jprdonnelly/MachineLearningNotebooks
1
0
Fork 0
mirror of https://github.com/Azure/MachineLearningNotebooks.git synced 2025-12-19 17:17:04 -05:00
Code Issues Projects Releases Wiki Activity

update samples from Release-132 as a part of 1.0.48 SDK release

Browse Source
This commit is contained in:
vizhur
2019-07-09 22:02:57 +00:00
parent 9e0fc4f0e7
commit 475ea36106
195 changed files with 31305 additions and 4675 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
configuration.ipynb
View File

@@ -58,7 +58,7 @@
"\n", "\n",
"### What is an Azure Machine Learning workspace\n", "### What is an Azure Machine Learning workspace\n",
"\n", "\n",
"An Azure ML Workspace is an Azure resource that organizes and coordinates the actions of many other Azure resources to assist in executing and sharing machine learning workflows. In particular, an Azure ML Workspace coordinates storage, databases, and compute resources providing added functionality for machine learning experimentation, deployment, inferencing, and the monitoring of deployed models." "An Azure ML Workspace is an Azure resource that organizes and coordinates the actions of many other Azure resources to assist in executing and sharing machine learning workflows. In particular, an Azure ML Workspace coordinates storage, databases, and compute resources providing added functionality for machine learning experimentation, deployment, inference, and the monitoring of deployed models."
] ]
}, },
{ {
@@ -103,7 +103,7 @@
"source": [ "source": [
"import azureml.core\n", "import azureml.core\n",
"\n", "\n",
"print(\"This notebook was created using version 1.0.45 of the Azure ML SDK\")\n", "print(\"This notebook was created using version 1.0.48 of the Azure ML SDK\")\n",
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")" "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
] ]
}, },
@@ -258,7 +258,7 @@
"```shell\n", "```shell\n",
"az vm list-skus -o tsv\n", "az vm list-skus -o tsv\n",
"```\n", "```\n",
"* min_nodes - this sets the minimum size of the cluster. If you set the minimum to 0 the cluster will shut down all nodes while note in use. Setting this number to a value higher than 0 will allow for faster start-up times, but you will also be billed when the cluster is not in use.\n", "* min_nodes - this sets the minimum size of the cluster. If you set the minimum to 0 the cluster will shut down all nodes while not in use. Setting this number to a value higher than 0 will allow for faster start-up times, but you will also be billed when the cluster is not in use.\n",
"* max_nodes - this sets the maximum size of the cluster. Setting this to a larger number allows for more concurrency and a greater distributed processing of scale-out jobs.\n", "* max_nodes - this sets the maximum size of the cluster. Setting this to a larger number allows for more concurrency and a greater distributed processing of scale-out jobs.\n",
"\n", "\n",
"\n", "\n",

4
configuration.yml Normal file
View File

@@ -0,0 +1,4 @@
name: configuration
dependencies:
- pip:
- azureml-sdk

24
contrib/datadrift/azure-ml-datadrift.ipynb
View File

@@ -33,10 +33,9 @@
"source": [ "source": [
"## Install the DataDrift package\n", "## Install the DataDrift package\n",
"\n", "\n",
"Install the azureml-contrib-datadrift, azureml-contrib-opendatasets and lightgbm packages before running this notebook.\n", "Install the azureml-contrib-datadrift, azureml-opendatasets and lightgbm packages before running this notebook.\n",
"```\n", "```\n",
"pip install azureml-contrib-datadrift\n", "pip install azureml-contrib-datadrift\n",
"pip install azureml-contrib-datasets\n",
"pip install lightgbm\n", "pip install lightgbm\n",
"```" "```"
] ]
@@ -63,7 +62,7 @@
"import pandas as pd\n", "import pandas as pd\n",
"import requests\n", "import requests\n",
"from azureml.contrib.datadrift import DataDriftDetector, AlertConfiguration\n", "from azureml.contrib.datadrift import DataDriftDetector, AlertConfiguration\n",
"from azureml.contrib.opendatasets import NoaaIsdWeather\n", "from azureml.opendatasets import NoaaIsdWeather\n",
"from azureml.core import Dataset, Workspace, Run\n", "from azureml.core import Dataset, Workspace, Run\n",
"from azureml.core.compute import AksCompute, ComputeTarget\n", "from azureml.core.compute import AksCompute, ComputeTarget\n",
"from azureml.core.conda_dependencies import CondaDependencies\n", "from azureml.core.conda_dependencies import CondaDependencies\n",
@@ -259,8 +258,7 @@
"trainingDataset = Dataset.auto_read_files(dpath, include_path=True)\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", "trainingDataset = trainingDataset.register(workspace=ws, name=dataset_name, description=\"dset\", exist_ok=True)\n",
"\n", "\n",
"trainingDataSnapshot = trainingDataset.create_snapshot(snapshot_name=snapshot_name, compute_target=None, create_data_snapshot=True)\n", "datasets = [(Dataset.Scenario.TRAINING, trainingDataset)]\n",
"datasets = [(Dataset.Scenario.TRAINING, trainingDataSnapshot)]\n",
"print(\"dataset registration done.\\n\")\n", "print(\"dataset registration done.\\n\")\n",
"datasets" "datasets"
] ]
@@ -574,6 +572,22 @@
" time.sleep(3)" " time.sleep(3)"
] ]
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We need to wait up to 10 minutes for the Model Data Collector to dump the model input and inference data to storage in the Workspace, where it's used by the DataDriftDetector job."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"time.sleep(600)"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},

8
contrib/datadrift/azure-ml-datadrift.yml Normal file
View File

@@ -0,0 +1,8 @@
name: azure-ml-datadrift
dependencies:
- pip:
- azureml-sdk
- azureml-contrib-datadrift
- azureml-opendatasets
- lightgbm
- azureml-widgets

1
how-to-use-azureml/automated-machine-learning/automl_env.yml
View File

@@ -2,6 +2,7 @@ name: azure_automl
dependencies: dependencies:
# The python interpreter version. # The python interpreter version.
# Currently Azure ML only supports 3.5.2 and later. # Currently Azure ML only supports 3.5.2 and later.
- pip
- python>=3.5.2,<3.6.8 - python>=3.5.2,<3.6.8
- nb_conda - nb_conda
- matplotlib==2.1.0 - matplotlib==2.1.0

1452
how-to-use-azureml/automated-machine-learning/classification-bank-marketing/auto-ml-classification-bank-marketing.ipynb
View File

File diff suppressed because it is too large Load Diff

8
how-to-use-azureml/automated-machine-learning/classification-bank-marketing/auto-ml-classification-bank-marketing.yml Normal file
View File

@@ -0,0 +1,8 @@
name: auto-ml-classification-bank-marketing
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml

1418
how-to-use-azureml/automated-machine-learning/classification-credit-card-fraud/auto-ml-classification-credit-card-fraud.ipynb
View File

File diff suppressed because it is too large Load Diff

8
how-to-use-azureml/automated-machine-learning/classification-credit-card-fraud/auto-ml-classification-credit-card-fraud.yml Normal file
View File

@@ -0,0 +1,8 @@
name: auto-ml-classification-credit-card-fraud
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml

8
how-to-use-azureml/automated-machine-learning/classification-with-deployment/auto-ml-classification-with-deployment.yml Normal file
View File

@@ -0,0 +1,8 @@
name: auto-ml-classification-with-deployment
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml

9
how-to-use-azureml/automated-machine-learning/classification-with-onnx/auto-ml-classification-with-onnx.yml Normal file
View File

@@ -0,0 +1,9 @@
name: auto-ml-classification-with-onnx
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml
- onnxruntime

8
how-to-use-azureml/automated-machine-learning/classification-with-whitelisting/auto-ml-classification-with-whitelisting.yml Normal file
View File

@@ -0,0 +1,8 @@
name: auto-ml-classification-with-whitelisting
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml

8
how-to-use-azureml/automated-machine-learning/classification/auto-ml-classification.yml Normal file
View File

@@ -0,0 +1,8 @@
name: auto-ml-classification
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml

8
how-to-use-azureml/automated-machine-learning/dataprep-remote-execution/auto-ml-dataprep-remote-execution.yml Normal file
View File

@@ -0,0 +1,8 @@
name: auto-ml-dataprep-remote-execution
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml

14
how-to-use-azureml/automated-machine-learning/dataprep/auto-ml-dataprep.ipynb
View File

@@ -1,5 +1,12 @@
{ {
"cells": [ "cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/dataprep/auto-ml-dataprep.png)"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
@@ -9,13 +16,6 @@
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/dataprep/auto-ml-dataprep.png)"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},

8
how-to-use-azureml/automated-machine-learning/dataprep/auto-ml-dataprep.yml Normal file
View File

@@ -0,0 +1,8 @@
name: auto-ml-dataprep
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml

8
how-to-use-azureml/automated-machine-learning/exploring-previous-runs/auto-ml-exploring-previous-runs.yml Normal file
View File

@@ -0,0 +1,8 @@
name: auto-ml-exploring-previous-runs
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml

213
how-to-use-azureml/automated-machine-learning/forecasting-bike-share/auto-ml-forecasting-bike-share.ipynb
View File

