diff --git a/configuration.ipynb b/configuration.ipynb
index d383a4f6c..c7e741399 100644
--- a/configuration.ipynb
+++ b/configuration.ipynb
@@ -103,7 +103,7 @@
"source": [
"import azureml.core\n",
"\n",
- "print(\"This notebook was created using version 1.36.0 of the Azure ML SDK\")\n",
+ "print(\"This notebook was created using version 1.37.0 of the Azure ML SDK\")\n",
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
]
},
diff --git a/contrib/fairness/fairlearn-azureml-mitigation.yml b/contrib/fairness/fairlearn-azureml-mitigation.yml
index 89e1e4518..c8e12d554 100644
--- a/contrib/fairness/fairlearn-azureml-mitigation.yml
+++ b/contrib/fairness/fairlearn-azureml-mitigation.yml
@@ -6,4 +6,4 @@ dependencies:
- fairlearn>=0.6.2
- joblib
- liac-arff
- - raiwidgets~=0.13.0
+ - raiwidgets~=0.15.0
diff --git a/contrib/fairness/upload-fairness-dashboard.yml b/contrib/fairness/upload-fairness-dashboard.yml
index 5596446ac..5720c954c 100644
--- a/contrib/fairness/upload-fairness-dashboard.yml
+++ b/contrib/fairness/upload-fairness-dashboard.yml
@@ -6,4 +6,4 @@ dependencies:
- fairlearn>=0.6.2
- joblib
- liac-arff
- - raiwidgets~=0.13.0
+ - raiwidgets~=0.15.0
diff --git a/how-to-use-azureml/automated-machine-learning/automl_env.yml b/how-to-use-azureml/automated-machine-learning/automl_env.yml
index 35a684ead..17b4e8fc7 100644
--- a/how-to-use-azureml/automated-machine-learning/automl_env.yml
+++ b/how-to-use-azureml/automated-machine-learning/automl_env.yml
@@ -4,7 +4,6 @@ dependencies:
# Currently Azure ML only supports 3.5.2 and later.
- pip==21.1.2
- python>=3.5.2,<3.8
-- nb_conda
- boto3==1.15.18
- matplotlib==2.1.0
- numpy==1.18.5
@@ -22,9 +21,9 @@ dependencies:
- pip:
# Required packages for AzureML execution, history, and data preparation.
- - azureml-widgets~=1.36.0
+ - azureml-widgets~=1.37.0
- pytorch-transformers==1.0.0
- spacy==2.1.8
- https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz
- - -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.36.0/validated_win32_requirements.txt [--no-deps]
+ - -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.37.0/validated_win32_requirements.txt [--no-deps]
- arch==4.14
diff --git a/how-to-use-azureml/automated-machine-learning/automl_env_linux.yml b/how-to-use-azureml/automated-machine-learning/automl_env_linux.yml
index 88e78c764..3d16c2b6b 100644
--- a/how-to-use-azureml/automated-machine-learning/automl_env_linux.yml
+++ b/how-to-use-azureml/automated-machine-learning/automl_env_linux.yml
@@ -22,9 +22,9 @@ dependencies:
- pip:
# Required packages for AzureML execution, history, and data preparation.
- - azureml-widgets~=1.36.0
+ - azureml-widgets~=1.37.0
- pytorch-transformers==1.0.0
- spacy==2.1.8
- https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz
- - -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.36.0/validated_linux_requirements.txt [--no-deps]
+ - -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.37.0/validated_linux_requirements.txt [--no-deps]
- arch==4.14
diff --git a/how-to-use-azureml/automated-machine-learning/automl_env_mac.yml b/how-to-use-azureml/automated-machine-learning/automl_env_mac.yml
index 60b3f0083..602b0c5b9 100644
--- a/how-to-use-azureml/automated-machine-learning/automl_env_mac.yml
+++ b/how-to-use-azureml/automated-machine-learning/automl_env_mac.yml
@@ -23,9 +23,9 @@ dependencies:
- pip:
# Required packages for AzureML execution, history, and data preparation.
- - azureml-widgets~=1.36.0
+ - azureml-widgets~=1.37.0
- pytorch-transformers==1.0.0
- spacy==2.1.8
- https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz
- - -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.36.0/validated_darwin_requirements.txt [--no-deps]
+ - -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.37.0/validated_darwin_requirements.txt [--no-deps]
- arch==4.14
diff --git a/how-to-use-azureml/automated-machine-learning/classification-bank-marketing-all-features/auto-ml-classification-bank-marketing-all-features.ipynb b/how-to-use-azureml/automated-machine-learning/classification-bank-marketing-all-features/auto-ml-classification-bank-marketing-all-features.ipynb
index 1e5bebc32..eb58da8ca 100644
--- a/how-to-use-azureml/automated-machine-learning/classification-bank-marketing-all-features/auto-ml-classification-bank-marketing-all-features.ipynb
+++ b/how-to-use-azureml/automated-machine-learning/classification-bank-marketing-all-features/auto-ml-classification-bank-marketing-all-features.ipynb
@@ -77,6 +77,7 @@
"metadata": {},
"outputs": [],
"source": [
+ "import json\n",
"import logging\n",
"\n",
"from matplotlib import pyplot as plt\n",
@@ -104,7 +105,7 @@
"metadata": {},
"outputs": [],
"source": [
- "print(\"This notebook was created using version 1.36.0 of the Azure ML SDK\")\n",
+ "print(\"This notebook was created using version 1.37.0 of the Azure ML SDK\")\n",
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
]
},
@@ -410,7 +411,8 @@
"metadata": {},
"outputs": [],
"source": [
- "best_run_customized, fitted_model_customized = remote_run.get_output()"
+ "# Retrieve the best Run object\n",
+ "best_run = remote_run.get_best_child()"
]
},
{
@@ -419,7 +421,7 @@
"source": [
"## Transparency\n",
"\n",
- "View updated featurization summary"
+ "View featurization summary for the best model - to study how different features were transformed. This is stored as a JSON file in the outputs directory for the run."
]
},
{
@@ -428,36 +430,14 @@
"metadata": {},
"outputs": [],
"source": [
- "custom_featurizer = fitted_model_customized.named_steps['datatransformer']\n",
- "df = custom_featurizer.get_featurization_summary()\n",
- "pd.DataFrame(data=df)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "Set `is_user_friendly=False` to get a more detailed summary for the transforms being applied."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "df = custom_featurizer.get_featurization_summary(is_user_friendly=False)\n",
- "pd.DataFrame(data=df)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "df = custom_featurizer.get_stats_feature_type_summary()\n",
- "pd.DataFrame(data=df)"
+ "# Download the featuurization summary JSON file locally\n",
+ "best_run.download_file(\"outputs/featurization_summary.json\", \"featurization_summary.json\")\n",
+ "\n",
+ "# Render the JSON as a pandas DataFrame\n",
+ "with open(\"featurization_summary.json\", \"r\") as f:\n",
+ " records = json.load(f)\n",
+ "\n",
+ "pd.DataFrame.from_records(records)"
]
},
{
@@ -499,7 +479,7 @@
"model_explainability_run.wait_for_completion()\n",
"\n",
"# Get the best run object\n",
- "best_run, fitted_model = remote_run.get_output()"
+ "best_run = remote_run.get_best_child()"
]
},
{
@@ -629,7 +609,16 @@
"\n",
"### Retrieve the Best Model\n",
"\n",
- "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+ "Below we select the best pipeline from our iterations. The `get_best_child` method returns the Run object for the best model based on the default primary metric. There are additional flags that can be passed to the method if we want to retrieve the best Run based on any of the other supported metrics, or if we are just interested in the best run among the ONNX compatible runs. As always, you can execute `remote_run.get_best_child??` in a new cell to view the source or docs for the function."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "remote_run.get_best_child??"
]
},
{
@@ -649,7 +638,7 @@
"metadata": {},
"outputs": [],
"source": [
- "best_run, fitted_model = remote_run.get_output()"
+ "best_run = remote_run.get_best_child()"
]
},
{
diff --git a/how-to-use-azureml/automated-machine-learning/classification-credit-card-fraud/auto-ml-classification-credit-card-fraud.ipynb b/how-to-use-azureml/automated-machine-learning/classification-credit-card-fraud/auto-ml-classification-credit-card-fraud.ipynb
index 0b0af0fe2..9f429e908 100644
--- a/how-to-use-azureml/automated-machine-learning/classification-credit-card-fraud/auto-ml-classification-credit-card-fraud.ipynb
+++ b/how-to-use-azureml/automated-machine-learning/classification-credit-card-fraud/auto-ml-classification-credit-card-fraud.ipynb
@@ -93,7 +93,7 @@
"metadata": {},
"outputs": [],
"source": [
- "print(\"This notebook was created using version 1.36.0 of the Azure ML SDK\")\n",
+ "print(\"This notebook was created using version 1.37.0 of the Azure ML SDK\")\n",
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
]
},
diff --git a/how-to-use-azureml/automated-machine-learning/classification-text-dnn/auto-ml-classification-text-dnn.ipynb b/how-to-use-azureml/automated-machine-learning/classification-text-dnn/auto-ml-classification-text-dnn.ipynb
index 433f83dd5..7bfd14ca6 100644
--- a/how-to-use-azureml/automated-machine-learning/classification-text-dnn/auto-ml-classification-text-dnn.ipynb
+++ b/how-to-use-azureml/automated-machine-learning/classification-text-dnn/auto-ml-classification-text-dnn.ipynb
@@ -63,6 +63,7 @@
"metadata": {},
"outputs": [],
"source": [
+ "import json\n",
"import logging\n",
"import os\n",
"import shutil\n",
@@ -96,7 +97,7 @@
"metadata": {},
"outputs": [],
"source": [
- "print(\"This notebook was created using version 1.36.0 of the Azure ML SDK\")\n",
+ "print(\"This notebook was created using version 1.37.0 of the Azure ML SDK\")\n",
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
]
},
@@ -340,8 +341,9 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "You can test the model locally to get a feel of the input/output. When the model contains BERT, this step will require pytorch and pytorch-transformers installed in your local environment. The exact versions of these packages can be found in the **automl_env.yml** file located in the local copy of your MachineLearningNotebooks folder here:\n",
- "MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/automl_env.yml"
+ "For local inferencing, you can load the model locally via. the method `remote_run.get_output()`. For more information on the arguments expected by this method, you can run `remote_run.get_output??`.\n",
+ "Note that when the model contains BERT, this step will require pytorch and pytorch-transformers installed in your local environment. The exact versions of these packages can be found in the **automl_env.yml** file located in the local copy of your MachineLearningNotebooks folder here:\n",
+ "MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/automl_env.yml\n"
]
},
{
@@ -350,7 +352,8 @@
"metadata": {},
"outputs": [],
"source": [
- "best_run, fitted_model = automl_run.get_output()"
+ "# Retrieve the best Run object\n",
+ "best_run = automl_run.get_best_child()"
]
},
{
@@ -366,10 +369,15 @@
"metadata": {},
"outputs": [],
"source": [
- "text_transformations_used = []\n",
- "for column_group in fitted_model.named_steps['datatransformer'].get_featurization_summary():\n",
- " text_transformations_used.extend(column_group['Transformations'])\n",
- "text_transformations_used"
+ "# Download the featuurization summary JSON file locally\n",
+ "best_run.download_file(\"outputs/featurization_summary.json\", \"featurization_summary.json\")\n",
+ "\n",
+ "# Render the JSON as a pandas DataFrame\n",
+ "with open(\"featurization_summary.json\", \"r\") as f:\n",
+ " records = json.load(f)\n",
+ "\n",
+ "featurization_summary = pd.DataFrame.from_records(records)\n",
+ "featurization_summary['Transformations'].tolist()"
]
},
{
diff --git a/how-to-use-azureml/automated-machine-learning/continuous-retraining/auto-ml-continuous-retraining.ipynb b/how-to-use-azureml/automated-machine-learning/continuous-retraining/auto-ml-continuous-retraining.ipynb
index b4513a973..4fccb351f 100644
--- a/how-to-use-azureml/automated-machine-learning/continuous-retraining/auto-ml-continuous-retraining.ipynb
+++ b/how-to-use-azureml/automated-machine-learning/continuous-retraining/auto-ml-continuous-retraining.ipynb
@@ -81,7 +81,7 @@
"metadata": {},
"outputs": [],
"source": [
- "print(\"This notebook was created using version 1.36.0 of the Azure ML SDK\")\n",
+ "print(\"This notebook was created using version 1.37.0 of the Azure ML SDK\")\n",
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
]
},
diff --git a/how-to-use-azureml/automated-machine-learning/experimental/classification-credit-card-fraud-local-managed/auto-ml-classification-credit-card-fraud-local-managed.ipynb b/how-to-use-azureml/automated-machine-learning/experimental/classification-credit-card-fraud-local-managed/auto-ml-classification-credit-card-fraud-local-managed.ipynb
index c7f2d0d2d..7d9ac27d7 100644
--- a/how-to-use-azureml/automated-machine-learning/experimental/classification-credit-card-fraud-local-managed/auto-ml-classification-credit-card-fraud-local-managed.ipynb
+++ b/how-to-use-azureml/automated-machine-learning/experimental/classification-credit-card-fraud-local-managed/auto-ml-classification-credit-card-fraud-local-managed.ipynb
@@ -92,7 +92,7 @@
"metadata": {},
"outputs": [],
"source": [
- "print(\"This notebook was created using version 1.36.0 of the Azure ML SDK\")\n",
+ "print(\"This notebook was created using version 1.37.0 of the Azure ML SDK\")\n",
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
]
},
diff --git a/how-to-use-azureml/automated-machine-learning/experimental/regression-model-proxy/auto-ml-regression-model-proxy.ipynb b/how-to-use-azureml/automated-machine-learning/experimental/regression-model-proxy/auto-ml-regression-model-proxy.ipynb
index c2aea2a11..7f66b09d8 100644
--- a/how-to-use-azureml/automated-machine-learning/experimental/regression-model-proxy/auto-ml-regression-model-proxy.ipynb
+++ b/how-to-use-azureml/automated-machine-learning/experimental/regression-model-proxy/auto-ml-regression-model-proxy.ipynb
@@ -91,7 +91,7 @@
"metadata": {},
"outputs": [],
"source": [
- "print(\"This notebook was created using version 1.36.0 of the Azure ML SDK\")\n",
+ "print(\"This notebook was created using version 1.37.0 of the Azure ML SDK\")\n",
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
]
},
diff --git a/how-to-use-azureml/automated-machine-learning/forecasting-backtest-many-models/Backtesting.png b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-many-models/Backtesting.png
new file mode 100644
index 000000000..4697e68fa
Binary files /dev/null and b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-many-models/Backtesting.png differ
diff --git a/how-to-use-azureml/automated-machine-learning/forecasting-backtest-many-models/assets/score.py b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-many-models/assets/score.py
new file mode 100644
index 000000000..43c9ac215
--- /dev/null
+++ b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-many-models/assets/score.py
@@ -0,0 +1,167 @@
+from typing import Any, Dict, Optional, List
+
+import argparse
+import json
+import os
+import re
+
+import pandas as pd
+
+from matplotlib import pyplot as plt
+from matplotlib.backends.backend_pdf import PdfPages
+
+from azureml.automl.core.shared import constants
+from azureml.automl.core.shared.types import GrainType
+from azureml.automl.runtime.shared.score import scoring
+
+GRAIN = "time_series_id"
+BACKTEST_ITER = "backtest_iteration"
+ACTUALS = "actual_level"
+PREDICTIONS = "predicted_level"
+ALL_GRAINS = "all_sets"
+
+FORECASTS_FILE = "forecast.csv"
+SCORES_FILE = "scores.csv"
+PLOTS_FILE = "plots_fcst_vs_actual.pdf"
+RE_INVALID_SYMBOLS = re.compile("[: ]")
+
+
+def _compute_metrics(df: pd.DataFrame, metrics: List[str]):
+ """
+ Compute metrics for one data frame.
+
+ :param df: The data frame which contains actual_level and predicted_level columns.
+ :return: The data frame with two columns - metric_name and metric.
+ """
+ scores = scoring.score_regression(
+ y_test=df[ACTUALS], y_pred=df[PREDICTIONS], metrics=metrics
+ )
+ metrics_df = pd.DataFrame(list(scores.items()), columns=["metric_name", "metric"])
+ metrics_df.sort_values(["metric_name"], inplace=True)
+ metrics_df.reset_index(drop=True, inplace=True)
+ return metrics_df
+
+
+def _format_grain_name(grain: GrainType) -> str:
+ """
+ Convert grain name to string.
+
+ :param grain: the grain name.
+ :return: the string representation of the given grain.
+ """
+ if not isinstance(grain, tuple) and not isinstance(grain, list):
+ return str(grain)
+ grain = list(map(str, grain))
+ return "|".join(grain)
+
+
+def compute_all_metrics(
+ fcst_df: pd.DataFrame,
+ ts_id_colnames: List[str],
+ metric_names: Optional[List[set]] = None,
+):
+ """
+ Calculate metrics per grain.
