of sales would set the horizon accordingly. Please see the [energy_demand notebook](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand) for more discussion of forecast horizon.\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 *X_valid* and *y_valid* parameters of AutoMLConfig.\n",
|
||||
"\n",
|
||||
@@ -269,7 +263,7 @@
|
||||
" 'time_column_name': time_column_name,\n",
|
||||
" 'grain_column_names': grain_column_names,\n",
|
||||
" 'drop_column_names': ['logQuantity'],\n",
|
||||
" 'max_horizon': n_test_periods # optional\n",
|
||||
" 'max_horizon': n_test_periods\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"automl_config = AutoMLConfig(task='forecasting',\n",
|
||||
@@ -278,7 +272,7 @@
|
||||
" iterations=10,\n",
|
||||
" X=X_train,\n",
|
||||
" y=y_train,\n",
|
||||
" n_cross_validations=5,\n",
|
||||
" n_cross_validations=3,\n",
|
||||
" enable_ensembling=False,\n",
|
||||
" path=project_folder,\n",
|
||||
" verbosity=logging.INFO,\n",
|
||||
@@ -324,7 +318,8 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Predict\n",
|
||||
"# Forecasting\n",
|
||||
"\n",
|
||||
"Now that we have retrieved the best pipeline/model, it can be used to make predictions on test data. First, we remove the target values from the test set:"
|
||||
]
|
||||
},
|
||||
@@ -852,7 +847,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.7"
|
||||
"version": "3.6.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -0,0 +1,9 @@
|
||||
name: auto-ml-forecasting-orange-juice-sales
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
- statsmodels
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-missing-data-blacklist-early-termination
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,9 @@
|
||||
name: auto-ml-model-explanation
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
- azureml-explain-model
|
||||
@@ -0,0 +1,800 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Automated Machine Learning\n",
|
||||
"_**Regression with Deployment using Hardware Performance Dataset**_\n",
|
||||
"\n",
|
||||
"## Contents\n",
|
||||
"1. [Introduction](#Introduction)\n",
|
||||
"1. [Setup](#Setup)\n",
|
||||
"1. [Data](#Data)\n",
|
||||
"1. [Train](#Train)\n",
|
||||
"1. [Results](#Results)\n",
|
||||
"1. [Test](#Test)\n",
|
||||
"1. [Acknowledgements](#Acknowledgements)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Introduction\n",
|
||||
"In this example we use the Predicting Compressive Strength of Concrete Dataset to showcase how you can use AutoML for a regression problem. The regression goal is to predict the compressive strength of concrete based off of different ingredient combinations and the quantities of those ingredients.\n",
|
||||
"\n",
|
||||
"If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, go through the [configuration](../../../configuration.ipynb) notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
|
||||
"\n",
|
||||
"In this notebook you will learn how to:\n",
|
||||
"1. Create an `Experiment` in an existing `Workspace`.\n",
|
||||
"2. Configure AutoML using `AutoMLConfig`.\n",
|
||||
"3. Train the model using local compute.\n",
|
||||
"4. Explore the results.\n",
|
||||
"5. Test the best fitted model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setup\n",
|
||||
"As part of the setup you have already created an Azure ML Workspace object. For AutoML you will need to create an Experiment object, which is a named object in a Workspace used to run experiments."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import logging\n",
|
||||
"\n",
|
||||
"from matplotlib import pyplot as plt\n",
|
||||
"import numpy as np\n",
|
||||
"import pandas as pd\n",
|
||||
"import os\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"import azureml.dataprep as dprep\n",
|
||||
" \n",
|
||||
"\n",
|
||||
"import azureml.core\n",
|
||||
"from azureml.core.experiment import Experiment\n",
|
||||
"from azureml.core.workspace import Workspace\n",
|
||||
"from azureml.train.automl import AutoMLConfig"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ws = Workspace.from_config()\n",
|
||||
"\n",
|
||||
"# Choose a name for the experiment and specify the project folder.\n",
|
||||
"experiment_name = 'automl-regression-concrete'\n",
|
||||
"project_folder = './sample_projects/automl-regression-concrete'\n",
|
||||
"\n",
|
||||
"experiment = Experiment(ws, experiment_name)\n",
|
||||
"\n",
|
||||
"output = {}\n",
|
||||
"output['SDK version'] = azureml.core.VERSION\n",
|
||||
"output['Subscription ID'] = ws.subscription_id\n",
|
||||
"output['Workspace Name'] = ws.name\n",
|
||||
"output['Resource Group'] = ws.resource_group\n",
|
||||
"output['Location'] = ws.location\n",
|
||||
"output['Project Directory'] = project_folder\n",
|
||||
"output['Experiment Name'] = experiment.name\n",
|
||||
"pd.set_option('display.max_colwidth', -1)\n",
|
||||
"outputDf = pd.DataFrame(data = output, index = [''])\n",
|
||||
"outputDf.T"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Create or Attach existing AmlCompute\n",
|
||||
"You will need to create a compute target for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
|
||||
"#### Creation of AmlCompute takes approximately 5 minutes. \n",
|
||||
"If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
|
||||
"As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read this article on the default limits and how to request more quota."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.compute import AmlCompute\n",
|
||||
"from azureml.core.compute import ComputeTarget\n",
|
||||
"\n",
|
||||
"# Choose a name for your cluster.\n",
|
||||
"amlcompute_cluster_name = \"automlcl\"\n",
|
||||
"\n",
|
||||
"found = False\n",
|
||||
"# Check if this compute target already exists in the workspace.\n",
|
||||
"cts = ws.compute_targets\n",
|
||||
"if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
|
||||
" found = True\n",
|
||||
" print('Found existing compute target.')\n",
|
||||
" compute_target = cts[amlcompute_cluster_name]\n",
|
||||
" \n",
|
||||
"if not found:\n",
|
||||
" print('Creating a new compute target...')\n",
|
||||
" provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
|
||||
" #vm_priority = 'lowpriority', # optional\n",
|
||||
" max_nodes = 6)\n",
|
||||
"\n",
|
||||
" # Create the cluster.\n",
|
||||
" compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
|
||||
" \n",
|
||||
" # Can poll for a minimum number of nodes and for a specific timeout.\n",
|
||||
" # If no min_node_count is provided, it will use the scale settings for the cluster.\n",
|
||||
" compute_target.wait_for_completion(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
|
||||
" \n",
|
||||
" # For a more detailed view of current AmlCompute status, use get_status()."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Data\n",
|
||||
"\n",
|
||||
"Here load the data in the get_data script to be utilized in azure compute. To do this, first load all the necessary libraries and dependencies to set up paths for the data and to create the conda_run_config."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if not os.path.isdir('data'):\n",
|
||||
" os.mkdir('data')\n",
|
||||
" \n",
|
||||
"if not os.path.exists(project_folder):\n",
|
||||
" os.makedirs(project_folder)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.runconfig import RunConfiguration\n",
|
||||
"from azureml.core.conda_dependencies import CondaDependencies\n",
|
||||
"\n",
|
||||
"# create a new RunConfig object\n",
|
||||
"conda_run_config = RunConfiguration(framework=\"python\")\n",
|
||||
"\n",
|
||||
"# Set compute target to AmlCompute\n",
|
||||
"conda_run_config.target = compute_target\n",
|
||||
"conda_run_config.environment.docker.enabled = True\n",
|
||||
"conda_run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy'])\n",
|
||||
"conda_run_config.environment.python.conda_dependencies = cd"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Load Data\n",
|
||||
"\n",
|
||||