@@ -36,19 +36,17 @@
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Introduction\n", "## 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", "\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", "\n",
"Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n", "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
"\n", "\n",
"In this notebook you would see\n", "Notebook synopsis:\n",
"1. Creating an Experiment in an existing Workspace\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", "2. Configuration and local run of AutoML for a time-series model with lag and holiday features \n",
"3. Training the Model using local compute\n", "3. Viewing the engineered names for featurized data and featurization summary for all raw features\n",
"4. Exploring the results\n", "4. Evaluating the fitted model using a rolling test "
"5. Viewing the engineered names for featurized data and featurization summary for all raw features\n",
"6. Testing the fitted model"
] ]
}, },
{ {
@@ -69,6 +67,9 @@
"import numpy as np\n", "import numpy as np\n",
"import logging\n", "import logging\n",
"import warnings\n", "import warnings\n",
"\n",
"from pandas.tseries.frequencies import to_offset\n",
"\n",
"# Squash warning messages for cleaner output in the notebook\n", "# Squash warning messages for cleaner output in the notebook\n",
"warnings.showwarning = lambda *args, **kwargs: None\n", "warnings.showwarning = lambda *args, **kwargs: None\n",
"\n", "\n",
@@ -83,7 +84,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "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."
] ]
}, },
{ {
@@ -128,14 +129,15 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "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", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Let's set up what we know abou the dataset. \n", "Let's set up what we know about the dataset. \n",
"\n", "\n",
"**Target column** is what we want to forecast.\n", "**Target column** is what we want to forecast.\n",
"\n", "\n",
@@ -193,8 +195,7 @@
"source": [ "source": [
"### Setting forecaster maximum horizon \n", "### Setting forecaster maximum horizon \n",
"\n", "\n",
"Assuming your test data forms a full and regular time series(regular time intervals and no holes), \n", "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). "
"the maximum horizon you will need to forecast is the length of the longest grain in your test set."
] ]
}, },
{ {
@@ -203,10 +204,7 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"if len(grain_column_names) == 0:\n", "max_horizon = 14"
" max_horizon = len(X_test)\n",
"else:\n",
" max_horizon = X_test.groupby(grain_column_names)[time_column_name].count().max()"
] ]
}, },
{ {
@@ -236,26 +234,25 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"time_column_name = 'date'\n",
"automl_settings = {\n", "automl_settings = {\n",
" \"time_column_name\": time_column_name,\n", " 'time_column_name': time_column_name,\n",
" # these columns are a breakdown of the total and therefore a leak\n", " 'max_horizon': max_horizon,\n",
" \"drop_column_names\": ['casual', 'registered'],\n",
" # knowing the country/region allows Automated ML to bring in holidays\n", " # knowing the country/region allows Automated ML to bring in holidays\n",
" \"country_or_region\" : 'US',\n", " 'country_or_region': 'US',\n",
" \"max_horizon\" : max_horizon,\n", " 'target_lags': 1,\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",
"\n", "\n",
"automl_config = AutoMLConfig(task = 'forecasting', \n", "automl_config = AutoMLConfig(task='forecasting', \n",
" primary_metric='normalized_root_mean_squared_error',\n", " primary_metric='normalized_root_mean_squared_error',\n",
" iterations = 10,\n", " iterations=10,\n",
" iteration_timeout_minutes = 5,\n", " iteration_timeout_minutes=5,\n",
" X = X_train,\n", " X=X_train,\n",
" y = y_train,\n", " y=y_train,\n",
" n_cross_validations = 3, \n", " n_cross_validations=3, \n",
" path=project_folder,\n", " path=project_folder,\n",
" verbosity = logging.INFO,\n", " verbosity=logging.INFO,\n",
" **automl_settings)" " **automl_settings)"
] ]
}, },
@@ -263,7 +260,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "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."
] ]
}, },
{ {
@@ -355,11 +352,16 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "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", "\n",
"Predict on training and test set, and calculate residual values.\n", "We always score on the original dataset whose schema matches the training set schema."
"\n",
"We always score on the original dataset whose schema matches the scheme of the training dataset."
] ]
}, },
{ {
@@ -371,21 +373,12 @@
"X_test.head()" "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", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "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." "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."
] ]
}, },
@@ -395,7 +388,8 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "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", " \"\"\"\n",
" Demonstrates how to get the output aligned to the inputs\n", " Demonstrates how to get the output aligned to the inputs\n",
" using pandas indexes. Helps understand what happened if\n", " using pandas indexes. Helps understand what happened if\n",
@@ -407,7 +401,8 @@
" * model was asked to predict past max_horizon -> increase max horizon\n", " * 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", " * data at start of X_test was needed for lags -> provide previous periods\n",
" \"\"\"\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", " # y and X outputs are aligned by forecast() function contract\n",
" df_fcst.index = X_trans.index\n", " df_fcst.index = X_trans.index\n",
" \n", " \n",
@@ -426,7 +421,49 @@
" clean = together[together[[target_column_name, predicted_column_name]].notnull().all(axis=1)]\n", " clean = together[together[[target_column_name, predicted_column_name]].notnull().all(axis=1)]\n",
" return(clean)\n", " return(clean)\n",
"\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)"
] ]
}, },
{ {
@@ -435,6 +472,30 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "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", "def MAPE(actual, pred):\n",
" \"\"\"\n", " \"\"\"\n",
" Calculate mean absolute percentage error.\n", " Calculate mean absolute percentage error.\n",
@@ -444,8 +505,7 @@
" not_zero = ~np.isclose(actual, 0.0)\n", " not_zero = ~np.isclose(actual, 0.0)\n",
" actual_safe = actual[not_na & not_zero]\n", " actual_safe = actual[not_na & not_zero]\n",
" pred_safe = pred[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(actual_safe, pred_safe))"
" return np.mean(APE)"
] ]
}, },
{ {
@@ -468,12 +528,57 @@
"plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n", "plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
"plt.show()" "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": { "metadata": {
"authors": [ "authors": [
{ {
"name": "xiaga@microsoft.com, tosingli@microsoft.com" "name": "xiaga@microsoft.com, tosingli@microsoft.com, erwright@microsoft.com"
} }
], ],
"kernelspec": { "kernelspec": {
@@ -491,7 +596,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.6.7" "version": "3.6.8"
} }
}, },
"nbformat": 4, "nbformat": 4,

9
how-to-use-azureml/automated-machine-learning/forecasting-bike-share/auto-ml-forecasting-bike-share.yml Normal file
View File

@@ -0,0 +1,9 @@
name: auto-ml-forecasting-bike-share
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml
- statsmodels

167
how-to-use-azureml/automated-machine-learning/forecasting-energy-demand/auto-ml-forecasting-energy-demand.ipynb
View File