+
+ :param fcst_df: forecast data frame. Must contain 2 columns: 'actual_level' and 'predicted_level'
+ :param metric_names: (optional) the list of metric names to return
+ :param ts_id_colnames: (optional) list of grain column names
+ :return: dictionary of summary table for all tests and final decision on stationary vs nonstaionary
+ """
+ if not metric_names:
+ metric_names = list(constants.Metric.SCALAR_REGRESSION_SET)
+
+ if ts_id_colnames is None:
+ ts_id_colnames = []
+
+ metrics_list = []
+ if ts_id_colnames:
+ for grain, df in fcst_df.groupby(ts_id_colnames):
+ one_grain_metrics_df = _compute_metrics(df, metric_names)
+ one_grain_metrics_df[GRAIN] = _format_grain_name(grain)
+ metrics_list.append(one_grain_metrics_df)
+
+ # overall metrics
+ one_grain_metrics_df = _compute_metrics(fcst_df, metric_names)
+ one_grain_metrics_df[GRAIN] = ALL_GRAINS
+ metrics_list.append(one_grain_metrics_df)
+
+ # collect into a data frame
+ return pd.concat(metrics_list)
+
+
+def _draw_one_plot(
+ df: pd.DataFrame,
+ time_column_name: str,
+ grain_column_names: List[str],
+ pdf: PdfPages,
+) -> None:
+ """
+ Draw the single plot.
+
+ :param df: The data frame with the data to build plot.
+ :param time_column_name: The name of a time column.
+ :param grain_column_names: The name of grain columns.
+ :param pdf: The pdf backend used to render the plot.
+ """
+ fig, _ = plt.subplots(figsize=(20, 10))
+ df = df.set_index(time_column_name)
+ plt.plot(df[[ACTUALS, PREDICTIONS]])
+ plt.xticks(rotation=45)
+ iteration = df[BACKTEST_ITER].iloc[0]
+ if grain_column_names:
+ grain_name = [df[grain].iloc[0] for grain in grain_column_names]
+ plt.title(f"Time series ID: {_format_grain_name(grain_name)} {iteration}")
+ plt.legend(["actual", "forecast"])
+ plt.close(fig)
+ pdf.savefig(fig)
+
+
+def calculate_scores_and_build_plots(
+ input_dir: str, output_dir: str, automl_settings: Dict[str, Any]
+):
+ os.makedirs(output_dir, exist_ok=True)
+ grains = automl_settings.get(constants.TimeSeries.GRAIN_COLUMN_NAMES)
+ time_column_name = automl_settings.get(constants.TimeSeries.TIME_COLUMN_NAME)
+ if grains is None:
+ grains = []
+ if isinstance(grains, str):
+ grains = [grains]
+ while BACKTEST_ITER in grains:
+ grains.remove(BACKTEST_ITER)
+
+ dfs = []
+ for fle in os.listdir(input_dir):
+ file_path = os.path.join(input_dir, fle)
+ if os.path.isfile(file_path) and file_path.endswith(".csv"):
+ df_iter = pd.read_csv(file_path, parse_dates=[time_column_name])
+ for _, iteration in df_iter.groupby(BACKTEST_ITER):
+ dfs.append(iteration)
+ forecast_df = pd.concat(dfs, sort=False, ignore_index=True)
+ # To make sure plots are in order, sort the predictions by grain and iteration.
+ ts_index = grains + [BACKTEST_ITER]
+ forecast_df.sort_values(by=ts_index, inplace=True)
+ pdf = PdfPages(os.path.join(output_dir, PLOTS_FILE))
+ for _, one_forecast in forecast_df.groupby(ts_index):
+ _draw_one_plot(one_forecast, time_column_name, grains, pdf)
+ pdf.close()
+ forecast_df.to_csv(os.path.join(output_dir, FORECASTS_FILE), index=False)
+ metrics = compute_all_metrics(forecast_df, grains + [BACKTEST_ITER])
+ metrics.to_csv(os.path.join(output_dir, SCORES_FILE), index=False)
+
+
+if __name__ == "__main__":
+ args = {"forecasts": "--forecasts", "scores_out": "--output-dir"}
+ parser = argparse.ArgumentParser("Parsing input arguments.")
+ for argname, arg in args.items():
+ parser.add_argument(arg, dest=argname, required=True)
+ parsed_args, _ = parser.parse_known_args()
+ input_dir = parsed_args.forecasts
+ output_dir = parsed_args.scores_out
+ with open(
+ os.path.join(
+ os.path.dirname(os.path.realpath(__file__)), "automl_settings.json"
+ )
+ ) as json_file:
+ automl_settings = json.load(json_file)
+ calculate_scores_and_build_plots(input_dir, output_dir, automl_settings)
diff --git a/how-to-use-azureml/automated-machine-learning/forecasting-backtest-many-models/auto-ml-forecasting-backtest-many-models.ipynb b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-many-models/auto-ml-forecasting-backtest-many-models.ipynb
new file mode 100644
index 000000000..610948ed5
--- /dev/null
+++ b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-many-models/auto-ml-forecasting-backtest-many-models.ipynb
@@ -0,0 +1,725 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+ "\n",
+ "Licensed under the MIT License."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ ""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Many Models with Backtesting - Automated ML\n",
+ "**_Backtest many models time series forecasts with Automated Machine Learning_**\n",
+ "\n",
+ "---"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "For this notebook we are using a synthetic dataset to demonstrate the back testing in many model scenario. This allows us to check historical performance of AutoML on a historical data. To do that we step back on the backtesting period by the data set several times and split the data to train and test sets. Then these data sets are used for training and evaluation of model.
\n",
+ "\n",
+ "Thus, it is a quick way of evaluating AutoML as if it was in production. Here, we do not test historical performance of a particular model, for this see the [notebook](../forecasting-backtest-single-model/auto-ml-forecasting-backtest-single-model.ipynb). Instead, the best model for every backtest iteration can be different since AutoML chooses the best model for a given training set.\n",
+ "\n",
+ "\n",
+ "**NOTE: There are limits on how many runs we can do in parallel per workspace, and we currently recommend to set the parallelism to maximum of 320 runs per experiment per workspace. If users want to have more parallelism and increase this limit they might encounter Too Many Requests errors (HTTP 429).**"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Prerequisites\n",
+ "You'll need to create a compute Instance by following the instructions in the [EnvironmentSetup.md](../Setup_Resources/EnvironmentSetup.md)."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 1.0 Set up workspace, datastore, experiment"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "gather": {
+ "logged": 1613003526897
+ }
+ },
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "\n",
+ "import azureml.core\n",
+ "from azureml.core import Workspace, Datastore\n",
+ "import numpy as np\n",
+ "import pandas as pd\n",
+ "\n",
+ "from pandas.tseries.frequencies import to_offset\n",
+ "\n",
+ "# Set up your workspace\n",
+ "ws = Workspace.from_config()\n",
+ "ws.get_details()\n",
+ "\n",
+ "# Set up your datastores\n",
+ "dstore = ws.get_default_datastore()\n",
+ "\n",
+ "output = {}\n",
+ "output[\"SDK version\"] = azureml.core.VERSION\n",
+ "output[\"Subscription ID\"] = ws.subscription_id\n",
+ "output[\"Workspace\"] = ws.name\n",
+ "output[\"Resource Group\"] = ws.resource_group\n",
+ "output[\"Location\"] = ws.location\n",
+ "output[\"Default datastore name\"] = dstore.name\n",
+ "pd.set_option(\"display.max_colwidth\", -1)\n",
+ "outputDf = pd.DataFrame(data=output, index=[\"\"])\n",
+ "outputDf.T"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "This notebook is compatible with Azure ML SDK version 1.35.1 or later."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Choose an experiment"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "gather": {
+ "logged": 1613003540729
+ }
+ },
+ "outputs": [],
+ "source": [
+ "from azureml.core import Experiment\n",
+ "\n",
+ "experiment = Experiment(ws, \"automl-many-models-backtest\")\n",
+ "\n",
+ "print(\"Experiment name: \" + experiment.name)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 2.0 Data\n",
+ "\n",
+ "#### 2.1 Data generation\n",
+ "For this notebook we will generate the artificial data set with two [time series IDs](https://docs.microsoft.com/en-us/python/api/azureml-automl-core/azureml.automl.core.forecasting_parameters.forecastingparameters?view=azure-ml-py). Then we will generate backtest folds and will upload it to the default BLOB storage and create a [TabularDataset](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.tabular_dataset.tabulardataset?view=azure-ml-py)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# simulate data: 2 grains - 700\n",
+ "TIME_COLNAME = \"date\"\n",
+ "TARGET_COLNAME = \"value\"\n",
+ "TIME_SERIES_ID_COLNAME = \"ts_id\"\n",
+ "\n",
+ "sample_size = 700\n",
+ "# Set the random seed for reproducibility of results.\n",
+ "np.random.seed(20)\n",
+ "X1 = pd.DataFrame(\n",
+ " {\n",
+ " TIME_COLNAME: pd.date_range(start=\"2018-01-01\", periods=sample_size),\n",
+ " TARGET_COLNAME: np.random.normal(loc=100, scale=20, size=sample_size),\n",
+ " TIME_SERIES_ID_COLNAME: \"ts_A\",\n",
+ " }\n",
+ ")\n",
+ "X2 = pd.DataFrame(\n",
+ " {\n",
+ " TIME_COLNAME: pd.date_range(start=\"2018-01-01\", periods=sample_size),\n",
+ " TARGET_COLNAME: np.random.normal(loc=100, scale=20, size=sample_size),\n",
+ " TIME_SERIES_ID_COLNAME: \"ts_B\",\n",
+ " }\n",
+ ")\n",
+ "\n",
+ "X = pd.concat([X1, X2], ignore_index=True, sort=False)\n",
+ "print(\"Simulated dataset contains {} rows \\n\".format(X.shape[0]))\n",
+ "X.head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Now we will generate 8 backtesting folds with backtesting period of 7 days and with the same forecasting horizon. We will add the column \"backtest_iteration\", which will identify the backtesting period by the last training date."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "offset_type = \"7D\"\n",
+ "NUMBER_OF_BACKTESTS = 8 # number of train/test sets to generate\n",
+ "\n",
+ "dfs_train = []\n",
+ "dfs_test = []\n",
+ "for ts_id, df_one in X.groupby(TIME_SERIES_ID_COLNAME):\n",
+ "\n",
+ " data_end = df_one[TIME_COLNAME].max()\n",
+ "\n",
+ " for i in range(NUMBER_OF_BACKTESTS):\n",
+ " train_cutoff_date = data_end - to_offset(offset_type)\n",
+ " df_one = df_one.copy()\n",
+ " df_one[\"backtest_iteration\"] = \"iteration_\" + str(train_cutoff_date)\n",
+ " train = df_one[df_one[TIME_COLNAME] <= train_cutoff_date]\n",
+ " test = df_one[\n",
+ " (df_one[TIME_COLNAME] > train_cutoff_date)\n",
+ " & (df_one[TIME_COLNAME] <= data_end)\n",
+ " ]\n",
+ " data_end = train[TIME_COLNAME].max()\n",
+ " dfs_train.append(train)\n",
+ " dfs_test.append(test)\n",
+ "\n",
+ "X_train = pd.concat(dfs_train, sort=False, ignore_index=True)\n",
+ "X_test = pd.concat(dfs_test, sort=False, ignore_index=True)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### 2.2 Create the Tabular Data Set.\n",
+ "\n",
+ "A Datastore is a place where data can be stored that is then made accessible to a compute either by means of mounting or copying the data to the compute target.\n",
+ "\n",
+ "Please refer to [Datastore](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.datastore(class)?view=azure-ml-py) documentation on how to access data from Datastore.\n",
+ "\n",
+ "In this next step, we will upload the data and create a TabularDataset."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from azureml.data.dataset_factory import TabularDatasetFactory\n",
+ "\n",
+ "ds = ws.get_default_datastore()\n",
+ "# Upload saved data to the default data store.\n",
+ "train_data = TabularDatasetFactory.register_pandas_dataframe(\n",
+ " X_train, target=(ds, \"data_mm\"), name=\"data_train\"\n",
+ ")\n",
+ "test_data = TabularDatasetFactory.register_pandas_dataframe(\n",
+ " X_test, target=(ds, \"data_mm\"), name=\"data_test\"\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 3.0 Build the training pipeline\n",
+ "Now that the dataset, WorkSpace, and datastore are set up, we can put together a pipeline for training.\n",
+ "\n",
+ "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Choose a compute target\n",
+ "\n",
+ "You will need to create a [compute target](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-set-up-training-targets#amlcompute) for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
+ "\n",
+ "\\*\\*Creation of AmlCompute takes approximately 5 minutes.**\n",
+ "\n",
+ "If the AmlCompute with that name is already in your workspace this code will skip the creation process. As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read this [article](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-manage-quotas) on the default limits and how to request more quota."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "gather": {
+ "logged": 1613007037308
+ }
+ },
+ "outputs": [],
+ "source": [
+ "from azureml.core.compute import ComputeTarget, AmlCompute\n",
+ "\n",
+ "# Name your cluster\n",
+ "compute_name = \"backtest-mm\"\n",
+ "\n",
+ "\n",
+ "if compute_name in ws.compute_targets:\n",
+ " compute_target = ws.compute_targets[compute_name]\n",
+ " if compute_target and type(compute_target) is AmlCompute:\n",
+ " print(\"Found compute target: \" + compute_name)\n",
+ "else:\n",
+ " print(\"Creating a new compute target...\")\n",
+ " provisioning_config = AmlCompute.provisioning_configuration(\n",
+ " vm_size=\"STANDARD_DS12_V2\", max_nodes=6\n",
+ " )\n",
+ " # Create the compute target\n",
+ " compute_target = ComputeTarget.create(ws, compute_name, provisioning_config)\n",
+ "\n",
+ " # Can poll for a minimum number of nodes and for a specific timeout.\n",
+ " # If no min node count is provided it will use the scale settings for the cluster\n",
+ " compute_target.wait_for_completion(\n",
+ " show_output=True, min_node_count=None, timeout_in_minutes=20\n",
+ " )\n",
+ "\n",
+ " # For a more detailed view of current cluster status, use the 'status' property\n",
+ " print(compute_target.status.serialize())"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Set up training parameters\n",
+ "\n",
+ "This dictionary defines the AutoML and many models settings. For this forecasting task we need to define several settings including the name of the time column, the maximum forecast horizon, and the partition column name definition. Please note, that in this case we are setting grain_column_names to be the time series ID column plus iteration, because we want to train a separate model for each time series and iteration.\n",
+ "\n",
+ "| Property | Description|\n",
+ "| :--------------- | :------------------- |\n",
+ "| **task** | forecasting |\n",
+ "| **primary_metric** | This is the metric that you want to optimize.
