update samples from Release-167 as a part of 1.0.83 SDK release

Author: vizhur

configuration.ipynb

@@ -103,7 +103,7 @@
       "source": [
         "import azureml.core\n",
         "\n",
-        "print(\"This notebook was created using version 1.0.81 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version 1.0.83 of the Azure ML SDK\")\n",
         "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },

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

@@ -13,7 +13,6 @@ dependencies:
 - scikit-learn>=0.19.0,<=0.20.3
 - pandas>=0.22.0,<=0.23.4
 - py-xgboost<=0.80
-- pyarrow>=0.11.0
 - fbprophet==0.5
 - pytorch=1.1.0
 - cudatoolkit=9.0

how-to-use-azureml/automated-machine-learning/automl_env_mac.yml

@@ -14,7 +14,6 @@ dependencies:
 - scikit-learn>=0.19.0,<=0.20.3
 - pandas>=0.22.0,<0.23.0
 - py-xgboost<=0.80
-- pyarrow>=0.11.0
 - fbprophet==0.5
 - pytorch=1.1.0
 - cudatoolkit=9.0

how-to-use-azureml/automated-machine-learning/classification-bank-marketing-all-features/auto-ml-classification-bank-marketing-all-features.yml

@@ -2,12 +2,3 @@ name: auto-ml-classification-bank-marketing-all-features
 dependencies:
 - pip:
   - azureml-sdk
-  - interpret
-  - azureml-defaults
-  - azureml-train-automl
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml
-  - onnxruntime==1.0.0
-  - azureml-explain-model
-  - azureml-contrib-interpret

how-to-use-azureml/automated-machine-learning/classification-credit-card-fraud/auto-ml-classification-credit-card-fraud.yml

@@ -2,10 +2,3 @@ name: auto-ml-classification-credit-card-fraud
 dependencies:
 - pip:
   - azureml-sdk
-  - interpret
-  - azureml-defaults
-  - azureml-explain-model
-  - azureml-train-automl
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml

how-to-use-azureml/automated-machine-learning/classification-text-dnn/auto-ml-classification-text-dnn.ipynb

@@ -519,12 +519,12 @@
         "name": "anshirga"
       }
     ],
-    "datasets": [
-      "None"
-    ],
     "compute": [
       "AML Compute"
     ],
+    "datasets": [
+      "None"
+    ],
     "deployment": [
       "None"
     ],

how-to-use-azureml/automated-machine-learning/classification-text-dnn/auto-ml-classification-text-dnn.yml

@@ -2,9 +2,3 @@ name: auto-ml-classification-text-dnn
 dependencies:
 - pip:
   - azureml-sdk
-  - azureml-train-automl
-  - azureml-train
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml
-  - statsmodels

how-to-use-azureml/automated-machine-learning/continuous-retraining/auto-ml-continuous-retraining.ipynb

@@ -347,7 +347,7 @@
         "\n",
         "automl_settings = {\n",
         "    \"iteration_timeout_minutes\": 10,\n",
-        "    \"experiment_timeout_minutes\": 10,\n",
+        "    \"experiment_timeout_hours\": 0.2,\n",
         "    \"n_cross_validations\": 3,\n",
         "    \"primary_metric\": 'r2_score',\n",
         "    \"preprocess\": True,\n",
@@ -378,7 +378,7 @@
         "metrics_output_name = 'metrics_output'\n",
         "best_model_output_name = 'best_model_output'\n",
         "\n",
-        "metirics_data = PipelineData(name='metrics_data',\n",
+        "metrics_data = PipelineData(name='metrics_data',\n",
         "                           datastore=dstor,\n",
         "                           pipeline_output_name=metrics_output_name,\n",
         "                           training_output=TrainingOutput(type='Metrics'))\n",
@@ -397,7 +397,7 @@
         "automl_step = AutoMLStep(\n",
         "    name='automl_module',\n",
         "    automl_config=automl_config,\n",
-        "    outputs=[metirics_data, model_data],\n",
+        "    outputs=[metrics_data, model_data],\n",
         "    allow_reuse=False)"
       ]
     },

how-to-use-azureml/automated-machine-learning/continuous-retraining/auto-ml-continuous-retraining.yml