@@ -35,17 +35,16 @@
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Introduction\n", "## 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", "\n",
"Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n", "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
"\n", "\n",
"In this notebook you would see\n", "Notebook synopsis:\n",
"1. Creating an Experiment in an existing Workspace\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", "2. Configuration and local run of AutoML for a simple time-series model\n",
"3. Training the Model using local compute\n", "3. View engineered features and prediction results\n",
"4. Exploring the results\n", "4. Configuration and local run of AutoML for a time-series model with lag and rolling window features\n",
"5. Viewing the engineered names for featurized data and featurization summary for all raw features\n", "5. Estimate feature importance"
"6. Testing the fitted model"
] ]
}, },
{ {
@@ -65,6 +64,10 @@
"import pandas as pd\n", "import pandas as pd\n",
"import numpy as np\n", "import numpy as np\n",
"import logging\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.workspace import Workspace\n",
"from azureml.core.experiment import Experiment\n", "from azureml.core.experiment import Experiment\n",
@@ -77,7 +80,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "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."
] ]
}, },
{ {
@@ -113,7 +116,7 @@
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Data\n", "## 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. "
] ]
}, },
{ {
@@ -126,13 +129,20 @@
"data.head()" "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", "cell_type": "code",
"execution_count": null, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# let's take note of what columns means what in the data\n", "# Dataset schema\n",
"time_column_name = 'timeStamp'\n", "time_column_name = 'timeStamp'\n",
"target_column_name = 'demand'" "target_column_name = 'demand'"
] ]
@@ -141,7 +151,14 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "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."
] ]
}, },
{ {
@@ -150,8 +167,32 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"X_train = data[data[time_column_name] < '2017-02-01']\n", "max_horizon = 48"
"X_test = data[data[time_column_name] >= '2017-02-01']\n", ]
},
{
"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_train = X_train.pop(target_column_name).values\n",
"y_test = X_test.pop(target_column_name).values" "y_test = X_test.pop(target_column_name).values"
] ]
@@ -162,7 +203,7 @@
"source": [ "source": [
"## Train\n", "## Train\n",
"\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", "\n",
"|Property|Description|\n", "|Property|Description|\n",
"|-|-|\n", "|-|-|\n",
@@ -172,7 +213,7 @@
"|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n", "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
"|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n", "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
"|**y**|(sparse) array-like, shape = [n_samples, ], targets values.|\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. " "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder. "
] ]
}, },
@@ -182,22 +223,22 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"automl_settings = {\n", "time_series_settings = {\n",
" \"time_column_name\": time_column_name \n", " 'time_column_name': time_column_name,\n",
" 'max_horizon': max_horizon\n",
"}\n", "}\n",
"\n", "\n",
"\n", "automl_config = AutoMLConfig(task='forecasting',\n",
"automl_config = AutoMLConfig(task = 'forecasting',\n", " debug_log='automl_nyc_energy_errors.log',\n",
" debug_log = 'automl_nyc_energy_errors.log',\n",
" primary_metric='normalized_root_mean_squared_error',\n", " primary_metric='normalized_root_mean_squared_error',\n",
" iterations = 10,\n", " iterations=10,\n",
" iteration_timeout_minutes = 5,\n", " iteration_timeout_minutes=5,\n",
" X = X_train,\n", " X=X_train,\n",
" y = y_train,\n", " y=y_train,\n",
" n_cross_validations = 3,\n", " n_cross_validations=3,\n",
" path=project_folder,\n", " path=project_folder,\n",
" verbosity = logging.INFO,\n", " verbosity = logging.INFO,\n",
" **automl_settings)" " **time_series_settings)"
] ]
}, },
{ {
@@ -354,7 +395,8 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "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."
] ]
}, },
{ {
@@ -391,9 +433,12 @@
"\n", "\n",
"# Plot outputs\n", "# Plot outputs\n",
"%matplotlib notebook\n", "%matplotlib notebook\n",
"test_pred = plt.scatter(df_all[target_column_name], df_all['predicted'], color='b')\n", "pred, = plt.plot(df_all[time_column_name], df_all['predicted'], color='b')\n",
"test_test = plt.scatter(y_test, y_test, color='g')\n", "actual, = plt.plot(df_all[time_column_name], df_all[target_column_name], color='g')\n",
"plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\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()" "plt.show()"
] ]
}, },
@@ -408,16 +453,16 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Using lags and rolling window features to improve the forecast" "### Using lags and rolling window features"
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "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", "\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."
] ]
}, },
{ {
@@ -426,27 +471,32 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"automl_settings_lags = {\n", "time_series_settings_with_lags = {\n",
" 'time_column_name': time_column_name,\n", " 'time_column_name': time_column_name,\n",
" 'target_lags': 1,\n", " 'max_horizon': max_horizon,\n",
" 'target_rolling_window_size': 5,\n", " 'target_lags': 12,\n",
" # you MUST set the max_horizon when using lags and rolling windows\n", " 'target_rolling_window_size': 4\n",
" # it is optional when looking-back features are not used \n",
" 'max_horizon': len(y_test), # only one grain\n",
"}\n", "}\n",
"\n", "\n",
"\n", "automl_config_lags = AutoMLConfig(task='forecasting',\n",
"automl_config_lags = AutoMLConfig(task = 'forecasting',\n", " debug_log='automl_nyc_energy_errors.log',\n",
" debug_log = 'automl_nyc_energy_errors.log',\n", " primary_metric='normalized_root_mean_squared_error',\n",
" primary_metric='normalized_root_mean_squared_error',\n", " blacklist_models=['ElasticNet'],\n",
" iterations = 10,\n", " iterations=10,\n",
" iteration_timeout_minutes = 5,\n", " iteration_timeout_minutes=10,\n",
" X = X_train,\n", " X=X_train,\n",
" y = y_train,\n", " y=y_train,\n",
" n_cross_validations = 3,\n", " n_cross_validations=3,\n",
" path=project_folder,\n", " path=project_folder,\n",
" verbosity = logging.INFO,\n", " verbosity=logging.INFO,\n",
" **automl_settings_lags)" " **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."
] ]
}, },
{ {
@@ -494,9 +544,10 @@
"\n", "\n",
"# Plot outputs\n", "# Plot outputs\n",
"%matplotlib notebook\n", "%matplotlib notebook\n",
"test_pred = plt.scatter(df_lags[target_column_name], df_lags['predicted'], color='b')\n", "pred, = plt.plot(df_lags[time_column_name], df_lags['predicted'], color='b')\n",
"test_test = plt.scatter(y_test, y_test, color='g')\n", "actual, = plt.plot(df_lags[time_column_name], df_lags[target_column_name], color='g')\n",
"plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n", "plt.xticks(fontsize=8)\n",
"plt.legend((pred, actual), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
"plt.show()" "plt.show()"
] ]
}, },
@@ -516,8 +567,8 @@
"from azureml.train.automl.automlexplainer import explain_model\n", "from azureml.train.automl.automlexplainer import explain_model\n",
"\n", "\n",
"# feature names are everything in the transformed data except the target\n", "# feature names are everything in the transformed data except the target\n",
"features = X_trans.columns[:-1]\n", "features = X_trans_lags.columns[:-1]\n",
"expl = explain_model(fitted_model, X_train, X_test, features = features, best_run=best_run_lags, y_train = y_train)\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", "# unpack the tuple\n",
"shap_values, expected_values, feat_overall_imp, feat_names, per_class_summary, per_class_imp = expl\n", "shap_values, expected_values, feat_overall_imp, feat_names, per_class_summary, per_class_imp = expl\n",
"best_run_lags" "best_run_lags"
@@ -536,7 +587,7 @@
"metadata": { "metadata": {
"authors": [ "authors": [
{ {
"name": "xiaga, tosingli" "name": "xiaga, tosingli, erwright"
} }
], ],
"kernelspec": { "kernelspec": {
@@ -554,7 +605,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.6.7" "version": "3.6.8"
} }
}, },
"nbformat": 4, "nbformat": 4,

10
how-to-use-azureml/automated-machine-learning/forecasting-energy-demand/auto-ml-forecasting-energy-demand.yml Normal file
View File

@@ -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

25
how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales/auto-ml-forecasting-orange-juice-sales.ipynb
View File

@@ -37,16 +37,10 @@
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Introduction\n", "## 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", "\n",
"Make sure you have executed the [configuration notebook](../../../configuration.ipynb) before running this notebook.\n", "Make sure you have executed the [configuration notebook](../../../configuration.ipynb) before running this notebook.\n",
"\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." "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."
] ]
}, },
@@ -67,6 +61,10 @@
"import pandas as pd\n", "import pandas as pd\n",
"import numpy as np\n", "import numpy as np\n",
"import logging\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.workspace import Workspace\n",
"from azureml.core.experiment import Experiment\n", "from azureml.core.experiment import Experiment\n",
@@ -78,7 +76,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "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. "
] ]
}, },
{ {
@@ -232,7 +230,7 @@
"\n", "\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", "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", "\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", "\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", "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", "\n",
@@ -265,7 +263,7 @@
" 'time_column_name': time_column_name,\n", " 'time_column_name': time_column_name,\n",
" 'grain_column_names': grain_column_names,\n", " 'grain_column_names': grain_column_names,\n",
" 'drop_column_names': ['logQuantity'],\n", " 'drop_column_names': ['logQuantity'],\n",
" 'max_horizon': n_test_periods # optional\n", " 'max_horizon': n_test_periods\n",
"}\n", "}\n",
"\n", "\n",
"automl_config = AutoMLConfig(task='forecasting',\n", "automl_config = AutoMLConfig(task='forecasting',\n",
@@ -274,7 +272,7 @@
" iterations=10,\n", " iterations=10,\n",
" X=X_train,\n", " X=X_train,\n",
" y=y_train,\n", " y=y_train,\n",
" n_cross_validations=5,\n", " n_cross_validations=3,\n",
" enable_ensembling=False,\n", " enable_ensembling=False,\n",
" path=project_folder,\n", " path=project_folder,\n",
" verbosity=logging.INFO,\n", " verbosity=logging.INFO,\n",
@@ -320,7 +318,8 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "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:" "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:"
] ]
}, },
@@ -848,7 +847,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.6.7" "version": "3.6.8"
} }
}, },
"nbformat": 4, "nbformat": 4,

9
how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales/auto-ml-forecasting-orange-juice-sales.yml Normal file
View File

@@ -0,0 +1,9 @@
name: auto-ml-forecasting-orange-juice-sales
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml
- statsmodels

8
how-to-use-azureml/automated-machine-learning/missing-data-blacklist-early-termination/auto-ml-missing-data-blacklist-early-termination.yml Normal file
View File

@@ -0,0 +1,8 @@
name: auto-ml-missing-data-blacklist-early-termination
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml

9
how-to-use-azureml/automated-machine-learning/model-explanation/auto-ml-model-explanation.yml Normal file
View File

@@ -0,0 +1,9 @@
name: auto-ml-model-explanation
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml
- azureml-explain-model

1594
how-to-use-azureml/automated-machine-learning/regression-concrete-strength/auto-ml-regression-concrete-strength.ipynb
View File

File diff suppressed because it is too large Load Diff

8
how-to-use-azureml/automated-machine-learning/regression-concrete-strength/auto-ml-regression-concrete-strength.yml Normal file
View File

@@ -0,0 +1,8 @@
name: auto-ml-regression-concrete-strength
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml

1594
how-to-use-azureml/automated-machine-learning/regression-hardware-performance/auto-ml-regression-hardware-performance.ipynb
View File

File diff suppressed because it is too large Load Diff

8
how-to-use-azureml/automated-machine-learning/regression-hardware-performance/auto-ml-regression-hardware-performance.yml Normal file
View File

@@ -0,0 +1,8 @@
name: auto-ml-regression-hardware-performance
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml

9
how-to-use-azureml/automated-machine-learning/regression/auto-ml-regression.yml Normal file
View File