Forecasting supports the following primary metrics
normalized_root_mean_squared_error
normalized_mean_absolute_error |\n",
+ "| **iteration_timeout_minutes** | Maximum amount of time in minutes that the model can train. This is optional but provides customers with greater control on exit criteria. |\n",
+ "| **iterations** | Number of models to train. This is optional but provides customers with greater control on exit criteria. |\n",
+ "| **experiment_timeout_hours** | Maximum amount of time in hours that the experiment can take before it terminates. This is optional but provides customers with greater control on exit criteria. |\n",
+ "| **label_column_name** | The name of the label column. |\n",
+ "| **max_horizon** | The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly). Periods are inferred from your data. |\n",
+ "| **n_cross_validations** | Number of cross validation splits. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
+ "| **time_column_name** | The name of your time column. |\n",
+ "| **grain_column_names** | The column names used to uniquely identify timeseries in data that has multiple rows with the same timestamp. |\n",
+ "| **track_child_runs** | Flag to disable tracking of child runs. Only best run is tracked if the flag is set to False (this includes the model and metrics of the run). |\n",
+ "| **partition_column_names** | The names of columns used to group your models. For timeseries, the groups must not split up individual time-series. That is, each group must contain one or more whole time-series. |"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "gather": {
+ "logged": 1613007061544
+ }
+ },
+ "outputs": [],
+ "source": [
+ "from azureml.train.automl.runtime._many_models.many_models_parameters import (\n",
+ " ManyModelsTrainParameters,\n",
+ ")\n",
+ "\n",
+ "partition_column_names = [TIME_SERIES_ID_COLNAME, \"backtest_iteration\"]\n",
+ "automl_settings = {\n",
+ " \"task\": \"forecasting\",\n",
+ " \"primary_metric\": \"normalized_root_mean_squared_error\",\n",
+ " \"iteration_timeout_minutes\": 10, # This needs to be changed based on the dataset. We ask customer to explore how long training is taking before settings this value\n",
+ " \"iterations\": 15,\n",
+ " \"experiment_timeout_hours\": 0.25, # This also needs to be changed based on the dataset. For larger data set this number needs to be bigger.\n",
+ " \"label_column_name\": TARGET_COLNAME,\n",
+ " \"n_cross_validations\": 3,\n",
+ " \"time_column_name\": TIME_COLNAME,\n",
+ " \"max_horizon\": 6,\n",
+ " \"grain_column_names\": partition_column_names,\n",
+ " \"track_child_runs\": False,\n",
+ "}\n",
+ "\n",
+ "mm_paramters = ManyModelsTrainParameters(\n",
+ " automl_settings=automl_settings, partition_column_names=partition_column_names\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Set up many models pipeline"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Parallel run step is leveraged to train multiple models at once. To configure the ParallelRunConfig you will need to determine the appropriate number of workers and nodes for your use case. The process_count_per_node is based off the number of cores of the compute VM. The node_count will determine the number of master nodes to use, increasing the node count will speed up the training process.\n",
+ "\n",
+ "| Property | Description|\n",
+ "| :--------------- | :------------------- |\n",
+ "| **experiment** | The experiment used for training. |\n",
+ "| **train_data** | The file dataset to be used as input to the training run. |\n",
+ "| **node_count** | The number of compute nodes to be used for running the user script. We recommend to start with 3 and increase the node_count if the training time is taking too long. |\n",
+ "| **process_count_per_node** | Process count per node, we recommend 2:1 ratio for number of cores: number of processes per node. eg. If node has 16 cores then configure 8 or less process count per node or optimal performance. |\n",
+ "| **train_pipeline_parameters** | The set of configuration parameters defined in the previous section. |\n",
+ "\n",
+ "Calling this method will create a new aggregated dataset which is generated dynamically on pipeline execution."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from azureml.contrib.automl.pipeline.steps import AutoMLPipelineBuilder\n",
+ "\n",
+ "\n",
+ "training_pipeline_steps = AutoMLPipelineBuilder.get_many_models_train_steps(\n",
+ " experiment=experiment,\n",
+ " train_data=train_data,\n",
+ " compute_target=compute_target,\n",
+ " node_count=2,\n",
+ " process_count_per_node=2,\n",
+ " run_invocation_timeout=920,\n",
+ " train_pipeline_parameters=mm_paramters,\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from azureml.pipeline.core import Pipeline\n",
+ "\n",
+ "training_pipeline = Pipeline(ws, steps=training_pipeline_steps)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Submit the pipeline to run\n",
+ "Next we submit our pipeline to run. The whole training pipeline takes about 20 minutes using a STANDARD_DS12_V2 VM with our current ParallelRunConfig setting."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "training_run = experiment.submit(training_pipeline)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "training_run.wait_for_completion(show_output=False)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Check the run status, if training_run is in completed state, continue to next section. Otherwise, check the portal for failures."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 4.0 Backtesting\n",
+ "Now that we selected the best AutoML model for each backtest fold, we will use these models to generate the forecasts and compare with the actuals."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Set up output dataset for inference data\n",
+ "Output of inference can be represented as [OutputFileDatasetConfig](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.output_dataset_config.outputdatasetconfig?view=azure-ml-py) object and OutputFileDatasetConfig can be registered as a dataset. "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from azureml.data import OutputFileDatasetConfig\n",
+ "\n",
+ "output_inference_data_ds = OutputFileDatasetConfig(\n",
+ " name=\"many_models_inference_output\",\n",
+ " destination=(dstore, \"backtesting/inference_data/\"),\n",
+ ").register_on_complete(name=\"backtesting_data_ds\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "For many models we need to provide the ManyModelsInferenceParameters object.\n",
+ "\n",
+ "#### ManyModelsInferenceParameters arguments\n",
+ "| Property | Description|\n",
+ "| :--------------- | :------------------- |\n",
+ "| **partition_column_names** | List of column names that identifies groups. |\n",
+ "| **target_column_name** | \\[Optional\\] Column name only if the inference dataset has the target. |\n",
+ "| **time_column_name** | Column name only if it is timeseries. |\n",
+ "| **many_models_run_id** | \\[Optional\\] Many models pipeline run id where models were trained. |\n",
+ "\n",
+ "#### get_many_models_batch_inference_steps arguments\n",
+ "| Property | Description|\n",
+ "| :--------------- | :------------------- |\n",
+ "| **experiment** | The experiment used for inference run. |\n",
+ "| **inference_data** | The data to use for inferencing. It should be the same schema as used for training.\n",
+ "| **compute_target** | The compute target that runs the inference pipeline.|\n",
+ "| **node_count** | The number of compute nodes to be used for running the user script. We recommend to start with the number of cores per node (varies by compute sku). |\n",
+ "| **process_count_per_node** | The number of processes per node.\n",
+ "| **train_run_id** | \\[Optional\\] The run id of the hierarchy training, by default it is the latest successful training many model run in the experiment. |\n",
+ "| **train_experiment_name** | \\[Optional\\] The train experiment that contains the train pipeline. This one is only needed when the train pipeline is not in the same experiement as the inference pipeline. |\n",
+ "| **process_count_per_node** | \\[Optional\\] The number of processes per node, by default it's 4. |"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from azureml.contrib.automl.pipeline.steps import AutoMLPipelineBuilder\n",
+ "from azureml.train.automl.runtime._many_models.many_models_parameters import (\n",
+ " ManyModelsInferenceParameters,\n",
+ ")\n",
+ "\n",
+ "mm_parameters = ManyModelsInferenceParameters(\n",
+ " partition_column_names=partition_column_names,\n",
+ " time_column_name=TIME_COLNAME,\n",
+ " target_column_name=TARGET_COLNAME,\n",
+ ")\n",
+ "\n",
+ "inference_steps = AutoMLPipelineBuilder.get_many_models_batch_inference_steps(\n",
+ " experiment=experiment,\n",
+ " inference_data=test_data,\n",
+ " node_count=2,\n",
+ " process_count_per_node=2,\n",
+ " compute_target=compute_target,\n",
+ " run_invocation_timeout=300,\n",
+ " output_datastore=output_inference_data_ds,\n",
+ " train_run_id=training_run.id,\n",
+ " train_experiment_name=training_run.experiment.name,\n",
+ " inference_pipeline_parameters=mm_parameters,\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from azureml.pipeline.core import Pipeline\n",
+ "\n",
+ "inference_pipeline = Pipeline(ws, steps=inference_steps)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "inference_run = experiment.submit(inference_pipeline)\n",
+ "inference_run.wait_for_completion(show_output=False)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 5.0 Retrieve results and calculate metrics\n",
+ "\n",
+ "The pipeline returns one file with the predictions for each times series ID and outputs the result to the forecasting_output Blob container. The details of the blob container is listed in 'forecasting_output.txt' under Outputs+logs. \n",
+ "\n",
+ "The next code snippet does the following:\n",
+ "1. Downloads the contents of the output folder that is passed in the parallel run step \n",
+ "2. Reads the parallel_run_step.txt file that has the predictions as pandas dataframe \n",
+ "3. Saves the table in csv format and \n",
+ "4. Displays the top 10 rows of the predictions"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from azureml.contrib.automl.pipeline.steps.utilities import get_output_from_mm_pipeline\n",
+ "\n",
+ "forecasting_results_name = \"forecasting_results\"\n",
+ "forecasting_output_name = \"many_models_inference_output\"\n",
+ "forecast_file = get_output_from_mm_pipeline(\n",
+ " inference_run, forecasting_results_name, forecasting_output_name\n",
+ ")\n",
+ "df = pd.read_csv(forecast_file, delimiter=\" \", header=None, parse_dates=[0])\n",
+ "df.columns = list(X_train.columns) + [\"predicted_level\"]\n",
+ "print(\n",
+ " \"Prediction has \", df.shape[0], \" rows. Here the first 10 rows are being displayed.\"\n",
+ ")\n",
+ "# Save the scv file with header to read it in the next step.\n",
+ "df.rename(columns={TARGET_COLNAME: \"actual_level\"}, inplace=True)\n",
+ "df.to_csv(os.path.join(forecasting_results_name, \"forecast.csv\"), index=False)\n",
+ "df.head(10)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## View metrics\n",
+ "We will read in the obtained results and run the helper script, which will generate metrics and create the plots of predicted versus actual values."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from assets.score import calculate_scores_and_build_plots\n",
+ "\n",
+ "backtesting_results = \"backtesting_mm_results\"\n",
+ "os.makedirs(backtesting_results, exist_ok=True)\n",
+ "calculate_scores_and_build_plots(\n",
+ " forecasting_results_name, backtesting_results, automl_settings\n",
+ ")\n",
+ "pd.DataFrame({\"File\": os.listdir(backtesting_results)})"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "The directory contains a set of files with results:\n",
+ "- forecast.csv contains forecasts for all backtest iterations. The backtest_iteration column contains iteration identifier with the last training date as a suffix\n",
+ "- scores.csv contains all metrics. If data set contains several time series, the metrics are given for all combinations of time series id and iterations, as well as scores for all iterations and time series ids, which are marked as \"all_sets\"\n",
+ "- plots_fcst_vs_actual.pdf contains the predictions vs forecast plots for each iteration and, eash time series is saved as separate plot.\n",
+ "\n",
+ "For demonstration purposes we will display the table of metrics for one of the time series with ID \"ts0\". We will create the utility function, which will build the table with metrics."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def get_metrics_for_ts(all_metrics, ts):\n",
+ " \"\"\"\n",
+ " Get the metrics for the time series with ID ts and return it as pandas data frame.\n",
+ "\n",
+ " :param all_metrics: The table with all the metrics.\n",
+ " :param ts: The ID of a time series of interest.\n",
+ " :return: The pandas DataFrame with metrics for one time series.\n",
+ " \"\"\"\n",
+ " results_df = None\n",
+ " for ts_id, one_series in all_metrics.groupby(\"time_series_id\"):\n",
+ " if not ts_id.startswith(ts):\n",
+ " continue\n",
+ " iteration = ts_id.split(\"|\")[-1]\n",
+ " df = one_series[[\"metric_name\", \"metric\"]]\n",
+ " df.rename({\"metric\": iteration}, axis=1, inplace=True)\n",
+ " df.set_index(\"metric_name\", inplace=True)\n",
+ " if results_df is None:\n",
+ " results_df = df\n",
+ " else:\n",
+ " results_df = results_df.merge(\n",
+ " df, how=\"inner\", left_index=True, right_index=True\n",
+ " )\n",
+ " results_df.sort_index(axis=1, inplace=True)\n",
+ " return results_df\n",
+ "\n",
+ "\n",
+ "metrics_df = pd.read_csv(os.path.join(backtesting_results, \"scores.csv\"))\n",
+ "ts = \"ts_A\"\n",
+ "get_metrics_for_ts(metrics_df, ts)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Forecast vs actuals plots."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from IPython.display import IFrame\n",
+ "\n",
+ "IFrame(\"./backtesting_mm_results/plots_fcst_vs_actual.pdf\", width=800, height=300)"
+ ]
+ }
+ ],
+ "metadata": {
+ "authors": [
+ {
+ "name": "jialiu"
+ }
+ ],
+ "categories": [
+ "how-to-use-azureml",
+ "automated-machine-learning"
+ ],
+ "kernelspec": {
+ "display_name": "Python 3.6",
+ "language": "python",
+ "name": "python36"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.6.9"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
\ No newline at end of file
diff --git a/how-to-use-azureml/automated-machine-learning/forecasting-backtest-many-models/auto-ml-forecasting-backtest-many-models.yml b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-many-models/auto-ml-forecasting-backtest-many-models.yml
new file mode 100644
index 000000000..55b2188d3
--- /dev/null
+++ b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-many-models/auto-ml-forecasting-backtest-many-models.yml
@@ -0,0 +1,4 @@
+name: auto-ml-forecasting-backtest-many-models
+dependencies:
+- pip:
+ - azureml-sdk
diff --git a/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/Backtesting.png b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/Backtesting.png
new file mode 100644
index 000000000..4697e68fa
Binary files /dev/null and b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/Backtesting.png differ
diff --git a/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/assets/data_split.py b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/assets/data_split.py
new file mode 100644
index 000000000..c9b6b8a89
--- /dev/null
+++ b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/assets/data_split.py
@@ -0,0 +1,45 @@
+import argparse
+import os
+
+import pandas as pd
+
+import azureml.train.automl.runtime._hts.hts_runtime_utilities as hru
+
+from azureml.core import Run
+from azureml.core.dataset import Dataset
+
+# Parse the arguments.
+args = {
+ "step_size": "--step-size",
+ "step_number": "--step-number",
+ "time_column_name": "--time-column-name",
+ "time_series_id_column_names": "--time-series-id-column-names",
+ "out_dir": "--output-dir",
+}
+parser = argparse.ArgumentParser("Parsing input arguments.")
+for argname, arg in args.items():
+ parser.add_argument(arg, dest=argname, required=True)
+parsed_args, _ = parser.parse_known_args()
+step_number = int(parsed_args.step_number)
+step_size = int(parsed_args.step_size)
+# Create the working dirrectory to store the temporary csv files.
+working_dir = parsed_args.out_dir
+os.makedirs(working_dir, exist_ok=True)
+# Set input and output
+script_run = Run.get_context()
+input_dataset = script_run.input_datasets["training_data"]
+X_train = input_dataset.to_pandas_dataframe()
+# Split the data.
+for i in range(step_number):
+ file_name = os.path.join(working_dir, "backtest_{}.csv".format(i))
+ if parsed_args.time_series_id_column_names:
+ dfs = []
+ for _, one_series in X_train.groupby([parsed_args.time_series_id_column_names]):
+ one_series = one_series.sort_values(
+ by=[parsed_args.time_column_name], inplace=False
+ )
+ dfs.append(one_series.iloc[: len(one_series) - step_size * i])
+ pd.concat(dfs, sort=False, ignore_index=True).to_csv(file_name, index=False)
+ else:
+ X_train.sort_values(by=[parsed_args.time_column_name], inplace=True)
+ X_train.iloc[: len(X_train) - step_size * i].to_csv(file_name, index=False)
diff --git a/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/assets/retrain_models.py b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/assets/retrain_models.py
new file mode 100644
index 000000000..a20c24e5c
--- /dev/null
+++ b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/assets/retrain_models.py
@@ -0,0 +1,173 @@
+# ---------------------------------------------------------
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# ---------------------------------------------------------
+"""The batch script needed for back testing of models using PRS."""
+import argparse
+import json
+import logging
+import os
+import pickle
+import re
+
+import pandas as pd
+
+from azureml.core.experiment import Experiment
+from azureml.core.model import Model
+from azureml.core.run import Run
+from azureml.automl.core.shared import constants
+from azureml.automl.runtime.shared.score import scoring
+from azureml.train.automl import AutoMLConfig
+
+RE_INVALID_SYMBOLS = re.compile(r"[:\s]")
+
+model_name = None
+target_column_name = None
+current_step_run = None
+output_dir = None
+
+logger = logging.getLogger(__name__)
+
+
+def _get_automl_settings():
+ with open(
+ os.path.join(
+ os.path.dirname(os.path.realpath(__file__)), "automl_settings.json"
+ )
+ ) as json_file:
+ return json.load(json_file)
+
+
+def init():
+ global model_name
+ global target_column_name
+ global output_dir
+ global automl_settings
+ global model_uid
+ logger.info("Initialization of the run.")
+ parser = argparse.ArgumentParser("Parsing input arguments.")
+ parser.add_argument("--output-dir", dest="out", required=True)
+ parser.add_argument("--model-name", dest="model", default=None)
+ parser.add_argument("--model-uid", dest="model_uid", default=None)
+
+ parsed_args, _ = parser.parse_known_args()
+ model_name = parsed_args.model
+ automl_settings = _get_automl_settings()
+ target_column_name = automl_settings.get("label_column_name")
+ output_dir = parsed_args.out
+ model_uid = parsed_args.model_uid
+ os.makedirs(output_dir, exist_ok=True)
+ os.environ["AUTOML_IGNORE_PACKAGE_VERSION_INCOMPATIBILITIES".lower()] = "True"
+
+
+def get_run():
+ global current_step_run
+ if current_step_run is None:
+ current_step_run = Run.get_context()
+ return current_step_run
+
+
+def run_backtest(data_input_name: str, file_name: str, experiment: Experiment):
+ """Re-train the model and return metrics."""
+ data_input = pd.read_csv(
+ data_input_name,
+ parse_dates=[automl_settings[constants.TimeSeries.TIME_COLUMN_NAME]],
+ )
+ print(data_input.head())
+ if not automl_settings.get(constants.TimeSeries.GRAIN_COLUMN_NAMES):
+ # There is no grains.
+ data_input.sort_values(
+ [automl_settings[constants.TimeSeries.TIME_COLUMN_NAME]], inplace=True
+ )
+ X_train = data_input.iloc[: -automl_settings["max_horizon"]]
+ y_train = X_train.pop(target_column_name).values
+ X_test = data_input.iloc[-automl_settings["max_horizon"] :]
+ y_test = X_test.pop(target_column_name).values
+ else:
+ # The data contain grains.
+ dfs_train = []
+ dfs_test = []
+ for _, one_series in data_input.groupby(
+ automl_settings.get(constants.TimeSeries.GRAIN_COLUMN_NAMES)
+ ):
+ one_series.sort_values(
+ [automl_settings[constants.TimeSeries.TIME_COLUMN_NAME]], inplace=True
+ )
+ dfs_train.append(one_series.iloc[: -automl_settings["max_horizon"]])
+ dfs_test.append(one_series.iloc[-automl_settings["max_horizon"] :])
+ X_train = pd.concat(dfs_train, sort=False, ignore_index=True)
+ y_train = X_train.pop(target_column_name).values
+ X_test = pd.concat(dfs_test, sort=False, ignore_index=True)
+ y_test = X_test.pop(target_column_name).values
+
+ last_training_date = str(
+ X_train[automl_settings[constants.TimeSeries.TIME_COLUMN_NAME]].max()
+ )
+
+ if file_name:
+ # If file name is provided, we will load model and retrain it on backtest data.