"Here create the script to be run in azure compute for loading the data, load the concrete strength dataset into the X and y variables. Next, split the data using train_test_split and return X_train and y_train for training the model. Finally, return X_train and y_train for training the model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/compresive_strength_concrete.csv\"\n",
|
||||
"dflow = dprep.auto_read_file(data)\n",
|
||||
"dflow.get_profile()\n",
|
||||
"X = dflow.drop_columns(columns=['CONCRETE'])\n",
|
||||
"y = dflow.keep_columns(columns=['CONCRETE'], validate_column_exists=True)\n",
|
||||
"X_train, X_test = X.random_split(percentage=0.8, seed=223)\n",
|
||||
"y_train, y_test = y.random_split(percentage=0.8, seed=223) \n",
|
||||
"dflow.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Train\n",
|
||||
"\n",
|
||||
"Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
|
||||
"\n",
|
||||
"|Property|Description|\n",
|
||||
"|-|-|\n",
|
||||
"|**task**|classification or regression|\n",
|
||||
"|**primary_metric**|This is the metric that you want to optimize. Regression supports the following primary metrics: <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>|\n",
|
||||
"|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
|
||||
"|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
|
||||
"|**n_cross_validations**|Number of cross validation splits.|\n",
|
||||
"|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
|
||||
"|**y**|(sparse) array-like, shape = [n_samples, ], targets values.|\n",
|
||||
"|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|\n",
|
||||
"\n",
|
||||
"**_You can find more information about primary metrics_** [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#primary-metric)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"##### If you would like to see even better results increase \"iteration_time_out minutes\" to 10+ mins and increase \"iterations\" to a minimum of 30"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"automl_settings = {\n",
|
||||
" \"iteration_timeout_minutes\": 5,\n",
|
||||
" \"iterations\": 10,\n",
|
||||
" \"n_cross_validations\": 5,\n",
|
||||
" \"primary_metric\": 'spearman_correlation',\n",
|
||||
" \"preprocess\": True,\n",
|
||||
" \"max_concurrent_iterations\": 5,\n",
|
||||
" \"verbosity\": logging.INFO,\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"automl_config = AutoMLConfig(task = 'regression',\n",
|
||||
" debug_log = 'automl.log',\n",
|
||||
" path = project_folder,\n",
|
||||
" run_configuration=conda_run_config,\n",
|
||||
" X = X_train,\n",
|
||||
" y = y_train,\n",
|
||||
" **automl_settings\n",
|
||||
" )"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"remote_run = experiment.submit(automl_config, show_output = True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"remote_run"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Results\n",
|
||||
"Widget for Monitoring Runs\n",
|
||||
"The widget will first report a \u00e2\u20ac\u0153loading status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
|
||||
"Note: The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.widgets import RunDetails\n",
|
||||
"RunDetails(remote_run).show() "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"\n",
|
||||
"Retrieve All Child Runs\n",
|
||||
"You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"children = list(remote_run.get_children())\n",
|
||||
"metricslist = {}\n",
|
||||
"for run in children:\n",
|
||||
" properties = run.get_properties()\n",
|
||||
" metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
|
||||
" metricslist[int(properties['iteration'])] = metrics\n",
|
||||
"\n",
|
||||
"rundata = pd.DataFrame(metricslist).sort_index(1)\n",
|
||||
"rundata"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Retrieve the Best Model\n",
|
||||
"Below we select the best pipeline from our iterations. The get_output method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing. Overloads on get_output allow you to retrieve the best run and fitted model for any logged metric or for a particular iteration."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"best_run, fitted_model = remote_run.get_output()\n",
|
||||
"print(best_run)\n",
|
||||
"print(fitted_model)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Best Model Based on Any Other Metric\n",
|
||||
"Show the run and the model that has the smallest root_mean_squared_error value (which turned out to be the same as the one with largest spearman_correlation value):"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"lookup_metric = \"root_mean_squared_error\"\n",
|
||||
"best_run, fitted_model = remote_run.get_output(metric = lookup_metric)\n",
|
||||
"print(best_run)\n",
|
||||
"print(fitted_model)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"iteration = 3\n",
|
||||
"third_run, third_model = remote_run.get_output(iteration = iteration)\n",
|
||||
"print(third_run)\n",
|
||||
"print(third_model)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Register the Fitted Model for Deployment\n",
|
||||
"If neither metric nor iteration are specified in the register_model call, the iteration with the best primary metric is registered."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"description = 'AutoML Model'\n",
|
||||
"tags = None\n",
|
||||
"model = remote_run.register_model(description = description, tags = tags)\n",
|
||||
"\n",
|
||||
"print(remote_run.model_id) # This will be written to the script file later in the notebook."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create Scoring Script\n",
|
||||
"The scoring script is required to generate the image for deployment. It contains the code to do the predictions on input data."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import pickle\n",
|
||||
"import json\n",
|
||||
"import numpy\n",
|
||||
"import azureml.train.automl\n",
|
||||
"from sklearn.externals import joblib\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global model\n",
|
||||
" model_path = Model.get_model_path(model_name = '<<modelid>>') # this name is model.id of model that we want to deploy\n",
|
||||
" # deserialize the model file back into a sklearn model\n",
|
||||
" model = joblib.load(model_path)\n",
|
||||
"\n",
|
||||
"def run(rawdata):\n",
|
||||
" try:\n",
|
||||
" data = json.loads(rawdata)['data']\n",
|
||||
" data = numpy.array(data)\n",
|
||||
" result = model.predict(data)\n",
|
||||
" except Exception as e:\n",
|
||||
" result = str(e)\n",
|
||||
" return json.dumps({\"error\": result})\n",
|
||||
" return json.dumps({\"result\":result.tolist()})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create a YAML File for the Environment"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To ensure the fit results are consistent with the training results, the SDK dependency versions need to be the same as the environment that trains the model. Details about retrieving the versions can be found in notebook [12.auto-ml-retrieve-the-training-sdk-versions](12.auto-ml-retrieve-the-training-sdk-versions.ipynb)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"dependencies = remote_run.get_run_sdk_dependencies(iteration = 1)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"for p in ['azureml-train-automl', 'azureml-sdk', 'azureml-core']:\n",
|
||||
" print('{}\\t{}'.format(p, dependencies[p]))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.conda_dependencies import CondaDependencies\n",
|
||||
"\n",
|
||||
"myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn'], pip_packages=['azureml-sdk[automl]'])\n",
|
||||
"\n",
|
||||
"conda_env_file_name = 'myenv.yml'\n",
|
||||
"myenv.save_to_file('.', conda_env_file_name)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Substitute the actual version number in the environment file.\n",
|
||||
"# This is not strictly needed in this notebook because the model should have been generated using the current SDK version.\n",
|
||||
"# However, we include this in case this code is used on an experiment from a previous SDK version.\n",