@@ -0,0 +1,9 @@
name: auto-ml-regression
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml
- paramiko<2.5.0

8
how-to-use-azureml/automated-machine-learning/remote-amlcompute/auto-ml-remote-amlcompute.yml Normal file
View File

@@ -0,0 +1,8 @@
name: auto-ml-remote-amlcompute
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml

8
how-to-use-azureml/automated-machine-learning/sample-weight/auto-ml-sample-weight.yml Normal file
View File

@@ -0,0 +1,8 @@
name: auto-ml-sample-weight
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml

8
how-to-use-azureml/automated-machine-learning/sparse-data-train-test-split/auto-ml-sparse-data-train-test-split.yml Normal file
View File

@@ -0,0 +1,8 @@
name: auto-ml-sparse-data-train-test-split
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml

23
how-to-use-azureml/automated-machine-learning/sql-server/energy-demand/ForecastEnergyDemand.sql Normal file
View File

@@ -0,0 +1,23 @@
-- This shows using the AutoMLForecast stored procedure to predict using a forecasting model for the nyc_energy dataset.
DECLARE @Model NVARCHAR(MAX) = (SELECT TOP 1 Model FROM dbo.aml_model
WHERE ExperimentName = 'automl-sql-forecast'
ORDER BY CreatedDate DESC)
DECLARE @max_horizon INT = 48
DECLARE @split_time NVARCHAR(22) = (SELECT DATEADD(hour, -@max_horizon, MAX(timeStamp)) FROM nyc_energy WHERE demand IS NOT NULL)
DECLARE @TestDataQuery NVARCHAR(MAX) = '
SELECT CAST(timeStamp AS NVARCHAR(30)) AS timeStamp,
demand,
precip,
temp
FROM nyc_energy
WHERE demand IS NOT NULL AND precip IS NOT NULL AND temp IS NOT NULL
AND timeStamp > ''' + @split_time + ''''
EXEC dbo.AutoMLForecast @input_query=@TestDataQuery,
@label_column='demand',
@time_column_name='timeStamp',
@model=@model
WITH RESULT SETS ((timeStamp DATETIME, grain NVARCHAR(255), predicted_demand FLOAT, precip FLOAT, temp FLOAT, actual_demand FLOAT))

16
how-to-use-azureml/automated-machine-learning/sql-server/energy-demand/TrainEnergyDemand.sql
View File

@@ -1,21 +1,25 @@
-- This shows using the AutoMLTrain stored procedure to create a forecasting model for the nyc_energy dataset. -- This shows using the AutoMLTrain stored procedure to create a forecasting model for the nyc_energy dataset.
INSERT INTO dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName) DECLARE @max_horizon INT = 48
EXEC dbo.AutoMLTrain @input_query=' DECLARE @split_time NVARCHAR(22) = (SELECT DATEADD(hour, -@max_horizon, MAX(timeStamp)) FROM nyc_energy WHERE demand IS NOT NULL)
DECLARE @TrainDataQuery NVARCHAR(MAX) = '
SELECT CAST(timeStamp as NVARCHAR(30)) as timeStamp, SELECT CAST(timeStamp as NVARCHAR(30)) as timeStamp,
demand, demand,
precip, precip,
temp, temp
CASE WHEN timeStamp < ''2017-01-01'' THEN 0 ELSE 1 END AS is_validate_column
FROM nyc_energy FROM nyc_energy
WHERE demand IS NOT NULL AND precip IS NOT NULL AND temp IS NOT NULL WHERE demand IS NOT NULL AND precip IS NOT NULL AND temp IS NOT NULL
and timeStamp < ''2017-02-01''', and timeStamp < ''' + @split_time + ''''
INSERT INTO dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)
EXEC dbo.AutoMLTrain @input_query= @TrainDataQuery,
@label_column='demand', @label_column='demand',
@task='forecasting', @task='forecasting',
@iterations=10, @iterations=10,
@iteration_timeout_minutes=5, @iteration_timeout_minutes=5,
@time_column_name='timeStamp', @time_column_name='timeStamp',
@is_validate_column='is_validate_column', @max_horizon=@max_horizon,
@experiment_name='automl-sql-forecast', @experiment_name='automl-sql-forecast',
@primary_metric='normalized_root_mean_squared_error' @primary_metric='normalized_root_mean_squared_error'

276
how-to-use-azureml/automated-machine-learning/sql-server/energy-demand/auto-ml-sql-energy-demand.ipynb
View File

@@ -1,141 +1,141 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Train a model and use it for prediction\r\n", "# Train a model and use it for prediction\r\n",
"\r\n", "\r\n",
"Before running this notebook, run the auto-ml-sql-setup.ipynb notebook." "Before running this notebook, run the auto-ml-sql-setup.ipynb notebook."
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/sql-server/energy-demand/auto-ml-sql-energy-demand.png)" "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/sql-server/energy-demand/auto-ml-sql-energy-demand.png)"
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Set the default database" "## Set the default database"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"USE [automl]\r\n", "USE [automl]\r\n",
"GO" "GO"
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Use the AutoMLTrain stored procedure to create a forecasting model for the nyc_energy dataset." "## Use the AutoMLTrain stored procedure to create a forecasting model for the nyc_energy dataset."
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"INSERT INTO dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)\r\n", "INSERT INTO dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)\r\n",
"EXEC dbo.AutoMLTrain @input_query='\r\n", "EXEC dbo.AutoMLTrain @input_query='\r\n",
"SELECT CAST(timeStamp as NVARCHAR(30)) as timeStamp,\r\n", "SELECT CAST(timeStamp as NVARCHAR(30)) as timeStamp,\r\n",
" demand,\r\n", " demand,\r\n",
"\t precip,\r\n", "\t precip,\r\n",
"\t temp,\r\n", "\t temp,\r\n",
"\t CASE WHEN timeStamp < ''2017-01-01'' THEN 0 ELSE 1 END AS is_validate_column\r\n", "\t CASE WHEN timeStamp < ''2017-01-01'' THEN 0 ELSE 1 END AS is_validate_column\r\n",
"FROM nyc_energy\r\n", "FROM nyc_energy\r\n",
"WHERE demand IS NOT NULL AND precip IS NOT NULL AND temp IS NOT NULL\r\n", "WHERE demand IS NOT NULL AND precip IS NOT NULL AND temp IS NOT NULL\r\n",
"and timeStamp < ''2017-02-01''',\r\n", "and timeStamp < ''2017-02-01''',\r\n",
"@label_column='demand',\r\n", "@label_column='demand',\r\n",
"@task='forecasting',\r\n", "@task='forecasting',\r\n",
"@iterations=10,\r\n", "@iterations=10,\r\n",
"@iteration_timeout_minutes=5,\r\n", "@iteration_timeout_minutes=5,\r\n",
"@time_column_name='timeStamp',\r\n", "@time_column_name='timeStamp',\r\n",
"@is_validate_column='is_validate_column',\r\n", "@is_validate_column='is_validate_column',\r\n",
"@experiment_name='automl-sql-forecast',\r\n", "@experiment_name='automl-sql-forecast',\r\n",
"@primary_metric='normalized_root_mean_squared_error'" "@primary_metric='normalized_root_mean_squared_error'"
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Use the AutoMLPredict stored procedure to predict using the forecasting model for the nyc_energy dataset." "## Use the AutoMLPredict stored procedure to predict using the forecasting model for the nyc_energy dataset."
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"DECLARE @Model NVARCHAR(MAX) = (SELECT TOP 1 Model FROM dbo.aml_model\r\n", "DECLARE @Model NVARCHAR(MAX) = (SELECT TOP 1 Model FROM dbo.aml_model\r\n",
" WHERE ExperimentName = 'automl-sql-forecast'\r\n", " WHERE ExperimentName = 'automl-sql-forecast'\r\n",
"\t\t\t\t\t\t\t\tORDER BY CreatedDate DESC)\r\n", "\t\t\t\t\t\t\t\tORDER BY CreatedDate DESC)\r\n",
"\r\n", "\r\n",
"EXEC dbo.AutoMLPredict @input_query='\r\n", "EXEC dbo.AutoMLPredict @input_query='\r\n",
"SELECT CAST(timeStamp AS NVARCHAR(30)) AS timeStamp,\r\n", "SELECT CAST(timeStamp AS NVARCHAR(30)) AS timeStamp,\r\n",
" demand,\r\n", " demand,\r\n",
"\t precip,\r\n", "\t precip,\r\n",
"\t temp\r\n", "\t temp\r\n",
"FROM nyc_energy\r\n", "FROM nyc_energy\r\n",
"WHERE demand IS NOT NULL AND precip IS NOT NULL AND temp IS NOT NULL\r\n", "WHERE demand IS NOT NULL AND precip IS NOT NULL AND temp IS NOT NULL\r\n",
"AND timeStamp >= ''2017-02-01''',\r\n", "AND timeStamp >= ''2017-02-01''',\r\n",
"@label_column='demand',\r\n", "@label_column='demand',\r\n",
"@model=@model\r\n", "@model=@model\r\n",
"WITH RESULT SETS ((timeStamp NVARCHAR(30), actual_demand FLOAT, precip FLOAT, temp FLOAT, predicted_demand FLOAT))" "WITH RESULT SETS ((timeStamp NVARCHAR(30), actual_demand FLOAT, precip FLOAT, temp FLOAT, predicted_demand FLOAT))"
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"## List all the metrics for all iterations for the most recent training run." "## List all the metrics for all iterations for the most recent training run."
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"DECLARE @RunId NVARCHAR(43)\r\n", "DECLARE @RunId NVARCHAR(43)\r\n",
"DECLARE @ExperimentName NVARCHAR(255)\r\n", "DECLARE @ExperimentName NVARCHAR(255)\r\n",
"\r\n", "\r\n",
"SELECT TOP 1 @ExperimentName=ExperimentName, @RunId=SUBSTRING(RunId, 1, 43)\r\n", "SELECT TOP 1 @ExperimentName=ExperimentName, @RunId=SUBSTRING(RunId, 1, 43)\r\n",
"FROM aml_model\r\n", "FROM aml_model\r\n",
"ORDER BY CreatedDate DESC\r\n", "ORDER BY CreatedDate DESC\r\n",
"\r\n", "\r\n",
"EXEC dbo.AutoMLGetMetrics @RunId, @ExperimentName" "EXEC dbo.AutoMLGetMetrics @RunId, @ExperimentName"
] ]
} }
],
"metadata": {
"authors": [
{
"name": "jeffshep"
}
], ],
"kernelspec": { "metadata": {
"display_name": "SQL", "authors": [
"language": "sql", {
"name": "SQL" "name": "jeffshep"
}
],
"kernelspec": {
"display_name": "Python 3.6",
"language": "sql",
"name": "python36"
},
"language_info": {
"name": "sql",
"version": ""
}
}, },
"language_info": { "nbformat": 4,
"name": "sql", "nbformat_minor": 2
"version": "" }
}
},
"nbformat": 4,
"nbformat_minor": 2
}