+ with open(file_name, "rb") as fp:
+ fitted_model = pickle.load(fp)
+ fitted_model.fit(X_train, y_train)
+ else:
+ # We will run the experiment and select the best model.
+ X_train[target_column_name] = y_train
+ automl_config = AutoMLConfig(training_data=X_train, **automl_settings)
+ automl_run = current_step_run.submit_child(automl_config, show_output=True)
+ best_run, fitted_model = automl_run.get_output()
+ # As we have generated models, we need to register them for the future use.
+ description = "Backtest model example"
+ tags = {"last_training_date": last_training_date, "experiment": experiment.name}
+ if model_uid:
+ tags["model_uid"] = model_uid
+ automl_run.register_model(
+ model_name=best_run.properties["model_name"],
+ description=description,
+ tags=tags,
+ )
+ print(f"The model {best_run.properties['model_name']} was registered.")
+
+ _, x_pred = fitted_model.forecast(X_test)
+ x_pred.reset_index(inplace=True, drop=False)
+ columns = [automl_settings[constants.TimeSeries.TIME_COLUMN_NAME]]
+ if automl_settings.get(constants.TimeSeries.GRAIN_COLUMN_NAMES):
+ # We know that fitted_model.grain_column_names is a list.
+ columns.extend(fitted_model.grain_column_names)
+ columns.append(constants.TimeSeriesInternal.DUMMY_TARGET_COLUMN)
+ # Remove featurized columns.
+ x_pred = x_pred[columns]
+ x_pred.rename(
+ {constants.TimeSeriesInternal.DUMMY_TARGET_COLUMN: "predicted_level"},
+ axis=1,
+ inplace=True,
+ )
+ x_pred["actual_level"] = y_test
+ x_pred["backtest_iteration"] = f"iteration_{last_training_date}"
+ date_safe = RE_INVALID_SYMBOLS.sub("_", last_training_date)
+ x_pred.to_csv(os.path.join(output_dir, f"iteration_{date_safe}.csv"), index=False)
+ return x_pred
+
+
+def run(input_files):
+ """Run the script"""
+ logger.info("Running mini batch.")
+ ws = get_run().experiment.workspace
+ file_name = None
+ if model_name:
+ models = Model.list(ws, name=model_name)
+ cloud_model = None
+ if models:
+ for one_mod in models:
+ if cloud_model is None or one_mod.version > cloud_model.version:
+ logger.info(
+ "Using existing model from the workspace. Model version: {}".format(
+ one_mod.version
+ )
+ )
+ cloud_model = one_mod
+ file_name = cloud_model.download(exist_ok=True)
+
+ forecasts = []
+ logger.info("Running backtest.")
+ for input_file in input_files:
+ forecasts.append(run_backtest(input_file, file_name, get_run().experiment))
+ return pd.concat(forecasts)
diff --git a/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/assets/score.py b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/assets/score.py
new file mode 100644
index 000000000..43c9ac215
--- /dev/null
+++ b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/assets/score.py
@@ -0,0 +1,167 @@
+from typing import Any, Dict, Optional, List
+
+import argparse
+import json
+import os
+import re
+
+import pandas as pd
+
+from matplotlib import pyplot as plt
+from matplotlib.backends.backend_pdf import PdfPages
+
+from azureml.automl.core.shared import constants
+from azureml.automl.core.shared.types import GrainType
+from azureml.automl.runtime.shared.score import scoring
+
+GRAIN = "time_series_id"
+BACKTEST_ITER = "backtest_iteration"
+ACTUALS = "actual_level"
+PREDICTIONS = "predicted_level"
+ALL_GRAINS = "all_sets"
+
+FORECASTS_FILE = "forecast.csv"
+SCORES_FILE = "scores.csv"
+PLOTS_FILE = "plots_fcst_vs_actual.pdf"
+RE_INVALID_SYMBOLS = re.compile("[: ]")
+
+
+def _compute_metrics(df: pd.DataFrame, metrics: List[str]):
+ """
+ Compute metrics for one data frame.
+
+ :param df: The data frame which contains actual_level and predicted_level columns.
+ :return: The data frame with two columns - metric_name and metric.
+ """
+ scores = scoring.score_regression(
+ y_test=df[ACTUALS], y_pred=df[PREDICTIONS], metrics=metrics
+ )
+ metrics_df = pd.DataFrame(list(scores.items()), columns=["metric_name", "metric"])
+ metrics_df.sort_values(["metric_name"], inplace=True)
+ metrics_df.reset_index(drop=True, inplace=True)
+ return metrics_df
+
+
+def _format_grain_name(grain: GrainType) -> str:
+ """
+ Convert grain name to string.
+
+ :param grain: the grain name.
+ :return: the string representation of the given grain.
+ """
+ if not isinstance(grain, tuple) and not isinstance(grain, list):
+ return str(grain)
+ grain = list(map(str, grain))
+ return "|".join(grain)
+
+
+def compute_all_metrics(
+ fcst_df: pd.DataFrame,
+ ts_id_colnames: List[str],
+ metric_names: Optional[List[set]] = None,
+):
+ """
+ Calculate metrics per grain.
+
+ :param fcst_df: forecast data frame. Must contain 2 columns: 'actual_level' and 'predicted_level'
+ :param metric_names: (optional) the list of metric names to return
+ :param ts_id_colnames: (optional) list of grain column names
+ :return: dictionary of summary table for all tests and final decision on stationary vs nonstaionary
+ """
+ if not metric_names:
+ metric_names = list(constants.Metric.SCALAR_REGRESSION_SET)
+
+ if ts_id_colnames is None:
+ ts_id_colnames = []
+
+ metrics_list = []
+ if ts_id_colnames:
+ for grain, df in fcst_df.groupby(ts_id_colnames):
+ one_grain_metrics_df = _compute_metrics(df, metric_names)
+ one_grain_metrics_df[GRAIN] = _format_grain_name(grain)
+ metrics_list.append(one_grain_metrics_df)
+
+ # overall metrics
+ one_grain_metrics_df = _compute_metrics(fcst_df, metric_names)
+ one_grain_metrics_df[GRAIN] = ALL_GRAINS
+ metrics_list.append(one_grain_metrics_df)
+
+ # collect into a data frame
+ return pd.concat(metrics_list)
+
+
+def _draw_one_plot(
+ df: pd.DataFrame,
+ time_column_name: str,
+ grain_column_names: List[str],
+ pdf: PdfPages,
+) -> None:
+ """
+ Draw the single plot.
+
+ :param df: The data frame with the data to build plot.
+ :param time_column_name: The name of a time column.
+ :param grain_column_names: The name of grain columns.
+ :param pdf: The pdf backend used to render the plot.
+ """
+ fig, _ = plt.subplots(figsize=(20, 10))
+ df = df.set_index(time_column_name)
+ plt.plot(df[[ACTUALS, PREDICTIONS]])
+ plt.xticks(rotation=45)
+ iteration = df[BACKTEST_ITER].iloc[0]
+ if grain_column_names:
+ grain_name = [df[grain].iloc[0] for grain in grain_column_names]
+ plt.title(f"Time series ID: {_format_grain_name(grain_name)} {iteration}")
+ plt.legend(["actual", "forecast"])
+ plt.close(fig)
+ pdf.savefig(fig)
+
+
+def calculate_scores_and_build_plots(
+ input_dir: str, output_dir: str, automl_settings: Dict[str, Any]
+):
+ os.makedirs(output_dir, exist_ok=True)
+ grains = automl_settings.get(constants.TimeSeries.GRAIN_COLUMN_NAMES)
+ time_column_name = automl_settings.get(constants.TimeSeries.TIME_COLUMN_NAME)
+ if grains is None:
+ grains = []
+ if isinstance(grains, str):
+ grains = [grains]
+ while BACKTEST_ITER in grains:
+ grains.remove(BACKTEST_ITER)
+
+ dfs = []
+ for fle in os.listdir(input_dir):
+ file_path = os.path.join(input_dir, fle)
+ if os.path.isfile(file_path) and file_path.endswith(".csv"):
+ df_iter = pd.read_csv(file_path, parse_dates=[time_column_name])
+ for _, iteration in df_iter.groupby(BACKTEST_ITER):
+ dfs.append(iteration)
+ forecast_df = pd.concat(dfs, sort=False, ignore_index=True)
+ # To make sure plots are in order, sort the predictions by grain and iteration.
+ ts_index = grains + [BACKTEST_ITER]
+ forecast_df.sort_values(by=ts_index, inplace=True)
+ pdf = PdfPages(os.path.join(output_dir, PLOTS_FILE))
+ for _, one_forecast in forecast_df.groupby(ts_index):
+ _draw_one_plot(one_forecast, time_column_name, grains, pdf)
+ pdf.close()
+ forecast_df.to_csv(os.path.join(output_dir, FORECASTS_FILE), index=False)
+ metrics = compute_all_metrics(forecast_df, grains + [BACKTEST_ITER])
+ metrics.to_csv(os.path.join(output_dir, SCORES_FILE), index=False)
+
+
+if __name__ == "__main__":
+ args = {"forecasts": "--forecasts", "scores_out": "--output-dir"}
+ parser = argparse.ArgumentParser("Parsing input arguments.")
+ for argname, arg in args.items():
+ parser.add_argument(arg, dest=argname, required=True)
+ parsed_args, _ = parser.parse_known_args()
+ input_dir = parsed_args.forecasts
+ output_dir = parsed_args.scores_out
+ with open(
+ os.path.join(
+ os.path.dirname(os.path.realpath(__file__)), "automl_settings.json"
+ )
+ ) as json_file:
+ automl_settings = json.load(json_file)
+ calculate_scores_and_build_plots(input_dir, output_dir, automl_settings)
diff --git a/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/auto-ml-forecasting-backtest-single-model.ipynb b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/auto-ml-forecasting-backtest-single-model.ipynb
new file mode 100644
index 000000000..64cada912
--- /dev/null
+++ b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/auto-ml-forecasting-backtest-single-model.ipynb
@@ -0,0 +1,719 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+ "\n",
+ "Licensed under the MIT License.\n",
+ ""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Automated MachineLearning\n",
+ "_**The model backtesting**_\n",
+ "\n",
+ "## Contents\n",
+ "1. [Introduction](#Introduction)\n",
+ "2. [Setup](#Setup)\n",
+ "3. [Data](#Data)\n",
+ "4. [Prepare remote compute and data.](#prepare_remote)\n",
+ "5. [Create the configuration for AutoML backtesting](#train)\n",
+ "6. [Backtest AutoML](#backtest_automl)\n",
+ "7. [View metrics](#Metrics)\n",
+ "8. [Backtest the best model](#backtest_model)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Introduction\n",
+ "Model backtesting is used to evaluate its performance on historical data. To do that we step back on the backtesting period by the data set several times and split the data to train and test sets. Then these data sets are used for training and evaluation of model.
\n",
+ "This notebook is intended to demonstrate backtesting on a single model, this is the best solution for small data sets with a few or one time series in it. For scenarios where we would like to choose the best AutoML model for every backtest iteration, please see [AutoML Forecasting Backtest Many Models Example](../forecasting-backtest-many-models/auto-ml-forecasting-backtest-many-models.ipynb) notebook.\n",
+ "\n",
+ "This notebook demonstrates two ways of backtesting:\n",
+ "- AutoML backtesting: we will train separate AutoML models for historical data\n",
+ "- Model backtesting: from the first run we will select the best model trained on the most recent data, retrain it on the past data and evaluate."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Setup"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "import numpy as np\n",
+ "import pandas as pd\n",
+ "import shutil\n",
+ "\n",
+ "import azureml.core\n",
+ "from azureml.core import Experiment, Model, Workspace"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "This notebook is compatible with Azure ML SDK version 1.35.1 or later."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "As part of the setup you have already created a Workspace."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "ws = Workspace.from_config()\n",
+ "\n",
+ "output = {}\n",
+ "output[\"Subscription ID\"] = ws.subscription_id\n",
+ "output[\"Workspace\"] = ws.name\n",
+ "output[\"SKU\"] = ws.sku\n",
+ "output[\"Resource Group\"] = ws.resource_group\n",
+ "output[\"Location\"] = ws.location\n",
+ "pd.set_option(\"display.max_colwidth\", -1)\n",
+ "outputDf = pd.DataFrame(data=output, index=[\"\"])\n",
+ "outputDf.T"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Data\n",
+ "For the demonstration purposes we will simulate one year of daily data. To do this we need to specify the following parameters: time column name, time series ID column names and label column name. Our intention is to forecast for two weeks ahead."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "TIME_COLUMN_NAME = \"date\"\n",
+ "TIME_SERIES_ID_COLUMN_NAMES = \"time_series_id\"\n",
+ "LABEL_COLUMN_NAME = \"y\"\n",
+ "FORECAST_HORIZON = 14\n",
+ "FREQUENCY = \"D\"\n",
+ "\n",
+ "\n",
+ "def simulate_timeseries_data(\n",
+ " train_len: int,\n",
+ " test_len: int,\n",
+ " time_column_name: str,\n",
+ " target_column_name: str,\n",
+ " time_series_id_column_name: str,\n",
+ " time_series_number: int = 1,\n",
+ " freq: str = \"H\",\n",
+ "):\n",
+ " \"\"\"\n",
+ " Return the time series of designed length.\n",
+ "\n",
+ " :param train_len: The length of training data (one series).\n",
+ " :type train_len: int\n",
+ " :param test_len: The length of testing data (one series).\n",
+ " :type test_len: int\n",
+ " :param time_column_name: The desired name of a time column.\n",
+ " :type time_column_name: str\n",
+ " :param time_series_number: The number of time series in the data set.\n",
+ " :type time_series_number: int\n",
+ " :param freq: The frequency string representing pandas offset.\n",
+ " see https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html\n",
+ " :type freq: str\n",
+ " :returns: the tuple of train and test data sets.\n",
+ " :rtype: tuple\n",
+ "\n",
+ " \"\"\"\n",
+ " data_train = [] # type: List[pd.DataFrame]\n",
+ " data_test = [] # type: List[pd.DataFrame]\n",
+ " data_length = train_len + test_len\n",
+ " for i in range(time_series_number):\n",
+ " X = pd.DataFrame(\n",
+ " {\n",
+ " time_column_name: pd.date_range(\n",
+ " start=\"2000-01-01\", periods=data_length, freq=freq\n",
+ " ),\n",
+ " target_column_name: np.arange(data_length).astype(float)\n",
+ " + np.random.rand(data_length)\n",
+ " + i * 5,\n",
+ " \"ext_predictor\": np.asarray(range(42, 42 + data_length)),\n",
+ " time_series_id_column_name: np.repeat(\"ts{}\".format(i), data_length),\n",
+ " }\n",
+ " )\n",
+ " data_train.append(X[:train_len])\n",
+ " data_test.append(X[train_len:])\n",
+ " train = pd.concat(data_train)\n",
+ " label_train = train.pop(target_column_name).values\n",
+ " test = pd.concat(data_test)\n",
+ " label_test = test.pop(target_column_name).values\n",
+ " return train, label_train, test, label_test\n",
+ "\n",
+ "\n",
+ "n_test_periods = FORECAST_HORIZON\n",
+ "n_train_periods = 365\n",
+ "X_train, y_train, X_test, y_test = simulate_timeseries_data(\n",
+ " train_len=n_train_periods,\n",
+ " test_len=n_test_periods,\n",
+ " time_column_name=TIME_COLUMN_NAME,\n",
+ " target_column_name=LABEL_COLUMN_NAME,\n",
+ " time_series_id_column_name=TIME_SERIES_ID_COLUMN_NAMES,\n",
+ " time_series_number=2,\n",
+ " freq=FREQUENCY,\n",
+ ")\n",
+ "X_train[LABEL_COLUMN_NAME] = y_train"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Let's see what the training data looks like."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "X_train.tail()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Prepare remote compute and data. \n",
+ "The [Machine Learning service workspace](https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-workspace), is paired with the storage account, which contains the default data store. We will use it to upload the artificial data and create [tabular dataset](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.tabulardataset?view=azure-ml-py) for training. A tabular dataset defines a series of lazily-evaluated, immutable operations to load data from the data source into tabular representation."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from azureml.data.dataset_factory import TabularDatasetFactory\n",
+ "\n",
+ "ds = ws.get_default_datastore()\n",
+ "# Upload saved data to the default data store.\n",
+ "train_data = TabularDatasetFactory.register_pandas_dataframe(\n",
+ " X_train, target=(ds, \"data\"), name=\"data_backtest\"\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "You will need to create a compute target for backtesting. In this [tutorial](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-set-up-training-targets#amlcompute), you create AmlCompute as your training compute resource.\n",
+ "\n",
+ "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from azureml.core.compute import ComputeTarget, AmlCompute\n",
+ "from azureml.core.compute_target import ComputeTargetException\n",
+ "\n",
+ "# Choose a name for your CPU cluster\n",
+ "amlcompute_cluster_name = \"backtest-cluster\"\n",
+ "\n",
+ "# Verify that cluster does not exist already\n",
+ "try:\n",
+ " compute_target = ComputeTarget(workspace=ws, name=amlcompute_cluster_name)\n",
+ " print(\"Found existing cluster, use it.\")\n",
+ "except ComputeTargetException:\n",
+ " compute_config = AmlCompute.provisioning_configuration(\n",
+ " vm_size=\"STANDARD_DS12_V2\", max_nodes=6\n",
+ " )\n",
+ " compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, compute_config)\n",
+ "\n",
+ "compute_target.wait_for_completion(show_output=True)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Create the configuration for AutoML backtesting \n",
+ "\n",
+ "This dictionary defines the AutoML and many models settings. For this forecasting task we need to define several settings including the name of the time column, the maximum forecast horizon, and the partition column name definition.\n",
+ "\n",
+ "| Property | Description|\n",
+ "| :--------------- | :------------------- |\n",
+ "| **task** | forecasting |\n",
+ "| **primary_metric** | This is the metric that you want to optimize.
