mirror of
https://github.com/Azure/MachineLearningNotebooks.git
synced 2025-12-22 18:42:41 -05:00
Compare commits
12 Commits
azureml-sd
...
azureml-sd
| Author | SHA1 | Date | |
|---|---|---|---|
|
0814eee151 | ||
|
|
f45b815221 | ||
|
|
bd629ae454 | ||
|
|
41de75a584 | ||
|
|
96a426dc36 | ||
|
|
824dd40f7e | ||
|
|
fa2e649fe8 | ||
|
|
e25e8e3a41 | ||
|
|
aa3670a902 | ||
|
|
ef1f9205ac | ||
|
|
3228bbfc63 | ||
|
|
f18a0dfc4d |
@@ -103,7 +103,7 @@
|
||||
"source": [
|
||||
"import azureml.core\n",
|
||||
"\n",
|
||||
"print(\"This notebook was created using version 1.45.0 of the Azure ML SDK\")\n",
|
||||
"print(\"This notebook was created using version 1.47.0 of the Azure ML SDK\")\n",
|
||||
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
|
||||
]
|
||||
},
|
||||
@@ -367,9 +367,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -525,9 +525,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -599,9 +599,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -6,7 +6,7 @@ dependencies:
|
||||
- fairlearn>=0.6.2
|
||||
- joblib
|
||||
- liac-arff
|
||||
- raiwidgets~=0.21.0
|
||||
- raiwidgets~=0.22.0
|
||||
- itsdangerous==2.0.1
|
||||
- markupsafe<2.1.0
|
||||
- protobuf==3.20.0
|
||||
|
||||
@@ -523,9 +523,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -6,7 +6,7 @@ dependencies:
|
||||
- fairlearn>=0.6.2
|
||||
- joblib
|
||||
- liac-arff
|
||||
- raiwidgets~=0.21.0
|
||||
- raiwidgets~=0.22.0
|
||||
- itsdangerous==2.0.1
|
||||
- markupsafe<2.1.0
|
||||
- protobuf==3.20.0
|
||||
|
||||
@@ -10,27 +10,27 @@ dependencies:
|
||||
- python>=3.6,<3.9
|
||||
- matplotlib==3.2.1
|
||||
- py-xgboost==1.3.3
|
||||
- pytorch::pytorch=1.4.0
|
||||
- pytorch::pytorch=1.11.0
|
||||
- conda-forge::fbprophet==0.7.1
|
||||
- cudatoolkit=10.1.243
|
||||
- scipy==1.5.3
|
||||
- notebook
|
||||
- pywin32==227
|
||||
- PySocks==1.7.1
|
||||
- conda-forge::pyqt==5.12.3
|
||||
- jsonschema==4.15.0
|
||||
- jinja2<=2.11.2
|
||||
- markupsafe<2.1.0
|
||||
- tqdm==4.64.0
|
||||
- tqdm==4.64.1
|
||||
- jsonschema==4.16.0
|
||||
- websocket-client==1.4.1
|
||||
|
||||
- pip:
|
||||
# Required packages for AzureML execution, history, and data preparation.
|
||||
- azureml-widgets~=1.45.0
|
||||
- azureml-defaults~=1.45.0
|
||||
- azureml-widgets~=1.47.0
|
||||
- azureml-defaults~=1.47.0
|
||||
- pytorch-transformers==1.0.0
|
||||
- spacy==2.2.4
|
||||
- pystan==2.19.1.1
|
||||
- https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz
|
||||
- -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.45.0/validated_win32_requirements.txt [--no-deps]
|
||||
- -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.47.0/validated_win32_requirements.txt [--no-deps]
|
||||
- arch==4.14
|
||||
- wasabi==0.9.1
|
||||
|
||||
@@ -6,10 +6,8 @@ channels:
|
||||
dependencies:
|
||||
# The python interpreter version.
|
||||
# Currently Azure ML only supports 3.6.0 and later.
|
||||
- pip==20.2.4
|
||||
- pip==20.1.1
|
||||
- python>=3.6,<3.9
|
||||
- boto3==1.20.19
|
||||
- botocore<=1.23.19
|
||||
- matplotlib==3.2.1
|
||||
- numpy>=1.21.6,<=1.22.3
|
||||
- cython==0.29.14
|
||||
@@ -19,18 +17,19 @@ dependencies:
|
||||
- py-xgboost<=1.3.3
|
||||
- holidays==0.10.3
|
||||
- conda-forge::fbprophet==0.7.1
|
||||
- pytorch::pytorch=1.4.0
|
||||
- pytorch::pytorch=1.11.0
|
||||
- cudatoolkit=10.1.243
|
||||
- notebook
|
||||
- jinja2<=2.11.2
|
||||
- markupsafe<2.1.0
|
||||
|
||||
- pip:
|
||||
# Required packages for AzureML execution, history, and data preparation.
|
||||
- azureml-widgets~=1.45.0
|
||||
- azureml-defaults~=1.45.0
|
||||
- azureml-widgets~=1.47.0
|
||||
- azureml-defaults~=1.47.0
|
||||
- pytorch-transformers==1.0.0
|
||||
- spacy==2.2.4
|
||||
- pystan==2.19.1.1
|
||||
- https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz
|
||||
- -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.45.0/validated_linux_requirements.txt [--no-deps]
|
||||
- -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.47.0/validated_linux_requirements.txt [--no-deps]
|
||||
- arch==4.14
|
||||
|
||||
@@ -6,11 +6,8 @@ channels:
|
||||
dependencies:
|
||||
# The python interpreter version.
|
||||
# Currently Azure ML only supports 3.6.0 and later.
|
||||
- pip==20.2.4
|
||||
- nomkl
|
||||
- pip==20.1.1
|
||||
- python>=3.6,<3.9
|
||||
- boto3==1.20.19
|
||||
- botocore<=1.23.19
|
||||
- matplotlib==3.2.1
|
||||
- numpy>=1.21.6,<=1.22.3
|
||||
- cython==0.29.14
|
||||
@@ -20,18 +17,19 @@ dependencies:
|
||||
- py-xgboost<=1.3.3
|
||||
- holidays==0.10.3
|
||||
- conda-forge::fbprophet==0.7.1
|
||||
- pytorch::pytorch=1.4.0
|
||||
- pytorch::pytorch=1.11.0
|
||||
- cudatoolkit=9.0
|
||||
- notebook
|
||||
- jinja2<=2.11.2
|
||||
- markupsafe<2.1.0
|
||||
|
||||
- pip:
|
||||
# Required packages for AzureML execution, history, and data preparation.
|
||||
- azureml-widgets~=1.45.0
|
||||
- azureml-defaults~=1.45.0
|
||||
- azureml-widgets~=1.47.0
|
||||
- azureml-defaults~=1.47.0
|
||||
- pytorch-transformers==1.0.0
|
||||
- spacy==2.2.4
|
||||
- pystan==2.19.1.1
|
||||
- https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz
|
||||
- -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.45.0/validated_darwin_requirements.txt [--no-deps]
|
||||
- -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.47.0/validated_darwin_requirements.txt [--no-deps]
|
||||
- arch==4.14
|
||||
|
||||
@@ -33,6 +33,8 @@ if not errorlevel 1 (
|
||||
call conda env create -f %automl_env_file% -n %conda_env_name%
|
||||
)
|
||||
|
||||
python "%conda_prefix%\scripts\pywin32_postinstall.py" -install
|
||||
|
||||
call conda activate %conda_env_name% 2>nul:
|
||||
if errorlevel 1 goto ErrorExit
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
from distutils.version import LooseVersion
|
||||
from setuptools._vendor.packaging import version
|
||||
import platform
|
||||
|
||||
try:
|
||||
@@ -17,7 +17,7 @@ if architecture != "64bit":
|
||||
|
||||
minimumVersion = "4.7.8"
|
||||
|
||||
versionInvalid = (LooseVersion(conda.__version__) < LooseVersion(minimumVersion))
|
||||
versionInvalid = (version.parse(conda.__version__) < version.parse(minimumVersion))
|
||||
|
||||
if versionInvalid:
|
||||
print('Setup requires conda version ' + minimumVersion + ' or higher.')