@@ -2,8 +2,3 @@ name: auto-ml-continuous-retraining
 dependencies:
 - pip:
   - azureml-sdk
-  - azureml-train-automl
-  - azureml-pipeline
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml

how-to-use-azureml/automated-machine-learning/forecasting-beer-remote/auto-ml-forecasting-beer-remote.ipynb

@@ -358,7 +358,7 @@
         "\n",
         "automl_config = AutoMLConfig(task='forecasting',                             \n",
         "                             primary_metric='normalized_root_mean_squared_error',\n",
-        "                             experiment_timeout_minutes = 60,\n",
+        "                             experiment_timeout_hours = 1,\n",
         "                             training_data=train_dataset,\n",
         "                             label_column_name=target_column_name,\n",
         "                             validation_data=valid_dataset, \n",

how-to-use-azureml/automated-machine-learning/forecasting-beer-remote/auto-ml-forecasting-beer-remote.yml

@@ -1,12 +1,4 @@
 name: auto-ml-forecasting-beer-remote
 dependencies:
-- fbprophet==0.5
-- py-xgboost<=0.80
 - pip:
   - azureml-sdk
-  - azureml-train-automl
-  - azureml-train
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml
-  - statsmodels

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

@@ -248,7 +248,7 @@
         "|**task**|forecasting|\n",
         "|**primary_metric**|This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>\n",
         "|**blacklist_models**|Models in blacklist won't be used by AutoML. All supported models can be found at [here](https://docs.microsoft.com/en-us/python/api/azureml-train-automl-client/azureml.train.automl.constants.supportedmodels.forecasting?view=azure-ml-py).|\n",
-        "|**experiment_timeout_minutes**|Experimentation timeout in minutes.|\n",
+        "|**experiment_timeout_hours**|Experimentation timeout in hours.|\n",
         "|**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",
@@ -260,7 +260,7 @@
         "|**target_lags**|The target_lags specifies how far back we will construct the lags of the target variable.|\n",
         "|**drop_column_names**|Name(s) of columns to drop prior to modeling|\n",
         "\n",
-        "This notebook uses the blacklist_models parameter to exclude some models that take a longer time to train on this dataset. You can choose to remove models from the blacklist_models list but you may need to increase the experiment_timeout_minutes parameter value to get results."
+        "This notebook uses the blacklist_models parameter to exclude some models that take a longer time to train on this dataset. You can choose to remove models from the blacklist_models list but you may need to increase the experiment_timeout_hours parameter value to get results."
       ]
     },
     {
@@ -305,7 +305,7 @@
         "automl_config = AutoMLConfig(task='forecasting',                             \n",
         "                             primary_metric='normalized_root_mean_squared_error',\n",
         "                             blacklist_models = ['ExtremeRandomTrees'],                             \n",
-        "                             experiment_timeout_minutes=20,\n",
+        "                             experiment_timeout_hours=0.3,\n",
         "                             training_data=train,\n",
         "                             label_column_name=target_column_name,\n",
         "                             compute_target=compute_target,\n",

how-to-use-azureml/automated-machine-learning/forecasting-bike-share/auto-ml-forecasting-bike-share.yml

@@ -1,11 +1,4 @@
 name: auto-ml-forecasting-bike-share
 dependencies:
-- fbprophet==0.5
-- py-xgboost<=0.80
 - pip:
   - azureml-sdk
-  - azureml-train-automl
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml
-  - statsmodels