Forecasting supports the following primary metrics
normalized_root_mean_squared_error
normalized_mean_absolute_error |\n",
+ "| **iteration_timeout_minutes** | Maximum amount of time in minutes that the model can train. This is optional but provides customers with greater control on exit criteria. |\n",
+ "| **iterations** | Number of models to train. This is optional but provides customers with greater control on exit criteria. |\n",
+ "| **experiment_timeout_hours** | Maximum amount of time in hours that the experiment can take before it terminates. This is optional but provides customers with greater control on exit criteria. |\n",
+ "| **label_column_name** | The name of the label column. |\n",
+ "| **max_horizon** | The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly). Periods are inferred from your data. |\n",
+ "| **n_cross_validations** | Number of cross validation splits. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
+ "| **time_column_name** | The name of your time column. |\n",
+ "| **grain_column_names** | The column names used to uniquely identify timeseries in data that has multiple rows with the same timestamp. |"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "automl_settings = {\n",
+ " \"task\": \"forecasting\",\n",
+ " \"primary_metric\": \"normalized_root_mean_squared_error\",\n",
+ " \"iteration_timeout_minutes\": 10, # This needs to be changed based on the dataset. We ask customer to explore how long training is taking before settings this value\n",
+ " \"iterations\": 15,\n",
+ " \"experiment_timeout_hours\": 1, # This also needs to be changed based on the dataset. For larger data set this number needs to be bigger.\n",
+ " \"label_column_name\": LABEL_COLUMN_NAME,\n",
+ " \"n_cross_validations\": 3,\n",
+ " \"time_column_name\": TIME_COLUMN_NAME,\n",
+ " \"max_horizon\": FORECAST_HORIZON,\n",
+ " \"track_child_runs\": False,\n",
+ " \"grain_column_names\": TIME_SERIES_ID_COLUMN_NAMES,\n",
+ "}"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Backtest AutoML \n",
+ "First we set backtesting parameters: we will step back by 30 days and will make 5 such steps; for each step we will forecast for next two weeks."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# The number of periods to step back on each backtest iteration.\n",
+ "BACKTESTING_PERIOD = 30\n",
+ "# The number of times we will back test the model.\n",
+ "NUMBER_OF_BACKTESTS = 5"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "To train AutoML on backtesting folds we will use the [Azure Machine Learning pipeline](https://docs.microsoft.com/en-us/azure/machine-learning/concept-ml-pipelines). It will generate backtest folds, then train model for each of them and calculate the accuracy metrics. To run pipeline, you also need to create an Experiment. An Experiment corresponds to a prediction problem you are trying to solve (here, it is a forecasting), while a Run corresponds to a specific approach to the problem."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from uuid import uuid1\n",
+ "\n",
+ "from pipeline_helper import get_backtest_pipeline\n",
+ "\n",
+ "pipeline_exp = Experiment(ws, \"automl-backtesting\")\n",
+ "\n",
+ "# We will create the unique identifier to mark our models.\n",
+ "model_uid = str(uuid1())\n",
+ "\n",
+ "pipeline = get_backtest_pipeline(\n",
+ " experiment=pipeline_exp,\n",
+ " dataset=train_data,\n",
+ " # The STANDARD_DS12_V2 has 4 vCPU per node, we will set 2 process per node to be safe.\n",
+ " process_per_node=2,\n",
+ " # The maximum number of nodes for our compute is 6.\n",
+ " node_count=6,\n",
+ " compute_target=compute_target,\n",
+ " automl_settings=automl_settings,\n",
+ " step_size=BACKTESTING_PERIOD,\n",
+ " step_number=NUMBER_OF_BACKTESTS,\n",
+ " model_uid=model_uid,\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Run the pipeline and wait for results."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "pipeline_run = pipeline_exp.submit(pipeline)\n",
+ "pipeline_run.wait_for_completion(show_output=False)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "After the run is complete, we can download the results. "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "metrics_output = pipeline_run.get_pipeline_output(\"results\")\n",
+ "metrics_output.download(\"backtest_metrics\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## View metrics\n",
+ "To distinguish these metrics from the model backtest, which we will obtain in the next section, we will move the directory with metrics out of the backtest_metrics and will remove the parent folder. We will create the utility function for that."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def copy_scoring_directory(new_name):\n",
+ " scores_path = os.path.join(\"backtest_metrics\", \"azureml\")\n",
+ " directory_list = [os.path.join(scores_path, d) for d in os.listdir(scores_path)]\n",
+ " latest_file = max(directory_list, key=os.path.getctime)\n",
+ " print(\n",
+ " f\"The output directory {latest_file} was created on {pd.Timestamp(os.path.getctime(latest_file), unit='s')} GMT.\"\n",
+ " )\n",
+ " shutil.move(os.path.join(latest_file, \"results\"), new_name)\n",
+ " shutil.rmtree(\"backtest_metrics\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Move the directory and list its contents."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "copy_scoring_directory(\"automl_backtest\")\n",
+ "pd.DataFrame({\"File\": os.listdir(\"automl_backtest\")})"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "The directory contains a set of files with results:\n",
+ "- forecast.csv contains forecasts for all backtest iterations. The backtest_iteration column contains iteration identifier with the last training date as a suffix\n",
+ "- scores.csv contains all metrics. If data set contains several time series, the metrics are given for all combinations of time series id and iterations, as well as scores for all iterations and time series id are marked as \"all_sets\"\n",
+ "- plots_fcst_vs_actual.pdf contains the predictions vs forecast plots for each iteration and time series.\n",
+ "\n",
+ "For demonstration purposes we will display the table of metrics for one of the time series with ID \"ts0\". Again, we will create the utility function, which will be re used in model backtesting."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def get_metrics_for_ts(all_metrics, ts):\n",
+ " \"\"\"\n",
+ " Get the metrics for the time series with ID ts and return it as pandas data frame.\n",
+ "\n",
+ " :param all_metrics: The table with all the metrics.\n",
+ " :param ts: The ID of a time series of interest.\n",
+ " :return: The pandas DataFrame with metrics for one time series.\n",
+ " \"\"\"\n",
+ " results_df = None\n",
+ " for ts_id, one_series in all_metrics.groupby(\"time_series_id\"):\n",
+ " if not ts_id.startswith(ts):\n",
+ " continue\n",
+ " iteration = ts_id.split(\"|\")[-1]\n",
+ " df = one_series[[\"metric_name\", \"metric\"]]\n",
+ " df.rename({\"metric\": iteration}, axis=1, inplace=True)\n",
+ " df.set_index(\"metric_name\", inplace=True)\n",
+ " if results_df is None:\n",
+ " results_df = df\n",
+ " else:\n",
+ " results_df = results_df.merge(\n",
+ " df, how=\"inner\", left_index=True, right_index=True\n",
+ " )\n",
+ " results_df.sort_index(axis=1, inplace=True)\n",
+ " return results_df\n",
+ "\n",
+ "\n",
+ "metrics_df = pd.read_csv(os.path.join(\"automl_backtest\", \"scores.csv\"))\n",
+ "ts_id = \"ts0\"\n",
+ "get_metrics_for_ts(metrics_df, ts_id)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Forecast vs actuals plots."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from IPython.display import IFrame\n",
+ "\n",
+ "IFrame(\"./automl_backtest/plots_fcst_vs_actual.pdf\", width=800, height=300)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Backtest the best model \n",
+ "\n",
+ "For model backtesting we will use the same parameters we used to backtest AutoML. All the models, we have obtained in the previous run were registered in our workspace. To identify the model, each was assigned a tag with the last trainig date."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "model_list = Model.list(ws, tags={\"experiment\": \"automl-backtesting\"})\n",
+ "model_data = {\"name\": [], \"last_training_date\": []}\n",
+ "for model in model_list:\n",
+ " if (\n",
+ " \"last_training_date\" not in model.tags\n",
+ " or \"model_uid\" not in model.tags\n",
+ " or model.tags[\"model_uid\"] != model_uid\n",
+ " ):\n",
+ " continue\n",
+ " model_data[\"name\"].append(model.name)\n",
+ " model_data[\"last_training_date\"].append(\n",
+ " pd.Timestamp(model.tags[\"last_training_date\"])\n",
+ " )\n",
+ "df_models = pd.DataFrame(model_data)\n",
+ "df_models.sort_values([\"last_training_date\"], inplace=True)\n",
+ "df_models.reset_index(inplace=True, drop=True)\n",
+ "df_models"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "We will backtest the model trained on the most recet data."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "model_name = df_models[\"name\"].iloc[-1]\n",
+ "model_name"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Retrain the models.\n",
+ "Assemble the pipeline, which will retrain the best model from AutoML run on historical data."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "pipeline_exp = Experiment(ws, \"model-backtesting\")\n",
+ "\n",
+ "pipeline = get_backtest_pipeline(\n",
+ " experiment=pipeline_exp,\n",
+ " dataset=train_data,\n",
+ " # The STANDARD_DS12_V2 has 4 vCPU per node, we will set 2 process per node to be safe.\n",
+ " process_per_node=2,\n",
+ " # The maximum number of nodes for our compute is 6.\n",
+ " node_count=6,\n",
+ " compute_target=compute_target,\n",
+ " automl_settings=automl_settings,\n",
+ " step_size=BACKTESTING_PERIOD,\n",
+ " step_number=NUMBER_OF_BACKTESTS,\n",
+ " model_name=model_name,\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Launch the backtesting pipeline."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "pipeline_run = pipeline_exp.submit(pipeline)\n",
+ "pipeline_run.wait_for_completion(show_output=False)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "The metrics are stored in the pipeline output named \"score\". The next code will download the table with metrics."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "metrics_output = pipeline_run.get_pipeline_output(\"results\")\n",
+ "metrics_output.download(\"backtest_metrics\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Again, we will copy the data files from the downloaded directory, but in this case we will call the folder \"model_backtest\"; it will contain the same files as the one for AutoML backtesting."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "copy_scoring_directory(\"model_backtest\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Finally, we will display the metrics."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "model_metrics_df = pd.read_csv(os.path.join(\"model_backtest\", \"scores.csv\"))\n",
+ "get_metrics_for_ts(model_metrics_df, ts_id)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Forecast vs actuals plots."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from IPython.display import IFrame\n",
+ "\n",
+ "IFrame(\"./model_backtest/plots_fcst_vs_actual.pdf\", width=800, height=300)"
+ ]
+ }
+ ],
+ "metadata": {
+ "authors": [
+ {
+ "name": "jialiu"
+ }
+ ],
+ "category": "tutorial",
+ "compute": [
+ "Remote"
+ ],
+ "datasets": [
+ "None"
+ ],
+ "deployment": [
+ "None"
+ ],
+ "exclude_from_index": false,
+ "framework": [
+ "Azure ML AutoML"
+ ],
+ "kernelspec": {
+ "display_name": "Python 3.6",
+ "language": "python",
+ "name": "python36"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.6.9"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
\ No newline at end of file
diff --git a/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/auto-ml-forecasting-backtest-single-model.yml b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/auto-ml-forecasting-backtest-single-model.yml
new file mode 100644
index 000000000..6871fafb4
--- /dev/null
+++ b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/auto-ml-forecasting-backtest-single-model.yml
@@ -0,0 +1,4 @@
+name: auto-ml-forecasting-backtest-single-model
+dependencies:
+- pip:
+ - azureml-sdk
diff --git a/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/pipeline_helper.py b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/pipeline_helper.py
new file mode 100644
index 000000000..c00793437
--- /dev/null
+++ b/how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/pipeline_helper.py
@@ -0,0 +1,166 @@
+from typing import Any, Dict, Optional
+
+import os
+
+import azureml.train.automl.runtime._hts.hts_runtime_utilities as hru
+
+from azureml._restclient.jasmine_client import JasmineClient
+from azureml.contrib.automl.pipeline.steps import utilities
+from azureml.core import RunConfiguration
+from azureml.core.compute import ComputeTarget
+from azureml.core.experiment import Experiment
+from azureml.data import LinkTabularOutputDatasetConfig, TabularDataset
+from azureml.pipeline.core import Pipeline, PipelineData, PipelineParameter
+from azureml.pipeline.steps import ParallelRunConfig, ParallelRunStep, PythonScriptStep
+from azureml.train.automl.constants import Scenarios
+from azureml.data.dataset_consumption_config import DatasetConsumptionConfig
+
+
+PROJECT_FOLDER = "assets"
+SETTINGS_FILE = "automl_settings.json"
+
+
+def get_backtest_pipeline(
+ experiment: Experiment,
+ dataset: TabularDataset,
+ process_per_node: int,
+ node_count: int,
+ compute_target: ComputeTarget,
+ automl_settings: Dict[str, Any],
+ step_size: int,
+ step_number: int,
+ model_name: Optional[str] = None,
+ model_uid: Optional[str] = None,
+) -> Pipeline:
+ """
+ :param experiment: The experiment used to run the pipeline.
+ :param dataset: Tabular data set to be used for model training.
+ :param process_per_node: The number of processes per node. Generally it should be the number of cores
+ on the node divided by two.
+ :param node_count: The number of nodes to be used.
+ :param compute_target: The compute target to be used to run the pipeline.
+ :param model_name: The name of a model to be back tested.
+ :param automl_settings: The dictionary with automl settings.
+ :param step_size: The number of periods to step back in backtesting.
+ :param step_number: The number of backtesting iterations.
+ :param model_uid: The uid to mark models from this run of the experiment.
+ :return: The pipeline to be used for model retraining.
+ **Note:** The output will be uploaded in the pipeline output
+ called 'score'.
+ """
+ jasmine_client = JasmineClient(
+ service_context=experiment.workspace.service_context,
+ experiment_name=experiment.name,
+ experiment_id=experiment.id,
+ )
+ env = jasmine_client.get_curated_environment(
+ scenario=Scenarios.AUTOML,
+ enable_dnn=False,
+ enable_gpu=False,
+ compute=compute_target,
+ compute_sku=experiment.workspace.compute_targets.get(
+ compute_target.name
+ ).vm_size,
+ )
+ data_results = PipelineData(
+ name="results", datastore=None, pipeline_output_name="results"
+ )
+ ############################################################
+ # Split the data set using python script.
+ ############################################################
+ run_config = RunConfiguration()
+ run_config.docker.use_docker = True
+ run_config.environment = env
+
+ split_data = PipelineData(name="split_data_output", datastore=None).as_dataset()
+ split_step = PythonScriptStep(
+ name="split_data_for_backtest",
+ script_name="data_split.py",
+ inputs=[dataset.as_named_input("training_data")],
+ outputs=[split_data],
+ source_directory=PROJECT_FOLDER,
+ arguments=[
+ "--step-size",
+ step_size,
+ "--step-number",
+ step_number,
+ "--time-column-name",
+ automl_settings.get("time_column_name"),
+ "--time-series-id-column-names",
+ automl_settings.get("grain_column_names"),
+ "--output-dir",
+ split_data,
+ ],
+ runconfig=run_config,
+ compute_target=compute_target,
+ allow_reuse=False,
+ )
+ ############################################################
+ # We will do the backtest the parallel run step.
+ ############################################################
+ settings_path = os.path.join(PROJECT_FOLDER, SETTINGS_FILE)
+ hru.dump_object_to_json(automl_settings, settings_path)
+ mini_batch_size = PipelineParameter(name="batch_size_param", default_value=str(1))
+ back_test_config = ParallelRunConfig(
+ source_directory=PROJECT_FOLDER,
+ entry_script="retrain_models.py",
+ mini_batch_size=mini_batch_size,
+ error_threshold=-1,
+ output_action="append_row",
+ append_row_file_name="outputs.txt",
+ compute_target=compute_target,
+ environment=env,
+ process_count_per_node=process_per_node,
+ run_invocation_timeout=3600,
+ node_count=node_count,
+ )
+ forecasts = PipelineData(name="forecasts", datastore=None)
+ if model_name:
+ parallel_step_name = "{}-backtest".format(model_name.replace("_", "-"))
+ else:
+ parallel_step_name = "AutoML-backtest"
+
+ prs_args = [
+ "--target_column_name",
+ automl_settings.get("label_column_name"),
+ "--output-dir",
+ forecasts,
+ ]
+ if model_name is not None:
+ prs_args.append("--model-name")
+ prs_args.append(model_name)
+ if model_uid is not None:
+ prs_args.append("--model-uid")
+ prs_args.append(model_uid)
+ backtest_prs = ParallelRunStep(
+ name=parallel_step_name,
+ parallel_run_config=back_test_config,
+ arguments=prs_args,
+ inputs=[split_data],
+ output=forecasts,
+ allow_reuse=False,
+ )
+ ############################################################
+ # Then we collect the output and return it as scores output.