|
||||
"\n",
|
||||
"with open(conda_env_file_name, 'r') as cefr:\n",
|
||||
" content = cefr.read()\n",
|
||||
"\n",
|
||||
"with open(conda_env_file_name, 'w') as cefw:\n",
|
||||
" cefw.write(content.replace(azureml.core.VERSION, dependencies['azureml-sdk']))\n",
|
||||
"\n",
|
||||
"# Substitute the actual model id in the script file.\n",
|
||||
"\n",
|
||||
"script_file_name = 'score.py'\n",
|
||||
"\n",
|
||||
"with open(script_file_name, 'r') as cefr:\n",
|
||||
" content = cefr.read()\n",
|
||||
"\n",
|
||||
"with open(script_file_name, 'w') as cefw:\n",
|
||||
" cefw.write(content.replace('<<modelid>>', remote_run.model_id))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create a Container Image\n",
|
||||
"\n",
|
||||
"Next use Azure Container Instances for deploying models as a web service for quickly deploying and validating your model\n",
|
||||
"or when testing a model that is under development."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.image import Image, ContainerImage\n",
|
||||
"\n",
|
||||
"image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
|
||||
" execution_script = script_file_name,\n",
|
||||
" conda_file = conda_env_file_name,\n",
|
||||
" tags = {'area': \"digits\", 'type': \"automl_regression\"},\n",
|
||||
" description = \"Image for automl regression sample\")\n",
|
||||
"\n",
|
||||
"image = Image.create(name = \"automlsampleimage\",\n",
|
||||
" # this is the model object \n",
|
||||
" models = [model],\n",
|
||||
" image_config = image_config, \n",
|
||||
" workspace = ws)\n",
|
||||
"\n",
|
||||
"image.wait_for_creation(show_output = True)\n",
|
||||
"\n",
|
||||
"if image.creation_state == 'Failed':\n",
|
||||
" print(\"Image build log at: \" + image.image_build_log_uri)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Deploy the Image as a Web Service on Azure Container Instance\n",
|
||||
"\n",
|
||||
"Deploy an image that contains the model and other assets needed by the service."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import AciWebservice\n",
|
||||
"\n",
|
||||
"aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
|
||||
" memory_gb = 1, \n",
|
||||
" tags = {'area': \"digits\", 'type': \"automl_regression\"}, \n",
|
||||
" description = 'sample service for Automl Regression')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import Webservice\n",
|
||||
"\n",
|
||||
"aci_service_name = 'automl-sample-concrete'\n",
|
||||
"print(aci_service_name)\n",
|
||||
"aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
|
||||
" image = image,\n",
|
||||
" name = aci_service_name,\n",
|
||||
" workspace = ws)\n",
|
||||
"aci_service.wait_for_deployment(True)\n",
|
||||
"print(aci_service.state)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Delete a Web Service\n",
|
||||
"\n",
|
||||
"Deletes the specified web service."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#aci_service.delete()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Get Logs from a Deployed Web Service\n",
|
||||
"\n",
|
||||
"Gets logs from a deployed web service."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#aci_service.get_logs()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Test\n",
|
||||
"\n",
|
||||
"Now that the model is trained, split the data in the same way the data was split for training (The difference here is the data is being split locally) and then run the test data through the trained model to get the predicted values."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X_test = X_test.to_pandas_dataframe()\n",
|
||||
"y_test = y_test.to_pandas_dataframe()\n",
|
||||
"y_test = np.array(y_test)\n",
|
||||
"y_test = y_test[:,0]\n",
|
||||
"X_train = X_train.to_pandas_dataframe()\n",
|
||||
"y_train = y_train.to_pandas_dataframe()\n",
|
||||
"y_train = np.array(y_train)\n",
|
||||
"y_train = y_train[:,0]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"##### Predict on training and test set, and calculate residual values."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"y_pred_train = fitted_model.predict(X_train)\n",
|
||||
"y_residual_train = y_train - y_pred_train\n",
|
||||
"\n",
|
||||
"y_pred_test = fitted_model.predict(X_test)\n",
|
||||
"y_residual_test = y_test - y_pred_test\n",
|
||||
"\n",
|
||||
"y_residual_train.shape"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%matplotlib inline\n",
|
||||
"from sklearn.metrics import mean_squared_error, r2_score\n",
|
||||
"\n",
|
||||
"# Set up a multi-plot chart.\n",
|
||||
"f, (a0, a1) = plt.subplots(1, 2, gridspec_kw = {'width_ratios':[1, 1], 'wspace':0, 'hspace': 0})\n",
|
||||
"f.suptitle('Regression Residual Values', fontsize = 18)\n",
|
||||
"f.set_figheight(6)\n",
|
||||
"f.set_figwidth(16)\n",
|
||||
"\n",
|
||||
"# Plot residual values of training set.\n",
|
||||
"a0.axis([0, 360, -200, 200])\n",
|
||||
"a0.plot(y_residual_train, 'bo', alpha = 0.5)\n",
|
||||
"a0.plot([-10,360],[0,0], 'r-', lw = 3)\n",
|
||||
"a0.text(16,170,'RMSE = {0:.2f}'.format(np.sqrt(mean_squared_error(y_train, y_pred_train))), fontsize = 12)\n",
|
||||
"a0.text(16,140,'R2 score = {0:.2f}'.format(r2_score(y_train, y_pred_train)), fontsize = 12)\n",
|
||||
"a0.set_xlabel('Training samples', fontsize = 12)\n",
|
||||
"a0.set_ylabel('Residual Values', fontsize = 12)\n",
|
||||
"\n",
|
||||
"# Plot a histogram.\n",
|
||||
"#a0.hist(y_residual_train, orientation = 'horizontal', color = ['b']*len(y_residual_train), bins = 10, histtype = 'step')\n",
|
||||
"#a0.hist(y_residual_train, orientation = 'horizontal', color = ['b']*len(y_residual_train), alpha = 0.2, bins = 10)\n",
|
||||
"\n",
|
||||
"# Plot residual values of test set.\n",
|
||||
"a1.axis([0, 90, -200, 200])\n",
|
||||
"a1.plot(y_residual_test, 'bo', alpha = 0.5)\n",
|
||||
"a1.plot([-10,360],[0,0], 'r-', lw = 3)\n",
|
||||
"a1.text(5,170,'RMSE = {0:.2f}'.format(np.sqrt(mean_squared_error(y_test, y_pred_test))), fontsize = 12)\n",
|
||||
"a1.text(5,140,'R2 score = {0:.2f}'.format(r2_score(y_test, y_pred_test)), fontsize = 12)\n",
|
||||
"a1.set_xlabel('Test samples', fontsize = 12)\n",
|
||||
"a1.set_yticklabels([])\n",
|
||||
"\n",
|
||||
"# Plot a histogram.\n",
|
||||
"#a1.hist(y_residual_test, orientation = 'horizontal', color = ['b']*len(y_residual_test), bins = 10, histtype = 'step')\n",
|
||||
"#a1.hist(y_residual_test, orientation = 'horizontal', color = ['b']*len(y_residual_test), alpha = 0.2, bins = 10)\n",
|
||||
"\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Calculate metrics for the prediction\n",
|
||||
"\n",
|
||||
"Now visualize the data on a scatter plot to show what our truth (actual) values are compared to the predicted values \n",
|
||||
"from the trained model that was returned."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Plot outputs\n",
|
||||
"%matplotlib notebook\n",
|
||||
"test_pred = plt.scatter(y_test, y_pred_test, color='b')\n",
|
||||
"test_test = plt.scatter(y_test, y_test, color='g')\n",
|
||||
"plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Acknowledgements\n",
|
||||
"\n",
|
||||
"This Predicting Compressive Strength of Concrete Dataset is made available under the CC0 1.0 Universal (CC0 1.0)\n",
|
||||
"Public Domain Dedication License: https://creativecommons.org/publicdomain/zero/1.0/. Any rights in individual contents of the database are licensed under the CC0 1.0 Universal (CC0 1.0)\n",
|
||||
"Public Domain Dedication License: https://creativecommons.org/publicdomain/zero/1.0/ . The dataset itself can be found here: https://www.kaggle.com/pavanraj159/concrete-compressive-strength-data-set and http://archive.ics.uci.edu/ml/datasets/concrete+compressive+strength\n",
|
||||
"\n",
|
||||
"I-Cheng Yeh, \"Modeling of strength of high performance concrete using artificial neural networks,\" Cement and Concrete Research, Vol. 28, No. 12, pp. 1797-1808 (1998). \n",
|
||||
"\n",
|
||||
"Dua, D. and Graff, C. (2019). UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science."