|
||||
|
||||
@@ -1060,9 +1060,9 @@
|
||||
"name": "python3-azureml"
|
||||
},
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -456,9 +456,9 @@
|
||||
"friendly_name": "Classification of credit card fraudulent transactions using Automated ML",
|
||||
"index_order": 5,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -567,9 +567,9 @@
|
||||
"friendly_name": "DNN Text Featurization",
|
||||
"index_order": 2,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -564,9 +564,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -97,7 +97,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"This notebook was created using version 1.45.0 of the Azure ML SDK\")\n",
|
||||
"print(\"This notebook was created using version 1.47.0 of the Azure ML SDK\")\n",
|
||||
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
|
||||
]
|
||||
},
|
||||
@@ -324,9 +324,9 @@
|
||||
"hash": "adb464b67752e4577e3dc163235ced27038d19b7d88def00d75d1975bde5d9ab"
|
||||
},
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -97,7 +97,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"This notebook was created using version 1.45.0 of the Azure ML SDK\")\n",
|
||||
"print(\"This notebook was created using version 1.47.0 of the Azure ML SDK\")\n",
|
||||
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
|
||||
]
|
||||
},
|
||||
@@ -713,9 +713,9 @@
|
||||
"hash": "adb464b67752e4577e3dc163235ced27038d19b7d88def00d75d1975bde5d9ab"
|
||||
},
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -7,9 +7,8 @@ dependencies:
|
||||
- cython==0.29.14
|
||||
- urllib3==1.26.7
|
||||
- PyJWT < 2.0.0
|
||||
- numpy==1.21.6
|
||||
- numpy==1.22.3
|
||||
- pywin32==227
|
||||
- cryptography<37.0.0
|
||||
|
||||
- pip:
|
||||
# Required packages for AzureML execution, history, and data preparation.
|
||||
@@ -21,3 +20,4 @@ dependencies:
|
||||
- azureml-mlflow
|
||||
- pandas
|
||||
- mlflow
|
||||
- docker<6.0.0
|
||||
|
||||
@@ -11,7 +11,6 @@ dependencies:
|
||||
- urllib3==1.26.7
|
||||
- PyJWT < 2.0.0
|
||||
- numpy>=1.21.6,<=1.22.3
|
||||
- cryptography<37.0.0
|
||||
|
||||
- pip:
|
||||
# Required packages for AzureML execution, history, and data preparation.
|
||||
|
||||
@@ -92,7 +92,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"This notebook was created using version 1.45.0 of the Azure ML SDK\")\n",
|
||||
"print(\"This notebook was created using version 1.47.0 of the Azure ML SDK\")\n",
|
||||
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
|
||||
]
|
||||
},
|
||||
@@ -354,7 +354,7 @@
|
||||
"This Credit Card fraud Detection dataset is made available under the Open Database License: http://opendatacommons.org/licenses/odbl/1.0/. Any rights in individual contents of the database are licensed under the Database Contents License: http://opendatacommons.org/licenses/dbcl/1.0/ and is available at: https://www.kaggle.com/mlg-ulb/creditcardfraud\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"The dataset has been collected and analysed during a research collaboration of Worldline and the Machine Learning Group (http://mlg.ulb.ac.be) of ULB (Universit\u00c3\u0192\u00c2\u00a9 Libre de Bruxelles) on big data mining and fraud detection. More details on current and past projects on related topics are available on https://www.researchgate.net/project/Fraud-detection-5 and the page of the DefeatFraud project\n",
|
||||
"The dataset has been collected and analysed during a research collaboration of Worldline and the Machine Learning Group (http://mlg.ulb.ac.be) of ULB (Universit\u00c3\u0192\u00c2\u00a9 Libre de Bruxelles) on big data mining and fraud detection. More details on current and past projects on related topics are available on https://www.researchgate.net and the page of the DefeatFraud project\n",
|
||||
"Please cite the following works: \n",
|
||||
"\u00c3\u00a2\u00e2\u201a\u00ac\u00c2\u00a2\tAndrea Dal Pozzolo, Olivier Caelen, Reid A. Johnson and Gianluca Bontempi. Calibrating Probability with Undersampling for Unbalanced Classification. In Symposium on Computational Intelligence and Data Mining (CIDM), IEEE, 2015\n",
|
||||
"\u00c3\u00a2\u00e2\u201a\u00ac\u00c2\u00a2\tDal Pozzolo, Andrea; Caelen, Olivier; Le Borgne, Yann-Ael; Waterschoot, Serge; Bontempi, Gianluca. Learned lessons in credit card fraud detection from a practitioner perspective, Expert systems with applications,41,10,4915-4928,2014, Pergamon\n",
|
||||
@@ -389,9 +389,9 @@
|
||||
"friendly_name": "Classification of credit card fraudulent transactions using Automated ML",
|
||||
"index_order": 5,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -91,7 +91,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"This notebook was created using version 1.45.0 of the Azure ML SDK\")\n",
|
||||
"print(\"This notebook was created using version 1.47.0 of the Azure ML SDK\")\n",
|
||||
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
|
||||
]
|
||||
},
|
||||
@@ -448,9 +448,9 @@
|
||||
"automated-machine-learning"
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -406,7 +406,7 @@
|
||||
" compute_target=compute_target,\n",
|
||||
" node_count=2,\n",
|
||||
" process_count_per_node=2,\n",
|
||||
" run_invocation_timeout=920,\n",
|
||||
" run_invocation_timeout=1200,\n",
|
||||
" train_pipeline_parameters=mm_paramters,\n",
|
||||
")"
|
||||
]
|
||||
@@ -706,9 +706,9 @@
|
||||
"automated-machine-learning"
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -43,11 +43,20 @@ def init():
|
||||
global output_dir
|
||||
global automl_settings
|
||||
global model_uid
|
||||
global forecast_quantiles
|
||||
|
||||
logger.info("Initialization of the run.")
|
||||
parser = argparse.ArgumentParser("Parsing input arguments.")
|
||||
parser.add_argument("--output-dir", dest="out", required=True)
|
||||
parser.add_argument("--model-name", dest="model", default=None)
|
||||
parser.add_argument("--model-uid", dest="model_uid", default=None)
|
||||
parser.add_argument(
|
||||
"--forecast_quantiles",
|
||||
nargs="*",
|
||||
type=float,
|
||||
help="forecast quantiles list",
|
||||
default=None,
|
||||
)
|
||||
|
||||
parsed_args, _ = parser.parse_known_args()
|
||||
model_name = parsed_args.model
|
||||
@@ -55,6 +64,7 @@ def init():
|
||||
target_column_name = automl_settings.get("label_column_name")
|
||||
output_dir = parsed_args.out
|
||||
model_uid = parsed_args.model_uid
|
||||
forecast_quantiles = parsed_args.forecast_quantiles
|
||||
os.makedirs(output_dir, exist_ok=True)
|
||||
os.environ["AUTOML_IGNORE_PACKAGE_VERSION_INCOMPATIBILITIES".lower()] = "True"
|
||||
|
||||
@@ -126,23 +136,18 @@ def run_backtest(data_input_name: str, file_name: str, experiment: Experiment):
|
||||
)
|
||||
print(f"The model {best_run.properties['model_name']} was registered.")
|
||||
|
||||
_, x_pred = fitted_model.forecast(X_test)
|
||||
x_pred.reset_index(inplace=True, drop=False)
|
||||
columns = [automl_settings[constants.TimeSeries.TIME_COLUMN_NAME]]
|
||||
if automl_settings.get(constants.TimeSeries.GRAIN_COLUMN_NAMES):
|
||||
# We know that fitted_model.grain_column_names is a list.
|
||||
columns.extend(fitted_model.grain_column_names)
|
||||
columns.append(constants.TimeSeriesInternal.DUMMY_TARGET_COLUMN)
|
||||
# Remove featurized columns.
|
||||
x_pred = x_pred[columns]
|
||||
x_pred.rename(
|
||||
{constants.TimeSeriesInternal.DUMMY_TARGET_COLUMN: "predicted_level"},
|
||||
axis=1,
|
||||
inplace=True,
|
||||
)
|
||||
# By default we will have forecast quantiles of 0.5, which is our target
|
||||
if forecast_quantiles:
|
||||
if 0.5 not in forecast_quantiles:
|
||||
forecast_quantiles.append(0.5)
|
||||
fitted_model.quantiles = forecast_quantiles
|
||||
|
||||
x_pred = fitted_model.forecast_quantiles(X_test)
|
||||
x_pred["actual_level"] = y_test
|
||||
x_pred["backtest_iteration"] = f"iteration_{last_training_date}"
|
||||
x_pred.rename({0.5: "predicted_level"}, axis=1, inplace=True)
|
||||
date_safe = RE_INVALID_SYMBOLS.sub("_", last_training_date)
|
||||
|
||||
x_pred.to_csv(os.path.join(output_dir, f"iteration_{date_safe}.csv"), index=False)
|
||||
return x_pred
|
||||
|
||||
|
||||
@@ -365,6 +365,7 @@
|
||||
" step_size=BACKTESTING_PERIOD,\n",
|
||||
" step_number=NUMBER_OF_BACKTESTS,\n",
|
||||
" model_uid=model_uid,\n",
|
||||
" forecast_quantiles=[0.025, 0.975], # Optional\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
@@ -590,6 +591,7 @@
|
||||
" step_size=BACKTESTING_PERIOD,\n",
|
||||
" step_number=NUMBER_OF_BACKTESTS,\n",
|
||||
" model_name=model_name,\n",
|
||||
" forecast_quantiles=[0.025, 0.975],\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
@@ -700,9 +702,9 @@
|
||||
"Azure ML AutoML"
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -31,6 +31,7 @@ def get_backtest_pipeline(
|
||||
step_number: int,
|
||||
model_name: Optional[str] = None,
|
||||
model_uid: Optional[str] = None,
|
||||
forecast_quantiles: Optional[list] = None,
|
||||
) -> Pipeline:
|
||||
"""
|
||||
:param experiment: The experiment used to run the pipeline.
|
||||
@@ -44,6 +45,7 @@ def get_backtest_pipeline(
|
||||
:param step_size: The number of periods to step back in backtesting.
|
||||
:param step_number: The number of backtesting iterations.
|
||||
:param model_uid: The uid to mark models from this run of the experiment.
|
||||
:param forecast_quantiles: The forecast quantiles that are required in the inference.
|
||||
:return: The pipeline to be used for model retraining.
|
||||
**Note:** The output will be uploaded in the pipeline output
|
||||
called 'score'.
