mirror of
https://github.com/Azure/MachineLearningNotebooks.git
synced 2025-12-21 10:05:09 -05:00
Compare commits
10 Commits
azureml-sd
...
azureml-sd
| Author | SHA1 | Date | |
|---|---|---|---|
|
badb620261 | ||
|
|
acf46100ae | ||
|
|
cf2e3804d5 | ||
|
|
b7be42357f | ||
|
|
3ac82c07ae | ||
|
|
9743c0a1fa | ||
|
|
ba4dac530e | ||
|
|
7f7f0040fd | ||
|
|
9ca567cd9c | ||
|
|
e0c9376aab |
41
SECURITY.md
Normal file
41
SECURITY.md
Normal file
@@ -0,0 +1,41 @@
|
||||
<!-- BEGIN MICROSOFT SECURITY.MD V0.0.7 BLOCK -->
|
||||
|
||||
## Security
|
||||
|
||||
Microsoft takes the security of our software products and services seriously, which includes all source code repositories managed through our GitHub organizations, which include [Microsoft](https://github.com/Microsoft), [Azure](https://github.com/Azure), [DotNet](https://github.com/dotnet), [AspNet](https://github.com/aspnet), [Xamarin](https://github.com/xamarin), and [our GitHub organizations](https://opensource.microsoft.com/).
|
||||
|
||||
If you believe you have found a security vulnerability in any Microsoft-owned repository that meets [Microsoft's definition of a security vulnerability](https://aka.ms/opensource/security/definition), please report it to us as described below.
|
||||
|
||||
## Reporting Security Issues
|
||||
|
||||
**Please do not report security vulnerabilities through public GitHub issues.**
|
||||
|
||||
Instead, please report them to the Microsoft Security Response Center (MSRC) at [https://msrc.microsoft.com/create-report](https://aka.ms/opensource/security/create-report).
|
||||
|
||||
If you prefer to submit without logging in, send email to [secure@microsoft.com](mailto:secure@microsoft.com). If possible, encrypt your message with our PGP key; please download it from the [Microsoft Security Response Center PGP Key page](https://aka.ms/opensource/security/pgpkey).
|
||||
|
||||
You should receive a response within 24 hours. If for some reason you do not, please follow up via email to ensure we received your original message. Additional information can be found at [microsoft.com/msrc](https://aka.ms/opensource/security/msrc).
|
||||
|
||||
Please include the requested information listed below (as much as you can provide) to help us better understand the nature and scope of the possible issue:
|
||||
|
||||
* Type of issue (e.g. buffer overflow, SQL injection, cross-site scripting, etc.)
|
||||
* Full paths of source file(s) related to the manifestation of the issue
|
||||
* The location of the affected source code (tag/branch/commit or direct URL)
|
||||
* Any special configuration required to reproduce the issue
|
||||
* Step-by-step instructions to reproduce the issue
|
||||
* Proof-of-concept or exploit code (if possible)
|
||||
* Impact of the issue, including how an attacker might exploit the issue
|
||||
|
||||
This information will help us triage your report more quickly.
|
||||
|
||||
If you are reporting for a bug bounty, more complete reports can contribute to a higher bounty award. Please visit our [Microsoft Bug Bounty Program](https://aka.ms/opensource/security/bounty) page for more details about our active programs.
|
||||
|
||||
## Preferred Languages
|
||||
|
||||
We prefer all communications to be in English.
|
||||
|
||||
## Policy
|
||||
|
||||
Microsoft follows the principle of [Coordinated Vulnerability Disclosure](https://aka.ms/opensource/security/cvd).
|
||||
|
||||
<!-- END MICROSOFT SECURITY.MD BLOCK -->
|
||||
@@ -103,7 +103,7 @@
|
||||
"source": [
|
||||
"import azureml.core\n",
|
||||
"\n",
|
||||
"print(\"This notebook was created using version 1.44.0 of the Azure ML SDK\")\n",
|
||||
"print(\"This notebook was created using version 1.45.0 of the Azure ML SDK\")\n",
|
||||
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
|
||||
]
|
||||
},
|
||||
|
||||
@@ -6,7 +6,7 @@ dependencies:
|
||||
- fairlearn>=0.6.2
|
||||
- joblib
|
||||
- liac-arff
|
||||
- raiwidgets~=0.19.0
|
||||
- raiwidgets~=0.21.0
|
||||
- itsdangerous==2.0.1
|
||||
- markupsafe<2.1.0
|
||||
- protobuf==3.20.0
|
||||
|
||||
@@ -6,7 +6,7 @@ dependencies:
|
||||
- fairlearn>=0.6.2
|
||||
- joblib
|
||||
- liac-arff
|
||||
- raiwidgets~=0.19.0
|
||||
- raiwidgets~=0.21.0
|
||||
- itsdangerous==2.0.1
|
||||
- markupsafe<2.1.0
|
||||
- protobuf==3.20.0
|
||||
|
||||
@@ -18,16 +18,19 @@ dependencies:
|
||||
- pywin32==227
|
||||
- PySocks==1.7.1
|
||||
- conda-forge::pyqt==5.12.3
|
||||
- jsonschema==4.9.1
|
||||
- Pygments==2.12.0
|
||||
- jsonschema==4.15.0
|
||||
- jinja2<=2.11.2
|
||||
- markupsafe<2.1.0
|
||||
- tqdm==4.64.0
|
||||
|
||||
- pip:
|
||||
# Required packages for AzureML execution, history, and data preparation.
|
||||
- azureml-widgets~=1.44.0
|
||||
- azureml-widgets~=1.45.0
|
||||
- azureml-defaults~=1.45.0
|
||||
- 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/1.44.0/validated_win32_requirements.txt [--no-deps]
|
||||
- -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.45.0/validated_win32_requirements.txt [--no-deps]
|
||||
- arch==4.14
|
||||
- wasabi==0.9.1
|
||||
|
||||
@@ -21,13 +21,16 @@ dependencies:
|
||||
- conda-forge::fbprophet==0.7.1
|
||||
- pytorch::pytorch=1.4.0
|
||||
- cudatoolkit=10.1.243
|
||||
- jinja2<=2.11.2
|
||||
- markupsafe<2.1.0
|
||||
|
||||
- pip:
|
||||
# Required packages for AzureML execution, history, and data preparation.
|
||||
- azureml-widgets~=1.44.0
|
||||
- azureml-widgets~=1.45.0
|
||||
- azureml-defaults~=1.45.0
|
||||
- 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/1.44.0/validated_linux_requirements.txt [--no-deps]
|
||||
- -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.45.0/validated_linux_requirements.txt [--no-deps]
|
||||
- arch==4.14
|
||||
|
||||
@@ -22,13 +22,16 @@ dependencies:
|
||||
- conda-forge::fbprophet==0.7.1
|
||||
- pytorch::pytorch=1.4.0
|
||||
- cudatoolkit=9.0
|
||||
- jinja2<=2.11.2
|
||||
- markupsafe<2.1.0
|
||||
|
||||
- pip:
|
||||
# Required packages for AzureML execution, history, and data preparation.
|
||||
- azureml-widgets~=1.44.0
|
||||
- azureml-widgets~=1.45.0
|
||||
- azureml-defaults~=1.45.0
|
||||
- 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/1.44.0/validated_darwin_requirements.txt [--no-deps]
|
||||
- -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.45.0/validated_darwin_requirements.txt [--no-deps]
|
||||
- arch==4.14
|
||||
|
||||
@@ -97,7 +97,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"This notebook was created using version 1.44.0 of the Azure ML SDK\")\n",
|
||||
"print(\"This notebook was created using version 1.45.0 of the Azure ML SDK\")\n",
|
||||
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
|
||||
]
|
||||
},
|
||||
|
||||
@@ -97,7 +97,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"This notebook was created using version 1.44.0 of the Azure ML SDK\")\n",
|
||||
"print(\"This notebook was created using version 1.45.0 of the Azure ML SDK\")\n",
|
||||
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
|
||||
]
|
||||
},
|
||||
|
||||
@@ -3,7 +3,7 @@ dependencies:
|
||||
# The python interpreter version.
|
||||
# Currently Azure ML only supports 3.6.0 and later.
|
||||
- pip<=20.2.4
|
||||
- python>=3.6.0,<3.9
|
||||
- python>=3.6.0,<3.10
|
||||
- cython==0.29.14
|
||||
- urllib3==1.26.7
|
||||
- PyJWT < 2.0.0
|
||||
@@ -18,4 +18,6 @@ dependencies:
|
||||
- azureml-defaults
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
- azureml-mlflow
|
||||
- pandas
|
||||
- mlflow
|
||||
|
||||
@@ -7,7 +7,7 @@ dependencies:
|
||||
# Currently Azure ML only supports 3.6.0 and later.
|
||||
- pip<=20.2.4
|
||||
- nomkl
|
||||
- python>=3.6.0,<3.9
|
||||
- python>=3.6.0,<3.10
|
||||
- urllib3==1.26.7
|
||||
- PyJWT < 2.0.0
|
||||
- numpy>=1.21.6,<=1.22.3
|
||||
@@ -20,4 +20,6 @@ dependencies:
|
||||
- azureml-defaults
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
- azureml-mlflow
|
||||
- pandas
|
||||
- mlflow
|
||||
|
||||
@@ -92,7 +92,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"This notebook was created using version 1.44.0 of the Azure ML SDK\")\n",
|
||||
"print(\"This notebook was created using version 1.45.0 of the Azure ML SDK\")\n",
|
||||
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
|
||||
]
|
||||
},
|
||||
|
||||
@@ -91,7 +91,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"This notebook was created using version 1.44.0 of the Azure ML SDK\")\n",
|
||||
"print(\"This notebook was created using version 1.45.0 of the Azure ML SDK\")\n",
|
||||
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
|
||||
]
|
||||
},
|
||||
|
||||
@@ -324,7 +324,8 @@
|
||||
"| **experiment_timeout_hours** | Maximum amount of time in hours that the experiment can take before it terminates. This is optional but provides customers with greater control on exit criteria. |\n",
|
||||
"| **label_column_name** | The name of the label column. |\n",
|
||||
"| **forecast_horizon** | The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly). Periods are inferred from your data. |\n",
|
||||
"| **n_cross_validations** | Number of cross validation splits. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
|
||||
"| **n_cross_validations** | Number of cross validation splits. The default value is \"auto\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
|
||||
"|**cv_step_size**|Number of periods between two consecutive cross-validation folds. The default value is \"auto\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value.\n",
|
||||
"| **time_column_name** | The name of your time column. |\n",
|
||||
"| **time_series_id_column_names** | The column names used to uniquely identify timeseries in data that has multiple rows with the same timestamp. |\n",
|
||||
"| **track_child_runs** | Flag to disable tracking of child runs. Only best run is tracked if the flag is set to False (this includes the model and metrics of the run). |\n",
|
||||
@@ -353,7 +354,8 @@
|
||||
" \"iterations\": 15,\n",
|
||||
" \"experiment_timeout_hours\": 0.25, # This also needs to be changed based on the dataset. For larger data set this number needs to be bigger.\n",
|
||||
" \"label_column_name\": TARGET_COLNAME,\n",
|
||||
" \"n_cross_validations\": 3,\n",
|
||||
" \"n_cross_validations\": \"auto\", # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
|
||||
" \"cv_step_size\": \"auto\",\n",
|
||||