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "v-rasav"
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-regression-concrete-strength
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,800 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Automated Machine Learning\n",
|
||||
"_**Regression with Deployment using Hardware Performance Dataset**_\n",
|
||||
"\n",
|
||||
"## Contents\n",
|
||||
"1. [Introduction](#Introduction)\n",
|
||||
"1. [Setup](#Setup)\n",
|
||||
"1. [Data](#Data)\n",
|
||||
"1. [Train](#Train)\n",
|
||||
"1. [Results](#Results)\n",
|
||||
"1. [Test](#Test)\n",
|
||||
"1. [Acknowledgements](#Acknowledgements)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Introduction\n",
|
||||
"In this example we use the Hardware Performance Dataset to showcase how you can use AutoML for a simple regression problem. The Regression goal is to predict the performance of certain combinations of hardware parts.\n",
|
||||
"\n",
|
||||
"If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, go through the [configuration](../../../configuration.ipynb) notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
|
||||
"\n",
|
||||
"In this notebook you will learn how to:\n",
|
||||
"1. Create an `Experiment` in an existing `Workspace`.\n",
|
||||
"2. Configure AutoML using `AutoMLConfig`.\n",
|
||||
"3. Train the model using local compute.\n",
|
||||
"4. Explore the results.\n",
|
||||
"5. Test the best fitted model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setup\n",
|
||||
"As part of the setup you have already created an Azure ML Workspace object. For AutoML you will need to create an Experiment object, which is a named object in a Workspace used to run experiments."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import logging\n",
|
||||
"\n",
|
||||
"from matplotlib import pyplot as plt\n",
|
||||
"import numpy as np\n",
|
||||
"import pandas as pd\n",
|
||||
"import os\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"import azureml.dataprep as dprep\n",
|
||||
" \n",
|
||||
"\n",
|
||||
"import azureml.core\n",
|
||||
"from azureml.core.experiment import Experiment\n",
|
||||
"from azureml.core.workspace import Workspace\n",
|
||||
"from azureml.train.automl import AutoMLConfig"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ws = Workspace.from_config()\n",
|
||||
"\n",
|
||||
"# Choose a name for the experiment and specify the project folder.\n",
|
||||
"experiment_name = 'automl-regression-hardware'\n",
|
||||
"project_folder = './sample_projects/automl-remote-regression'\n",
|
||||
"\n",
|
||||
"experiment = Experiment(ws, experiment_name)\n",
|
||||
"\n",
|
||||
"output = {}\n",
|
||||
"output['SDK version'] = azureml.core.VERSION\n",
|
||||
"output['Subscription ID'] = ws.subscription_id\n",
|
||||
"output['Workspace Name'] = ws.name\n",
|
||||
"output['Resource Group'] = ws.resource_group\n",
|
||||
"output['Location'] = ws.location\n",
|
||||
"output['Project Directory'] = project_folder\n",
|
||||
"output['Experiment Name'] = experiment.name\n",
|
||||
"pd.set_option('display.max_colwidth', -1)\n",
|
||||
"outputDf = pd.DataFrame(data = output, index = [''])\n",
|
||||
"outputDf.T"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Create or Attach existing AmlCompute\n",
|
||||
"You will need to create a compute target for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
|
||||
"#### Creation of AmlCompute takes approximately 5 minutes. \n",
|
||||
"If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
|
||||
"As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read this article on the default limits and how to request more quota."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.compute import AmlCompute\n",
|
||||
"from azureml.core.compute import ComputeTarget\n",
|
||||
"\n",
|
||||
"# Choose a name for your cluster.\n",
|
||||
"amlcompute_cluster_name = \"automlcl\"\n",
|
||||
"\n",
|
||||
"found = False\n",
|
||||
"# Check if this compute target already exists in the workspace.\n",
|
||||
"cts = ws.compute_targets\n",
|
||||
"if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
|
||||
" found = True\n",
|
||||
" print('Found existing compute target.')\n",
|
||||
" compute_target = cts[amlcompute_cluster_name]\n",
|
||||
" \n",
|
||||
"if not found:\n",
|
||||
" print('Creating a new compute target...')\n",
|
||||
" provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
|
||||
" #vm_priority = 'lowpriority', # optional\n",
|
||||
" max_nodes = 6)\n",
|
||||
"\n",
|
||||
" # Create the cluster.\n",
|
||||
" compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
|
||||
" \n",
|
||||
" # Can poll for a minimum number of nodes and for a specific timeout.\n",
|
||||
" # If no min_node_count is provided, it will use the scale settings for the cluster.\n",
|
||||
" compute_target.wait_for_completion(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
|
||||
" \n",
|
||||
" # For a more detailed view of current AmlCompute status, use get_status()."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Data\n",
|
||||
"\n",
|
||||
"Here load the data in the get_data script to be utilized in azure compute. To do this, first load all the necessary libraries and dependencies to set up paths for the data and to create the conda_run_config."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if not os.path.isdir('data'):\n",
|
||||
" os.mkdir('data')\n",
|
||||
" \n",
|
||||
"if not os.path.exists(project_folder):\n",
|
||||
" os.makedirs(project_folder)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.runconfig import RunConfiguration\n",
|
||||
"from azureml.core.conda_dependencies import CondaDependencies\n",
|
||||
"\n",
|
||||
"# create a new RunConfig object\n",
|
||||
"conda_run_config = RunConfiguration(framework=\"python\")\n",
|
||||
"\n",
|
||||
"# Set compute target to AmlCompute\n",
|
||||
"conda_run_config.target = compute_target\n",
|
||||
"conda_run_config.environment.docker.enabled = True\n",
|
||||
"conda_run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy'])\n",
|
||||
"conda_run_config.environment.python.conda_dependencies = cd"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Load Data\n",
|
||||
"\n",
|
||||
"Here create the script to be run in azure compute for loading the data, load the hardware dataset into the X and y variables. Next split the data using train_test_split and return X_train and y_train for training the model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/machineData.csv\"\n",
|
||||
"dflow = dprep.auto_read_file(data)\n",
|
||||
"dflow.get_profile()\n",
|
||||
"X = dflow.drop_columns(columns=['ERP'])\n",
|
||||
"y = dflow.keep_columns(columns=['ERP'], validate_column_exists=True)\n",
|
||||
"X_train, X_test = X.random_split(percentage=0.8, seed=223)\n",
|
||||
"y_train, y_test = y.random_split(percentage=0.8, seed=223) \n",
|
||||
"dflow.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"\n",
|
||||
"## Train\n",
|
||||
"\n",
|
||||
"Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
|
||||
"\n",
|
||||
"|Property|Description|\n",
|
||||
"|-|-|\n",
|
||||
"|**task**|classification or regression|\n",
|
||||
"|**primary_metric**|This is the metric that you want to optimize. Regression supports the following primary metrics: <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>|\n",
|
||||
"|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
|
||||
"|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
|
||||
"|**n_cross_validations**|Number of cross validation splits.|\n",
|
||||
"|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
|
||||
"|**y**|(sparse) array-like, shape = [n_samples, ], targets values.|\n",
|
||||
"|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|\n",
|
||||
"\n",
|
||||
"**_You can find more information about primary metrics_** [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#primary-metric)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"##### If you would like to see even better results increase \"iteration_time_out minutes\" to 10+ mins and increase \"iterations\" to a minimum of 30"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"automl_settings = {\n",
|
||||
" \"iteration_timeout_minutes\": 5,\n",
|
||||
" \"iterations\": 10,\n",
|
||||
" \"n_cross_validations\": 5,\n",
|
||||
" \"primary_metric\": 'spearman_correlation',\n",
|
||||
" \"preprocess\": True,\n",
|
||||
" \"max_concurrent_iterations\": 5,\n",
|
||||
" \"verbosity\": logging.INFO,\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"automl_config = AutoMLConfig(task = 'regression',\n",
|
||||
" debug_log = 'automl_errors_20190417.log',\n",
|
||||
" path = project_folder,\n",
|
||||
" run_configuration=conda_run_config,\n",
|
||||
" X = X_train,\n",
|
||||
" y = y_train,\n",
|
||||
" **automl_settings\n",
|
||||
" )"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"remote_run = experiment.submit(automl_config, show_output = False)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"remote_run"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Results"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Widget for Monitoring Runs\n",
|
||||
"\n",
|
||||
"The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
|
||||
"\n",
|
||||
"**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.widgets import RunDetails\n",
|
||||
"RunDetails(remote_run).show() "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Wait until the run finishes.\n",
|
||||
"remote_run.wait_for_completion(show_output = True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Retrieve All Child Runs\n",
|
||||
"You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"children = list(remote_run.get_children())\n",
|
||||
"metricslist = {}\n",
|
||||