|
||||
@@ -135,6 +137,9 @@ def get_backtest_pipeline(
|
||||
if model_uid is not None:
|
||||
prs_args.append("--model-uid")
|
||||
prs_args.append(model_uid)
|
||||
if forecast_quantiles:
|
||||
prs_args.append("--forecast_quantiles")
|
||||
prs_args.extend(forecast_quantiles)
|
||||
backtest_prs = ParallelRunStep(
|
||||
name=parallel_step_name,
|
||||
parallel_run_config=back_test_config,
|
||||
|
||||
@@ -575,7 +575,32 @@
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"remote_run.download_file(\"outputs/predictions.csv\", \"predictions.csv\")\n",
|
||||
"df_all = pd.read_csv(\"predictions.csv\")"
|
||||
"fcst_df = pd.read_csv(\"predictions.csv\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Note that the rolling forecast can contain multiple predictions for each date, each from a different forecast origin. For example, consider 2012-09-05:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"fcst_df[fcst_df.date == \"2012-09-05\"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Here, the forecast origin refers to the latest date of actuals available for a given forecast. The earliest origin in the rolling forecast, 2012-08-31, is the last day in the training data. For origin date 2012-09-01, the forecasts use actual recorded counts from the training data *and* the actual count recorded on 2012-09-01. Note that the model is not retrained for origin dates later than 2012-08-31, but the values for model features, such as lagged values of daily count, are updated.\n",
|
||||
"\n",
|
||||
"Let's calculate the metrics over all rolling forecasts:"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -587,29 +612,17 @@
|
||||
"from azureml.automl.core.shared import constants\n",
|
||||
"from azureml.automl.runtime.shared.score import scoring\n",
|
||||
"from sklearn.metrics import mean_absolute_error, mean_squared_error\n",
|
||||
"from matplotlib import pyplot as plt\n",
|
||||
"\n",
|
||||
"# use automl metrics module\n",
|
||||
"scores = scoring.score_regression(\n",
|
||||
" y_test=df_all[target_column_name],\n",
|
||||
" y_pred=df_all[\"predicted\"],\n",
|
||||
" y_test=fcst_df[target_column_name],\n",
|
||||
" y_pred=fcst_df[\"predicted\"],\n",
|
||||
" metrics=list(constants.Metric.SCALAR_REGRESSION_SET),\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"print(\"[Test data scores]\\n\")\n",
|
||||
"for key, value in scores.items():\n",
|
||||
" print(\"{}: {:.3f}\".format(key, value))\n",
|
||||
"\n",
|
||||
"# Plot outputs\n",
|
||||
"%matplotlib inline\n",
|
||||
"test_pred = plt.scatter(df_all[target_column_name], df_all[\"predicted\"], color=\"b\")\n",
|
||||
"test_test = plt.scatter(\n",
|
||||
" df_all[target_column_name], df_all[target_column_name], color=\"g\"\n",
|
||||
")\n",
|
||||
"plt.legend(\n",
|
||||
" (test_pred, test_test), (\"prediction\", \"truth\"), loc=\"upper left\", fontsize=8\n",
|
||||
")\n",
|
||||
"plt.show()"
|
||||
" print(\"{}: {:.3f}\".format(key, value))"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -618,36 +631,15 @@
|
||||
"source": [
|
||||
"For more details on what metrics are included and how they are calculated, please refer to [supported metrics](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#regressionforecasting-metrics). You could also calculate residuals, like described [here](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#residuals).\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Since we did a rolling evaluation on the test set, we can analyze the predictions by their forecast horizon relative to the rolling origin. The model was initially trained at a forecast horizon of 14, so each prediction from the model is associated with a horizon value from 1 to 14. The horizon values are in a column named, \"horizon_origin,\" in the prediction set. For example, we can calculate some of the error metrics grouped by the horizon:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from metrics_helper import MAPE, APE\n",
|
||||
"\n",
|
||||
"df_all.groupby(\"horizon_origin\").apply(\n",
|
||||
" lambda df: pd.Series(\n",
|
||||
" {\n",
|
||||
" \"MAPE\": MAPE(df[target_column_name], df[\"predicted\"]),\n",
|
||||
" \"RMSE\": np.sqrt(\n",
|
||||
" mean_squared_error(df[target_column_name], df[\"predicted\"])\n",
|
||||
" ),\n",
|
||||
" \"MAE\": mean_absolute_error(df[target_column_name], df[\"predicted\"]),\n",
|
||||
" }\n",
|
||||
" )\n",
|
||||
")"
|
||||
"The rolling forecast metric values are very high in comparison to the validation metrics reported by the AutoML job. What's going on here? We will investigate in the following cells!"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To drill down more, we can look at the distributions of APE (absolute percentage error) by horizon. From the chart, it is clear that the overall MAPE is being skewed by one particular point where the actual value is of small absolute value."
|
||||
"### Forecast versus actuals plot\n",
|
||||
"We will plot predictions and actuals on a time series plot. Since there are many forecasts for each date, we select the 14-day-ahead forecast from each forecast origin for our comparison."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -656,21 +648,55 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"df_all_APE = df_all.assign(APE=APE(df_all[target_column_name], df_all[\"predicted\"]))\n",
|
||||
"APEs = [\n",
|
||||
" df_all_APE[df_all[\"horizon_origin\"] == h].APE.values\n",
|
||||
" for h in range(1, forecast_horizon + 1)\n",
|
||||
"]\n",
|
||||
"from matplotlib import pyplot as plt\n",
|
||||
"\n",
|
||||
"%matplotlib inline\n",
|
||||
"plt.boxplot(APEs)\n",
|
||||
"plt.yscale(\"log\")\n",
|
||||
"plt.xlabel(\"horizon\")\n",
|
||||
"plt.ylabel(\"APE (%)\")\n",
|
||||
"plt.title(\"Absolute Percentage Errors by Forecast Horizon\")\n",
|
||||
"\n",
|
||||
"fcst_df_h14 = (\n",
|
||||
" fcst_df.groupby(\"forecast_origin\", as_index=False)\n",
|
||||
" .last()\n",
|
||||
" .drop(columns=[\"forecast_origin\"])\n",
|
||||
")\n",
|
||||
"fcst_df_h14.set_index(time_column_name, inplace=True)\n",
|
||||
"plt.plot(fcst_df_h14[[target_column_name, \"predicted\"]])\n",
|
||||
"plt.xticks(rotation=45)\n",
|
||||
"plt.title(f\"Predicted vs. Actuals\")\n",
|
||||
"plt.legend([\"actual\", \"14-day-ahead forecast\"])\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Looking at the plot, there are two clear issues:\n",
|
||||
"1. An anomalously low count value on October 29th, 2012.\n",
|
||||
"2. End-of-year holidays (Thanksgiving and Christmas) in late November and late December.\n",
|
||||
"\n",
|
||||
"What happened on Oct. 29th, 2012? That day, Hurricane Sandy brought severe storm surge flooding to the east coast of the United States, particularly around New York City. This is certainly an anomalous event that the model did not account for!\n",
|
||||
"\n",
|
||||
"As for the late year holidays, the model apparently did not learn to account for the full reduction of bike share rentals on these major holidays. The training data covers 2011 and early 2012, so the model fit only had access to a single occurrence of these holidays. This makes it challenging to resolve holiday effects; however, a larger AutoML model search may result in a better model that is more holiday-aware.\n",
|
||||
"\n",
|
||||
"If we filter the predictions prior to the Thanksgiving holiday and remove the anomalous day of 2012-10-29, the metrics are closer to validation levels:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"date_filter = (fcst_df.date != \"2012-10-29\") & (fcst_df.date < \"2012-11-22\")\n",
|
||||
"scores = scoring.score_regression(\n",
|
||||
" y_test=fcst_df[date_filter][target_column_name],\n",
|
||||
" y_pred=fcst_df[date_filter][\"predicted\"],\n",
|
||||
" metrics=list(constants.Metric.SCALAR_REGRESSION_SET),\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"print(\"[Test data scores (filtered)]\\n\")\n",
|
||||
"for key, value in scores.items():\n",
|
||||
" print(\"{}: {:.3f}\".format(key, value))"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
@@ -697,9 +723,9 @@
|
||||
"friendly_name": "Forecasting BikeShare Demand",
|
||||
"index_order": 1,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
@@ -711,7 +737,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.5"
|
||||
"version": "3.7.13"
|
||||
},
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
|
||||
@@ -36,18 +36,18 @@ y_test_df = (
|
||||
|
||||
fitted_model = joblib.load("model.pkl")
|
||||
|
||||
y_pred, X_trans = fitted_model.rolling_evaluation(X_test_df, y_test_df.values)
|
||||
X_rf = fitted_model.rolling_forecast(X_test_df, y_test_df.values, step=1)
|
||||
|
||||
# Add predictions, actuals, and horizon relative to rolling origin to the test feature data
|
||||
assign_dict = {
|
||||
"horizon_origin": X_trans["horizon_origin"].values,
|
||||
"predicted": y_pred,
|
||||
target_column_name: y_test_df[target_column_name].values,
|
||||
fitted_model.forecast_origin_column_name: "forecast_origin",
|
||||
fitted_model.forecast_column_name: "predicted",
|
||||
fitted_model.actual_column_name: target_column_name,
|
||||
}
|
||||
df_all = X_test_df.assign(**assign_dict)
|
||||
X_rf.rename(columns=assign_dict, inplace=True)
|
||||
|
||||
file_name = "outputs/predictions.csv"
|
||||
export_csv = df_all.to_csv(file_name, header=True)