92
how-to-use-azureml/automated-machine-learning/sql-server/setup/AutoMLForecast.sql Normal file
View File

@@ -0,0 +1,92 @@
-- This procedure forecast values based on a forecasting model returned by AutoMLTrain.
-- It returns a dataset with the forecasted values.
SET ANSI_NULLS ON
GO
SET QUOTED_IDENTIFIER ON
GO
CREATE OR ALTER PROCEDURE [dbo].[AutoMLForecast]
(
@input_query NVARCHAR(MAX), -- A SQL query returning data to predict on.
@model NVARCHAR(MAX), -- A model returned from AutoMLTrain.
@time_column_name NVARCHAR(255)='', -- The name of the timestamp column for forecasting.
@label_column NVARCHAR(255)='', -- Optional name of the column from input_query, which should be ignored when predicting
@y_query_column NVARCHAR(255)='', -- Optional value column that can be used for predicting.
-- If specified, this can contain values for past times (after the model was trained)
-- and contain Nan for future times.
@forecast_column_name NVARCHAR(255) = 'predicted'
-- The name of the output column containing the forecast value.
) AS
BEGIN
EXEC sp_execute_external_script @language = N'Python', @script = N'import pandas as pd
import azureml.core
import numpy as np
from azureml.train.automl import AutoMLConfig
import pickle
import codecs
model_obj = pickle.loads(codecs.decode(model.encode(), "base64"))
test_data = input_data.copy()
if label_column != "" and label_column is not None:
y_test = test_data.pop(label_column).values
else:
y_test = None
if y_query_column != "" and y_query_column is not None:
y_query = test_data.pop(y_query_column).values
else:
y_query = np.repeat(np.nan, len(test_data))
X_test = test_data
if time_column_name != "" and time_column_name is not None:
X_test[time_column_name] = pd.to_datetime(X_test[time_column_name])
y_fcst, X_trans = model_obj.forecast(X_test, y_query)
def align_outputs(y_forecast, X_trans, X_test, y_test, forecast_column_name):
# Demonstrates how to get the output aligned to the inputs
# using pandas indexes. Helps understand what happened if
# the output shape differs from the input shape, or if
# the data got re-sorted by time and grain during forecasting.
# Typical causes of misalignment are:
# * we predicted some periods that were missing in actuals -> drop from eval
# * model was asked to predict past max_horizon -> increase max horizon
# * data at start of X_test was needed for lags -> provide previous periods
df_fcst = pd.DataFrame({forecast_column_name : y_forecast})
# y and X outputs are aligned by forecast() function contract
df_fcst.index = X_trans.index
# align original X_test to y_test
X_test_full = X_test.copy()
if y_test is not None:
X_test_full[label_column] = y_test
# X_test_full does not include origin, so reset for merge
df_fcst.reset_index(inplace=True)
X_test_full = X_test_full.reset_index().drop(columns=''index'')
together = df_fcst.merge(X_test_full, how=''right'')
# drop rows where prediction or actuals are nan
# happens because of missing actuals
# or at edges of time due to lags/rolling windows
clean = together[together[[label_column, forecast_column_name]].notnull().all(axis=1)]
return(clean)
combined_output = align_outputs(y_fcst, X_trans, X_test, y_test, forecast_column_name)
'
, @input_data_1 = @input_query
, @input_data_1_name = N'input_data'
, @output_data_1_name = N'combined_output'
, @params = N'@model NVARCHAR(MAX), @time_column_name NVARCHAR(255), @label_column NVARCHAR(255), @y_query_column NVARCHAR(255), @forecast_column_name NVARCHAR(255)'
, @model = @model
, @time_column_name = @time_column_name
, @label_column = @label_column
, @y_query_column = @y_query_column
, @forecast_column_name = @forecast_column_name
END

14
how-to-use-azureml/automated-machine-learning/sql-server/setup/AutoMLTrain.sql
View File

@@ -69,7 +69,10 @@ CREATE OR ALTER PROCEDURE [dbo].[AutoMLTrain]
@is_validate_column NVARCHAR(255)='', -- The name of the column in the result of @input_query that indicates if the row is for training or validation. @is_validate_column NVARCHAR(255)='', -- The name of the column in the result of @input_query that indicates if the row is for training or validation.
-- In the values of the column, 0 means for training and 1 means for validation. -- In the values of the column, 0 means for training and 1 means for validation.
@time_column_name NVARCHAR(255)='', -- The name of the timestamp column for forecasting. @time_column_name NVARCHAR(255)='', -- The name of the timestamp column for forecasting.
@connection_name NVARCHAR(255)='default' -- The AML connection to use. @connection_name NVARCHAR(255)='default', -- The AML connection to use.
@max_horizon INT = 0 -- 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.
-- For example, if data is recorded daily and max_horizon is 5, we will predict 5 days ahead.
) AS ) AS
BEGIN BEGIN
@@ -151,8 +154,10 @@ if __name__.startswith("sqlindb"):
if time_column_name != "" and time_column_name is not None: if time_column_name != "" and time_column_name is not None:
automl_settings = { "time_column_name": time_column_name } automl_settings = { "time_column_name": time_column_name }
preprocess = False preprocess = False
if max_horizon > 0:
automl_settings["max_horizon"] = max_horizon
log_file_name = "automl_errors.log" log_file_name = "automl_sqlindb_errors.log"
automl_config = AutoMLConfig(task = task, automl_config = AutoMLConfig(task = task,
debug_log = log_file_name, debug_log = log_file_name,
@@ -163,7 +168,6 @@ if __name__.startswith("sqlindb"):
n_cross_validations = n_cross_validations, n_cross_validations = n_cross_validations,
preprocess = preprocess, preprocess = preprocess,
verbosity = logging.INFO, verbosity = logging.INFO,
enable_ensembling = False,
X = X_train, X = X_train,
y = y_train, y = y_train,
path = project_folder, path = project_folder,
@@ -211,7 +215,8 @@ if __name__.startswith("sqlindb"):
@tenantid NVARCHAR(255), @tenantid NVARCHAR(255),
@appid NVARCHAR(255), @appid NVARCHAR(255),
@password NVARCHAR(255), @password NVARCHAR(255),
@config_file NVARCHAR(255)' @config_file NVARCHAR(255),
@max_horizon INT'
, @label_column = @label_column , @label_column = @label_column
, @primary_metric = @primary_metric , @primary_metric = @primary_metric
, @iterations = @iterations , @iterations = @iterations
@@ -230,5 +235,6 @@ if __name__.startswith("sqlindb"):
, @appid = @appid , @appid = @appid
, @password = @password , @password = @password
, @config_file = @config_file , @config_file = @config_file
, @max_horizon = @max_horizon
WITH RESULT SETS ((best_run NVARCHAR(250), experiment_name NVARCHAR(100), fitted_model VARCHAR(MAX), log_file_text NVARCHAR(MAX), workspace NVARCHAR(100))) WITH RESULT SETS ((best_run NVARCHAR(250), experiment_name NVARCHAR(100), fitted_model VARCHAR(MAX), log_file_text NVARCHAR(MAX), workspace NVARCHAR(100)))
END END

1118
how-to-use-azureml/automated-machine-learning/sql-server/setup/auto-ml-sql-setup.ipynb
View File

File diff suppressed because it is too large Load Diff

8
how-to-use-azureml/automated-machine-learning/subsampling/auto-ml-subsampling-local.yml Normal file
View File

@@ -0,0 +1,8 @@
name: auto-ml-subsampling-local
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml

1412
how-to-use-azureml/data-drift/azure-ml-datadrift.ipynb
View File

File diff suppressed because it is too large Load Diff

4
how-to-use-azureml/deploy-to-cloud/model-register-and-deploy.yml Normal file
View File

@@ -0,0 +1,4 @@
name: model-register-and-deploy
dependencies:
- pip:
- azureml-sdk

4
how-to-use-azureml/deployment/enable-app-insights-in-production-service/enable-app-insights-in-production-service.yml Normal file
View File

@@ -0,0 +1,4 @@
name: enable-app-insights-in-production-service
dependencies:
- pip:
- azureml-sdk

4
how-to-use-azureml/deployment/enable-data-collection-for-models-in-aks/enable-data-collection-for-models-in-aks.yml Normal file
View File

@@ -0,0 +1,4 @@
name: enable-data-collection-for-models-in-aks
dependencies:
- pip:
- azureml-sdk

6
how-to-use-azureml/deployment/onnx/onnx-convert-aml-deploy-tinyyolo.yml Normal file
View File

@@ -0,0 +1,6 @@
name: onnx-convert-aml-deploy-tinyyolo
dependencies:
- pip:
- azureml-sdk
- git+https://github.com/apple/coremltools
- onnxmltools==1.3.1

9
how-to-use-azureml/deployment/onnx/onnx-inference-facial-expression-recognition-deploy.yml Normal file
View File

@@ -0,0 +1,9 @@
name: onnx-inference-facial-expression-recognition-deploy
dependencies:
- pip:
- azureml-sdk
- azureml-widgets
- matplotlib
- numpy
- onnx
- opencv-python

9
how-to-use-azureml/deployment/onnx/onnx-inference-mnist-deploy.yml Normal file
View File

@@ -0,0 +1,9 @@
name: onnx-inference-mnist-deploy
dependencies:
- pip:
- azureml-sdk
- azureml-widgets
- matplotlib
- numpy
- onnx
- opencv-python

4
how-to-use-azureml/deployment/onnx/onnx-modelzoo-aml-deploy-resnet50.yml Normal file
View File

@@ -0,0 +1,4 @@
name: onnx-modelzoo-aml-deploy-resnet50
dependencies:
- pip:
- azureml-sdk

5
how-to-use-azureml/deployment/onnx/onnx-train-pytorch-aml-deploy-mnist.yml Normal file
View File

@@ -0,0 +1,5 @@
name: onnx-train-pytorch-aml-deploy-mnist
dependencies:
- pip:
- azureml-sdk
- azureml-widgets

8
how-to-use-azureml/deployment/production-deploy-to-aks/production-deploy-to-aks.yml Normal file
View File

@@ -0,0 +1,8 @@
name: production-deploy-to-aks
dependencies:
- pip:
- azureml-sdk
- matplotlib
- tqdm
- scipy
- sklearn

8
how-to-use-azureml/deployment/register-model-create-image-deploy-service/register-model-create-image-deploy-service.yml Normal file
View File

@@ -0,0 +1,8 @@
name: register-model-create-image-deploy-service
dependencies:
- pip:
- azureml-sdk
- matplotlib
- tqdm
- scipy
- sklearn

6
how-to-use-azureml/explain-model/explain-on-amlcompute/regression-sklearn-on-amlcompute.yml Normal file
View File

@@ -0,0 +1,6 @@
name: regression-sklearn-on-amlcompute
dependencies:
- pip:
- azureml-sdk
- azureml-explain-model
- azureml-contrib-explain-model

6
how-to-use-azureml/explain-model/explain-tabular-data-local/explain-local-sklearn-binary-classification.yml Normal file
View File

@@ -0,0 +1,6 @@
name: explain-local-sklearn-binary-classification
dependencies:
- pip:
- azureml-sdk
- azureml-explain-model
- azureml-contrib-explain-model

6
how-to-use-azureml/explain-model/explain-tabular-data-local/explain-local-sklearn-multiclass-classification.yml Normal file
View File

@@ -0,0 +1,6 @@
name: explain-local-sklearn-multiclass-classification
dependencies:
- pip:
- azureml-sdk
- azureml-explain-model
- azureml-contrib-explain-model

6
how-to-use-azureml/explain-model/explain-tabular-data-local/explain-local-sklearn-regression.yml Normal file
View File

@@ -0,0 +1,6 @@
name: explain-local-sklearn-regression
dependencies:
- pip:
- azureml-sdk
- azureml-explain-model
- azureml-contrib-explain-model

7
how-to-use-azureml/explain-model/explain-tabular-data-raw-features/explain-sklearn-raw-features.yml Normal file
View File

@@ -0,0 +1,7 @@
name: explain-sklearn-raw-features
dependencies:
- pip:
- azureml-sdk
- azureml-explain-model
- azureml-contrib-explain-model
- sklearn-pandas

6
how-to-use-azureml/explain-model/explain-tabular-data-run-history/explain-run-history-sklearn-classification.yml Normal file
View File

@@ -0,0 +1,6 @@
name: explain-run-history-sklearn-classification
dependencies:
- pip:
- azureml-sdk
- azureml-explain-model
- azureml-contrib-explain-model

6
how-to-use-azureml/explain-model/explain-tabular-data-run-history/explain-run-history-sklearn-regression.yml Normal file
View File

@@ -0,0 +1,6 @@
name: explain-run-history-sklearn-regression
dependencies:
- pip:
- azureml-sdk
- azureml-explain-model
- azureml-contrib-explain-model

5
how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-data-transfer.yml Normal file
View File

@@ -0,0 +1,5 @@
name: aml-pipelines-data-transfer
dependencies:
- pip:
- azureml-sdk
- azureml-widgets

5
how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-getting-started.yml Normal file
View File

@@ -0,0 +1,5 @@
name: aml-pipelines-getting-started
dependencies:
- pip:
- azureml-sdk
- azureml-widgets

5
how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-how-to-use-estimatorstep.yml Normal file
View File

@@ -0,0 +1,5 @@
name: aml-pipelines-how-to-use-estimatorstep
dependencies:
- pip:
- azureml-sdk
- azureml-widgets

6
how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-publish-and-run-using-rest-endpoint.yml Normal file
View File

@@ -0,0 +1,6 @@
name: aml-pipelines-publish-and-run-using-rest-endpoint
dependencies:
- pip:
- azureml-sdk
- azureml-widgets
- requests

8
how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-automated-machine-learning-step.yml Normal file
View File

@@ -0,0 +1,8 @@
name: aml-pipelines-with-automated-machine-learning-step
dependencies:
- pip:
- azureml-sdk
- azureml-train-automl
- azureml-widgets
- matplotlib
- pandas_ml

5
how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-data-dependency-steps.yml Normal file
View File

@@ -0,0 +1,5 @@
name: aml-pipelines-with-data-dependency-steps
dependencies:
- pip:
- azureml-sdk
- azureml-widgets

4
how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/nyc-taxi-data-regression-model-building.ipynb
View File

@@ -26,7 +26,7 @@
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Prepare data for regression modeling\n", "## Prepare data for regression modeling\n",
"First, we will prepare data for regression modeling. We will leverage the convenience of Azure Open Datasets along with the power of Azure Machine Learning service to create a regression model to predict NYC taxi fare prices. Perform `pip install azureml-contrib-opendatasets` to get the open dataset package. The Open Datasets package contains a class representing each data source (NycTlcGreen and NycTlcYellow) to easily filter date parameters before downloading.\n", "First, we will prepare data for regression modeling. We will leverage the convenience of Azure Open Datasets along with the power of Azure Machine Learning service to create a regression model to predict NYC taxi fare prices. Perform `pip install azureml-opendatasets` to get the open dataset package. The Open Datasets package contains a class representing each data source (NycTlcGreen and NycTlcYellow) to easily filter date parameters before downloading.\n",
"\n", "\n",
"\n", "\n",
"### Load data\n", "### Load data\n",
@@ -52,7 +52,7 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"from azureml.contrib.opendatasets import NycTlcGreen, NycTlcYellow\n", "from azureml.opendatasets import NycTlcGreen, NycTlcYellow\n",
"import pandas as pd\n", "import pandas as pd\n",
"from datetime import datetime\n", "from datetime import datetime\n",
"from dateutil.relativedelta import relativedelta\n", "from dateutil.relativedelta import relativedelta\n",

9
how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/nyc-taxi-data-regression-model-building.yml Normal file
View File

@@ -0,0 +1,9 @@
name: nyc-taxi-data-regression-model-building
dependencies:
- pip:
- azureml-sdk
- azureml-widgets
- azureml-opendatasets
- azureml-dataprep
- azureml-train-automl
- matplotlib

7
how-to-use-azureml/machine-learning-pipelines/pipeline-batch-scoring/pipeline-batch-scoring.yml Normal file
View File

@@ -0,0 +1,7 @@
name: pipeline-batch-scoring
dependencies:
- pip:
- azureml-sdk
- azureml-widgets
- pandas
- requests

3
how-to-use-azureml/machine-learning-pipelines/pipeline-style-transfer/neural_style.py
View File