" \"time_column_name\": TIME_COLNAME,\n",
|
||||
" \"forecast_horizon\": 6,\n",
|
||||
" \"time_series_id_column_names\": partition_column_names,\n",
|
||||
@@ -718,7 +720,12 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.9"
|
||||
"version": "3.8.5"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -283,7 +283,8 @@
|
||||
"| **experiment_timeout_hours** | Maximum amount of time in hours that the experiment can take before it terminates. This is optional but provides customers with greater control on exit criteria. |\n",
|
||||
"| **label_column_name** | The name of the label column. |\n",
|
||||
"| **max_horizon** | The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly). Periods are inferred from your data. |\n",
|
||||
"| **n_cross_validations** | Number of cross validation splits. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
|
||||
"| **n_cross_validations** | Number of cross validation splits. The default value is \"auto\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
|
||||
"|**cv_step_size**|Number of periods between two consecutive cross-validation folds. The default value is \"auto\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value.\n",
|
||||
"| **time_column_name** | The name of your time column. |\n",
|
||||
"| **grain_column_names** | The column names used to uniquely identify timeseries in data that has multiple rows with the same timestamp. |"
|
||||
]
|
||||
@@ -301,7 +302,8 @@
|
||||
" \"iterations\": 15,\n",
|
||||
" \"experiment_timeout_hours\": 1, # This also needs to be changed based on the dataset. For larger data set this number needs to be bigger.\n",
|
||||
" \"label_column_name\": LABEL_COLUMN_NAME,\n",
|
||||
" \"n_cross_validations\": 3,\n",
|
||||
" \"n_cross_validations\": \"auto\", # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
|
||||
" \"cv_step_size\": \"auto\",\n",
|
||||
" \"time_column_name\": TIME_COLUMN_NAME,\n",
|
||||
" \"max_horizon\": FORECAST_HORIZON,\n",
|
||||
" \"track_child_runs\": False,\n",
|
||||
@@ -712,7 +714,12 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.9"
|
||||
"version": "3.8.5"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -265,7 +265,8 @@
|
||||
"|**forecast_horizon**|The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly).|\n",
|
||||
"|**country_or_region_for_holidays**|The country/region used to generate holiday features. These should be ISO 3166 two-letter country/region codes (i.e. 'US', 'GB').|\n",
|
||||
"|**target_lags**|The target_lags specifies how far back we will construct the lags of the target variable.|\n",
|
||||
"|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information."
|
||||
"|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information.\n",
|
||||
"|**cv_step_size**|Number of periods between two consecutive cross-validation folds. The default value is \"auto\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -285,7 +286,7 @@
|
||||
"|**training_data**|Input dataset, containing both features and label column.|\n",
|
||||
"|**label_column_name**|The name of the label column.|\n",
|
||||
"|**compute_target**|The remote compute for training.|\n",
|
||||
"|**n_cross_validations**|Number of cross validation splits.|\n",
|
||||
"|**n_cross_validations**|Number of cross-validation folds to use for model/pipeline selection. The default value is \"auto\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value.\n",
|
||||
"|**enable_early_stopping**|If early stopping is on, training will stop when the primary metric is no longer improving.|\n",
|
||||
"|**forecasting_parameters**|A class that holds all the forecasting related parameters.|\n",
|
||||
"\n",
|
||||
@@ -350,6 +351,7 @@
|
||||
" country_or_region_for_holidays=\"US\", # set country_or_region will trigger holiday featurizer\n",
|
||||
" target_lags=\"auto\", # use heuristic based lag setting\n",
|
||||
" freq=\"D\", # Set the forecast frequency to be daily\n",
|
||||
" cv_step_size=\"auto\",\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"automl_config = AutoMLConfig(\n",
|
||||
@@ -362,7 +364,7 @@
|
||||
" label_column_name=target_column_name,\n",
|
||||
" compute_target=compute_target,\n",
|
||||
" enable_early_stopping=True,\n",
|
||||
" n_cross_validations=3,\n",
|
||||
" n_cross_validations=\"auto\", # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
|
||||
" max_concurrent_iterations=4,\n",
|
||||
" max_cores_per_iteration=-1,\n",
|
||||
" verbosity=logging.INFO,\n",
|
||||
@@ -709,7 +711,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.7"
|
||||
"version": "3.8.5"
|
||||
},
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
@@ -719,7 +721,12 @@
|
||||
"Forecasting"
|
||||
],
|
||||
"task": "Forecasting",
|
||||
"version": 3
|
||||
"version": 3,
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
|
||||
@@ -308,7 +308,8 @@
|
||||
"|-|-|\n",
|
||||
"|**time_column_name**|The name of your time column.|\n",
|
||||
"|**forecast_horizon**|The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly).|\n",
|
||||
"|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information."