|
||||
export_csv = X_rf.to_csv(file_name, header=True)
|
||||
|
||||
# Upload the predictions into artifacts
|
||||
run.upload_file(name=file_name, path_or_stream=file_name)
|
||||
|
||||
@@ -767,9 +767,9 @@
|
||||
"automated-machine-learning"
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -758,7 +758,15 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Forecasting farther than the forecast horizon <a id=\"recursive forecasting\"></a>\n",
|
||||
"When the forecast destination, or the latest date in the prediction data frame, is farther into the future than the specified forecast horizon, the `forecast()` function will still make point predictions out to the later date using a recursive operation mode. Internally, the method recursively applies the regular forecaster to generate context so that we can forecast further into the future. \n",
|
||||
"When the forecast destination, or the latest date in the prediction data frame, is farther into the future than the specified forecast horizon, the forecaster must be iteratively applied. Here, we advance the forecast origin on each iteration over the prediction window, predicting `max_horizon` periods ahead on each iteration. There are two choices for the context data to use as the forecaster advances into the prediction window:\n",
|
||||
"\n",
|
||||
"1. We can use forecasted values from previous iterations (recursive forecast),\n",
|
||||
"2. We can use known, actual values of the target if they are available (rolling forecast).\n",
|
||||
"\n",
|
||||
"The first method is useful in a true forecasting scenario when we do not yet know the actual target values while the second is useful in an evaluation scenario where we want to compute accuracy metrics for the `max_horizon`-period-ahead forecaster over a long test set. We refer to the first as a **recursive forecast** since we apply the forecaster recursively over the prediction window and the second as a **rolling forecast** since we roll forward over known actuals.\n",
|
||||
"\n",
|
||||
"### Recursive forecasting\n",
|
||||
"By default, the `forecast()` function will make point predictions out to the later date using a recursive operation mode. Internally, the method recursively applies the regular forecaster to generate context so that we can forecast further into the future. \n",
|
||||
"\n",
|
||||
"To illustrate the use-case and operation of recursive forecasting, we'll consider an example with a single time-series where the forecasting period directly follows the training period and is twice as long as the forecasting horizon given at training time.\n",
|
||||
"\n",
|
||||
@@ -818,6 +826,35 @@
|
||||
"np.array_equal(y_pred_all, y_pred_long)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Rolling forecasts\n",
|
||||
"A rolling forecast is a similar concept to the recursive forecasts described above except that we use known actual values of the target for our context data. We have provided a different, public method for this called `rolling_forecast`. In addition to test data and actuals (`X_test` and `y_test`), `rolling_forecast` also accepts an optional `step` parameter that controls how far the origin advances on each iteration. The recursive forecast mode uses a fixed step of `max_horizon` while `rolling_forecast` defaults to a step size of 1, but can be set to any integer from 1 to `max_horizon`, inclusive.\n",
|
||||
"\n",
|
||||
"Let's see what the rolling forecast looks like on the long test set with the step set to 1:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X_rf = fitted_model.rolling_forecast(X_test_long, y_test_long, step=1)\n",
|
||||
"X_rf.head(n=12)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Notice that `rolling_forecast` has returned a single DataFrame containing all results and has generated some new columns: `_automl_forecast_origin`, `_automl_forecast_y`, and `_automl_actual_y`. These are the origin date for each forecast, the forecasted value and the actual value, respectively. Note that \"y\" in the forecast and actual column names will generally be replaced by the target column name supplied to AutoML.\n",
|
||||
"\n",
|
||||
"The output above shows forecasts for two prediction windows, the first with origin at the end of the training set and the second including the first observation in the test set (2000-01-01 06:00:00). Since the forecast windows overlap, there are multiple forecasts for most dates which are associated with different origin dates."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
@@ -866,9 +903,9 @@
|
||||
"friendly_name": "Forecasting away from training data",
|
||||
"index_order": 3,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
@@ -880,7 +917,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.5"
|
||||
"version": "3.7.13"
|
||||
},
|
||||
"tags": [
|
||||
"Forecasting",
|
||||
@@ -894,5 +931,5 @@
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
@@ -325,7 +325,7 @@
|
||||
"source": [
|
||||
"### Setting forecaster maximum horizon \n",
|
||||
"\n",
|
||||
"The forecast horizon is the number of periods into the future that the model should predict. Here, we set the horizon to 12 periods (i.e. 12 months). Notice that this is much shorter than the number of months in the test set; we will need to use a rolling test to evaluate the performance on the whole test set. For more discussion of forecast horizons and guiding principles for setting them, please see the [energy demand notebook](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand). "
|
||||
"The forecast horizon is the number of periods into the future that the model should predict. Here, we set the horizon to 14 periods (i.e. 14 days). Notice that this is much shorter than the number of months in the test set; we will need to use a rolling test to evaluate the performance on the whole test set. For more discussion of forecast horizons and guiding principles for setting them, please see the [energy demand notebook](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand). "
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -337,7 +337,7 @@
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"forecast_horizon = 12"
|
||||
"forecast_horizon = 14"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -681,9 +681,9 @@
|
||||
],
|
||||
"hide_code_all_hidden": false,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
@@ -699,5 +699,5 @@
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
@@ -4,7 +4,6 @@ import os
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
|
||||
from pandas.tseries.frequencies import to_offset
|
||||
from sklearn.externals import joblib
|
||||
from sklearn.metrics import mean_absolute_error, mean_squared_error
|
||||
|
||||
@@ -19,219 +18,8 @@ except ImportError:
|
||||
_torch_present = False
|
||||
|
||||
|
||||
def align_outputs(
|
||||
y_predicted,
|
||||
X_trans,
|
||||
X_test,
|
||||
y_test,
|
||||
predicted_column_name="predicted",
|
||||
horizon_colname="horizon_origin",
|
||||
):
|
||||
"""
|
||||
Demonstrates how to get the output aligned to the inputs
|
||||
using pandas indexes. Helps understand what happened if
|
||||
the output's shape differs from the input shape, or if
|
||||
the data got re-sorted by time and grain during forecasting.
|
||||
|
||||
Typical causes of misalignment are:
|
||||
* we predicted some periods that were missing in actuals -> drop from eval
|
||||
* model was asked to predict past max_horizon -> increase max horizon
|
||||
* data at start of X_test was needed for lags -> provide previous periods
|
||||
"""
|
||||
if horizon_colname in X_trans:
|
||||
df_fcst = pd.DataFrame(
|
||||
{
|
||||
predicted_column_name: y_predicted,
|
||||
horizon_colname: X_trans[horizon_colname],
|
||||
}
|
||||
)
|
||||
else:
|
||||
df_fcst = pd.DataFrame({predicted_column_name: y_predicted})
|
||||
|
||||
# y and X outputs are aligned by forecast() function contract
|
||||
df_fcst.index = X_trans.index
|
||||
|
||||
# align original X_test to y_test
|
||||
X_test_full = X_test.copy()
|
||||
X_test_full[target_column_name] = y_test
|
||||
|
||||
# X_test_full's index does not include origin, so reset for merge
|
||||
df_fcst.reset_index(inplace=True)
|
||||
X_test_full = X_test_full.reset_index().drop(columns="index")
|
||||
together = df_fcst.merge(X_test_full, how="right")
|
||||
|
||||
# drop rows where prediction or actuals are nan
|
||||
# happens because of missing actuals
|
||||
# or at edges of time due to lags/rolling windows
|
||||
clean = together[
|
||||
together[[target_column_name, predicted_column_name]].notnull().all(axis=1)
|
||||
]
|
||||
return clean
|
||||
|
||||
|
||||
def do_rolling_forecast_with_lookback(
|
||||
fitted_model, X_test, y_test, max_horizon, X_lookback, y_lookback, freq="D"
|
||||
):
|
||||
"""
|
||||
Produce forecasts on a rolling origin over the given test set.
|
||||
|
||||
Each iteration makes a forecast for the next 'max_horizon' periods
|
||||
with respect to the current origin, then advances the origin by the
|
||||
horizon time duration. The prediction context for each forecast is set so
|
||||
that the forecaster uses the actual target values prior to the current
|
||||
origin time for constructing lag features.
|
||||
|
||||
This function returns a concatenated DataFrame of rolling forecasts.