+ ############################################################
+ collection_step = PythonScriptStep(
+ name="score",
+ script_name="score.py",
+ inputs=[forecasts.as_mount()],
+ outputs=[data_results],
+ source_directory=PROJECT_FOLDER,
+ arguments=[
+ "--forecasts",
+ forecasts,
+ "--output-dir",
+ data_results,
+ ],
+ runconfig=run_config,
+ compute_target=compute_target,
+ allow_reuse=False,
+ )
+ # Build and return the pipeline.
+ return Pipeline(
+ workspace=experiment.workspace,
+ steps=[split_step, backtest_prs, collection_step],
+ )
diff --git a/how-to-use-azureml/automated-machine-learning/forecasting-beer-remote/auto-ml-forecasting-beer-remote.ipynb b/how-to-use-azureml/automated-machine-learning/forecasting-beer-remote/auto-ml-forecasting-beer-remote.ipynb
index 9c0446979..cc7ae9dc7 100644
--- a/how-to-use-azureml/automated-machine-learning/forecasting-beer-remote/auto-ml-forecasting-beer-remote.ipynb
+++ b/how-to-use-azureml/automated-machine-learning/forecasting-beer-remote/auto-ml-forecasting-beer-remote.ipynb
@@ -113,7 +113,7 @@
"metadata": {},
"outputs": [],
"source": [
- "print(\"This notebook was created using version 1.36.0 of the Azure ML SDK\")\n",
+ "print(\"This notebook was created using version 1.37.0 of the Azure ML SDK\")\n",
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
]
},
diff --git a/how-to-use-azureml/automated-machine-learning/forecasting-bike-share/auto-ml-forecasting-bike-share.ipynb b/how-to-use-azureml/automated-machine-learning/forecasting-bike-share/auto-ml-forecasting-bike-share.ipynb
index 6142b4cce..a8ac43591 100644
--- a/how-to-use-azureml/automated-machine-learning/forecasting-bike-share/auto-ml-forecasting-bike-share.ipynb
+++ b/how-to-use-azureml/automated-machine-learning/forecasting-bike-share/auto-ml-forecasting-bike-share.ipynb
@@ -88,7 +88,7 @@
"metadata": {},
"outputs": [],
"source": [
- "print(\"This notebook was created using version 1.36.0 of the Azure ML SDK\")\n",
+ "print(\"This notebook was created using version 1.37.0 of the Azure ML SDK\")\n",
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
]
},
diff --git a/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand/auto-ml-forecasting-energy-demand.ipynb b/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand/auto-ml-forecasting-energy-demand.ipynb
index f9b462453..a36d116bf 100644
--- a/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand/auto-ml-forecasting-energy-demand.ipynb
+++ b/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand/auto-ml-forecasting-energy-demand.ipynb
@@ -99,7 +99,7 @@
"metadata": {},
"outputs": [],
"source": [
- "print(\"This notebook was created using version 1.36.0 of the Azure ML SDK\")\n",
+ "print(\"This notebook was created using version 1.37.0 of the Azure ML SDK\")\n",
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
]
},
diff --git a/how-to-use-azureml/automated-machine-learning/forecasting-forecast-function/auto-ml-forecasting-function.ipynb b/how-to-use-azureml/automated-machine-learning/forecasting-forecast-function/auto-ml-forecasting-function.ipynb
index ab57b31a3..d3e02e011 100644
--- a/how-to-use-azureml/automated-machine-learning/forecasting-forecast-function/auto-ml-forecasting-function.ipynb
+++ b/how-to-use-azureml/automated-machine-learning/forecasting-forecast-function/auto-ml-forecasting-function.ipynb
@@ -94,7 +94,7 @@
"metadata": {},
"outputs": [],
"source": [
- "print(\"This notebook was created using version 1.36.0 of the Azure ML SDK\")\n",
+ "print(\"This notebook was created using version 1.37.0 of the Azure ML SDK\")\n",
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
]
},
diff --git a/how-to-use-azureml/automated-machine-learning/forecasting-hierarchical-timeseries/auto-ml-forecasting-hierarchical-timeseries.ipynb b/how-to-use-azureml/automated-machine-learning/forecasting-hierarchical-timeseries/auto-ml-forecasting-hierarchical-timeseries.ipynb
index 7a01a1014..e2ab133f9 100644
--- a/how-to-use-azureml/automated-machine-learning/forecasting-hierarchical-timeseries/auto-ml-forecasting-hierarchical-timeseries.ipynb
+++ b/how-to-use-azureml/automated-machine-learning/forecasting-hierarchical-timeseries/auto-ml-forecasting-hierarchical-timeseries.ipynb
@@ -150,37 +150,13 @@
"datastore"
]
},
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "gather": {
- "logged": 1613005886349
- },
- "jupyter": {
- "outputs_hidden": false,
- "source_hidden": false
- },
- "nteract": {
- "transient": {
- "deleting": false
- }
- }
- },
- "outputs": [],
- "source": [
- "datastore.upload(\n",
- " src_dir=\"./Data/\", target_path=datastore_path, overwrite=True, show_progress=True\n",
- ")"
- ]
- },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create the TabularDatasets \n",
"\n",
- "Datasets in Azure Machine Learning are references to specific data in a Datastore. The data can be retrieved as a [TabularDatasets](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.tabulardataset?view=azure-ml-py)."
+ "Datasets in Azure Machine Learning are references to specific data in a Datastore. The data can be retrieved as a [TabularDatasets](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.tabulardataset?view=azure-ml-py). We will read in the data as a pandas DataFrame, upload to the data store and register them to your Workspace using ```register_pandas_dataframe``` so they can be called as an input into the training pipeline. We will use the inference dataset as part of the forecasting pipeline. The step need only be completed once."
]
},
{
@@ -193,34 +169,20 @@
},
"outputs": [],
"source": [
- "from azureml.core.dataset import Dataset\n",
+ "from azureml.data.dataset_factory import TabularDatasetFactory\n",
"\n",
- "train_ds = Dataset.Tabular.from_delimited_files(\n",
- " path=datastore.path(\"hts-sample/hts-sample-train.csv\"), validate=False\n",
+ "registered_train = TabularDatasetFactory.register_pandas_dataframe(\n",
+ " pd.read_csv(\"Data/hts-sample-train.csv\"),\n",
+ " target=(datastore, \"hts-sample\"),\n",
+ " name=\"hts-sales-train\",\n",
")\n",
- "inference_ds = Dataset.Tabular.from_delimited_files(\n",
- " path=datastore.path(\"hts-sample/hts-sample-test.csv\"), validate=False\n",
+ "registered_inference = TabularDatasetFactory.register_pandas_dataframe(\n",
+ " pd.read_csv(\"Data/hts-sample-test.csv\"),\n",
+ " target=(datastore, \"hts-sample\"),\n",
+ " name=\"hts-sales-test\",\n",
")"
]
},
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Register the TabularDatasets to the Workspace \n",
- "Finally, register the dataset to your Workspace so it can be called as an input into the training pipeline in the next notebook. We will use the inference dataset as part of the forecasting pipeline. The step need only be completed once."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "registered_train = train_ds.register(ws, \"hts-sales-train\")\n",
- "registered_inference = inference_ds.register(ws, \"hts-sales-test\")"
- ]
- },
{
"cell_type": "markdown",
"metadata": {},
diff --git a/how-to-use-azureml/automated-machine-learning/forecasting-many-models/auto-ml-forecasting-many-models.ipynb b/how-to-use-azureml/automated-machine-learning/forecasting-many-models/auto-ml-forecasting-many-models.ipynb
index cea964435..75caf8596 100644
--- a/how-to-use-azureml/automated-machine-learning/forecasting-many-models/auto-ml-forecasting-many-models.ipynb
+++ b/how-to-use-azureml/automated-machine-learning/forecasting-many-models/auto-ml-forecasting-many-models.ipynb
@@ -30,7 +30,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "For this notebook we are using a synthetic dataset portraying sales data to predict the the quantity of a vartiety of product skus across several states, stores, and product categories.\n",
+ "For this notebook we are using a synthetic dataset portraying sales data to predict the quantity of a vartiety of product SKUs across several states, stores, and product categories.\n",
"\n",
"**NOTE: There are limits on how many runs we can do in parallel per workspace, and we currently recommend to set the parallelism to maximum of 320 runs per experiment per workspace. If users want to have more parallelism and increase this limit they might encounter Too Many Requests errors (HTTP 429).**"
]
@@ -308,7 +308,7 @@
"source": [
"### Set up training parameters\n",
"\n",
- "This dictionary defines the AutoML and many models settings. For this forecasting task we need to define several settings inncluding the name of the time column, the maximum forecast horizon, and the partition column name definition.\n",
+ "This dictionary defines the AutoML and many models settings. For this forecasting task we need to define several settings including the name of the time column, the maximum forecast horizon, and the partition column name definition.\n",
"\n",
"| Property | Description|\n",
"| :--------------- | :------------------- |\n",
@@ -554,12 +554,12 @@
"| :--------------- | :------------------- |\n",
"| **experiment** | The experiment used for inference run. |\n",
"| **inference_data** | The data to use for inferencing. It should be the same schema as used for training.\n",
- "| **compute_target** The compute target that runs the inference pipeline.|\n",
+ "| **compute_target** | The compute target that runs the inference pipeline.|\n",
"| **node_count** | The number of compute nodes to be used for running the user script. We recommend to start with the number of cores per node (varies by compute sku). |\n",
- "| **process_count_per_node** The number of processes per node.\n",
- "| **train_run_id** | \\[Optional] The run id of the hierarchy training, by default it is the latest successful training many model run in the experiment. |\n",
- "| **train_experiment_name** | \\[Optional] The train experiment that contains the train pipeline. This one is only needed when the train pipeline is not in the same experiement as the inference pipeline. |\n",
- "| **process_count_per_node** | \\[Optional] The number of processes per node, by default it's 4. |"
+ "| **process_count_per_node** | The number of processes per node.\n",
+ "| **train_run_id** | \\[Optional\\] The run id of the hierarchy training, by default it is the latest successful training many model run in the experiment. |\n",
+ "| **train_experiment_name** | \\[Optional\\] The train experiment that contains the train pipeline. This one is only needed when the train pipeline is not in the same experiement as the inference pipeline. |\n",
+ "| **process_count_per_node** | \\[Optional\\] The number of processes per node, by default it's 4. |"
]
},
{
diff --git a/how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales/auto-ml-forecasting-orange-juice-sales.ipynb b/how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales/auto-ml-forecasting-orange-juice-sales.ipynb
index f9bd63862..05e6f27ba 100644
--- a/how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales/auto-ml-forecasting-orange-juice-sales.ipynb
+++ b/how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales/auto-ml-forecasting-orange-juice-sales.ipynb
@@ -81,7 +81,7 @@
"metadata": {},
"outputs": [],
"source": [
- "print(\"This notebook was created using version 1.36.0 of the Azure ML SDK\")\n",
+ "print(\"This notebook was created using version 1.37.0 of the Azure ML SDK\")\n",
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
]
},
@@ -262,22 +262,14 @@
"metadata": {},
"outputs": [],
"source": [
- "train.to_csv(r\"./dominicks_OJ_train.csv\", index=None, header=True)\n",
- "test.to_csv(r\"./dominicks_OJ_test.csv\", index=None, header=True)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
+ "from azureml.data.dataset_factory import TabularDatasetFactory\n",
+ "\n",
"datastore = ws.get_default_datastore()\n",
- "datastore.upload_files(\n",
- " files=[\"./dominicks_OJ_train.csv\", \"./dominicks_OJ_test.csv\"],\n",
- " target_path=\"dataset/\",\n",
- " overwrite=True,\n",
- " show_progress=True,\n",
+ "train_dataset = TabularDatasetFactory.register_pandas_dataframe(\n",
+ " train, target=(datastore, \"dataset/\"), name=\"dominicks_OJ_train\"\n",
+ ")\n",
+ "test_dataset = TabularDatasetFactory.register_pandas_dataframe(\n",
+ " test, target=(datastore, \"dataset/\"), name=\"dominicks_OJ_test\"\n",
")"
]
},
@@ -288,22 +280,6 @@
"### Create dataset for training"
]
},
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "from azureml.core.dataset import Dataset\n",
- "\n",
- "train_dataset = Dataset.Tabular.from_delimited_files(\n",
- " path=datastore.path(\"dataset/dominicks_OJ_train.csv\")\n",
- ")\n",
- "test_dataset = Dataset.Tabular.from_delimited_files(\n",
- " path=datastore.path(\"dataset/dominicks_OJ_test.csv\")\n",
- ")"
- ]
- },
{
"cell_type": "code",
"execution_count": null,
diff --git a/how-to-use-azureml/automated-machine-learning/local-run-classification-credit-card-fraud/auto-ml-classification-credit-card-fraud-local.ipynb b/how-to-use-azureml/automated-machine-learning/local-run-classification-credit-card-fraud/auto-ml-classification-credit-card-fraud-local.ipynb
index e89800f18..7e25a8dba 100644
--- a/how-to-use-azureml/automated-machine-learning/local-run-classification-credit-card-fraud/auto-ml-classification-credit-card-fraud-local.ipynb
+++ b/how-to-use-azureml/automated-machine-learning/local-run-classification-credit-card-fraud/auto-ml-classification-credit-card-fraud-local.ipynb
@@ -96,7 +96,7 @@
"metadata": {},
"outputs": [],
"source": [
- "print(\"This notebook was created using version 1.36.0 of the Azure ML SDK\")\n",
+ "print(\"This notebook was created using version 1.37.0 of the Azure ML SDK\")\n",
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
]
},
diff --git a/how-to-use-azureml/automated-machine-learning/regression-explanation-featurization/auto-ml-regression-explanation-featurization.ipynb b/how-to-use-azureml/automated-machine-learning/regression-explanation-featurization/auto-ml-regression-explanation-featurization.ipynb
index 8905fff4e..1d42f9563 100644
--- a/how-to-use-azureml/automated-machine-learning/regression-explanation-featurization/auto-ml-regression-explanation-featurization.ipynb
+++ b/how-to-use-azureml/automated-machine-learning/regression-explanation-featurization/auto-ml-regression-explanation-featurization.ipynb
@@ -68,6 +68,7 @@
"metadata": {},
"outputs": [],
"source": [
+ "import json\n",
"import logging\n",
"\n",
"from matplotlib import pyplot as plt\n",
@@ -95,7 +96,7 @@
"metadata": {},
"outputs": [],
"source": [
- "print(\"This notebook was created using version 1.36.0 of the Azure ML SDK\")\n",
+ "print(\"This notebook was created using version 1.37.0 of the Azure ML SDK\")\n",
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
]
},
@@ -339,16 +340,8 @@
"metadata": {},
"outputs": [],
"source": [
- "best_run, fitted_model = remote_run.get_output()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "best_run_customized, fitted_model_customized = remote_run.get_output()"
+ "# Retrieve the best Run object\n",
+ "best_run = remote_run.get_best_child()"
]
},
{
@@ -357,32 +350,7 @@
"source": [
"## Transparency\n",
"\n",
- "View updated featurization summary"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "custom_featurizer = fitted_model_customized.named_steps['datatransformer']"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "custom_featurizer.get_featurization_summary()"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "is_user_friendly=False allows for more detailed summary for transforms being applied"
+ "View featurization summary for the best model - to study how different features were transformed. This is stored as a JSON file in the outputs directory for the run."