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

@@ -302,7 +302,7 @@
         "|**task**|forecasting|\n",
         "|**primary_metric**|This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>|\n",
         "|**blacklist_models**|Models in blacklist won't be used by AutoML. All supported models can be found at [here](https://docs.microsoft.com/en-us/python/api/azureml-train-automl-client/azureml.train.automl.constants.supportedmodels.forecasting?view=azure-ml-py).|\n",
-        "|**experiment_timeout_minutes**|Maximum amount of time in minutes that the experiment take before it terminates.|\n",
+        "|**experiment_timeout_hours**|Maximum amount of time in hours that the experiment take before it terminates.|\n",
         "|**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",
@@ -316,7 +316,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "This notebook uses the blacklist_models parameter to exclude some models that take a longer time to train on this dataset. You can choose to remove models from the blacklist_models list but you may need to increase the experiment_timeout_minutes parameter value to get results."
+        "This notebook uses the blacklist_models parameter to exclude some models that take a longer time to train on this dataset. You can choose to remove models from the blacklist_models list but you may need to increase the experiment_timeout_hours parameter value to get results."
       ]
     },
     {
@@ -333,7 +333,7 @@
         "automl_config = AutoMLConfig(task='forecasting',                             \n",
         "                             primary_metric='normalized_root_mean_squared_error',\n",
         "                             blacklist_models = ['ExtremeRandomTrees', 'AutoArima', 'Prophet'],                             \n",
-        "                             experiment_timeout_minutes=20,\n",
+        "                             experiment_timeout_hours=0.3,\n",
         "                             training_data=train,\n",
         "                             label_column_name=target_column_name,\n",
         "                             compute_target=compute_target,\n",
@@ -578,7 +578,7 @@
         "automl_config = AutoMLConfig(task='forecasting',                             \n",
         "                             primary_metric='normalized_root_mean_squared_error',\n",
         "                             blacklist_models = ['ElasticNet','ExtremeRandomTrees','GradientBoosting','XGBoostRegressor','ExtremeRandomTrees', 'AutoArima', 'Prophet'], #These models are blacklisted for tutorial purposes, remove this for real use cases.                            \n",
-        "                             experiment_timeout_minutes=20,\n",
+        "                             experiment_timeout_hours=0.3,\n",
         "                             training_data=train,\n",
         "                             label_column_name=target_column_name,\n",
         "                             compute_target=compute_target,\n",

how-to-use-azureml/automated-machine-learning/forecasting-energy-demand/auto-ml-forecasting-energy-demand.yml

@@ -2,11 +2,3 @@ name: auto-ml-forecasting-energy-demand
 dependencies:
 - pip:
   - azureml-sdk
-  - interpret
-  - azureml-train-automl
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml
-  - statsmodels
-  - azureml-explain-model
-  - azureml-contrib-interpret

how-to-use-azureml/automated-machine-learning/forecasting-grouping/auto-ml-forecasting-grouping.ipynb

@@ -251,7 +251,7 @@
       "source": [
         "automl_settings = {\n",
         "    \"iteration_timeout_minutes\" : 5,\n",
-        "    \"experiment_timeout_minutes\" : 15,\n",
+        "    \"experiment_timeout_hours\" : 0.25,\n",
         "    \"primary_metric\" : 'normalized_mean_absolute_error',\n",
         "    \"time_column_name\": time_column_name,\n",
         "    \"grain_column_names\": grain_column_names,\n",

how-to-use-azureml/automated-machine-learning/forecasting-grouping/auto-ml-forecasting-grouping.yml

@@ -2,9 +2,3 @@ name: auto-ml-forecasting-grouping
 dependencies:
 - pip:
   - azureml-sdk
-  - azureml-train-automl
-  - azureml-pipeline
-  - azureml-widgets
-  - pandas_ml
-  - statsmodels
-  - matplotlib

how-to-use-azureml/automated-machine-learning/forecasting-grouping/build.py

@@ -71,7 +71,7 @@ def build_pipeline_steps(automlconfig: AutoMLConfig,
     # create each automl step end-to-end (train, register)
     for group_name, conf in configs.items():
         # create automl metrics output
-        metirics_data = PipelineData(
+        metrics_data = PipelineData(
             name='metrics_data_{}'.format(group_name),
             pipeline_output_name=metrics_output_name.format(group_name),
             training_output=TrainingOutput(type='Metrics'))
@@ -84,7 +84,7 @@ def build_pipeline_steps(automlconfig: AutoMLConfig,
         automl_step = AutoMLStep(
             name='automl_{}'.format(group_name),
             automl_config=conf,
-            outputs=[metirics_data, model_data],
+            outputs=[metrics_data, model_data],
             allow_reuse=True)
         steps.append(automl_step)
 

how-to-use-azureml/automated-machine-learning/forecasting-high-frequency/automl-forecasting-function.ipynb

@@ -335,7 +335,7 @@
         "automl_config = AutoMLConfig(task='forecasting',\n",
         "                             debug_log='automl_forecasting_function.log',\n",
         "                             primary_metric='normalized_root_mean_squared_error',\n",
-        "                             experiment_timeout_minutes=15,\n",
+        "                             experiment_timeout_hours=0.25,\n",
         "                             enable_early_stopping=True,\n",
         "                             training_data=train_data,\n",
         "                             compute_target=compute_target,\n",

how-to-use-azureml/automated-machine-learning/forecasting-high-frequency/automl-forecasting-function.yml