|
||||
"""
|
||||
print("Using lookback of size: ", y_lookback.size)
|
||||
df_list = []
|
||||
origin_time = X_test[time_column_name].min()
|
||||
X = X_lookback.append(X_test)
|
||||
y = np.concatenate((y_lookback, y_test), axis=0)
|
||||
while origin_time <= X_test[time_column_name].max():
|
||||
# Set the horizon time - end date of the forecast
|
||||
horizon_time = origin_time + max_horizon * to_offset(freq)
|
||||
|
||||
# Extract test data from an expanding window up-to the horizon
|
||||
expand_wind = X[time_column_name] < horizon_time
|
||||
X_test_expand = X[expand_wind]
|
||||
y_query_expand = np.zeros(len(X_test_expand)).astype(float)
|
||||
y_query_expand.fill(np.NaN)
|
||||
|
||||
if origin_time != X[time_column_name].min():
|
||||
# Set the context by including actuals up-to the origin time
|
||||
test_context_expand_wind = X[time_column_name] < origin_time
|
||||
context_expand_wind = X_test_expand[time_column_name] < origin_time
|
||||
y_query_expand[context_expand_wind] = y[test_context_expand_wind]
|
||||
|
||||
# Print some debug info
|
||||
print(
|
||||
"Horizon_time:",
|
||||
horizon_time,
|
||||
" origin_time: ",
|
||||
origin_time,
|
||||
" max_horizon: ",
|
||||
max_horizon,
|
||||
" freq: ",
|
||||
freq,
|
||||
)
|
||||
print("expand_wind: ", expand_wind)
|
||||
print("y_query_expand")
|
||||
print(y_query_expand)
|
||||
print("X_test")
|
||||
print(X)
|
||||
print("X_test_expand")
|
||||
print(X_test_expand)
|
||||
print("Type of X_test_expand: ", type(X_test_expand))
|
||||
print("Type of y_query_expand: ", type(y_query_expand))
|
||||
|
||||
print("y_query_expand")
|
||||
print(y_query_expand)
|
||||
|
||||
# Make a forecast out to the maximum horizon
|
||||
# y_fcst, X_trans = y_query_expand, X_test_expand
|
||||
y_fcst, X_trans = fitted_model.forecast(X_test_expand, y_query_expand)
|
||||
|
||||
print("y_fcst")
|
||||
print(y_fcst)
|
||||
|
||||
# Align forecast with test set for dates within
|
||||
# the current rolling window
|
||||
trans_tindex = X_trans.index.get_level_values(time_column_name)
|
||||
trans_roll_wind = (trans_tindex >= origin_time) & (trans_tindex < horizon_time)
|
||||
test_roll_wind = expand_wind & (X[time_column_name] >= origin_time)
|
||||
df_list.append(
|
||||
align_outputs(
|
||||
y_fcst[trans_roll_wind],
|
||||
X_trans[trans_roll_wind],
|
||||
X[test_roll_wind],
|
||||
y[test_roll_wind],
|
||||
)
|
||||
)
|
||||
|
||||
# Advance the origin time
|
||||
origin_time = horizon_time
|
||||
|
||||
return pd.concat(df_list, ignore_index=True)
|
||||
|
||||
|
||||
def do_rolling_forecast(fitted_model, X_test, y_test, max_horizon, freq="D"):
|
||||
"""
|
||||
Produce forecasts on a rolling origin over the given test set.
|
||||
|
||||
Each iteration makes a forecast for the next 'max_horizon' periods
|
||||
with respect to the current origin, then advances the origin by the
|
||||
horizon time duration. The prediction context for each forecast is set so
|
||||
that the forecaster uses the actual target values prior to the current
|
||||
origin time for constructing lag features.
|
||||
|
||||
This function returns a concatenated DataFrame of rolling forecasts.
|
||||
"""
|
||||
df_list = []
|
||||
origin_time = X_test[time_column_name].min()
|
||||
while origin_time <= X_test[time_column_name].max():
|
||||
# Set the horizon time - end date of the forecast
|
||||
horizon_time = origin_time + max_horizon * to_offset(freq)
|
||||
|
||||
# Extract test data from an expanding window up-to the horizon
|
||||
expand_wind = X_test[time_column_name] < horizon_time
|
||||
X_test_expand = X_test[expand_wind]
|
||||
y_query_expand = np.zeros(len(X_test_expand)).astype(float)
|
||||
y_query_expand.fill(np.NaN)
|
||||
|
||||
if origin_time != X_test[time_column_name].min():
|
||||
# Set the context by including actuals up-to the origin time
|
||||
test_context_expand_wind = X_test[time_column_name] < origin_time
|
||||
context_expand_wind = X_test_expand[time_column_name] < origin_time
|
||||
y_query_expand[context_expand_wind] = y_test[test_context_expand_wind]
|
||||
|
||||
# Print some debug info
|
||||
print(
|
||||
"Horizon_time:",
|
||||
horizon_time,
|
||||
" origin_time: ",
|
||||
origin_time,
|
||||
" max_horizon: ",
|
||||
max_horizon,
|
||||
" freq: ",
|
||||
freq,
|
||||
)
|
||||
print("expand_wind: ", expand_wind)
|
||||
print("y_query_expand")
|
||||
print(y_query_expand)
|
||||
print("X_test")
|
||||
print(X_test)
|
||||
print("X_test_expand")
|
||||
print(X_test_expand)
|
||||
print("Type of X_test_expand: ", type(X_test_expand))
|
||||
print("Type of y_query_expand: ", type(y_query_expand))
|
||||
print("y_query_expand")
|
||||
print(y_query_expand)
|
||||
|
||||
# Make a forecast out to the maximum horizon
|
||||
y_fcst, X_trans = fitted_model.forecast(X_test_expand, y_query_expand)
|
||||
|
||||
print("y_fcst")
|
||||
print(y_fcst)
|
||||
|
||||
# Align forecast with test set for dates within the
|
||||
# current rolling window
|
||||
trans_tindex = X_trans.index.get_level_values(time_column_name)
|
||||
trans_roll_wind = (trans_tindex >= origin_time) & (trans_tindex < horizon_time)
|
||||
test_roll_wind = expand_wind & (X_test[time_column_name] >= origin_time)
|
||||
df_list.append(
|
||||
align_outputs(
|
||||
y_fcst[trans_roll_wind],
|
||||
X_trans[trans_roll_wind],
|
||||
X_test[test_roll_wind],
|
||||
y_test[test_roll_wind],
|
||||
)
|
||||
)
|
||||
|
||||
# Advance the origin time
|
||||
origin_time = horizon_time
|
||||
|
||||
return pd.concat(df_list, ignore_index=True)
|
||||
def map_location_cuda(storage, loc):
|
||||
return storage.cuda()
|
||||
|
||||
|
||||
def APE(actual, pred):
|
||||
@@ -254,10 +42,6 @@ def MAPE(actual, pred):
|
||||
return np.mean(APE(actual_safe, pred_safe))
|
||||
|
||||
|
||||
def map_location_cuda(storage, loc):
|
||||
return storage.cuda()
|
||||
|
||||
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument(
|
||||
"--max_horizon",
|
||||
@@ -303,7 +87,6 @@ print(model_path)
|
||||
run = Run.get_context()
|
||||
# get input dataset by name
|
||||
test_dataset = run.input_datasets["test_data"]
|
||||
lookback_dataset = run.input_datasets["lookback_data"]
|
||||
|
||||
grain_column_names = []
|
||||
|
||||
@@ -312,15 +95,8 @@ df = test_dataset.to_pandas_dataframe()
|
||||
print("Read df")
|
||||
print(df)
|
||||
|
||||
X_test_df = test_dataset.drop_columns(columns=[target_column_name])
|
||||
y_test_df = test_dataset.with_timestamp_columns(None).keep_columns(
|
||||
columns=[target_column_name]
|
||||
)
|
||||
|
||||
X_lookback_df = lookback_dataset.drop_columns(columns=[target_column_name])
|
||||
y_lookback_df = lookback_dataset.with_timestamp_columns(None).keep_columns(
|
||||
columns=[target_column_name]
|
||||
)
|
||||
X_test_df = df
|
||||
y_test = df.pop(target_column_name).to_numpy()
|
||||
|
||||
_, ext = os.path.splitext(model_path)
|
||||
if ext == ".pt":
|
||||
@@ -336,37 +112,20 @@ else:
|
||||
# Load the sklearn pipeline.
|
||||
fitted_model = joblib.load(model_path)
|
||||
|
||||
if hasattr(fitted_model, "get_lookback"):
|
||||
lookback = fitted_model.get_lookback()
|
||||
df_all = do_rolling_forecast_with_lookback(
|
||||
fitted_model,
|
||||
X_test_df.to_pandas_dataframe(),
|
||||
y_test_df.to_pandas_dataframe().values.T[0],
|
||||
max_horizon,
|
||||
X_lookback_df.to_pandas_dataframe()[-lookback:],
|
||||
y_lookback_df.to_pandas_dataframe().values.T[0][-lookback:],
|
||||
freq,
|
||||
)
|
||||
else:
|
||||
df_all = do_rolling_forecast(
|
||||
fitted_model,
|
||||
X_test_df.to_pandas_dataframe(),
|
||||
y_test_df.to_pandas_dataframe().values.T[0],
|
||||
max_horizon,
|
||||
freq,
|
||||
)
|
||||
X_rf = fitted_model.rolling_forecast(X_test_df, y_test, step=1)
|
||||
assign_dict = {
|
||||
fitted_model.forecast_origin_column_name: "forecast_origin",
|
||||
fitted_model.forecast_column_name: "predicted",
|
||||
fitted_model.actual_column_name: target_column_name,
|
||||
}
|
||||
X_rf.rename(columns=assign_dict, inplace=True)
|
||||
|
||||
print(df_all)
|
||||
|
||||
print("target values:::")
|
||||
print(df_all[target_column_name])
|
||||
print("predicted values:::")
|
||||
print(df_all["predicted"])
|
||||
print(X_rf.head())
|
||||
|
||||
# Use the AutoML scoring module
|
||||
regression_metrics = list(constants.REGRESSION_SCALAR_SET)
|
||||
y_test = np.array(df_all[target_column_name])
|
||||
y_pred = np.array(df_all["predicted"])
|
||||
y_test = np.array(X_rf[target_column_name])
|
||||
y_pred = np.array(X_rf["predicted"])
|
||||
scores = scoring.score_regression(y_test, y_pred, regression_metrics)
|
||||
|
||||
print("scores:")
|
||||
@@ -376,11 +135,11 @@ for key, value in scores.items():
|
||||
run.log(key, value)
|
||||
|
||||
print("Simple forecasting model")
|
||||
rmse = np.sqrt(mean_squared_error(df_all[target_column_name], df_all["predicted"]))
|
||||
rmse = np.sqrt(mean_squared_error(X_rf[target_column_name], X_rf["predicted"]))
|
||||
print("[Test Data] \nRoot Mean squared error: %.2f" % rmse)
|
||||
mae = mean_absolute_error(df_all[target_column_name], df_all["predicted"])
|
||||
mae = mean_absolute_error(X_rf[target_column_name], X_rf["predicted"])
|
||||
print("mean_absolute_error score: %.2f" % mae)
|
||||
print("MAPE: %.2f" % MAPE(df_all[target_column_name], df_all["predicted"]))
|
||||
print("MAPE: %.2f" % MAPE(X_rf[target_column_name], X_rf["predicted"]))
|
||||
|
||||
run.log("rmse", rmse)
|
||||
run.log("mae", mae)
|
||||
|
||||
@@ -365,6 +365,7 @@
|
||||
" node_count=2,\n",
|
||||
" process_count_per_node=8,\n",
|
||||
" train_pipeline_parameters=hts_parameters,\n",
|
||||
" run_invocation_timeout=3900,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
@@ -620,9 +621,9 @@
|
||||
"automated-machine-learning"
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
@@ -634,7 +635,12 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.8"
|
||||
"version": "3.7.13"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "6db9c8d9f0cce2d9127e384e15560d42c3b661994c9f717d0553d1d8985ab1ea"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -517,7 +517,7 @@
|
||||
" compute_target=compute_target,\n",
|
||||
" node_count=2,\n",
|
||||
" process_count_per_node=8,\n",
|
||||
" run_invocation_timeout=920,\n",
|
||||
" run_invocation_timeout=1200,\n",
|
||||
" train_pipeline_parameters=mm_paramters,\n",
|
||||
")"
|
||||
]
|
||||
@@ -837,9 +837,9 @@
|
||||
"automated-machine-learning"
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
|
Before Width: | Height: | Size: 2.6 MiB After Width: | Height: | Size: 2.6 MiB |
@@ -821,9 +821,9 @@
|
||||
"friendly_name": "Forecasting orange juice sales with deployment",
|
||||
"index_order": 1,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -799,9 +799,9 @@
|
||||
"friendly_name": "Forecasting orange juice sales with deployment",
|
||||
"index_order": 1,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -472,9 +472,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -572,9 +572,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -870,9 +870,9 @@
|
||||
"friendly_name": "Classification of credit card fraudulent transactions using Automated ML",
|
||||
"index_order": 5,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -895,9 +895,9 @@
|
||||
"friendly_name": "Automated ML run with featurization and model explainability.",
|
||||
"index_order": 5,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -449,9 +449,9 @@
|
||||
"automated-machine-learning"
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -429,9 +429,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -557,9 +557,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -161,9 +161,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -215,9 +215,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -482,9 +482,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -302,9 +302,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -86,7 +86,7 @@
|
||||
"source": [
|
||||
"In this example, we will be using and registering two models. \n",
|
||||
"\n",
|
||||
"First we will train two simple models on the [diabetes dataset](https://scikit-learn.org/stable/datasets/index.html#diabetes-dataset) included with scikit-learn, serializing them to files in the current directory."
|
||||
"First we will train two simple models on the [diabetes dataset](https://scikit-learn.org/stable/datasets/toy_dataset.html#diabetes-dataset) included with scikit-learn, serializing them to files in the current directory."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -373,9 +373,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -541,7 +541,7 @@
|
||||
" - To run a local web service, see the [notebook on deployment to a local Docker container](../deploy-to-local/register-model-deploy-local.ipynb).\n",
|
||||
" - For more information on datasets, see the [notebook on training with datasets](../../work-with-data/datasets-tutorial/train-with-datasets/train-with-datasets.ipynb).\n",
|
||||
" - For more information on environments, see the [notebook on using environments](../../training/using-environments/using-environments.ipynb).\n",
|
||||
" - For information on all the available deployment targets, see [“How and where to deploy models”](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-deploy-and-where#choose-a-compute-target)."
|
||||
" - For information on all the available deployment targets, see [“How and where to deploy models”](https://docs.microsoft.com/azure/machine-learning/v1/how-to-deploy-and-where#choose-a-compute-target)."
|
||||
]
|
||||
}
|
||||
],
|
||||
@@ -568,9 +568,9 @@
|
||||
"friendly_name": "Register model and deploy as webservice",
|
||||
"index_order": 3,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -473,9 +473,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -529,9 +529,9 @@
|
||||
"friendly_name": "Register a model and deploy locally",
|
||||
"index_order": 1,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -344,9 +344,9 @@
|
||||
"friendly_name": "Deploy models to AKS using controlled roll out",
|
||||
"index_order": 3,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -476,9 +476,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -405,9 +405,9 @@
|
||||
"friendly_name": "Convert and deploy TinyYolo with ONNX Runtime",
|
||||
"index_order": 5,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -773,9 +773,9 @@
|
||||
"friendly_name": "Deploy Facial Expression Recognition (FER+) with ONNX Runtime",
|
||||
"index_order": 2,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -750,9 +750,9 @@
|
||||
"friendly_name": "Deploy MNIST digit recognition with ONNX Runtime",
|
||||
"index_order": 1,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -206,9 +206,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -389,9 +389,9 @@
|
||||
"friendly_name": "Deploy ResNet50 with ONNX Runtime",
|
||||
"index_order": 4,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -564,9 +564,9 @@
|
||||
"friendly_name": "Train MNIST in PyTorch, convert, and deploy with ONNX Runtime",
|
||||
"index_order": 3,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -329,9 +329,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -213,7 +213,7 @@
|
||||
"\n",
|
||||
"> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
|
||||
"\n",
|
||||
"See code snippet below. Check the documentation [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-secure-web-service) for more details"
|
||||
"See code snippet below. Check the documentation [here](https://docs.microsoft.com/azure/machine-learning/v1/how-to-secure-web-service) for more details"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -334,9 +334,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -366,7 +366,7 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Create AKS Cluster in an existing virtual network (optional)\n",
|
||||
"See code snippet below. Check the documentation [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-enable-virtual-network#use-azure-kubernetes-service) for more details."
|
||||
"See code snippet below. Check the documentation [here](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-network-security-overview) for more details."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -397,7 +397,7 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Enable SSL on the AKS Cluster (optional)\n",
|
||||
"See code snippet below. Check the documentation [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-secure-web-service) for more details"
|
||||
"See code snippet below. Check the documentation [here](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-network-security-overview#secure-the-inferencing-environment-v1) for more details"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -603,9 +603,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -327,9 +327,9 @@
|
||||
],
|
||||
"friendly_name": "Register Spark model and deploy as webservice",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -106,7 +106,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"This notebook was created using version 1.45.0 of the Azure ML SDK\")\n",
|
||||
"print(\"This notebook was created using version 1.47.0 of the Azure ML SDK\")\n",
|
||||
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
|
||||
]
|
||||
},
|
||||
@@ -241,6 +241,8 @@
|
||||
"for dist in list(available_packages):\n",
|
||||
" if dist.key == 'pandas':\n",
|
||||
" pandas_ver = dist.version\n",
|
||||
" if dist.key == 'numpy':\n",
|
||||
" numpy_ver = dist.version\n",
|
||||
"pandas_dep = 'pandas'\n",
|
||||
"numpy_dep = 'numpy'\n",
|
||||
"if pandas_ver:\n",
|
||||
@@ -286,7 +288,7 @@
|
||||
"pip uninstall -y xgboost && \\\n",
|
||||
"conda install py-xgboost==1.3.3 && \\\n",
|
||||
"pip uninstall -y numpy && \\\n",
|
||||
"conda install {numpy_dep} \\\n",
|
||||
"pip install {numpy_dep} \\\n",
|
||||
"\"\"\"\n",
|
||||
"\n",
|
||||
"env.python.user_managed_dependencies = True\n",
|
||||
@@ -481,9 +483,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -10,7 +10,7 @@ dependencies:
|
||||
- ipython
|
||||
- matplotlib
|
||||
- ipywidgets
|
||||
- raiwidgets~=0.21.0
|
||||
- raiwidgets~=0.22.0
|
||||
- itsdangerous==2.0.1
|
||||
- markupsafe<2.1.0
|
||||
- scipy>=1.5.3
|
||||
|
||||
@@ -496,9 +496,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -10,7 +10,7 @@ dependencies:
|
||||
- matplotlib
|
||||
- azureml-dataset-runtime
|
||||
- ipywidgets
|
||||
- raiwidgets~=0.21.0
|
||||
- raiwidgets~=0.22.0
|
||||
- itsdangerous==2.0.1
|
||||
- markupsafe<2.1.0
|
||||
- scipy>=1.5.3
|
||||
|
||||
@@ -595,9 +595,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -9,7 +9,7 @@ dependencies:
|
||||
- ipython
|
||||
- matplotlib
|
||||
- ipywidgets
|
||||
- raiwidgets~=0.21.0
|
||||
- raiwidgets~=0.22.0
|
||||
- packaging>=20.9
|
||||
- itsdangerous==2.0.1
|
||||
- markupsafe<2.1.0
|
||||
|
||||
@@ -516,9 +516,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -9,7 +9,7 @@ dependencies:
|
||||
- ipython
|
||||
- matplotlib
|
||||
- ipywidgets
|
||||
- raiwidgets~=0.21.0
|
||||
- raiwidgets~=0.22.0
|
||||
- packaging>=20.9
|
||||
- itsdangerous==2.0.1
|
||||
- markupsafe<2.1.0
|
||||
|
||||
@@ -576,9 +576,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -11,7 +11,7 @@ dependencies:
|
||||
- azureml-dataset-runtime
|
||||
- azureml-core
|
||||
- ipywidgets
|
||||
- raiwidgets~=0.21.0
|
||||
- raiwidgets~=0.22.0
|
||||
- itsdangerous==2.0.1
|
||||
- markupsafe<2.1.0
|
||||
- scipy>=1.5.3
|
||||
|
||||
@@ -579,9 +579,9 @@
|
||||
],
|
||||
"friendly_name": "Azure Machine Learning Pipeline with DataTranferStep",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -632,9 +632,9 @@
|
||||
],
|
||||
"friendly_name": "Getting Started with Azure Machine Learning Pipelines",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -384,9 +384,9 @@
|
||||
],
|
||||
"friendly_name": "Azure Machine Learning Pipeline with AzureBatchStep",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -470,9 +470,9 @@
|
||||
],
|
||||
"friendly_name": "How to use ModuleStep with AML Pipelines",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -261,9 +261,9 @@
|
||||
],
|
||||
"friendly_name": "How to use Pipeline Drafts to create a Published Pipeline",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -292,7 +292,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tf_env = Environment.get(ws, name='AzureML-TensorFlow-2.0-GPU')"
|
||||
"tf_env = Environment.get(ws, name='AzureML-tensorflow-2.6-ubuntu20.04-py38-cuda11-gpu')"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -595,9 +595,9 @@
|
||||
],
|
||||
"friendly_name": "Azure Machine Learning Pipeline with HyperDriveStep",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -443,9 +443,9 @@
|
||||
],
|
||||
"friendly_name": "How to Publish a Pipeline and Invoke the REST endpoint",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -432,7 +432,7 @@
|
||||
"This schedule will run when additions or modifications are made to Blobs in the Datastore.\n",
|
||||
"By default, the Datastore container is monitored for changes. Use the path_on_datastore parameter to instead specify a path on the Datastore to monitor for changes. Note: the path_on_datastore will be under the container for the datastore, so the actual path monitored will be container/path_on_datastore. Changes made to subfolders in the container/path will not trigger the schedule.\n",
|
||||
"Note: Only Blob Datastores are supported.\n",
|
||||
"Note: Not supported for CMK workspaces. Please review these [instructions](https://docs.microsoft.com/azure/machine-learning/how-to-trigger-published-pipeline) in order to setup a blob trigger submission schedule with CMK enabled. Also see those instructions to bring your own LogicApp to avoid the schedule triggers per month limit."