"for run in children:\n",
|
||||
" properties = run.get_properties()\n",
|
||||
" metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
|
||||
" metricslist[int(properties['iteration'])] = metrics\n",
|
||||
"\n",
|
||||
"rundata = pd.DataFrame(metricslist).sort_index(1)\n",
|
||||
"rundata"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Retrieve the Best Model\n",
|
||||
"Below we select the best pipeline from our iterations. The get_output method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing. Overloads on get_output allow you to retrieve the best run and fitted model for any logged metric or for a particular iteration."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"best_run, fitted_model = remote_run.get_output()\n",
|
||||
"print(best_run)\n",
|
||||
"print(fitted_model)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Best Model Based on Any Other Metric\n",
|
||||
"Show the run and the model that has the smallest `root_mean_squared_error` value (which turned out to be the same as the one with largest `spearman_correlation` value):"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"lookup_metric = \"root_mean_squared_error\"\n",
|
||||
"best_run, fitted_model = remote_run.get_output(metric = lookup_metric)\n",
|
||||
"print(best_run)\n",
|
||||
"print(fitted_model)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"iteration = 3\n",
|
||||
"third_run, third_model = remote_run.get_output(iteration = iteration)\n",
|
||||
"print(third_run)\n",
|
||||
"print(third_model)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Register the Fitted Model for Deployment\n",
|
||||
"If neither metric nor iteration are specified in the register_model call, the iteration with the best primary metric is registered."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"description = 'AutoML Model'\n",
|
||||
"tags = None\n",
|
||||
"model = remote_run.register_model(description = description, tags = tags)\n",
|
||||
"\n",
|
||||
"print(remote_run.model_id) # This will be written to the script file later in the notebook."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create Scoring Script\n",
|
||||
"The scoring script is required to generate the image for deployment. It contains the code to do the predictions on input data."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import pickle\n",
|
||||
"import json\n",
|
||||
"import numpy\n",
|
||||
"import azureml.train.automl\n",
|
||||
"from sklearn.externals import joblib\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global model\n",
|
||||
" model_path = Model.get_model_path(model_name = '<<modelid>>') # this name is model.id of model that we want to deploy\n",
|
||||
" # deserialize the model file back into a sklearn model\n",
|
||||
" model = joblib.load(model_path)\n",
|
||||
"\n",
|
||||
"def run(rawdata):\n",
|
||||
" try:\n",
|
||||
" data = json.loads(rawdata)['data']\n",
|
||||
" data = numpy.array(data)\n",
|
||||
" result = model.predict(data)\n",
|
||||
" except Exception as e:\n",
|
||||
" result = str(e)\n",
|
||||
" return json.dumps({\"error\": result})\n",
|
||||
" return json.dumps({\"result\":result.tolist()})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create a YAML File for the Environment"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To ensure the fit results are consistent with the training results, the SDK dependency versions need to be the same as the environment that trains the model. Details about retrieving the versions can be found in notebook [12.auto-ml-retrieve-the-training-sdk-versions](12.auto-ml-retrieve-the-training-sdk-versions.ipynb)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"dependencies = remote_run.get_run_sdk_dependencies(iteration = 1)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"for p in ['azureml-train-automl', 'azureml-sdk', 'azureml-core']:\n",
|
||||
" print('{}\\t{}'.format(p, dependencies[p]))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn'], pip_packages=['azureml-sdk[automl]'])\n",
|
||||
"\n",
|
||||
"conda_env_file_name = 'myenv.yml'\n",
|
||||
"myenv.save_to_file('.', conda_env_file_name)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Substitute the actual version number in the environment file.\n",
|
||||
"# This is not strictly needed in this notebook because the model should have been generated using the current SDK version.\n",
|
||||
"# However, we include this in case this code is used on an experiment from a previous SDK version.\n",
|
||||
"\n",
|
||||
"with open(conda_env_file_name, 'r') as cefr:\n",
|
||||
" content = cefr.read()\n",
|
||||
"\n",
|
||||
"with open(conda_env_file_name, 'w') as cefw:\n",
|
||||
" cefw.write(content.replace(azureml.core.VERSION, dependencies['azureml-sdk']))\n",
|
||||
"\n",
|
||||
"# Substitute the actual model id in the script file.\n",
|
||||
"\n",
|
||||
"script_file_name = 'score.py'\n",
|
||||
"\n",
|
||||
"with open(script_file_name, 'r') as cefr:\n",
|
||||
" content = cefr.read()\n",
|
||||
"\n",
|
||||
"with open(script_file_name, 'w') as cefw:\n",
|
||||
" cefw.write(content.replace('<<modelid>>', remote_run.model_id))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create a Container Image\n",
|
||||
"\n",
|
||||
"Next use Azure Container Instances for deploying models as a web service for quickly deploying and validating your model\n",
|
||||
"or when testing a model that is under development."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.image import Image, ContainerImage\n",
|
||||
"\n",
|
||||
"image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
|
||||
" execution_script = script_file_name,\n",
|
||||
" conda_file = conda_env_file_name,\n",
|
||||
" tags = {'area': \"digits\", 'type': \"automl_regression\"},\n",
|
||||
" description = \"Image for automl regression sample\")\n",
|
||||
"\n",
|
||||
"image = Image.create(name = \"automlsampleimage\",\n",
|
||||
" # this is the model object \n",
|
||||
" models = [model],\n",
|
||||
" image_config = image_config, \n",
|
||||
" workspace = ws)\n",
|
||||
"\n",
|
||||
"image.wait_for_creation(show_output = True)\n",
|
||||
"\n",
|
||||
"if image.creation_state == 'Failed':\n",
|
||||
" print(\"Image build log at: \" + image.image_build_log_uri)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Deploy the Image as a Web Service on Azure Container Instance\n",
|
||||
"\n",
|
||||
"Deploy an image that contains the model and other assets needed by the service."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import AciWebservice\n",
|
||||
"\n",
|
||||
"aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
|
||||
" memory_gb = 1, \n",
|
||||
" tags = {'area': \"digits\", 'type': \"automl_regression\"}, \n",
|
||||
" description = 'sample service for Automl Regression')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import Webservice\n",
|
||||
"\n",
|
||||
"aci_service_name = 'automl-sample-hardware'\n",
|
||||
"print(aci_service_name)\n",
|
||||
"aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
|
||||
" image = image,\n",
|
||||
" name = aci_service_name,\n",
|
||||
" workspace = ws)\n",
|
||||
"aci_service.wait_for_deployment(True)\n",
|
||||
"print(aci_service.state)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Delete a Web Service\n",
|
||||
"\n",
|
||||
"Deletes the specified web service."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#aci_service.delete()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Get Logs from a Deployed Web Service\n",
|
||||
"\n",
|
||||
"Gets logs from a deployed web service."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#aci_service.get_logs()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Test\n",
|
||||
"\n",
|
||||
"Now that the model is trained, split the data in the same way the data was split for training (The difference here is the data is being split locally) and then run the test data through the trained model to get the predicted values."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X_test = X_test.to_pandas_dataframe()\n",
|
||||
"y_test = y_test.to_pandas_dataframe()\n",
|
||||
"y_test = np.array(y_test)\n",
|
||||
"y_test = y_test[:,0]\n",
|
||||
"X_train = X_train.to_pandas_dataframe()\n",
|
||||
"y_train = y_train.to_pandas_dataframe()\n",
|
||||
"y_train = np.array(y_train)\n",
|
||||
"y_train = y_train[:,0]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"##### Predict on training and test set, and calculate residual values."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"y_pred_train = fitted_model.predict(X_train)\n",
|
||||
"y_residual_train = y_train - y_pred_train\n",
|
||||
"\n",
|
||||
"y_pred_test = fitted_model.predict(X_test)\n",
|
||||
"y_residual_test = y_test - y_pred_test"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Calculate metrics for the prediction\n",
|
||||
"\n",
|
||||
"Now visualize the data on a scatter plot to show what our truth (actual) values are compared to the predicted values \n",
|
||||
"from the trained model that was returned."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%matplotlib inline\n",
|
||||
"from sklearn.metrics import mean_squared_error, r2_score\n",
|
||||
"\n",
|
||||
"# Set up a multi-plot chart.\n",
|
||||
"f, (a0, a1) = plt.subplots(1, 2, gridspec_kw = {'width_ratios':[1, 1], 'wspace':0, 'hspace': 0})\n",
|
||||
"f.suptitle('Regression Residual Values', fontsize = 18)\n",
|
||||
"f.set_figheight(6)\n",
|
||||
"f.set_figwidth(16)\n",
|
||||
"\n",
|
||||
"# Plot residual values of training set.\n",
|
||||
"a0.axis([0, 360, -200, 200])\n",
|
||||
"a0.plot(y_residual_train, 'bo', alpha = 0.5)\n",
|
||||
"a0.plot([-10,360],[0,0], 'r-', lw = 3)\n",
|
||||