|
||||
"|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information.\n",
|
||||
"|**cv_step_size**|Number of periods between two consecutive cross-validation folds. The default value is \"auto\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -328,7 +329,7 @@
|
||||
"|**training_data**|The training data to be used within the experiment.|\n",
|
||||
"|**label_column_name**|The name of the label column.|\n",
|
||||
"|**compute_target**|The remote compute for training.|\n",
|
||||
"|**n_cross_validations**|Number of cross validation splits. Rolling Origin Validation is used to split time-series in a temporally consistent way.|\n",
|
||||
"|**n_cross_validations**|Number of cross-validation folds to use for model/pipeline selection. The default value is \"auto\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value.\n",
|
||||
"|**enable_early_stopping**|Flag to enble early termination if the score is not improving in the short term.|\n",
|
||||
"|**forecasting_parameters**|A class holds all the forecasting related parameters.|\n"
|
||||
]
|
||||
@@ -352,6 +353,7 @@
|
||||
" time_column_name=time_column_name,\n",
|
||||
" forecast_horizon=forecast_horizon,\n",
|
||||
" freq=\"H\", # Set the forecast frequency to be hourly\n",
|
||||
" cv_step_size=\"auto\",\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"automl_config = AutoMLConfig(\n",
|
||||
@@ -363,7 +365,7 @@
|
||||
" label_column_name=target_column_name,\n",
|
||||
" compute_target=compute_target,\n",
|
||||
" enable_early_stopping=True,\n",
|
||||
" n_cross_validations=3,\n",
|
||||
" n_cross_validations=\"auto\", # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
|
||||
" verbosity=logging.INFO,\n",
|
||||
" forecasting_parameters=forecasting_parameters,\n",
|
||||
")"
|
||||
@@ -609,6 +611,7 @@
|
||||
" forecast_horizon=forecast_horizon,\n",
|
||||
" target_lags=12,\n",
|
||||
" target_rolling_window_size=4,\n",
|
||||
" cv_step_size=\"auto\",\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"automl_config = AutoMLConfig(\n",
|
||||
@@ -628,7 +631,7 @@
|
||||
" label_column_name=target_column_name,\n",
|
||||
" compute_target=compute_target,\n",
|
||||
" enable_early_stopping=True,\n",
|
||||
" n_cross_validations=3,\n",
|
||||
" n_cross_validations=\"auto\", # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
|
||||
" verbosity=logging.INFO,\n",
|
||||
" forecasting_parameters=advanced_forecasting_parameters,\n",
|
||||
")"
|
||||
@@ -778,7 +781,12 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.9"
|
||||
"version": "3.8.5"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -335,7 +335,8 @@
|
||||
" forecast_horizon=forecast_horizon,\n",
|
||||
" time_series_id_column_names=[TIME_SERIES_ID_COLUMN_NAME],\n",
|
||||
" target_lags=lags,\n",
|
||||
" freq=\"H\", # Set the forecast frequency to be hourly\n",
|
||||
" freq=\"H\", # Set the forecast frequency to be hourly,\n",
|
||||
" cv_step_size=\"auto\",\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
@@ -365,7 +366,7 @@
|
||||
" enable_early_stopping=True,\n",
|
||||
" training_data=train_data,\n",
|
||||
" compute_target=compute_target,\n",
|
||||
" n_cross_validations=3,\n",
|
||||
" n_cross_validations=\"auto\", # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
|
||||
" verbosity=logging.INFO,\n",
|
||||
" max_concurrent_iterations=4,\n",
|
||||
" max_cores_per_iteration=-1,\n",
|
||||
@@ -879,13 +880,18 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.8"
|
||||
"version": "3.8.5"
|
||||
},
|
||||
"tags": [
|
||||
"Forecasting",
|
||||
"Confidence Intervals"
|
||||
],
|
||||
"task": "Forecasting"
|
||||
"task": "Forecasting",
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
|
||||
@@ -263,7 +263,8 @@
|
||||
"| **experiment_timeout_hours** | Maximum amount of time in hours that the experiment can take before it terminates. This is optional but provides customers with greater control on exit criteria. |\n",
|
||||
"| **label_column_name** | The name of the label column. |\n",
|
||||
"| **forecast_horizon** | The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly). Periods are inferred from your data. |\n",
|
||||
"| **n_cross_validations** | Number of cross validation splits. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
|
||||
"|**n_cross_validations**|Number of cross-validation folds to use for model/pipeline selection. The default value is \"auto\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value.\n",
|
||||
"|**cv_step_size**|Number of periods between two consecutive cross-validation folds. The default value is \"auto\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value.\n",
|
||||
"| **enable_early_stopping** | Flag to enable early termination if the score is not improving in the short term. |\n",
|
||||
"| **time_column_name** | The name of your time column. |\n",
|
||||
"| **hierarchy_column_names** | The names of columns that define the hierarchical structure of the data from highest level to most granular. |\n",
|
||||
@@ -311,10 +312,11 @@
|
||||
" \"track_child_runs\": False,\n",
|
||||
" \"pipeline_fetch_max_batch_size\": 15,\n",
|
||||
" \"model_explainability\": model_explainability,\n",
|
||||
" \"n_cross_validations\": \"auto\", # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
|
||||
" \"cv_step_size\": \"auto\",\n",
|
||||
" # The following settings are specific to this sample and should be adjusted according to your own needs.\n",
|
||||
" \"iteration_timeout_minutes\": 10,\n",
|
||||
" \"iterations\": 10,\n",
|
||||
" \"n_cross_validations\": 2,\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"hts_parameters = HTSTrainParameters(\n",
|
||||
|
||||
@@ -391,7 +391,8 @@
|
||||
"| **experiment_timeout_hours** | Maximum amount of time in hours that the experiment can take before it terminates. This is optional but provides customers with greater control on exit criteria. |\n",
|
||||
"| **label_column_name** | The name of the label column. |\n",
|
||||
"| **forecast_horizon** | The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly). Periods are inferred from your data. |\n",
|
||||
"| **n_cross_validations** | Number of cross validation splits. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
|
||||
"| **n_cross_validations** | Number of cross validation splits. The default value is \"auto\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value. Rolling Origin Validation is used to split time-series in a temporally consistent way. |\n",
|
||||
"|**cv_step_size**|Number of periods between two consecutive cross-validation folds. The default value is \"auto\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value.\n",
|
||||
"| **enable_early_stopping** | Flag to enable early termination if the score is not improving in the short term. |\n",
|
||||
"| **time_column_name** | The name of your time column. |\n",
|
||||
"| **enable_engineered_explanations** | Engineered feature explanations will be downloaded if enable_engineered_explanations flag is set to True. By default it is set to False to save storage space. |\n",
|
||||
@@ -423,7 +424,8 @@
|
||||
" \"iterations\": 15,\n",
|
||||
" \"experiment_timeout_hours\": 0.25,\n",
|
||||
" \"label_column_name\": \"Quantity\",\n",
|
||||
" \"n_cross_validations\": 3,\n",
|
||||
" \"n_cross_validations\": \"auto\", # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
|
||||
" \"cv_step_size\": \"auto\",\n",
|
||||
" \"time_column_name\": \"WeekStarting\",\n",
|
||||
" \"drop_column_names\": \"Revenue\",\n",
|
||||
" \"forecast_horizon\": 6,\n",
|
||||
@@ -849,7 +851,12 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.8"
|
||||
"version": "3.8.5"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -368,7 +368,8 @@
|
||||
"|**time_column_name**|The name of your time column.|\n",
|
||||
"|**forecast_horizon**|The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly).|\n",
|
||||
"|**time_series_id_column_names**|The column names used to uniquely identify the time series in data that has multiple rows with the same timestamp. If the time series identifiers are not defined, the data set is assumed to be one time series.|\n",
|
||||
"|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information."