|
||||
"Note: Not supported for CMK workspaces. Please review these [instructions](https://docs.microsoft.com/azure/machine-learning/v1/how-to-trigger-published-pipeline) in order to setup a blob trigger submission schedule with CMK enabled. Also see those instructions to bring your own LogicApp to avoid the schedule triggers per month limit."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -637,9 +637,9 @@
|
||||
],
|
||||
"friendly_name": "How to Setup a Schedule for a Published Pipeline or Pipeline Endpoint",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -581,9 +581,9 @@
|
||||
],
|
||||
"friendly_name": "How to setup a versioned Pipeline Endpoint",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -500,9 +500,9 @@
|
||||
],
|
||||
"friendly_name": "How to use DataPath as a PipelineParameter",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -496,9 +496,9 @@
|
||||
],
|
||||
"friendly_name": "How to use Dataset as a PipelineParameter",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -377,9 +377,9 @@
|
||||
],
|
||||
"friendly_name": "How to use AdlaStep with AML Pipelines",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -20,7 +20,7 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Using Databricks as a Compute Target from Azure Machine Learning Pipeline\n",
|
||||
"To use Databricks as a compute target from [Azure Machine Learning Pipeline](https://aka.ms/pl-concept), a [DatabricksStep](https://docs.microsoft.com/en-us/python/api/azureml-pipeline-steps/azureml.pipeline.steps.databricks_step.databricksstep?view=azure-ml-py) is used. This notebook demonstrates the use of DatabricksStep in Azure Machine Learning Pipeline.\n",
|
||||
"To use Databricks as a compute target from [Azure Machine Learning Pipeline](https://aka.ms/pl-concept), a [DatabricksStep](https://docs.microsoft.com/python/api/azureml-pipeline-steps/azureml.pipeline.steps.databricks_step.databricksstep?view=azure-ml-py) is used. This notebook demonstrates the use of DatabricksStep in Azure Machine Learning Pipeline.\n",
|
||||
"\n",
|
||||
"The notebook will show:\n",
|
||||
"1. Running an arbitrary Databricks notebook that the customer has in Databricks workspace\n",
|
||||
@@ -180,10 +180,9 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Data Connections with Inputs and Outputs\n",
|
||||
"The DatabricksStep supports DBFS, Azure Blob and ADLS for inputs and outputs. You also will need to define a [Secrets](https://docs.azuredatabricks.net/user-guide/secrets/index.html) scope to enable authentication to external data sources such as Blob and ADLS from Databricks.\n",
|
||||
"The DatabricksStep supports DBFS, Azure Blob and ADLS for inputs and outputs. You also will need to define a [Secrets](https://docs.microsoft.com/azure/databricks/security/access-control/secret-acl) scope to enable authentication to external data sources such as Blob and ADLS from Databricks.\n",
|
||||
"\n",
|
||||
"- Databricks documentation on [Azure Blob](https://docs.azuredatabricks.net/spark/latest/data-sources/azure/azure-storage.html)\n",
|
||||
"- Databricks documentation on [ADLS](https://docs.databricks.com/spark/latest/data-sources/azure/azure-datalake.html)\n",
|
||||
"- Databricks documentation on [Azure Storage](https://docs.microsoft.com/azure/databricks/data/data-sources/azure/azure-storage)\n",
|
||||
"\n",
|
||||
"### Type of Data Access\n",
|
||||
"Databricks allows to interact with Azure Blob and ADLS in two ways.\n",
|
||||
@@ -415,7 +414,7 @@
|
||||
"### 1. Running the demo notebook already added to the Databricks workspace\n",
|
||||
"Create a notebook in the Azure Databricks workspace, and provide the path to that notebook as the value associated with the environment variable \"DATABRICKS_NOTEBOOK_PATH\". This will then set the variable\u00c2\u00a0notebook_path\u00c2\u00a0when you run the code cell below:\n",
|
||||
"\n",
|
||||
"your notebook's path in Azure Databricks UI by hovering over to notebook's title. A typical path of notebook looks like this `/Users/example@databricks.com/example`. See [Databricks Workspace](https://docs.azuredatabricks.net/user-guide/workspace.html) to learn about the folder structure.\n",
|
||||
"your notebook's path in Azure Databricks UI by hovering over to notebook's title. A typical path of notebook looks like this `/Users/example@databricks.com/example`. See [Databricks Workspace](https://docs.microsoft.com/azure/databricks/workspace) to learn about the folder structure.\n",
|
||||
"\n",
|
||||
"Note: DataPath `PipelineParameter` should be provided in list of inputs. Such parameters can be accessed by the datapath `name`."
|
||||
]
|
||||
@@ -487,7 +486,7 @@
|
||||
"### 2. Running a Python script from DBFS\n",
|
||||
"This shows how to run a Python script in DBFS. \n",
|
||||
"\n",
|
||||
"To complete this, you will need to first upload the Python script in your local machine to DBFS using the [CLI](https://docs.azuredatabricks.net/user-guide/dbfs-databricks-file-system.html). The CLI command is given below:\n",
|
||||
"To complete this, you will need to first upload the Python script in your local machine to DBFS using the [CLI](https://docs.microsoft.com/azure/databricks/dbfs). The CLI command is given below:\n",
|
||||
"\n",
|
||||
"```\n",
|
||||
"dbfs cp ./train-db-dbfs.py dbfs:/train-db-dbfs.py\n",
|
||||
@@ -630,7 +629,7 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 4. Running a JAR job that is alreay added in DBFS\n",
|
||||
"To run a JAR job that is already uploaded to DBFS, follow the instructions below. You will first upload the JAR file to DBFS using the [CLI](https://docs.azuredatabricks.net/user-guide/dbfs-databricks-file-system.html).\n",
|
||||
"To run a JAR job that is already uploaded to DBFS, follow the instructions below. You will first upload the JAR file to DBFS using the [CLI](https://docs.microsoft.com/azure/databricks/dbfs).\n",
|
||||
"\n",
|
||||
"The commented out code in the below cell assumes that you have uploaded `train-db-dbfs.jar` to the root folder in DBFS. You can upload `train-db-dbfs.jar` to the root folder in DBFS using this commandline so you can use `jar_library_dbfs_path = \"dbfs:/train-db-dbfs.jar\"`:\n",
|
||||
"\n",
|
||||
@@ -704,7 +703,7 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 5. Running demo notebook already added to the Databricks workspace using existing cluster\n",
|
||||
"First you need register DBFS datastore and make sure path_on_datastore does exist in databricks file system, you can browser the files by refering [this](https://docs.azuredatabricks.net/user-guide/dbfs-databricks-file-system.html).\n",
|
||||
"First you need register DBFS datastore and make sure path_on_datastore does exist in databricks file system, you can browser the files by refering [this](https://docs.microsoft.com/azure/databricks/dbfs).\n",
|
||||
"\n",
|
||||
"Find existing_cluster_id by opeing Azure Databricks UI with Clusters page and in url you will find a string connected with '-' right after \"clusters/\"."