@@ -1,6 +1,3 @@
# Copyright (c) Microsoft. All rights reserved.
# Licensed under the MIT license.
# Original source: https://github.com/pytorch/examples/blob/master/fast_neural_style/neural_style/neural_style.py # Original source: https://github.com/pytorch/examples/blob/master/fast_neural_style/neural_style/neural_style.py
import argparse import argparse
import os import os

6
how-to-use-azureml/machine-learning-pipelines/pipeline-style-transfer/pipeline-style-transfer.yml Normal file
View File

@@ -0,0 +1,6 @@
name: pipeline-style-transfer
dependencies:
- pip:
- azureml-sdk
- azureml-widgets
- requests

57
how-to-use-azureml/manage-azureml-service/authentication-in-azureml/authentication-in-azureml.ipynb
View File

@@ -6,8 +6,20 @@
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License.\n", "Licensed under the MIT License."
"\n", ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/manage-azureml-service/authentication-in-azureml/authentication-in-azureml.png)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Authentication in Azure Machine Learning\n", "## Authentication in Azure Machine Learning\n",
"\n", "\n",
"This notebook shows you how to authenticate to your Azure ML Workspace using\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." "The interactive authentication is suitable for local experimentation on your own computer. Azure CLI authentication is suitable if you are already using Azure CLI for managing Azure resources, and want to sign in only once. The Service Principal authentication is suitable for automated workflows, for example as part of Azure Devops build."
] ]
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/manage-azureml-service/authentication-in-azureml/authentication-in-azureml.png)"
]
},
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
@@ -92,7 +97,7 @@
"source": [ "source": [
"In some cases, you may see a version of the error message containing text: ```All the subscriptions that you have access to = []```\n", "In some cases, you may see a version of the error message containing text: ```All the subscriptions that you have access to = []```\n",
"\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", "\n",
"Note that you must have administrator privileges over the Azure subscription to complete these steps.\n", "Note that you must have administrator privileges over the Azure subscription to complete these steps.\n",
"\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", "\n",
"Then click **Create**.\n", "Then click **Register**.\n",
"\n", "\n",
"![service principal creation]<img src=\"images/svc-pr-1.PNG\">" "![service principal creation](images/svc-pr-1.PNG)"
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"The next step is to obtain the _Application ID_ (also called username) and create _password_ for the service principal.\n", "From the page for your newly created service principal, copy the _Application ID_ and _Tenant ID_ as they are needed later.\n",
"\n", "![application and tenant id](images/svc-pr-2.PNG)"
"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",
"![application id and password](images/svc-pr-2.PNG)"
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "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", "\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", "\n",
"![tenant id](images/svc-pr-3.PNG)" "![tenant id](images/svc-pr-3.PNG)"
] ]
@@ -229,6 +230,20 @@
"\n", "\n",
"print(\"Found workspace {} at location {}\".format(ws.name, ws.location))" "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": { "metadata": {
@@ -252,7 +267,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.6.5" "version": "3.6.4"
} }
}, },
"nbformat": 4, "nbformat": 4,

BIN
how-to-use-azureml/manage-azureml-service/authentication-in-azureml/images/svc-pr-1.PNG
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 37 KiB

After

Width:  |  Height:  |  Size: 97 KiB

BIN
how-to-use-azureml/manage-azureml-service/authentication-in-azureml/images/svc-pr-2.PNG
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 68 KiB

After

Width:  |  Height:  |  Size: 82 KiB

BIN
how-to-use-azureml/manage-azureml-service/authentication-in-azureml/images/svc-pr-3.PNG
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 67 KiB

After

Width:  |  Height:  |  Size: 62 KiB

5
how-to-use-azureml/training-with-deep-learning/distributed-chainer/distributed-chainer.ipynb
View File

@@ -295,7 +295,7 @@
"metadata": { "metadata": {
"authors": [ "authors": [
{ {
"name": "minxia" "name": "ninhu"
} }
], ],
"kernelspec": { "kernelspec": {
@@ -314,8 +314,7 @@
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.6.6" "version": "3.6.6"
}, }
"msauthor": "minxia"
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2 "nbformat_minor": 2

5
how-to-use-azureml/training-with-deep-learning/distributed-chainer/distributed-chainer.yml Normal file
View File

@@ -0,0 +1,5 @@
name: distributed-chainer
dependencies:
- pip:
- azureml-sdk
- azureml-widgets

2
how-to-use-azureml/training-with-deep-learning/distributed-cntk-with-custom-docker/distributed-cntk-with-custom-docker.ipynb
View File

@@ -375,7 +375,7 @@
"metadata": { "metadata": {
"authors": [ "authors": [
{ {
"name": "minxia" "name": "ninhu"
} }
], ],
"kernelspec": { "kernelspec": {

6
how-to-use-azureml/training-with-deep-learning/distributed-cntk-with-custom-docker/distributed-cntk-with-custom-docker.yml Normal file
View File

@@ -0,0 +1,6 @@
name: distributed-cntk-with-custom-docker
dependencies:
- pip:
- azureml-sdk
- azureml-widgets
- numpy

5
how-to-use-azureml/training-with-deep-learning/distributed-pytorch-with-horovod/distributed-pytorch-with-horovod.ipynb
View File

@@ -315,7 +315,7 @@
"metadata": { "metadata": {
"authors": [ "authors": [
{ {
"name": "minxia" "name": "ninhu"
} }
], ],
"kernelspec": { "kernelspec": {
@@ -334,8 +334,7 @@
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.6.6" "version": "3.6.6"
}, }
"msauthor": "minxia"
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2 "nbformat_minor": 2

5
how-to-use-azureml/training-with-deep-learning/distributed-pytorch-with-horovod/distributed-pytorch-with-horovod.yml Normal file
View File

@@ -0,0 +1,5 @@
name: distributed-pytorch-with-horovod
dependencies:
- pip:
- azureml-sdk
- azureml-widgets

3
how-to-use-azureml/training-with-deep-learning/distributed-tensorflow-with-horovod/distributed-tensorflow-with-horovod.ipynb
View File

@@ -403,8 +403,7 @@
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.6.6" "version": "3.6.6"
}, }
"msauthor": "minxia"
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2 "nbformat_minor": 2

5
how-to-use-azureml/training-with-deep-learning/distributed-tensorflow-with-horovod/distributed-tensorflow-with-horovod.yml Normal file
View File

@@ -0,0 +1,5 @@
name: distributed-tensorflow-with-horovod
dependencies:
- pip:
- azureml-sdk
- azureml-widgets

5
how-to-use-azureml/training-with-deep-learning/distributed-tensorflow-with-parameter-server/distributed-tensorflow-with-parameter-server.ipynb
View File

@@ -299,7 +299,7 @@
"metadata": { "metadata": {
"authors": [ "authors": [
{ {
"name": "minxia" "name": "ninhu"
} }
], ],
"kernelspec": { "kernelspec": {
@@ -318,8 +318,7 @@
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.6.6" "version": "3.6.6"
}, }
"msauthor": "minxia"
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2 "nbformat_minor": 2

5
how-to-use-azureml/training-with-deep-learning/distributed-tensorflow-with-parameter-server/distributed-tensorflow-with-parameter-server.yml Normal file
View File

@@ -0,0 +1,5 @@
name: distributed-tensorflow-with-parameter-server
dependencies:
- pip:
- azureml-sdk
- azureml-widgets

9
how-to-use-azureml/training-with-deep-learning/export-run-history-to-tensorboard/export-run-history-to-tensorboard.yml Normal file
View File

@@ -0,0 +1,9 @@
name: export-run-history-to-tensorboard
dependencies:
- pip:
- azureml-sdk
- azureml-tensorboard
- tensorflow
- tqdm
- scipy
- sklearn

7
how-to-use-azureml/training-with-deep-learning/how-to-use-estimator/how-to-use-estimator.ipynb
View File

@@ -144,7 +144,7 @@
" print('Found existing compute target')\n", " print('Found existing compute target')\n",
"except ComputeTargetException:\n", "except ComputeTargetException:\n",
" print('Creating a new compute target...')\n", " print('Creating a new compute target...')\n",
" compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_NC6', max_nodes=4)\n", " compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_D2_V2', max_nodes=4)\n",
"\n", "\n",
" # create the cluster\n", " # create the cluster\n",
" cpu_cluster = ComputeTarget.create(ws, cluster_name, compute_config)\n", " cpu_cluster = ComputeTarget.create(ws, cluster_name, compute_config)\n",
@@ -515,7 +515,7 @@
"metadata": { "metadata": {
"authors": [ "authors": [
{ {
"name": "maxluk" "name": "ninhu"
} }
], ],
"kernelspec": { "kernelspec": {
@@ -534,8 +534,7 @@
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.6.8" "version": "3.6.8"
}, }
"msauthor": "jingywa"
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2 "nbformat_minor": 2

6
how-to-use-azureml/training-with-deep-learning/how-to-use-estimator/how-to-use-estimator.yml Normal file
View File

@@ -0,0 +1,6 @@
name: how-to-use-estimator
dependencies:
- pip:
- azureml-sdk
- azureml-widgets
- azureml-contrib-notebook

6
how-to-use-azureml/training-with-deep-learning/tensorboard/tensorboard.yml Normal file
View File

@@ -0,0 +1,6 @@
name: tensorboard
dependencies:
- pip:
- azureml-sdk
- azureml-tensorboard
- tensorflow