|
||||
"|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information.\n",
|
||||
"|**cv_step_size**|Number of periods between two consecutive cross-validation folds. The default value is \"auto\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -390,7 +391,7 @@
|
||||
"In the first case, AutoML loops over all time-series in your dataset and trains one model (e.g. AutoArima or Prophet, as the case may be) for each series. This can result in long runtimes to train these models if there are a lot of series in the data. One way to mitigate this problem is to fit models for different series in parallel if you have multiple compute cores available. To enable this behavior, set the `max_cores_per_iteration` parameter in your AutoMLConfig as shown in the example in the next cell. \n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Finally, a note about the cross-validation (CV) procedure for time-series data. AutoML uses out-of-sample error estimates to select a best pipeline/model, so it is important that the CV fold splitting is done correctly. Time-series can violate the basic statistical assumptions of the canonical K-Fold CV strategy, so AutoML implements a [rolling origin validation](https://robjhyndman.com/hyndsight/tscv/) procedure to create CV folds for time-series data. To use this procedure, you just need to specify the desired number of CV folds in the AutoMLConfig object. It is also possible to bypass CV and use your own validation set by setting the *validation_data* parameter of AutoMLConfig.\n",
|
||||
"Finally, a note about the cross-validation (CV) procedure for time-series data. AutoML uses out-of-sample error estimates to select a best pipeline/model, so it is important that the CV fold splitting is done correctly. Time-series can violate the basic statistical assumptions of the canonical K-Fold CV strategy, so AutoML implements a [rolling origin validation](https://robjhyndman.com/hyndsight/tscv/) procedure to create CV folds for time-series data. To use this procedure, you could specify the desired number of CV folds and the number of periods between two consecutive folds in the AutoMLConfig object, or AutoMl could set them automatically if you don't specify them. It is also possible to bypass CV and use your own validation set by setting the *validation_data* parameter of AutoMLConfig.\n",
|
||||
"\n",
|
||||
"Here is a summary of AutoMLConfig parameters used for training the OJ model:\n",
|
||||
"\n",
|
||||
@@ -403,7 +404,7 @@
|
||||
"|**training_data**|Input dataset, containing both features and label column.|\n",
|
||||
"|**label_column_name**|The name of the label column.|\n",
|
||||
"|**compute_target**|The remote compute for training.|\n",
|
||||
"|**n_cross_validations**|Number of cross-validation folds to use for model/pipeline selection|\n",
|
||||
"|**n_cross_validations**|Number of cross-validation folds to use for model/pipeline selection. The default value is \"auto\", in which case AutoMl determines the number of cross-validations automatically, if a validation set is not provided. Or users could specify an integer value.\n",
|
||||
"|**enable_voting_ensemble**|Allow AutoML to create a Voting ensemble of the best performing models|\n",
|
||||
"|**enable_stack_ensemble**|Allow AutoML to create a Stack ensemble of the best performing models|\n",
|
||||
"|**debug_log**|Log file path for writing debugging information|\n",
|
||||
@@ -424,6 +425,7 @@
|
||||
" forecast_horizon=n_test_periods,\n",
|
||||
" time_series_id_column_names=time_series_id_column_names,\n",
|
||||
" freq=\"W-THU\", # Set the forecast frequency to be weekly (start on each Thursday)\n",
|
||||
" cv_step_size=\"auto\",\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"automl_config = AutoMLConfig(\n",
|
||||
@@ -436,7 +438,7 @@
|
||||
" compute_target=compute_target,\n",
|
||||
" enable_early_stopping=True,\n",
|
||||
" featurization=featurization_config,\n",
|
||||
" n_cross_validations=3,\n",
|
||||
" n_cross_validations=\"auto\", # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
|
||||
" verbosity=logging.INFO,\n",
|
||||
" max_cores_per_iteration=-1,\n",
|
||||
" forecasting_parameters=forecasting_parameters,\n",
|
||||
@@ -833,12 +835,17 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.9"
|
||||
"version": "3.8.5"
|
||||
},
|
||||
"tags": [
|
||||
"None"
|
||||
],
|
||||
"task": "Forecasting"
|
||||
"task": "Forecasting",
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
|
||||
@@ -292,7 +292,8 @@
|
||||
"|**time_column_name**|The name of your time column.|\n",
|
||||
"|**forecast_horizon**|The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly).|\n",
|
||||
"|**time_series_id_column_names**|The column names used to uniquely identify the time series in data that has multiple rows with the same timestamp. If the time series identifiers are not defined, the data set is assumed to be one time series.|\n",
|
||||
"|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information."