|
||||
]
|
||||
@@ -941,9 +940,9 @@
|
||||
],
|
||||
"friendly_name": "How to use DatabricksStep with AML Pipelines",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -244,9 +244,9 @@
|
||||
],
|
||||
"friendly_name": "How to use KustoStep with AML Pipelines",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -498,9 +498,9 @@
|
||||
],
|
||||
"friendly_name": "How to use AutoMLStep with AML Pipelines",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -315,9 +315,9 @@
|
||||
],
|
||||
"friendly_name": "Azure Machine Learning Pipeline with CommandStep for R",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -278,9 +278,9 @@
|
||||
],
|
||||
"friendly_name": "Azure Machine Learning Pipeline with CommandStep",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -545,9 +545,9 @@
|
||||
],
|
||||
"friendly_name": "Azure Machine Learning Pipelines with Data Dependency",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -409,9 +409,9 @@
|
||||
],
|
||||
"friendly_name": "How to use run a notebook as a step in AML Pipelines",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -84,9 +84,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -1046,9 +1046,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -24,7 +24,7 @@
|
||||
"In this notebook, we will demonstrate how to make predictions on large quantities of data asynchronously using the ML pipelines with Azure Machine Learning. Batch inference (or batch scoring) provides cost-effective inference, with unparalleled throughput for asynchronous applications. Batch prediction pipelines can scale to perform inference on terabytes of production data. Batch prediction is optimized for high throughput, fire-and-forget predictions for a large collection of data.\n",
|
||||
"\n",
|
||||
"> **Tip**\n",
|
||||
"If your system requires low-latency processing (to process a single document or small set of documents quickly), use [real-time scoring](https://docs.microsoft.com/azure/machine-learning/service/how-to-consume-web-service) instead of batch prediction.\n",
|
||||
"If your system requires low-latency processing (to process a single document or small set of documents quickly), use [real-time scoring](https://docs.microsoft.com/azure/machine-learning/v1/how-to-consume-web-service) instead of batch prediction.\n",
|
||||
"\n",
|
||||
"In this example will be take a digit identification model already-trained on MNIST dataset using the [AzureML training with deep learning example notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/ml-frameworks/keras/train-hyperparameter-tune-deploy-with-keras/train-hyperparameter-tune-deploy-with-keras.ipynb), and run that trained model on some of the MNIST test images in batch. \n",
|
||||
"\n",
|
||||
@@ -277,7 +277,7 @@
|
||||
"### Register the model with Workspace\n",
|
||||
"A registered model is a logical container for one or more files that make up your model. For example, if you have a model that's stored in multiple files, you can register them as a single model in the workspace. After you register the files, you can then download or deploy the registered model and receive all the files that you registered.\n",
|
||||
"\n",
|
||||
"Using tags, you can track useful information such as the name and version of the machine learning library used to train the model. Note that tags must be alphanumeric. Learn more about registering models [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-deploy-and-where#registermodel) "
|
||||
"Using tags, you can track useful information such as the name and version of the machine learning library used to train the model. Note that tags must be alphanumeric. Learn more about registering models [here](https://docs.microsoft.com/azure/machine-learning/v1/how-to-deploy-and-where#registermodel) "
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -581,16 +581,7 @@
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "joringer"
|
||||
},
|
||||
{
|
||||
"name": "asraniwa"
|
||||
},
|
||||
{
|
||||
"name": "pansav"
|
||||
},
|
||||
{
|
||||
"name": "tracych"
|
||||
"name": "prsbjdev"
|
||||
}
|
||||
],
|
||||
"category": "Other notebooks",
|
||||
@@ -610,9 +601,9 @@
|
||||
"friendly_name": "MNIST data inferencing using ParallelRunStep",
|
||||
"index_order": 1,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -24,7 +24,7 @@
|
||||
"In this notebook, we will demonstrate how to make predictions on large quantities of data asynchronously using the ML pipelines with Azure Machine Learning. Batch inference (or batch scoring) provides cost-effective inference, with unparalleled throughput for asynchronous applications. Batch prediction pipelines can scale to perform inference on terabytes of production data. Batch prediction is optimized for high throughput, fire-and-forget predictions for a large collection of data.\n",
|
||||
"\n",
|
||||
"> **Tip**\n",
|
||||
"If your system requires low-latency processing (to process a single document or small set of documents quickly), use [real-time scoring](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-consume-web-service) instead of batch prediction.\n",
|
||||
"If your system requires low-latency processing (to process a single document or small set of documents quickly), use [real-time scoring](https://docs.microsoft.com/en-us/azure/machine-learning/v1/how-to-consume-web-service) instead of batch prediction.\n",
|
||||
"\n",
|
||||
"This example will create a sample dataset with nested folder structure, where the folder name corresponds to the attribute of the files inside it. The Batch Inference job would split the files inside the dataset according to their attributes, so that all files with identical value on the specified attribute will form up a single mini-batch to be processed.\n",
|
||||
"\n",
|
||||
@@ -356,13 +356,7 @@
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "pansav"
|
||||
},
|
||||
{
|
||||
"name": "tracych"
|
||||
},
|
||||
{
|
||||
"name": "migu"
|
||||
"name": "prsbjdev"
|
||||
}
|
||||
],
|
||||
"category": "Other notebooks",
|
||||
@@ -382,9 +376,9 @@
|
||||
"friendly_name": "Batch inferencing file data partitioned by folder using ParallelRunStep",
|
||||
"index_order": 1,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -24,7 +24,7 @@
|
||||
"In this notebook, we will demonstrate how to make predictions on large quantities of data asynchronously using the ML pipelines with Azure Machine Learning. Batch inference (or batch scoring) provides cost-effective inference, with unparalleled throughput for asynchronous applications. Batch prediction pipelines can scale to perform inference on terabytes of production data. Batch prediction is optimized for high throughput, fire-and-forget predictions for a large collection of data.\n",
|
||||
"\n",
|
||||
"> **Tip**\n",
|
||||
"If your system requires low-latency processing (to process a single document or small set of documents quickly), use [real-time scoring](https://docs.microsoft.com/azure/machine-learning/service/how-to-consume-web-service) instead of batch prediction.\n",
|
||||
"If your system requires low-latency processing (to process a single document or small set of documents quickly), use [real-time scoring](https://docs.microsoft.com/azure/machine-learning/v1/how-to-consume-web-service) instead of batch prediction.\n",
|
||||
"\n",
|
||||
"In this example we will take use a machine learning model already trained to predict different types of iris flowers and run that trained model on some of the data in a CSV file which has characteristics of different iris flowers. However, the same example can be extended to manipulating data to any embarrassingly-parallel processing through a python script.\n",
|
||||
"\n",
|
||||
@@ -487,16 +487,7 @@
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "joringer"
|
||||
},
|
||||
{
|
||||
"name": "asraniwa"
|
||||
},
|
||||
{
|
||||
"name": "pansav"
|
||||
},
|
||||
{
|
||||
"name": "tracych"
|
||||
"name": "prsbjdev"
|
||||
}
|
||||
],
|
||||
"category": "Other notebooks",
|
||||
@@ -516,9 +507,9 @@
|
||||
"friendly_name": "IRIS data inferencing using ParallelRunStep",
|
||||
"index_order": 1,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -24,7 +24,7 @@
|
||||
"In this notebook, we will demonstrate how to make predictions on large quantities of data asynchronously using the ML pipelines with Azure Machine Learning. Batch inference (or batch scoring) provides cost-effective inference, with unparalleled throughput for asynchronous applications. Batch prediction pipelines can scale to perform inference on terabytes of production data. Batch prediction is optimized for high throughput, fire-and-forget predictions for a large collection of data.\n",
|
||||
"\n",
|
||||
"> **Tip**\n",
|
||||
"If your system requires low-latency processing (to process a single document or small set of documents quickly), use [real-time scoring](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-consume-web-service) instead of batch prediction.\n",
|
||||
"If your system requires low-latency processing (to process a single document or small set of documents quickly), use [real-time scoring](https://docs.microsoft.com/en-us/azure/machine-learning/v1/how-to-consume-web-service) instead of batch prediction.\n",
|
||||
"\n",
|
||||
"This example will create a partitioned tabular dataset by splitting the rows in a large csv file by its value on specified column. Each partition will form up a mini-batch in the parallel processing procedure.\n",
|
||||
"\n",
|
||||
@@ -379,13 +379,7 @@
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "pansav"
|
||||
},
|
||||
{
|
||||
"name": "tracych"
|
||||
},
|
||||
{
|
||||
"name": "migu"
|
||||
"name": "prsbjdev"
|
||||
}
|
||||
],
|
||||
"category": "Other notebooks",
|
||||
@@ -405,9 +399,9 @@
|
||||
"friendly_name": "Batch inferencing OJ Sales Data partitioned by column using ParallelRunStep",
|
||||
"index_order": 1,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -27,7 +27,7 @@
|
||||
"3. Stitch the image back into a video.\n",
|
||||
"\n",
|
||||
"> **Tip**\n",
|
||||
"If your system requires low-latency processing (to process a single document or small set of documents quickly), use [real-time scoring](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-consume-web-service) instead of batch prediction."
|
||||
"If your system requires low-latency processing (to process a single document or small set of documents quickly), use [real-time scoring](https://docs.microsoft.com/en-us/azure/machine-learning/v1/how-to-consume-web-service) instead of batch prediction."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -726,9 +726,9 @@
|
||||
"friendly_name": "Style transfer using ParallelRunStep",
|
||||
"index_order": 1,
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
@@ -521,9 +521,9 @@
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"display_name": "Python 3.8 - AzureML",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"name": "python38-azureml"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user