]
},
{
@@ -391,16 +359,14 @@
"metadata": {},
"outputs": [],
"source": [
- "custom_featurizer.get_featurization_summary(is_user_friendly=False)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "custom_featurizer.get_stats_feature_type_summary()"
+ "# Download the featuurization summary JSON file locally\n",
+ "best_run.download_file(\"outputs/featurization_summary.json\", \"featurization_summary.json\")\n",
+ "\n",
+ "# Render the JSON as a pandas DataFrame\n",
+ "with open(\"featurization_summary.json\", \"r\") as f:\n",
+ " records = json.load(f)\n",
+ "\n",
+ "pd.DataFrame.from_records(records)"
]
},
{
diff --git a/how-to-use-azureml/automated-machine-learning/regression/auto-ml-regression.ipynb b/how-to-use-azureml/automated-machine-learning/regression/auto-ml-regression.ipynb
index 6f4d9fd10..d5c8bdd8e 100644
--- a/how-to-use-azureml/automated-machine-learning/regression/auto-ml-regression.ipynb
+++ b/how-to-use-azureml/automated-machine-learning/regression/auto-ml-regression.ipynb
@@ -92,7 +92,7 @@
"metadata": {},
"outputs": [],
"source": [
- "print(\"This notebook was created using version 1.36.0 of the Azure ML SDK\")\n",
+ "print(\"This notebook was created using version 1.37.0 of the Azure ML SDK\")\n",
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
]
},
diff --git a/how-to-use-azureml/explain-model/azure-integration/gpu-explanation/train-explain-model-gpu-tree-explainer.ipynb b/how-to-use-azureml/explain-model/azure-integration/gpu-explanation/train-explain-model-gpu-tree-explainer.ipynb
index 08bcd2c36..1530750f9 100644
--- a/how-to-use-azureml/explain-model/azure-integration/gpu-explanation/train-explain-model-gpu-tree-explainer.ipynb
+++ b/how-to-use-azureml/explain-model/azure-integration/gpu-explanation/train-explain-model-gpu-tree-explainer.ipynb
@@ -106,7 +106,7 @@
"metadata": {},
"outputs": [],
"source": [
- "print(\"This notebook was created using version 1.36.0 of the Azure ML SDK\")\n",
+ "print(\"This notebook was created using version 1.37.0 of the Azure ML SDK\")\n",
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
]
},
diff --git a/how-to-use-azureml/explain-model/azure-integration/remote-explanation/explain-model-on-amlcompute.yml b/how-to-use-azureml/explain-model/azure-integration/remote-explanation/explain-model-on-amlcompute.yml
index e297cb38a..416737ad2 100644
--- a/how-to-use-azureml/explain-model/azure-integration/remote-explanation/explain-model-on-amlcompute.yml
+++ b/how-to-use-azureml/explain-model/azure-integration/remote-explanation/explain-model-on-amlcompute.yml
@@ -11,4 +11,4 @@ dependencies:
- matplotlib
- azureml-dataset-runtime
- ipywidgets
- - raiwidgets~=0.10.0
+ - raiwidgets~=0.15.0
diff --git a/how-to-use-azureml/explain-model/azure-integration/run-history/save-retrieve-explanations-run-history.yml b/how-to-use-azureml/explain-model/azure-integration/run-history/save-retrieve-explanations-run-history.yml
index 5eefd9365..8dcb8cc9e 100644
--- a/how-to-use-azureml/explain-model/azure-integration/run-history/save-retrieve-explanations-run-history.yml
+++ b/how-to-use-azureml/explain-model/azure-integration/run-history/save-retrieve-explanations-run-history.yml
@@ -10,4 +10,4 @@ dependencies:
- ipython
- matplotlib
- ipywidgets
- - raiwidgets~=0.10.0
+ - raiwidgets~=0.15.0
diff --git a/how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-locally-and-deploy.ipynb b/how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-locally-and-deploy.ipynb
index 27c2b0161..4ba86a097 100644
--- a/how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-locally-and-deploy.ipynb
+++ b/how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-locally-and-deploy.ipynb
@@ -324,13 +324,15 @@
"outputs": [],
"source": [
"from azureml.core.conda_dependencies import CondaDependencies \n",
+ "import sys\n",
"\n",
"# azureml-defaults is required to host the model as a web service.\n",
"azureml_pip_packages = [\n",
" 'azureml-defaults', 'azureml-core', 'azureml-telemetry',\n",
" 'azureml-interpret'\n",
"]\n",
- " \n",
+ "\n",
+ "python_version = '{0}.{1}'.format(sys.version_info[0], sys.version_info[1])\n",
"\n",
"# Note: this is to pin the scikit-learn and pandas versions to be same as notebook.\n",
"# In production scenario user would choose their dependencies\n",
@@ -354,7 +356,9 @@
"# the submitted job is run in. Note the remote environment(s) needs to be similar to the local\n",
"# environment, otherwise if a model is trained or deployed in a different environment this can\n",
"# cause errors. Please take extra care when specifying your dependencies in a production environment.\n",
- "myenv = CondaDependencies.create(pip_packages=['pyyaml', sklearn_dep, pandas_dep] + azureml_pip_packages)\n",
+ "myenv = CondaDependencies.create(\n",
+ " python_version=python_version,\n",
+ " pip_packages=['pyyaml', sklearn_dep, pandas_dep] + azureml_pip_packages)\n",
"\n",
"with open(\"myenv.yml\",\"w\") as f:\n",
" f.write(myenv.serialize_to_string())\n",
diff --git a/how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-locally-and-deploy.yml b/how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-locally-and-deploy.yml
index 772ab8f76..85e31e5a4 100644
--- a/how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-locally-and-deploy.yml
+++ b/how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-locally-and-deploy.yml
@@ -10,4 +10,4 @@ dependencies:
- ipython
- matplotlib
- ipywidgets
- - raiwidgets~=0.10.0
+ - raiwidgets~=0.15.0
diff --git a/how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-on-amlcompute-and-deploy.ipynb b/how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-on-amlcompute-and-deploy.ipynb
index da221d1fc..a35a7aba3 100644
--- a/how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-on-amlcompute-and-deploy.ipynb
+++ b/how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-on-amlcompute-and-deploy.ipynb
@@ -251,6 +251,7 @@
"from azureml.core.runconfig import RunConfiguration\n",
"from azureml.core.conda_dependencies import CondaDependencies\n",
"from azureml.core.runconfig import DEFAULT_CPU_IMAGE\n",
+ "import sys\n",
"\n",
"# Create a new runconfig object\n",
"run_config = RunConfiguration()\n",
@@ -268,7 +269,7 @@
" 'azureml-defaults', 'azureml-telemetry', 'azureml-interpret'\n",
"]\n",
" \n",
- "\n",
+ "python_version = '{0}.{1}'.format(sys.version_info[0], sys.version_info[1])\n",
"\n",
"# Note: this is to pin the scikit-learn version to be same as notebook.\n",
"# In production scenario user would choose their dependencies\n",
@@ -293,7 +294,10 @@
"# environment, otherwise if a model is trained or deployed in a different environment this can\n",
"# cause errors. Please take extra care when specifying your dependencies in a production environment.\n",
"azureml_pip_packages.extend(['pyyaml', sklearn_dep, pandas_dep])\n",
- "run_config.environment.python.conda_dependencies = CondaDependencies.create(pip_packages=azureml_pip_packages)\n",
+ "run_config.environment.python.conda_dependencies = CondaDependencies.create(\n",
+ " python_version=python_version,\n",
+ " pip_packages=azureml_pip_packages)\n",
+ "\n",
"# Now submit a run on AmlCompute\n",
"from azureml.core.script_run_config import ScriptRunConfig\n",
"\n",
@@ -453,7 +457,7 @@
"# environment, otherwise if a model is trained or deployed in a different environment this can\n",
"# cause errors. Please take extra care when specifying your dependencies in a production environment.\n",
"azureml_pip_packages.extend(['pyyaml', sklearn_dep, pandas_dep])\n",
- "myenv = CondaDependencies.create(pip_packages=azureml_pip_packages)\n",
+ "myenv = CondaDependencies.create(python_version=python_version, pip_packages=azureml_pip_packages)\n",
"\n",
"with open(\"myenv.yml\",\"w\") as f:\n",
" f.write(myenv.serialize_to_string())\n",
diff --git a/how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-on-amlcompute-and-deploy.yml b/how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-on-amlcompute-and-deploy.yml
index e105d6482..b6672a5e7 100644
--- a/how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-on-amlcompute-and-deploy.yml
+++ b/how-to-use-azureml/explain-model/azure-integration/scoring-time/train-explain-model-on-amlcompute-and-deploy.yml
@@ -12,4 +12,4 @@ dependencies:
- azureml-dataset-runtime
- azureml-core
- ipywidgets
- - raiwidgets~=0.10.0
+ - raiwidgets~=0.15.0
diff --git a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/20news.pkl b/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/20news.pkl
deleted file mode 100644
index 396e01775..000000000
Binary files a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/20news.pkl and /dev/null differ
diff --git a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-getting-started.ipynb b/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-getting-started.ipynb
index 4f3527fd9..63233de15 100644
--- a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-getting-started.ipynb
+++ b/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-getting-started.ipynb
@@ -63,6 +63,8 @@
"outputs": [],
"source": [
"import os\n",
+ "import requests\n",
+ "import tempfile\n",
"import azureml.core\n",
"from azureml.core import Workspace, Experiment, Datastore\n",
"from azureml.widgets import RunDetails\n",
@@ -158,9 +160,14 @@
"metadata": {},
"outputs": [],
"source": [
+ "# download data file from remote\n",
+ "response = requests.get(\"https://dprepdata.blob.core.windows.net/demo/Titanic.csv\")\n",
+ "titanic_file = os.path.join(tempfile.mkdtemp(), \"Titanic.csv\")\n",
+ "with open(titanic_file, \"w\") as f:\n",
+ " f.write(response.content.decode(\"utf-8\"))\n",
"# get_default_datastore() gets the default Azure Blob Store associated with your workspace.\n",
"# Here we are reusing the def_blob_store object we obtained earlier\n",
- "def_blob_store.upload_files([\"./20news.pkl\"], target_path=\"20newsgroups\", overwrite=True)\n",
+ "def_blob_store.upload_files([titanic_file], target_path=\"titanic\", overwrite=True)\n",
"print(\"Upload call completed\")"
]
},
@@ -286,7 +293,7 @@
"- [**AzureBatchStep**](https://docs.microsoft.com/en-us/python/api/azureml-pipeline-steps/azureml.pipeline.steps.azurebatch_step.azurebatchstep?view=azure-ml-py): Creates a step for submitting jobs to Azure Batch\n",
"- [**EstimatorStep**](https://docs.microsoft.com/en-us/python/api/azureml-pipeline-steps/azureml.pipeline.steps.estimator_step.estimatorstep?view=azure-ml-py): Adds a step to run Estimator in a Pipeline.\n",
"- [**MpiStep**](https://docs.microsoft.com/en-us/python/api/azureml-pipeline-steps/azureml.pipeline.steps.mpi_step.mpistep?view=azure-ml-py): Adds a step to run a MPI job in a Pipeline.\n",
- "- [**AutoMLStep**](https://docs.microsoft.com/en-us/python/api/azureml-train-automl/azureml.train.automl.automlstep?view=azure-ml-py): Creates a AutoML step in a Pipeline.\n",
+ "- [**AutoMLStep**](https://docs.microsoft.com/en-us/python/api/azureml-pipeline-steps/azureml.pipeline.steps.automlstep?view=azure-ml-py): Creates a AutoML step in a Pipeline.\n",
"\n",
"The following code will create a PythonScriptStep to be executed in the Azure Machine Learning Compute we created above using train.py, one of the files already made available in the `source_directory`.\n",
"\n",
diff --git a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-publish-and-run-using-rest-endpoint.ipynb b/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-publish-and-run-using-rest-endpoint.ipynb
index 4f8d6996d..816e7f47c 100644
--- a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-publish-and-run-using-rest-endpoint.ipynb
+++ b/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-publish-and-run-using-rest-endpoint.ipynb
@@ -120,8 +120,10 @@
"metadata": {},
"outputs": [],
"source": [
- "# Uploading data to the datastore\n",
- "data_path = def_blob_store.upload_files([\"./20news.pkl\"], target_path=\"20newsgroups\", overwrite=True)"
+ "# Specify a public dataset path\n",
+ "data_path = \"https://dprepdata.blob.core.windows.net/demo/Titanic.csv\"\n",
+ "# Or uploading data to the datastore\n",
+ "# data_path = def_blob_store.upload_files([\"./your_data.pkl\"], target_path=\"your_path\", overwrite=True)"
]
},
{
@@ -400,11 +402,11 @@
"source": [
"try:\n",
" response.raise_for_status()\n",
- "except Exception: \n",
+ "except Exception as ex: \n",
" raise Exception('Received bad response from the endpoint: {}\\n'\n",
" 'Response Code: {}\\n'\n",
" 'Headers: {}\\n'\n",
- " 'Content: {}'.format(rest_endpoint, response.status_code, response.headers, response.content))\n",
+ " 'Content: {}'.format(rest_endpoint1, response.status_code, response.headers, response.content)) from ex\n",
"\n",
"run_id = response.json().get('Id')\n",
"print('Submitted pipeline run: ', run_id)"
diff --git a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-use-databricks-as-compute-target.ipynb b/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-use-databricks-as-compute-target.ipynb
index 40e2147de..60c72fe4f 100644
--- a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-use-databricks-as-compute-target.ipynb
+++ b/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-use-databricks-as-compute-target.ipynb
@@ -875,7 +875,12 @@
"\n",
"def populate_environ():\n",
" parser = argparse.ArgumentParser(description='Process arguments passed to script')\n",
+ "\n",
+ " # The AZUREML_SCRIPT_DIRECTORY_NAME argument will be filled in if the DatabricksStep\n",
+ " # was run using a local source_directory and python_script_name\n",
" parser.add_argument('--AZUREML_SCRIPT_DIRECTORY_NAME')\n",
+ "\n",
+ " # Remaining arguments are filled in for all databricks jobs and can be used to build the run context\n",
" parser.add_argument('--AZUREML_RUN_TOKEN')\n",
" parser.add_argument('--AZUREML_RUN_TOKEN_EXPIRY')\n",
" parser.add_argument('--AZUREML_RUN_ID')\n",
@@ -884,9 +889,10 @@
" parser.add_argument('--AZUREML_ARM_WORKSPACE_NAME')\n",
" parser.add_argument('--AZUREML_ARM_PROJECT_NAME')\n",
" parser.add_argument('--AZUREML_SERVICE_ENDPOINT')\n",
+ " parser.add_argument('--AZUREML_WORKSPACE_ID')\n",
+ " parser.add_argument('--AZUREML_EXPERIMENT_ID')\n",
"\n",
- " args = parser.parse_args()\n",
- " os.environ['AZUREML_SCRIPT_DIRECTORY_NAME'] = args.AZUREML_SCRIPT_DIRECTORY_NAME\n",
+ " (args, extra_args) = parser.parse_known_args()\n",
" os.environ['AZUREML_RUN_TOKEN'] = args.AZUREML_RUN_TOKEN\n",
" os.environ['AZUREML_RUN_TOKEN_EXPIRY'] = args.AZUREML_RUN_TOKEN_EXPIRY\n",
" os.environ['AZUREML_RUN_ID'] = args.AZUREML_RUN_ID\n",
@@ -895,10 +901,12 @@
" os.environ['AZUREML_ARM_WORKSPACE_NAME'] = args.AZUREML_ARM_WORKSPACE_NAME\n",
" os.environ['AZUREML_ARM_PROJECT_NAME'] = args.AZUREML_ARM_PROJECT_NAME\n",
" os.environ['AZUREML_SERVICE_ENDPOINT'] = args.AZUREML_SERVICE_ENDPOINT\n",
+ " os.environ['AZUREML_WORKSPACE_ID'] = args.AZUREML_WORKSPACE_ID\n",
+ " os.environ['AZUREML_EXPERIMENT_ID'] = args.AZUREML_EXPERIMENT_ID\n",
"\n",
"populate_environ()\n",
"run = Run.get_context(allow_offline=False)\n",
- "print(run._run_dto[\"parent_run_id\"])\n",
+ "print(run.parent.id)\n",
"```"
]
},
@@ -947,7 +955,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.6.2"
+ "version": "3.7.9"
},
"order_index": 5,
"star_tag": [
diff --git a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-data-dependency-steps.ipynb b/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-data-dependency-steps.ipynb
index 419303a42..fa89e5c3b 100644
--- a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-data-dependency-steps.ipynb
+++ b/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-data-dependency-steps.ipynb
@@ -213,7 +213,7 @@
"blob_input_data = DataReference(\n",
" datastore=def_blob_store,\n",
" data_reference_name=\"test_data\",\n",
- " path_on_datastore=\"20newsgroups/20news.pkl\")\n",
+ " path_on_datastore=\"titanic/Titanic.csv\")\n",
"print(\"DataReference object created\")"
]
},
@@ -382,7 +382,7 @@
"from azureml.pipeline.core import PipelineParameter\n",
"from azureml.data.datapath import DataPath, DataPathComputeBinding\n",
"\n",
- "datapath = DataPath(datastore=def_blob_store, path_on_datastore='20newsgroups/20news.pkl')\n",
+ "datapath = DataPath(datastore=def_blob_store, path_on_datastore='titanic/Titanic.csv')\n",
"datapath_param = PipelineParameter(name=\"compare_data\", default_value=datapath)\n",
"data_parameter1 = (datapath_param, DataPathComputeBinding(mode='mount'))"
]
diff --git a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-notebook-runner-step.ipynb b/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-notebook-runner-step.ipynb
index 4e178747e..2d17c662f 100644
--- a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-notebook-runner-step.ipynb
+++ b/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-notebook-runner-step.ipynb
@@ -42,9 +42,7 @@
"Advantages of running your notebook as a step in pipeline:\n",
"1. Run your notebook like a python script without converting into .py files, leveraging complete end to end experience of Azure Machine Learning Pipelines.\n",
"2. Use pipeline intermediate data to and from the notebook along with other steps in pipeline.\n",
- "3. Parameterize your notebook with [Pipeline Parameters](./aml-pipelines-publish-and-run-using-rest-endpoint.ipynb).\n",
- "\n",
- "Try some more [quick start notebooks](https://github.com/microsoft/recommenders/tree/master/notebooks/00_quick_start) with `NotebookRunnerStep`."