|
||||
"|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information.\n",
|
||||
"|**cv_step_size**|Number of periods between two consecutive cross-validation folds. The default value is \"auto\", in which case AutoMl determines the cross-validation step size automatically, if a validation set is not provided. Or users could specify an integer value."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -307,7 +308,8 @@
|
||||
" time_column_name=time_column_name,\n",
|
||||
" forecast_horizon=n_test_periods,\n",
|
||||
" time_series_id_column_names=time_series_id_column_names,\n",
|
||||
" freq=\"W-THU\", # Set the forecast frequency to be weekly (start on each Thursday)\n",
|
||||
" freq=\"W-THU\", # Set the forecast frequency to be weekly (start on each Thursday),\n",
|
||||
" cv_step_size=\"auto\",\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"automl_config = AutoMLConfig(\n",
|
||||
@@ -319,7 +321,7 @@
|
||||
" label_column_name=target_column_name,\n",
|
||||
" compute_target=compute_target,\n",
|
||||
" enable_early_stopping=True,\n",
|
||||
" n_cross_validations=5,\n",
|
||||
" n_cross_validations=\"auto\", # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
|
||||
" verbosity=logging.INFO,\n",
|
||||
" max_cores_per_iteration=-1,\n",
|
||||
" forecasting_parameters=forecasting_parameters,\n",
|
||||
@@ -811,12 +813,17 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.9"
|
||||
"version": "3.8.5"
|
||||
},
|
||||
"tags": [
|
||||
"None"
|
||||
],
|
||||
"task": "Forecasting"
|
||||
"task": "Forecasting",
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
|
||||
@@ -358,7 +358,8 @@
|
||||
" enable_early_stopping=True,\n",
|
||||
" training_data=train_dataset,\n",
|
||||
" label_column_name=TARGET_COLNAME,\n",
|
||||
" n_cross_validations=5,\n",
|
||||
" n_cross_validations=\"auto\", # Feel free to set to a small integer (>=2) if runtime is an issue.\n",
|
||||
" cv_step_size=\"auto\",\n",
|
||||
" verbosity=logging.INFO,\n",
|
||||
" max_cores_per_iteration=-1,\n",
|
||||
" compute_target=compute_target,\n",
|
||||
@@ -585,7 +586,12 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.9"
|
||||
"version": "3.8.5"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "6bd77c88278e012ef31757c15997a7bea8c943977c43d6909403c00ae11d43ca"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -106,7 +106,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"This notebook was created using version 1.44.0 of the Azure ML SDK\")\n",
|
||||
"print(\"This notebook was created using version 1.45.0 of the Azure ML SDK\")\n",
|
||||
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
|
||||
]
|
||||
},
|
||||
@@ -237,12 +237,16 @@
|
||||
"import pkg_resources\n",
|
||||
"available_packages = pkg_resources.working_set\n",
|
||||
"pandas_ver = None\n",
|
||||
"numpy_ver = None\n",
|
||||
"for dist in list(available_packages):\n",
|
||||
" if dist.key == 'pandas':\n",
|
||||
" pandas_ver = dist.version\n",
|
||||
"pandas_dep = 'pandas'\n",
|
||||
"numpy_dep = 'numpy'\n",
|
||||
"if pandas_ver:\n",
|
||||
" pandas_dep = 'pandas=={}'.format(pandas_ver)\n",
|
||||
"if numpy_ver:\n",
|
||||
" numpy_dep = 'numpy=={}'.format(numpy_ver)\n",
|
||||
"\n",
|
||||
"# Note: we build shap at commit 690245 for Tesla K80 GPUs\n",
|
||||
"env.docker.base_dockerfile = f\"\"\"\n",
|
||||
@@ -282,7 +286,7 @@
|
||||
"pip uninstall -y xgboost && \\\n",
|
||||
"conda install py-xgboost==1.3.3 && \\\n",
|
||||
"pip uninstall -y numpy && \\\n",
|
||||
"conda install numpy==1.20.3 \\\n",
|
||||
"conda install {numpy_dep} \\\n",
|
||||
"\"\"\"\n",
|
||||
"\n",
|
||||
"env.python.user_managed_dependencies = True\n",
|
||||
|
||||
@@ -7,12 +7,12 @@ dependencies:
|
||||
- flask
|
||||
- flask-cors
|
||||
- gevent>=1.3.6
|
||||
- jinja2
|
||||
- ipython
|
||||
- matplotlib
|
||||
- ipywidgets
|
||||
- raiwidgets~=0.19.0
|
||||
- raiwidgets~=0.21.0
|
||||
- itsdangerous==2.0.1
|
||||
- markupsafe<2.1.0
|
||||
- scipy>=1.5.3
|
||||
- protobuf==3.20.0
|
||||
- jinja2==3.0.3
|
||||
|
||||
@@ -269,23 +269,29 @@
|
||||
"available_packages = pkg_resources.working_set\n",
|
||||
"sklearn_ver = None\n",
|
||||
"pandas_ver = None\n",
|
||||
"joblib_ver = None\n",
|
||||
"for dist in list(available_packages):\n",
|
||||
" if dist.key == 'scikit-learn':\n",
|
||||
" sklearn_ver = dist.version\n",
|
||||
" elif dist.key == 'pandas':\n",
|
||||
" pandas_ver = dist.version\n",
|
||||
" elif dist.key == 'joblib':\n",
|
||||
" joblib_ver = dist.version\n",
|
||||
"sklearn_dep = 'scikit-learn'\n",
|
||||
"pandas_dep = 'pandas'\n",
|
||||
"joblib_dep = 'joblib'\n",
|
||||
"if sklearn_ver:\n",
|
||||
" sklearn_dep = 'scikit-learn=={}'.format(sklearn_ver)\n",
|
||||
"if pandas_ver:\n",
|
||||
" pandas_dep = 'pandas=={}'.format(pandas_ver)\n",
|
||||
"if joblib_ver:\n",
|
||||
" joblib_dep = 'joblib=={}'.format(joblib_ver)\n",
|
||||
"# Specify CondaDependencies obj\n",
|
||||
"# The CondaDependencies specifies the conda and pip packages that are installed in the environment\n",
|
||||