5
how-to-use-azureml/training-with-deep-learning/train-hyperparameter-tune-deploy-with-chainer/train-hyperparameter-tune-deploy-with-chainer.ipynb
View File

@@ -405,7 +405,7 @@
"metadata": { "metadata": {
"authors": [ "authors": [
{ {
"name": "minxia" "name": "ninhu"
} }
], ],
"kernelspec": { "kernelspec": {
@@ -424,8 +424,7 @@
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.6.6" "version": "3.6.6"
}, }
"msauthor": "minxia"
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2 "nbformat_minor": 2

7
how-to-use-azureml/training-with-deep-learning/train-hyperparameter-tune-deploy-with-chainer/train-hyperparameter-tune-deploy-with-chainer.yml Normal file
View File

@@ -0,0 +1,7 @@
name: train-hyperparameter-tune-deploy-with-chainer
dependencies:
- pip:
- azureml-sdk
- azureml-widgets
- numpy
- pytest

7
how-to-use-azureml/training-with-deep-learning/train-hyperparameter-tune-deploy-with-keras/train-hyperparameter-tune-deploy-with-keras.ipynb
View File

@@ -700,7 +700,7 @@
"est = TensorFlow(source_directory=script_folder,\n", "est = TensorFlow(source_directory=script_folder,\n",
" script_params={'--data-folder': ds.path('mnist').as_mount()},\n", " script_params={'--data-folder': ds.path('mnist').as_mount()},\n",
" compute_target=compute_target,\n", " compute_target=compute_target,\n",
" conda_packages=['keras', 'matplotlib'],\n", " pip_packages=['keras', 'matplotlib'],\n",
" entry_script='keras_mnist.py', \n", " entry_script='keras_mnist.py', \n",
" use_gpu=True)" " use_gpu=True)"
] ]
@@ -1151,7 +1151,7 @@
"metadata": { "metadata": {
"authors": [ "authors": [
{ {
"name": "maxluk" "name": "ninhu"
} }
], ],
"kernelspec": { "kernelspec": {
@@ -1170,8 +1170,7 @@
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.6.7" "version": "3.6.7"
}, }
"msauthor": "maxluk"
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2 "nbformat_minor": 2

8
how-to-use-azureml/training-with-deep-learning/train-hyperparameter-tune-deploy-with-keras/train-hyperparameter-tune-deploy-with-keras.yml Normal file
View File

@@ -0,0 +1,8 @@
name: train-hyperparameter-tune-deploy-with-keras
dependencies:
- matplotlib
- tensorflow
- pip:
- azureml-sdk
- azureml-widgets
- keras

5
how-to-use-azureml/training-with-deep-learning/train-hyperparameter-tune-deploy-with-pytorch/train-hyperparameter-tune-deploy-with-pytorch.ipynb
View File

@@ -719,7 +719,7 @@
"metadata": { "metadata": {
"authors": [ "authors": [
{ {
"name": "minxia" "name": "ninhu"
} }
], ],
"kernelspec": { "kernelspec": {
@@ -738,8 +738,7 @@
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.6.6" "version": "3.6.6"
}, }
"msauthor": "minxia"
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2 "nbformat_minor": 2

9
how-to-use-azureml/training-with-deep-learning/train-hyperparameter-tune-deploy-with-pytorch/train-hyperparameter-tune-deploy-with-pytorch.yml Normal file
View File

@@ -0,0 +1,9 @@
name: train-hyperparameter-tune-deploy-with-pytorch
dependencies:
- pip:
- azureml-sdk
- azureml-widgets
- pillow==5.4.1
- matplotlib
- https://download.pytorch.org/whl/cpu/torch-1.1.0-cp35-cp35m-win_amd64.whl
- https://download.pytorch.org/whl/cpu/torchvision-0.3.0-cp35-cp35m-win_amd64.whl

5
how-to-use-azureml/training-with-deep-learning/train-hyperparameter-tune-deploy-with-tensorflow/train-hyperparameter-tune-deploy-with-tensorflow.ipynb
View File

@@ -1151,7 +1151,7 @@
"metadata": { "metadata": {
"authors": [ "authors": [
{ {
"name": "minxia" "name": "ninhu"
} }
], ],
"kernelspec": { "kernelspec": {
@@ -1170,8 +1170,7 @@
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.6.8" "version": "3.6.8"
}, }
"msauthor": "minxia"
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2 "nbformat_minor": 2

8
how-to-use-azureml/training-with-deep-learning/train-hyperparameter-tune-deploy-with-tensorflow/train-hyperparameter-tune-deploy-with-tensorflow.yml Normal file
View File

@@ -0,0 +1,8 @@
name: train-hyperparameter-tune-deploy-with-tensorflow
dependencies:
- numpy
- matplotlib
- tensorflow
- pip:
- azureml-sdk
- azureml-widgets

5
how-to-use-azureml/training/README.md
View File

@@ -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. 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. 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. 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. 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. 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.
![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/training/README.png) ![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/training/README.png)

2
how-to-use-azureml/training/logging-api/logging-api.ipynb
View File

@@ -100,7 +100,7 @@
"\n", "\n",
"# Check core SDK version number\n", "# Check core SDK version number\n",
"\n", "\n",
"print(\"This notebook was created using SDK version 1.0.45, you are currently running version\", azureml.core.VERSION)" "print(\"This notebook was created using SDK version 1.0.48, you are currently running version\", azureml.core.VERSION)"
] ]
}, },
{ {

8
how-to-use-azureml/training/logging-api/logging-api.yml Normal file
View 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
View File

@@ -0,0 +1,4 @@
name: manage-runs
dependencies:
- pip:
- azureml-sdk

82
how-to-use-azureml/training/train-hyperparameter-tune-deploy-with-sklearn/train-hyperparameter-tune-deploy-with-sklearn.ipynb
View File

@@ -126,24 +126,13 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"from azureml.core.compute import ComputeTarget, AmlCompute\n", "from azureml.core.compute import ComputeTarget\n",
"from azureml.core.compute_target import ComputeTargetException\n",
"\n", "\n",
"# choose a name for your cluster\n", "# choose a name for your cluster\n",
"cluster_name = \"gpu-cluster\"\n", "cluster_name = \"cpu-cluster\"\n",
"\n", "\n",
"try:\n", "compute_target = ComputeTarget(workspace=ws, name=cluster_name)\n",
" compute_target = ComputeTarget(workspace=ws, name=cluster_name)\n", "print('Found existing compute target.')\n",
" print('Found existing compute target.')\n",
"except ComputeTargetException:\n",
" print('Creating a new compute target...')\n",
" compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_NC6',\n",
" max_nodes=4)\n",
"\n",
" # create the cluster\n",
" compute_target = ComputeTarget.create(ws, cluster_name, compute_config)\n",
"\n",
" compute_target.wait_for_completion(show_output=True)\n",
"\n", "\n",
"# use get_status() to get a detailed status for the current cluster. \n", "# use get_status() to get a detailed status for the current cluster. \n",
"print(compute_target.get_status().serialize())" "print(compute_target.get_status().serialize())"
@@ -153,7 +142,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"The above code creates GPU compute. If you instead want to create CPU compute, provide a different VM size to the `vm_size` parameter, such as `STANDARD_D2_V2`." "The above code retrieves an existing CPU compute target. Scikit-learn does not support GPU computing."
] ]
}, },
{ {
@@ -167,7 +156,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Now that you have your data and training script prepared, you are ready to train on your remote compute cluster. You can take advantage of Azure compute to leverage GPUs to cut down your training time." "Now that you have your data and training script prepared, you are ready to train on your remote compute. You can take advantage of Azure compute to leverage a CPU cluster."
] ]
}, },
{ {
@@ -299,7 +288,8 @@
"estimator = SKLearn(source_directory=project_folder, \n", "estimator = SKLearn(source_directory=project_folder, \n",
" script_params=script_params,\n", " script_params=script_params,\n",
" compute_target=compute_target,\n", " compute_target=compute_target,\n",
" entry_script='train_iris.py'\n", " entry_script='train_iris.py',\n",
" pip_packages=['joblib']\n",
" )" " )"
] ]
}, },
@@ -307,7 +297,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"The `script_params` parameter is a dictionary containing the command-line arguments to your training script `entry_script`. To leverage the Azure VM's GPU for training, we set `use_gpu=True`." "The `script_params` parameter is a dictionary containing the command-line arguments to your training script `entry_script`."
] ]
}, },
{ {
@@ -467,7 +457,57 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"run.wait_for_completion(show_output=True)" "hyperdrive_run.wait_for_completion(show_output=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Find and register best model\n",
"When all jobs finish, we can find out the one that has the highest accuracy."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"best_run = hyperdrive_run.get_best_run_by_primary_metric()\n",
"print(best_run.get_details()['runDefinition']['arguments'])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now, let's list the model files uploaded during the run."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"print(best_run.get_file_names())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We can then register the folder (and all files in it) as a model named `sklearn-iris` under the workspace for deployment"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"model = best_run.register_model(model_name='sklearn-iris', model_path='model.joblib')"
] ]
} }
], ],
@@ -492,7 +532,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.5.2" "version": "3.6.6"
}, },
"msauthor": "dipeck" "msauthor": "dipeck"
}, },

Some files were not shown because too many files have changed in this diff Show More