"a0.text(16,170,'RMSE = {0:.2f}'.format(np.sqrt(mean_squared_error(y_train, y_pred_train))), fontsize = 12)\n",
|
||||
"a0.text(16,140,'R2 score = {0:.2f}'.format(r2_score(y_train, y_pred_train)),fontsize = 12)\n",
|
||||
"a0.set_xlabel('Training samples', fontsize = 12)\n",
|
||||
"a0.set_ylabel('Residual Values', fontsize = 12)\n",
|
||||
"\n",
|
||||
"# Plot residual values of test set.\n",
|
||||
"a1.axis([0, 90, -200, 200])\n",
|
||||
"a1.plot(y_residual_test, 'bo', alpha = 0.5)\n",
|
||||
"a1.plot([-10,360],[0,0], 'r-', lw = 3)\n",
|
||||
"a1.text(5,170,'RMSE = {0:.2f}'.format(np.sqrt(mean_squared_error(y_test, y_pred_test))), fontsize = 12)\n",
|
||||
"a1.text(5,140,'R2 score = {0:.2f}'.format(r2_score(y_test, y_pred_test)),fontsize = 12)\n",
|
||||
"a1.set_xlabel('Test samples', fontsize = 12)\n",
|
||||
"a1.set_yticklabels([])\n",
|
||||
"\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%matplotlib notebook\n",
|
||||
"test_pred = plt.scatter(y_test, y_pred_test, color='')\n",
|
||||
"test_test = plt.scatter(y_test, y_test, color='g')\n",
|
||||
"plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Acknowledgements\n",
|
||||
"This Predicting Hardware Performance Dataset is made available under the CC0 1.0 Universal (CC0 1.0) Public Domain Dedication License: https://creativecommons.org/publicdomain/zero/1.0/. Any rights in individual contents of the database are licensed under the CC0 1.0 Universal (CC0 1.0) Public Domain Dedication License: https://creativecommons.org/publicdomain/zero/1.0/ . The dataset itself can be found here: https://www.kaggle.com/faizunnabi/comp-hardware-performance and https://archive.ics.uci.edu/ml/datasets/Computer+Hardware\n",
|
||||
"\n",
|
||||
"_**Citation Found Here**_\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "v-rasav"
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-regression-hardware-performance
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,9 @@
|
||||
name: auto-ml-regression
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
- paramiko<2.5.0
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-remote-amlcompute
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-sample-weight
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-sparse-data-train-test-split
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-subsampling-local
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -126,25 +126,6 @@
|
||||
"**Note:** Creation of a new workspace can take several minutes."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"##TESTONLY\n",
|
||||
"# Import the Workspace class and check the Azure ML SDK version.\n",
|
||||
"from azureml.core import Workspace\n",
|
||||
"\n",
|
||||
"ws = Workspace.create(name = workspace_name,\n",
|
||||
" subscription_id = subscription_id,\n",
|
||||
" resource_group = resource_group, \n",
|
||||
" location = workspace_region,\n",
|
||||
" auth = auth_sp,\n",
|
||||
" exist_ok=True)\n",
|
||||
"ws.get_details()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
@@ -612,7 +593,7 @@
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "Python",
|
||||
"name": "Python36"
|
||||
"name": "python36"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -0,0 +1,4 @@
|
||||
name: model-register-and-deploy
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
@@ -0,0 +1,4 @@
|
||||
name: enable-app-insights-in-production-service
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
@@ -0,0 +1,4 @@
|
||||
name: enable-data-collection-for-models-in-aks
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
@@ -0,0 +1,6 @@
|
||||
name: onnx-convert-aml-deploy-tinyyolo
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- git+https://github.com/apple/coremltools
|
||||
- onnxmltools==1.3.1
|
||||
@@ -0,0 +1,9 @@
|
||||
name: onnx-inference-facial-expression-recognition-deploy
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- numpy
|
||||
- onnx
|
||||
- opencv-python
|
||||
@@ -0,0 +1,9 @@
|
||||
name: onnx-inference-mnist-deploy
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- numpy
|
||||
- onnx
|
||||
- opencv-python
|
||||
@@ -0,0 +1,4 @@
|
||||
name: onnx-modelzoo-aml-deploy-resnet50
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
@@ -0,0 +1,5 @@
|
||||
name: onnx-train-pytorch-aml-deploy-mnist
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
@@ -385,9 +385,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
"name": "python36"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -0,0 +1,8 @@
|
||||
name: production-deploy-to-aks
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- matplotlib
|
||||
- tqdm
|
||||
- scipy
|
||||
- sklearn
|
||||
@@ -0,0 +1,8 @@
|
||||
name: register-model-create-image-deploy-service
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- matplotlib
|
||||
- tqdm
|
||||
- scipy
|
||||
- sklearn
|
||||
@@ -265,7 +265,7 @@
|
||||
"from azureml.core.compute_target import ComputeTargetException\n",
|
||||
"\n",
|
||||
"# Choose a name for your CPU cluster\n",
|
||||
"cpu_cluster_name = \"cpucluster\"\n",
|
||||
"cpu_cluster_name = \"cpu-cluster\"\n",
|
||||
"\n",
|
||||
"# Verify that cluster does not exist already\n",
|
||||
"try:\n",
|
||||
@@ -370,7 +370,7 @@
|
||||
"from azureml.core.compute_target import ComputeTargetException\n",
|
||||
"\n",
|
||||
"# Choose a name for your CPU cluster\n",
|
||||
"cpu_cluster_name = \"cpucluster\"\n",
|
||||
"cpu_cluster_name = \"cpu-cluster\"\n",
|
||||
"\n",
|
||||
"# Verify that cluster does not exist already\n",
|
||||
"try:\n",
|
||||
@@ -506,7 +506,7 @@
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Delete () is used to deprovision and delete the AmlCompute target. Useful if you want to re-use the compute name \n",
|
||||
"# 'cpucluster' in this case but use a different VM family for instance.\n",
|
||||
"# 'cpu-cluster' in this case but use a different VM family for instance.\n",
|
||||
"\n",
|
||||
"# cpu_cluster.delete()"
|
||||
]
|
||||
|
||||
@@ -0,0 +1,6 @@
|
||||
name: regression-sklearn-on-amlcompute
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-explain-model
|
||||
- azureml-contrib-explain-model
|
||||
@@ -0,0 +1,6 @@
|
||||
name: explain-local-sklearn-binary-classification
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-explain-model
|
||||
- azureml-contrib-explain-model
|
||||
@@ -0,0 +1,6 @@
|
||||
name: explain-local-sklearn-multiclass-classification
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-explain-model
|
||||
- azureml-contrib-explain-model
|
||||
@@ -0,0 +1,6 @@
|
||||
name: explain-local-sklearn-regression
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-explain-model
|
||||
- azureml-contrib-explain-model
|
||||
@@ -36,22 +36,6 @@
|
||||
"4. Visualize the global and local explanations with the visualization dashboard."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"This example needs sklearn-pandas. If it is not installed, uncomment and run the following line."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#!pip install sklearn-pandas"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
@@ -63,7 +47,6 @@
|
||||
"from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
|
||||
"from sklearn.linear_model import LogisticRegression\n",
|
||||
"from azureml.explain.model.tabular_explainer import TabularExplainer\n",
|
||||
"from sklearn_pandas import DataFrameMapper\n",
|
||||
"import pandas as pd\n",
|
||||
"import numpy as np"
|
||||
]
|
||||
@@ -113,6 +96,13 @@
|
||||
"x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"sklearn imports"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
@@ -121,7 +111,51 @@
|
||||
"source": [
|
||||
"from sklearn.pipeline import Pipeline\n",
|
||||
"from sklearn.impute import SimpleImputer\n",
|
||||
"from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
|
||||
"from sklearn.preprocessing import StandardScaler, OneHotEncoder"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can explain raw features by either using a `sklearn.compose.ColumnTransformer` or a list of fitted transformer tuples. The cell below uses `sklearn.compose.ColumnTransformer`. In case you want to run the example with the list of fitted transformer tuples, comment the cell below and uncomment the cell that follows after. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.compose import ColumnTransformer\n",
|
||||
"\n",
|
||||
"transformations = ColumnTransformer([\n",
|
||||
" (\"age_fare\", Pipeline(steps=[\n",
|
||||
" ('imputer', SimpleImputer(strategy='median')),\n",
|
||||
" ('scaler', StandardScaler())\n",
|
||||
" ]), [\"age\", \"fare\"]),\n",
|
||||
" (\"embarked\", Pipeline(steps=[\n",
|
||||
" (\"imputer\", SimpleImputer(strategy='constant', fill_value='missing')), \n",
|
||||
" (\"encoder\", OneHotEncoder(sparse=False))]), [\"embarked\"]),\n",
|
||||
" (\"sex_pclass\", OneHotEncoder(sparse=False), [\"sex\", \"pclass\"]) \n",
|
||||
"])\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# Append classifier to preprocessing pipeline.\n",
|
||||
"# Now we have a full prediction pipeline.\n",
|
||||
"clf = Pipeline(steps=[('preprocessor', transformations),\n",
|
||||
" ('classifier', LogisticRegression(solver='lbfgs'))])\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"'''\n",
|
||||
"# Uncomment below if sklearn-pandas is not installed\n",
|
||||
"#!pip install sklearn-pandas\n",
|
||||
"from sklearn_pandas import DataFrameMapper\n",
|
||||
"\n",
|
||||
"# Impute, standardize the numeric features and one-hot encode the categorical features. \n",
|
||||
@@ -141,7 +175,8 @@
|
||||
"# Append classifier to preprocessing pipeline.\n",
|
||||
"# Now we have a full prediction pipeline.\n",
|
||||
"clf = Pipeline(steps=[('preprocessor', DataFrameMapper(transformations)),\n",
|
||||
" ('classifier', LogisticRegression(solver='lbfgs'))])"