"# the submitted job is run in. Note the remote environment(s) needs to be similar to the local\n",
|
||||
"# environment, otherwise if a model is trained or deployed in a different environment this can\n",
|
||||
"# cause errors. Please take extra care when specifying your dependencies in a production environment.\n",
|
||||
"azureml_pip_packages.extend([sklearn_dep, pandas_dep])\n",
|
||||
"azureml_pip_packages.extend([sklearn_dep, pandas_dep, joblib_dep])\n",
|
||||
"run_config.environment.python.conda_dependencies = CondaDependencies.create(pip_packages=azureml_pip_packages, python_version=python_version)\n",
|
||||
"\n",
|
||||
"from azureml.core import ScriptRunConfig\n",
|
||||
|
||||
@@ -6,13 +6,13 @@ dependencies:
|
||||
- flask
|
||||
- flask-cors
|
||||
- gevent>=1.3.6
|
||||
- jinja2
|
||||
- ipython
|
||||
- matplotlib
|
||||
- azureml-dataset-runtime
|
||||
- ipywidgets
|
||||
- raiwidgets~=0.19.0
|
||||
- raiwidgets~=0.21.0
|
||||
- itsdangerous==2.0.1
|
||||
- markupsafe<2.1.0
|
||||
- scipy>=1.5.3
|
||||
- protobuf==3.20.0
|
||||
- jinja2==3.0.3
|
||||
|
||||
@@ -6,13 +6,13 @@ dependencies:
|
||||
- flask
|
||||
- flask-cors
|
||||
- gevent>=1.3.6
|
||||
- jinja2
|
||||
- ipython
|
||||
- matplotlib
|
||||
- ipywidgets
|
||||
- raiwidgets~=0.19.0
|
||||
- raiwidgets~=0.21.0
|
||||
- packaging>=20.9
|
||||
- itsdangerous==2.0.1
|
||||
- markupsafe<2.1.0
|
||||
- scipy>=1.5.3
|
||||
- protobuf==3.20.0
|
||||
- jinja2==3.0.3
|
||||
|
||||
@@ -6,13 +6,13 @@ dependencies:
|
||||
- flask
|
||||
- flask-cors
|
||||
- gevent>=1.3.6
|
||||
- jinja2
|
||||
- ipython
|
||||
- matplotlib
|
||||
- ipywidgets
|
||||
- raiwidgets~=0.19.0
|
||||
- raiwidgets~=0.21.0
|
||||
- packaging>=20.9
|
||||
- itsdangerous==2.0.1
|
||||
- markupsafe<2.1.0
|
||||
- scipy>=1.5.3
|
||||
- protobuf==3.20.0
|
||||
- jinja2==3.0.3
|
||||
|
||||
@@ -277,23 +277,29 @@
|
||||
"available_packages = pkg_resources.working_set\n",
|
||||
"sklearn_ver = None\n",
|
||||
"pandas_ver = None\n",
|
||||
"joblib_ver = None\n",
|
||||
"for dist in available_packages:\n",
|
||||
" if dist.key == 'scikit-learn':\n",
|
||||
" sklearn_ver = dist.version\n",
|
||||
" elif dist.key == 'pandas':\n",
|
||||
" pandas_ver = dist.version\n",
|
||||
" elif dist.key == 'joblib':\n",
|
||||
" joblib_ver = dist.version\n",
|
||||
"sklearn_dep = 'scikit-learn'\n",
|
||||
"pandas_dep = 'pandas'\n",
|
||||
"joblib_dep = 'joblib'\n",
|
||||
"if sklearn_ver:\n",
|
||||
" sklearn_dep = 'scikit-learn=={}'.format(sklearn_ver)\n",
|
||||
"if pandas_ver:\n",
|
||||
" pandas_dep = 'pandas=={}'.format(pandas_ver)\n",
|
||||
"if joblib_ver:\n",
|
||||
" joblib_dep = 'joblib=={}'.format(joblib_ver)\n",
|
||||
"# Specify CondaDependencies obj\n",
|
||||
"# The CondaDependencies specifies the conda and pip packages that are installed in the environment\n",
|
||||
"# the submitted job is run in. Note the remote environment(s) needs to be similar to the local\n",
|
||||
"# environment, otherwise if a model is trained or deployed in a different environment this can\n",
|
||||
"# cause errors. Please take extra care when specifying your dependencies in a production environment.\n",
|
||||
"azureml_pip_packages.extend(['pyyaml', sklearn_dep, pandas_dep])\n",
|
||||
"azureml_pip_packages.extend(['pyyaml', sklearn_dep, pandas_dep, joblib_dep])\n",
|
||||
"run_config.environment.python.conda_dependencies = CondaDependencies.create(\n",
|
||||
" python_version=python_version,\n",
|
||||
" pip_packages=azureml_pip_packages)\n",
|
||||
@@ -440,23 +446,29 @@
|
||||
"available_packages = pkg_resources.working_set\n",
|
||||
"sklearn_ver = None\n",
|
||||
"pandas_ver = None\n",
|
||||
"joblib_ver = None\n",
|
||||
"for dist in available_packages:\n",
|
||||
" if dist.key == 'scikit-learn':\n",
|
||||
" sklearn_ver = dist.version\n",
|
||||
" elif dist.key == 'pandas':\n",
|
||||
" pandas_ver = dist.version\n",
|
||||
" elif dist.key == 'joblib':\n",
|
||||
" joblib_ver = dist.version\n",
|
||||
"sklearn_dep = 'scikit-learn'\n",
|
||||
"pandas_dep = 'pandas'\n",
|
||||
"joblib_dep = 'joblib'\n",
|
||||
"if sklearn_ver:\n",
|
||||
" sklearn_dep = 'scikit-learn=={}'.format(sklearn_ver)\n",
|
||||
"if pandas_ver:\n",
|
||||
" pandas_dep = 'pandas=={}'.format(pandas_ver)\n",
|
||||
"if joblib_ver:\n",
|
||||
" joblib_dep = 'joblib=={}'.format(joblib_ver)\n",
|
||||
"# Specify CondaDependencies obj\n",
|
||||
"# The CondaDependencies specifies the conda and pip packages that are installed in the environment\n",
|
||||
"# the submitted job is run in. Note the remote environment(s) needs to be similar to the local\n",
|
||||
"# environment, otherwise if a model is trained or deployed in a different environment this can\n",
|
||||
"# cause errors. Please take extra care when specifying your dependencies in a production environment.\n",
|
||||
"azureml_pip_packages.extend(['pyyaml', sklearn_dep, pandas_dep])\n",
|
||||
"azureml_pip_packages.extend(['pyyaml', sklearn_dep, pandas_dep, joblib_dep])\n",
|
||||
"myenv = CondaDependencies.create(python_version=python_version, pip_packages=azureml_pip_packages)\n",