+ "3. Parameterize your notebook with [Pipeline Parameters](./aml-pipelines-publish-and-run-using-rest-endpoint.ipynb).\n"
]
},
{
@@ -61,6 +59,8 @@
"outputs": [],
"source": [
"import os\n",
+ "import requests\n",
+ "import tempfile\n",
"\n",
"import azureml.core\n",
"\n",
@@ -114,7 +114,12 @@
"metadata": {},
"outputs": [],
"source": [
- "Datastore.get(ws, \"workspaceblobstore\").upload_files([\"./20news.pkl\"], target_path=\"20newsgroups\", overwrite=True)\n",
+ "# download data file from remote\n",
+ "response = requests.get(\"https://dprepdata.blob.core.windows.net/demo/Titanic.csv\")\n",
+ "titanic_file = os.path.join(tempfile.mkdtemp(), \"Titanic.csv\")\n",
+ "with open(titanic_file, \"w\") as f:\n",
+ " f.write(response.content.decode(\"utf-8\"))\n",
+ "Datastore.get(ws, \"workspaceblobstore\").upload_files([titanic_file], target_path=\"titanic\", overwrite=True)\n",
"print(\"Upload call completed\")"
]
},
@@ -227,7 +232,7 @@
"input_data = DataReference(\n",
" datastore=Datastore.get(ws, \"workspaceblobstore\"),\n",
" data_reference_name=\"blob_test_data\",\n",
- " path_on_datastore=\"20newsgroups/20news.pkl\")\n",
+ " path_on_datastore=\"titanic/Titanic.csv\")\n",
"\n",
"output_data = PipelineData(name=\"processed_data\",\n",
" datastore=Datastore.get(ws, \"workspaceblobstore\"))"
diff --git a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/publish_run_extract/extract.py b/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/publish_run_extract/extract.py
index e3cc1e79a..aa487b717 100644
--- a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/publish_run_extract/extract.py
+++ b/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/publish_run_extract/extract.py
@@ -20,7 +20,7 @@
os.makedirs(args.output_extract, exist_ok=True)
print("%s created" % args.output_extract)
-with open(os.path.join(args.input_extract, '20news.pkl'), 'rb') as f:
+with open(os.path.join(args.input_extract, 'Titanic.csv'), 'rb') as f:
content = f.read()
- with open(os.path.join(args.output_extract, '20news.pkl'), 'wb') as fw:
+ with open(os.path.join(args.output_extract, 'Titanic.csv'), 'wb') as fw:
fw.write(content)
diff --git a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/publish_run_train/train.py b/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/publish_run_train/train.py
index 4f88f0de7..bc5a9ee6a 100644
--- a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/publish_run_train/train.py
+++ b/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/publish_run_train/train.py
@@ -21,7 +21,7 @@
os.makedirs(args.output_train, exist_ok=True)
print("%s created" % args.output_train)
-with open(os.path.join(args.input_data, '20news.pkl'), 'rb') as f:
+with open(os.path.join(args.input_data), 'rb') as f:
content = f.read()
- with open(os.path.join(args.output_train, '20news.pkl'), 'wb') as fw:
+ with open(os.path.join(args.output_train, 'Titanic.csv'), 'wb') as fw:
fw.write(content)
diff --git a/how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/prepdata/cleanse.py b/how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/prepdata/cleanse.py
index bae27e828..0da693cca 100644
--- a/how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/prepdata/cleanse.py
+++ b/how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/prepdata/cleanse.py
@@ -7,7 +7,7 @@
def get_dict(dict_str):
- pairs = dict_str.strip("{}").split("\;")
+ pairs = dict_str.strip("{}").split(r'\;')
new_dict = {}
for pair in pairs:
key, value = pair.strip().split(":")
@@ -31,14 +31,14 @@ def get_dict(dict_str):
args = parser.parse_args()
-print("Argument 1(columns to keep): %s" % str(args.useful_columns.strip("[]").split("\;")))
-print("Argument 2(columns renaming mapping): %s" % str(args.columns.strip("{}").split("\;")))
+print("Argument 1(columns to keep): %s" % str(args.useful_columns.strip("[]").split(r'\;')))
+print("Argument 2(columns renaming mapping): %s" % str(args.columns.strip("{}").split(r'\;')))
print("Argument 3(output cleansed taxi data path): %s" % args.output_cleanse)
# These functions ensure that null data is removed from the dataset,
# which will help increase machine learning model accuracy.
-useful_columns = [s.strip().strip("'") for s in args.useful_columns.strip("[]").split("\;")]
+useful_columns = [s.strip().strip("'") for s in args.useful_columns.strip("[]").split(r'\;')]
columns = get_dict(args.columns)
new_df = (raw_data.to_pandas_dataframe()
diff --git a/how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/prepdata/filter.py b/how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/prepdata/filter.py
index a999c54ec..21a93619b 100644
--- a/how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/prepdata/filter.py
+++ b/how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/prepdata/filter.py
@@ -29,14 +29,14 @@
combined_df = combined_df.astype({"pickup_longitude": 'float64', "pickup_latitude": 'float64',
"dropoff_longitude": 'float64', "dropoff_latitude": 'float64'})
-latlong_filtered_df = combined_df[(combined_df.pickup_longitude <= -73.72) &
- (combined_df.pickup_longitude >= -74.09) &
- (combined_df.pickup_latitude <= 40.88) &
- (combined_df.pickup_latitude >= 40.53) &
- (combined_df.dropoff_longitude <= -73.72) &
- (combined_df.dropoff_longitude >= -74.72) &
- (combined_df.dropoff_latitude <= 40.88) &
- (combined_df.dropoff_latitude >= 40.53)]
+latlong_filtered_df = combined_df[(combined_df.pickup_longitude <= -73.72)
+ & (combined_df.pickup_longitude >= -74.09)
+ & (combined_df.pickup_latitude <= 40.88)
+ & (combined_df.pickup_latitude >= 40.53)
+ & (combined_df.dropoff_longitude <= -73.72)
+ & (combined_df.dropoff_longitude >= -74.72)
+ & (combined_df.dropoff_latitude <= 40.88)
+ & (combined_df.dropoff_latitude >= 40.53)]
latlong_filtered_df.reset_index(inplace=True, drop=True)
diff --git a/how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/trainmodel/train_test_split.py b/how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/trainmodel/train_test_split.py
index 48571e64f..288811f4d 100644
--- a/how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/trainmodel/train_test_split.py
+++ b/how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/trainmodel/train_test_split.py
@@ -1,6 +1,6 @@
import argparse
import os
-import azureml.core
+# import azureml.core
from azureml.core import Run
from sklearn.model_selection import train_test_split
@@ -32,7 +32,7 @@ def write_output(df, path):
output_split_train.reset_index(inplace=True, drop=True)
output_split_test.reset_index(inplace=True, drop=True)
-if not (args.output_split_train is None and
- args.output_split_test is None):
+if not (args.output_split_train
+ is None and args.output_split_test is None):
write_output(output_split_train, args.output_split_train)
write_output(output_split_test, args.output_split_test)
diff --git a/how-to-use-azureml/responsible-ai/auto-ml-regression-responsibleai/auto-ml-regression-responsibleai.ipynb b/how-to-use-azureml/responsible-ai/auto-ml-regression-responsibleai/auto-ml-regression-responsibleai.ipynb
index 5a975f9fe..cd614d99c 100644
--- a/how-to-use-azureml/responsible-ai/auto-ml-regression-responsibleai/auto-ml-regression-responsibleai.ipynb
+++ b/how-to-use-azureml/responsible-ai/auto-ml-regression-responsibleai/auto-ml-regression-responsibleai.ipynb
@@ -95,7 +95,7 @@
"metadata": {},
"outputs": [],
"source": [
- "print(\"This notebook was created using version 1.36.0 of the Azure ML SDK\")\n",
+ "print(\"This notebook was created using version 1.37.0 of the Azure ML SDK\")\n",
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
]
},
diff --git a/how-to-use-azureml/responsible-ai/visualize-upload-loan-decision/rai-loan-decision.yml b/how-to-use-azureml/responsible-ai/visualize-upload-loan-decision/rai-loan-decision.yml
index 7af680b92..690e832ec 100644
--- a/how-to-use-azureml/responsible-ai/visualize-upload-loan-decision/rai-loan-decision.yml
+++ b/how-to-use-azureml/responsible-ai/visualize-upload-loan-decision/rai-loan-decision.yml
@@ -8,5 +8,5 @@ dependencies:
- matplotlib
- azureml-dataset-runtime
- ipywidgets
- - raiwidgets~=0.13.0
+ - raiwidgets~=0.15.0
- liac-arff
diff --git a/how-to-use-azureml/track-and-monitor-experiments/logging-api/logging-api.ipynb b/how-to-use-azureml/track-and-monitor-experiments/logging-api/logging-api.ipynb
index 52c937a17..b6793a165 100644
--- a/how-to-use-azureml/track-and-monitor-experiments/logging-api/logging-api.ipynb
+++ b/how-to-use-azureml/track-and-monitor-experiments/logging-api/logging-api.ipynb
@@ -100,7 +100,7 @@
"\n",
"# Check core SDK version number\n",
"\n",
- "print(\"This notebook was created using SDK version 1.36.0, you are currently running version\", azureml.core.VERSION)"
+ "print(\"This notebook was created using SDK version 1.37.0, you are currently running version\", azureml.core.VERSION)"
]
},
{
diff --git a/index.md b/index.md
index b961caf7e..0536b396a 100644
--- a/index.md
+++ b/index.md
@@ -28,6 +28,7 @@ Machine Learning notebook samples and encourage efficient retrieval of topics an
| [Classification of credit card fraudulent transactions using Automated ML](https://github.com/Azure/MachineLearningNotebooks/blob/master//how-to-use-azureml/automated-machine-learning/experimental/classification-credit-card-fraud-local-managed/auto-ml-classification-credit-card-fraud-local-managed.ipynb) | Classification | Creditcard | AML Compute | None | None | AutomatedML |
| [Automated ML run with featurization and model explainability.](https://github.com/Azure/MachineLearningNotebooks/blob/master//how-to-use-azureml/automated-machine-learning/regression-explanation-featurization/auto-ml-regression-explanation-featurization.ipynb) | Regression | MachineData | AML | ACI | None | featurization, explainability, remote_run, AutomatedML |
| [Automated ML run with featurization and model explainability.](https://github.com/Azure/MachineLearningNotebooks/blob/master//how-to-use-azureml/responsible-ai/auto-ml-regression-responsibleai/auto-ml-regression-responsibleai.ipynb) | Regression | MachineData | AML | ACI | None | featurization, explainability, remote_run, AutomatedML |
+| [auto-ml-forecasting-backtest-single-model](https://github.com/Azure/MachineLearningNotebooks/blob/master//how-to-use-azureml/automated-machine-learning/forecasting-backtest-single-model/auto-ml-forecasting-backtest-single-model.ipynb) | | None | Remote | None | Azure ML AutoML | |
| :star:[Azure Machine Learning Pipeline with DataTranferStep](https://github.com/Azure/MachineLearningNotebooks/blob/master//how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-data-transfer.ipynb) | Demonstrates the use of DataTranferStep | Custom | ADF | None | Azure ML | None |
| [Getting Started with Azure Machine Learning Pipelines](https://github.com/Azure/MachineLearningNotebooks/blob/master//how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-getting-started.ipynb) | Getting Started notebook for ANML Pipelines | Custom | AML Compute | None | Azure ML | None |
| [Azure Machine Learning Pipeline with AzureBatchStep](https://github.com/Azure/MachineLearningNotebooks/blob/master//how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-how-to-use-azurebatch-to-run-a-windows-executable.ipynb) | Demonstrates the use of AzureBatchStep | Custom | Azure Batch | None | Azure ML | None |
@@ -106,6 +107,7 @@ Machine Learning notebook samples and encourage efficient retrieval of topics an
| [azure-ml-with-nvidia-rapids](https://github.com/Azure/MachineLearningNotebooks/blob/master//contrib/RAPIDS/azure-ml-with-nvidia-rapids.ipynb) | | | | | | |
| [auto-ml-continuous-retraining](https://github.com/Azure/MachineLearningNotebooks/blob/master//how-to-use-azureml/automated-machine-learning/continuous-retraining/auto-ml-continuous-retraining.ipynb) | | | | | | |
| [auto-ml-regression-model-proxy](https://github.com/Azure/MachineLearningNotebooks/blob/master//how-to-use-azureml/automated-machine-learning/experimental/regression-model-proxy/auto-ml-regression-model-proxy.ipynb) | | | | | | |
+| [auto-ml-forecasting-backtest-many-models](https://github.com/Azure/MachineLearningNotebooks/blob/master//how-to-use-azureml/automated-machine-learning/forecasting-backtest-many-models/auto-ml-forecasting-backtest-many-models.ipynb) | | | | | | |
| [auto-ml-forecasting-beer-remote](https://github.com/Azure/MachineLearningNotebooks/blob/master//how-to-use-azureml/automated-machine-learning/forecasting-beer-remote/auto-ml-forecasting-beer-remote.ipynb) | | | | | | |
| [auto-ml-forecasting-energy-demand](https://github.com/Azure/MachineLearningNotebooks/blob/master//how-to-use-azureml/automated-machine-learning/forecasting-energy-demand/auto-ml-forecasting-energy-demand.ipynb) | | | | | | |
| [auto-ml-forecasting-hierarchical-timeseries](https://github.com/Azure/MachineLearningNotebooks/blob/master//how-to-use-azureml/automated-machine-learning/forecasting-hierarchical-timeseries/auto-ml-forecasting-hierarchical-timeseries.ipynb) | | | | | | |
diff --git a/setup-environment/configuration.ipynb b/setup-environment/configuration.ipynb
index 07218cae5..9ea0fcb36 100644
--- a/setup-environment/configuration.ipynb
+++ b/setup-environment/configuration.ipynb
@@ -102,7 +102,7 @@
"source": [
"import azureml.core\n",
"\n",
- "print(\"This notebook was created using version 1.36.0 of the Azure ML SDK\")\n",
+ "print(\"This notebook was created using version 1.37.0 of the Azure ML SDK\")\n",
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
]
},
diff --git a/tutorials/create-first-ml-experiment/tutorial-1st-experiment-sdk-train.ipynb b/tutorials/create-first-ml-experiment/tutorial-1st-experiment-sdk-train.ipynb
index 4ff9cc2c7..54d5d2337 100644
--- a/tutorials/create-first-ml-experiment/tutorial-1st-experiment-sdk-train.ipynb
+++ b/tutorials/create-first-ml-experiment/tutorial-1st-experiment-sdk-train.ipynb
@@ -145,7 +145,7 @@
"source": [
"from sklearn.linear_model import Ridge\n",
"from sklearn.metrics import mean_squared_error\n",
- "from sklearn.externals import joblib\n",
+ "import joblib\n",
"import math\n",
"\n",
"alphas = [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0]\n",
diff --git a/tutorials/image-classification-mnist-data/img-classification-part3-deploy-encrypted.ipynb b/tutorials/image-classification-mnist-data/img-classification-part3-deploy-encrypted.ipynb
index a8b985f21..18c6c209a 100644
--- a/tutorials/image-classification-mnist-data/img-classification-part3-deploy-encrypted.ipynb
+++ b/tutorials/image-classification-mnist-data/img-classification-part3-deploy-encrypted.ipynb
@@ -156,7 +156,7 @@
"\n",
"### Create scoring script\n",
"\n",
- "Create the scoring script, called score.py, used by the web service call to show how to use the model.\n",
+ "Create the scoring script, called score_encrypted.py, used by the web service call to show how to use the model.\n",
"\n",
"You must include two required functions into the scoring script:\n",
"* The `init()` function, which typically loads the model into a global object. This function is run only once when the Docker container is started. \n",
@@ -171,7 +171,7 @@
"metadata": {},
"outputs": [],
"source": [
- "%%writefile score.py\n",
+ "%%writefile score_encrypted.py\n",
"import json\n",
"import os\n",
"import pickle\n",
@@ -252,7 +252,7 @@
"\n",
"1. Create environment object containing dependencies needed by the model using the environment file (`myenv.yml`)\n",
"1. Create inference configuration necessary to deploy the model as a web service using:\n",
- " * The scoring file (`score.py`)\n",
+ " * The scoring file (`score_encrypted.py`)\n",
" * envrionment object created in previous step\n",
"1. Deploy the model to the ACI container.\n",
"1. Get the web service HTTP endpoint."
@@ -283,7 +283,7 @@
"model = Model(ws, 'sklearn_mnist')\n",
"\n",
"myenv = Environment.get(workspace=ws, name=\"tutorial-encryption-env\")\n",
- "inference_config = InferenceConfig(entry_script=\"score.py\", environment=myenv)\n",
+ "inference_config = InferenceConfig(entry_script=\"score_encrypted.py\", environment=myenv)\n",
"\n",
"service_name = 'sklearn-mnist-svc-' + str(uuid.uuid4())[:4]\n",
"service = Model.deploy(workspace=ws, \n",