|
||||
" ('classifier', LogisticRegression(solver='lbfgs'))])\n",
|
||||
"'''"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
@@ -0,0 +1,7 @@
|
||||
name: explain-sklearn-raw-features
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-explain-model
|
||||
- azureml-contrib-explain-model
|
||||
- sklearn-pandas
|
||||
@@ -0,0 +1,6 @@
|
||||
name: explain-run-history-sklearn-classification
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-explain-model
|
||||
- azureml-contrib-explain-model
|
||||
@@ -0,0 +1,6 @@
|
||||
name: explain-run-history-sklearn-regression
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-explain-model
|
||||
- azureml-contrib-explain-model
|
||||
@@ -0,0 +1,5 @@
|
||||
name: aml-pipelines-data-transfer
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
@@ -0,0 +1,5 @@
|
||||
name: aml-pipelines-getting-started
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
@@ -0,0 +1,5 @@
|
||||
name: aml-pipelines-how-to-use-estimatorstep
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
@@ -0,0 +1,6 @@
|
||||
name: aml-pipelines-publish-and-run-using-rest-endpoint
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
- requests
|
||||
@@ -0,0 +1,8 @@
|
||||
name: aml-pipelines-with-automated-machine-learning-step
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,5 @@
|
||||
name: aml-pipelines-with-data-dependency-steps
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
@@ -0,0 +1,24 @@
|
||||
# Copyright (c) Microsoft. All rights reserved.
|
||||
# Licensed under the MIT license.
|
||||
|
||||
import argparse
|
||||
import os
|
||||
|
||||
print("In compare.py")
|
||||
print("As a data scientist, this is where I use my compare code.")
|
||||
parser = argparse.ArgumentParser("compare")
|
||||
parser.add_argument("--compare_data1", type=str, help="compare_data1 data")
|
||||
parser.add_argument("--compare_data2", type=str, help="compare_data2 data")
|
||||
parser.add_argument("--output_compare", type=str, help="output_compare directory")
|
||||
parser.add_argument("--pipeline_param", type=int, help="pipeline parameter")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
print("Argument 1: %s" % args.compare_data1)
|
||||
print("Argument 2: %s" % args.compare_data2)
|
||||
print("Argument 3: %s" % args.output_compare)
|
||||
print("Argument 4: %s" % args.pipeline_param)
|
||||
|
||||
if not (args.output_compare is None):
|
||||
os.makedirs(args.output_compare, exist_ok=True)
|
||||
print("%s created" % args.output_compare)
|
||||
@@ -0,0 +1,21 @@
|
||||
# Copyright (c) Microsoft. All rights reserved.
|
||||
# Licensed under the MIT license.
|
||||
|
||||
import argparse
|
||||
import os
|
||||
|
||||
print("In extract.py")
|
||||
print("As a data scientist, this is where I use my extract code.")
|
||||
|
||||
parser = argparse.ArgumentParser("extract")
|
||||
parser.add_argument("--input_extract", type=str, help="input_extract data")
|
||||
parser.add_argument("--output_extract", type=str, help="output_extract directory")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
print("Argument 1: %s" % args.input_extract)
|
||||
print("Argument 2: %s" % args.output_extract)
|
||||
|
||||
if not (args.output_extract is None):
|
||||
os.makedirs(args.output_extract, exist_ok=True)
|
||||
print("%s created" % args.output_extract)
|
||||
@@ -0,0 +1,22 @@
|
||||
# Copyright (c) Microsoft. All rights reserved.
|
||||
# Licensed under the MIT license.
|
||||
|
||||
import argparse
|
||||
import os
|
||||
|
||||
print("In train.py")
|
||||
print("As a data scientist, this is where I use my training code.")
|
||||
|
||||
parser = argparse.ArgumentParser("train")
|
||||
|
||||
parser.add_argument("--input_data", type=str, help="input data")
|
||||
parser.add_argument("--output_train", type=str, help="output_train directory")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
print("Argument 1: %s" % args.input_data)
|
||||
print("Argument 2: %s" % args.output_train)
|
||||
|
||||
if not (args.output_train is None):
|
||||
os.makedirs(args.output_train, exist_ok=True)
|
||||
print("%s created" % args.output_train)
|
||||
@@ -0,0 +1,9 @@
|
||||
name: nyc-taxi-data-regression-model-building
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
- azureml-contrib-opendatasets
|
||||
- azureml-dataprep
|
||||
- azureml-train-automl
|
||||
- matplotlib
|
||||
@@ -0,0 +1,7 @@
|
||||
name: pipeline-batch-scoring
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
- pandas
|
||||
- requests
|
||||
@@ -0,0 +1,6 @@
|
||||
name: pipeline-style-transfer
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
- requests
|
||||
@@ -6,8 +6,20 @@
|
||||
"source": [
|
||||
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Authentication in Azure Machine Learning\n",
|
||||
"\n",
|
||||
"This notebook shows you how to authenticate to your Azure ML Workspace using\n",
|
||||
@@ -19,13 +31,6 @@
|
||||
"The interactive authentication is suitable for local experimentation on your own computer. Azure CLI authentication is suitable if you are already using Azure CLI for managing Azure resources, and want to sign in only once. The Service Principal authentication is suitable for automated workflows, for example as part of Azure Devops build."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
@@ -92,7 +97,7 @@
|
||||
"source": [
|
||||
"In some cases, you may see a version of the error message containing text: ```All the subscriptions that you have access to = []```\n",
|
||||
"\n",
|
||||
"In such a case, you may have to specify the tenant ID of the Azure Active Directory you're using. An example would be accessing a subscription as a guest to a tenant that is not your default. You specify the tenant by explicitly instantiating _InteractiveLoginAuthentication_ with tenant ID as argument ([see instructions how to obtain tenant Id](#get-tenant-id))."