|
||||
"\n",
|
||||
"with open(\"myenv.yml\",\"w\") as f:\n",
|
||||
|
||||
@@ -6,14 +6,14 @@ dependencies:
|
||||
- flask
|
||||
- flask-cors
|
||||
- gevent>=1.3.6
|
||||
- jinja2
|
||||
- ipython
|
||||
- matplotlib
|
||||
- azureml-dataset-runtime
|
||||
- azureml-core
|
||||
- ipywidgets
|
||||
- raiwidgets~=0.19.0
|
||||
- raiwidgets~=0.21.0
|
||||
- itsdangerous==2.0.1
|
||||
- markupsafe<2.1.0
|
||||
- scipy>=1.5.3
|
||||
- protobuf==3.20.0
|
||||
- jinja2==3.0.3
|
||||
|
||||
@@ -4,7 +4,7 @@ import os
|
||||
|
||||
import numpy as np
|
||||
|
||||
from utils import download_mnist
|
||||
from datautils import download_mnist
|
||||
|
||||
import chainer
|
||||
from chainer import backend
|
||||
|
||||
@@ -2,7 +2,7 @@ import numpy as np
|
||||
import os
|
||||
import json
|
||||
|
||||
from utils import download_mnist
|
||||
from datautils import download_mnist
|
||||
|
||||
from chainer import serializers, using_config, Variable, datasets
|
||||
import chainer.functions as F
|
||||
|
||||
@@ -210,7 +210,7 @@
|
||||
"\n",
|
||||
"shutil.copy('chainer_mnist.py', project_folder)\n",
|
||||
"shutil.copy('chainer_score.py', project_folder)\n",
|
||||
"shutil.copy('utils.py', project_folder)"
|
||||
"shutil.copy('datautils.py', project_folder)"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
@@ -283,7 +283,7 @@
|
||||
"\n",
|
||||
"# Specify a GPU base image\n",
|
||||
"pytorch_env.docker.enabled = True\n",
|
||||
"pytorch_env.docker.base_image = 'mcr.microsoft.com/azureml/openmpi3.1.2-cuda10.1-cudnn7-ubuntu18.04'"
|
||||
"pytorch_env.docker.base_image = 'mcr.microsoft.com/azureml/openmpi4.1.0-cuda11.1-cudnn8-ubuntu18.04'"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
@@ -8,7 +8,7 @@ dependencies:
|
||||
- matplotlib
|
||||
- azureml-dataset-runtime
|
||||
- ipywidgets
|
||||
- raiwidgets~=0.19.0
|
||||
- raiwidgets~=0.21.0
|
||||
- liac-arff
|
||||
- packaging>=20.9
|
||||
- itsdangerous==2.0.1
|
||||
|
||||
@@ -101,7 +101,7 @@
|
||||
"\n",
|
||||
"# Check core SDK version number\n",
|
||||
"\n",
|
||||
"print(\"This notebook was created using SDK version 1.44.0, you are currently running version\", azureml.core.VERSION)"
|
||||
"print(\"This notebook was created using SDK version 1.45.0, you are currently running version\", azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
@@ -1,10 +1,11 @@
|
||||
import keras
|
||||
from keras.models import Sequential
|
||||
from keras.layers import Dense, Dropout, Flatten
|
||||
from keras.layers import Conv2D, MaxPooling2D
|
||||
from keras.layers.normalization import BatchNormalization
|
||||
from keras.utils import to_categorical
|
||||
from keras.callbacks import Callback
|
||||
from tensorflow.keras.models import Sequential
|
||||
from tensorflow.keras.layers import Dense, Dropout, Flatten
|
||||
from tensorflow.keras.layers import Conv2D, MaxPooling2D
|
||||
from tensorflow.keras.layers import BatchNormalization
|
||||
from tensorflow.keras.losses import categorical_crossentropy
|
||||
from tensorflow.keras.optimizers import Adam
|
||||
from tensorflow.keras.utils import to_categorical
|
||||
from tensorflow.keras.callbacks import Callback
|
||||
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
@@ -64,8 +65,8 @@ model.add(Dense(128, activation='relu'))
|
||||
model.add(Dropout(0.3))
|
||||
model.add(Dense(num_classes, activation='softmax'))
|
||||
|
||||
model.compile(loss=keras.losses.categorical_crossentropy,
|
||||
optimizer=keras.optimizers.Adam(),
|
||||
model.compile(loss=categorical_crossentropy,
|
||||
optimizer=Adam(),
|
||||
metrics=['accuracy'])
|
||||
|
||||
# start an Azure ML run
|
||||
|
||||
@@ -270,16 +270,19 @@
|
||||
"%%writefile conda_dependencies.yml\n",
|
||||
"\n",
|
||||
"dependencies:\n",
|
||||
"- python=3.6.2\n",
|
||||
"- python=3.8\n",
|
||||
"- pip==20.2.4\n",
|
||||
"- pip:\n",
|
||||
" - azureml-core\n",
|
||||
" - azureml-dataset-runtime\n",
|
||||
" - keras==2.4.3\n",
|
||||
" - tensorflow==2.4.3\n",
|
||||
" - keras==2.6\n",
|
||||
" - tensorflow-gpu==2.6\n",
|
||||
" - numpy\n",
|
||||
" - scikit-learn\n",
|
||||
" - pandas\n",
|
||||
" - matplotlib"
|
||||
" - matplotlib\n",
|
||||
" - protobuf==3.20.1\n",
|
||||
" - typing-extensions==4.3.0"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
@@ -102,7 +102,7 @@
|
||||
"source": [
|
||||
"import azureml.core\n",
|
||||
"\n",
|
||||
"print(\"This notebook was created using version 1.44.0 of the Azure ML SDK\")\n",
|
||||
"print(\"This notebook was created using version 1.45.0 of the Azure ML SDK\")\n",
|
||||
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
|
||||
]
|
||||
},
|
||||
|
||||
@@ -151,8 +151,7 @@
|
||||
"# use a curated environment that has already been built for you\n",
|
||||
"\n",
|
||||
"env = Environment.get(workspace=ws, \n",
|
||||
" name=\"AzureML-Scikit-learn0.24-Cuda11-OpenMpi4.1.0-py36\", \n",
|
||||
" version=1)"
|
||||
" name=\"AzureML-sklearn-0.24-ubuntu18.04-py37-cpu\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
Reference in New Issue
Block a user