|
||||
"In such a case, you may have to specify the tenant ID of the Azure Active Directory you're using. An example would be accessing a subscription as a guest to a tenant that is not your default. You specify the tenant by explicitly instantiating _InteractiveLoginAuthentication_ with Tenant ID as argument. The Tenant ID can be found, for example, from https://portal.azure.com under **Azure Active Directory**, **Properties** as Directory ID."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -150,31 +155,27 @@
|
||||
"\n",
|
||||
"Note that you must have administrator privileges over the Azure subscription to complete these steps.\n",
|
||||
"\n",
|
||||
"The first step is to create a service principal. First, go to [Azure Portal](https://portal.azure.com), select **Azure Active Directory** and **App Registrations**. Then select **+New application registration**, give your service principal a name, for example _my-svc-principal_. You can leave application type as is, and specify a dummy value for Sign-on URL, such as _https://invalid_.\n",
|
||||
"The first step is to create a service principal. First, go to [Azure Portal](https://portal.azure.com), select **Azure Active Directory** and **App Registrations**. Then select **+New application**, give your service principal a name, for example _my-svc-principal_. You can leave other parameters as is.\n",
|
||||
"\n",
|
||||
"Then click **Create**.\n",
|
||||
"Then click **Register**.\n",
|
||||
"\n",
|
||||
"![service principal creation]<img src=\"images/svc-pr-1.PNG\">"
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The next step is to obtain the _Application ID_ (also called username) and create _password_ for the service principal.\n",
|
||||
"\n",
|
||||
"From the page for your newly created service principal, copy the _Application ID_. Then select **Settings** and **Keys**, write a description for your key, and select duration. Then click **Save**, and copy the _password_ to a secure location.\n",
|
||||
"\n",
|
||||
""
|
||||
"From the page for your newly created service principal, copy the _Application ID_ and _Tenant ID_ as they are needed later.\n",
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a id =\"get-tenant-id\"></a>\n",
|
||||
"Then select **Certificates & secrets**, and **+New client secret** write a description for your key, and select duration. Then click **Add**, and copy the value of client secret to a secure location.\n",
|
||||
"\n",
|
||||
"Also, you need to obtain the tenant ID of your Azure subscription. Go back to **Azure Active Directory**, select **Properties** and copy _Directory ID_.\n",
|
||||
"\n",
|
||||
""
|
||||
]
|
||||
@@ -229,6 +230,20 @@
|
||||
"\n",
|
||||
"print(\"Found workspace {} at location {}\".format(ws.name, ws.location))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"See [Register an application with the Microsoft identity platform](https://docs.microsoft.com/en-us/azure/active-directory/develop/quickstart-register-app) quickstart for more details about application registrations. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
@@ -252,7 +267,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.5"
|
||||
"version": "3.6.4"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 37 KiB After Width: | Height: | Size: 97 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 68 KiB After Width: | Height: | Size: 82 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 67 KiB After Width: | Height: | Size: 62 KiB |
@@ -0,0 +1,5 @@
|
||||
name: distributed-chainer
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
@@ -0,0 +1,6 @@
|
||||
name: distributed-cntk-with-custom-docker
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
- numpy
|
||||
@@ -0,0 +1,5 @@
|
||||
name: distributed-pytorch-with-horovod
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
@@ -0,0 +1,5 @@
|
||||
name: distributed-tensorflow-with-horovod
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
@@ -0,0 +1,5 @@
|
||||
name: distributed-tensorflow-with-parameter-server
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
@@ -0,0 +1,9 @@
|
||||
name: export-run-history-to-tensorboard
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-tensorboard
|
||||
- tensorflow
|
||||
- tqdm
|
||||
- scipy
|
||||
- sklearn
|
||||
@@ -299,7 +299,7 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can also specify a custom Docker image for exeution. In this case, you probably want to tell the system not to build a new conda environment for you. Instead, you can specify the path to an existing Python environment in the custom Docker image.\n",
|
||||
"You can also specify a custom Docker image for execution. In this case, you probably want to tell the system not to build a new conda environment for you. Instead, you can specify the path to an existing Python environment in the custom Docker image. If custom Docker image information is not specified, Azure ML uses the default Docker image to run your training. For more information about Docker containers used in Azure ML training, please see [Azure ML Containers repository](https://github.com/Azure/AzureML-Containers).\n",
|
||||
"\n",
|
||||
"**Note**: since the below example points to the preinstalled Python environment in the miniconda3 image maintained by continuum.io on Docker Hub where Azure ML SDK is not present, the logging metric code is not triggered. But a run history record is still recorded. "
|
||||
]
|
||||
|
||||
@@ -0,0 +1,6 @@
|
||||
name: how-to-use-estimator
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
- azureml-contrib-notebook
|
||||
@@ -0,0 +1,6 @@
|
||||
name: tensorboard
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-tensorboard
|
||||
- tensorflow
|
||||
@@ -0,0 +1,7 @@
|
||||
name: train-hyperparameter-tune-deploy-with-chainer
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
- numpy
|
||||
- pytest
|
||||
@@ -0,0 +1,8 @@
|
||||
name: train-hyperparameter-tune-deploy-with-keras
|
||||
dependencies:
|
||||
- matplotlib
|
||||
- tensorflow
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
- keras
|
||||
@@ -0,0 +1,8 @@
|
||||
name: train-hyperparameter-tune-deploy-with-tensorflow
|
||||
dependencies:
|
||||
- numpy
|
||||
- matplotlib
|
||||
- tensorflow
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
@@ -5,9 +5,10 @@ Follow these sample notebooks to learn:
|
||||
1. [Train within notebook](train-within-notebook): train a simple scikit-learn model using the Jupyter kernel and deploy the model to Azure Container Service.
|
||||
2. [Train on local](train-on-local): train a model using local computer as compute target.
|
||||
3. [Train on remote VM](train-on-remote-vm): train a model using a remote Azure VM as compute target.
|
||||
4. [Train on AmlCompute](train-on-amlcompute): train a model using an AmlCompute cluster as compute target.
|
||||
4. [Train on ML Compute](train-on-amlcompute): train a model using an ML Compute cluster as compute target.
|
||||
5. [Train in an HDI Spark cluster](train-in-spark): train a Spark ML model using an HDInsight Spark cluster as compute target.
|
||||
6. [Logging API](logging-api): experiment with various logging functions to create runs and automatically generate graphs.
|
||||
7. [Train and hyperparameter tune on Iris Dataset with Scikit-learn](train-hyperparameter-tune-deploy-with-sklearn): train a model using the Scikit-learn estimator and tune hyperparameters with Hyperdrive.
|
||||
7. [Manage runs](manage-runs): learn different ways how to start runs and child runs, monitor them, and cancel them.
|
||||
8. [Train and hyperparameter tune on Iris Dataset with Scikit-learn](train-hyperparameter-tune-deploy-with-sklearn): train a model using the Scikit-learn estimator and tune hyperparameters with Hyperdrive.
|
||||
|
||||
|
||||
@@ -100,7 +100,7 @@
|
||||
"\n",
|
||||
"# Check core SDK version number\n",
|
||||
"\n",
|
||||
"print(\"This notebook was created using SDK version 1.0.43, you are currently running version\", azureml.core.VERSION)"
|
||||
"print(\"This notebook was created using SDK version , you are currently running version\", azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
8
how-to-use-azureml/training/logging-api/logging-api.yml
Normal file
8
how-to-use-azureml/training/logging-api/logging-api.yml
Normal file
@@ -0,0 +1,8 @@
|
||||
name: logging-api
|
||||
dependencies:
|
||||
- numpy
|
||||
- matplotlib
|
||||
- tqdm
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
4
how-to-use-azureml/training/manage-runs/manage-runs.yml
Normal file
4
how-to-use-azureml/training/manage-runs/manage-runs.yml
Normal file
@@ -0,0 +1,4 @@
|
||||
name: manage-runs
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
@@ -0,0 +1,6 @@
|
||||
name: train-hyperparameter-tune-deploy-with-sklearn
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
- numpy
|
||||
@@ -0,0 +1,6 @@
|
||||
name: train-on-amlcompute
|
||||
dependencies:
|
||||
- scikit-learn
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
@@ -0,0 +1,7 @@
|
||||
name: train-on-local
|
||||
dependencies:
|
||||
- matplotlib
|
||||
- scikit-learn
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
@@ -362,7 +362,7 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The below run will likely fail because `train.py` needs dependency `azureml`, `scikit-learn` and others, which are not found in that Python environment. "
|
||||
"The below run will likely fail because `train.py` needs dependency `azureml`, `scikit-learn` and others, which are not found in that Python environment."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -372,7 +372,13 @@
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"run = exp.submit(config=src)\n",
|
||||
"run.wait_for_completion(show_output=True)"
|
||||
"\n",
|
||||
"from azureml.exceptions import ActivityFailedException\n",
|
||||
"\n",
|
||||
"try:\n",
|
||||
" run.wait_for_completion(show_output=True)\n",
|
||||
"except ActivityFailedException as ex:\n",
|
||||
" print(ex)"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
@@ -0,0 +1,8 @@
|
||||
name: train-on-remote-vm
|
||||
dependencies:
|
||||
- matplotlib
|
||||
- tqdm
|
||||
- scikit-learn
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
@@ -0,0 +1,8 @@
|
||||
name: train-within-notebook
|
||||
dependencies:
|
||||
- tqdm
|
||||
- scikit-learn
|
||||
- matplotlib
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
@@ -0,0 +1,4 @@
|
||||
name: using-environments
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
@@ -0,0 +1,8 @@
|
||||
name: deploy-model
|
||||
dependencies:
|
||||
- scikit-learn
|
||||
- matplotlib
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-mlflow
|
||||
- pandas
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user