@@ -1,11 +1,4 @@
 name: automl-forecasting-function
 dependencies:
-- fbprophet==0.5
-- py-xgboost<=0.80
 - pip:
   - azureml-sdk
-  - azureml-train-automl
-  - azureml-widgets
-  - pandas_ml
-  - statsmodels
-  - matplotlib

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

@@ -335,7 +335,7 @@
         "|-|-|\n",
         "|**task**|forecasting|\n",
         "|**primary_metric**|This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>\n",
-        "|**experiment_timeout_minutes**|Experimentation timeout in minutes.|\n",
+        "|**experiment_timeout_hours**|Experimentation timeout in hours.|\n",
         "|**enable_early_stopping**|If early stopping is on, training will stop when the primary metric is no longer improving.|\n",
         "|**training_data**|Input dataset, containing both features and label column.|\n",
         "|**label_column_name**|The name of the label column.|\n",
@@ -366,7 +366,7 @@
         "automl_config = AutoMLConfig(task='forecasting',\n",
         "                             debug_log='automl_oj_sales_errors.log',\n",
         "                             primary_metric='normalized_mean_absolute_error',\n",
-        "                             experiment_timeout_minutes=15,\n",
+        "                             experiment_timeout_hours=0.25,\n",
         "                             training_data=train_dataset,\n",
         "                             label_column_name=target_column_name,\n",
         "                             compute_target=compute_target,\n",

how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales/auto-ml-forecasting-orange-juice-sales.yml

@@ -1,11 +1,4 @@
 name: auto-ml-forecasting-orange-juice-sales
 dependencies:
-- fbprophet==0.5
-- py-xgboost<=0.80
 - pip:
   - azureml-sdk
-  - azureml-train-automl
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml
-  - statsmodels

how-to-use-azureml/automated-machine-learning/local-run-classification-credit-card-fraud/auto-ml-classification-credit-card-fraud-local.ipynb

@@ -156,7 +156,7 @@
         "    \"n_cross_validations\": 3,\n",
         "    \"primary_metric\": 'average_precision_score_weighted',\n",
         "    \"preprocess\": True,\n",
-        "    \"experiment_timeout_minutes\": 10, # This is a time limit for testing purposes, remove it for real use cases, this will drastically limit ablity to find the best model possible\n",
+        "    \"experiment_timeout_hours\": 0.2, # This is a time limit for testing purposes, remove it for real use cases, this will drastically limit ability to find the best model possible\n",
         "    \"verbosity\": logging.INFO,\n",
         "    \"enable_stack_ensemble\": False\n",
         "}\n",
@@ -260,17 +260,7 @@
       "metadata": {},
       "source": [
         "#### Print the properties of the model\n",
-        "The fitted_model is a python object and you can read the different properties of the object.\n",
-        "See *Print the properties of the model* section in [this sample notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/automated-machine-learning/classification/auto-ml-classification.ipynb)."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Deploy\n",
-        "\n",
-        "To deploy the model into a web service endpoint, see _Deploy_ section in [this sample notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/automated-machine-learning/classification-with-deployment/auto-ml-classification-with-deployment.ipynb)"
+        "The fitted_model is a python object and you can read the different properties of the object.\n"
       ]
     },
     {

how-to-use-azureml/automated-machine-learning/local-run-classification-credit-card-fraud/auto-ml-classification-credit-card-fraud-local.yml

@@ -2,10 +2,3 @@ name: auto-ml-classification-credit-card-fraud-local
 dependencies:
 - pip:
   - azureml-sdk
-  - interpret
-  - azureml-defaults
-  - azureml-explain-model
-  - azureml-train-automl
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml

how-to-use-azureml/automated-machine-learning/regression-hardware-performance-explanation-and-featurization/auto-ml-regression-hardware-performance-explanation-and-featurization.ipynb

@@ -206,7 +206,7 @@
         "|-|-|\n",
         "|**task**|classification, regression or forecasting|\n",
         "|**primary_metric**|This is the metric that you want to optimize. Regression supports the following primary metrics: <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>|\n",
-        "|**experiment_timeout_minutes**| Maximum amount of time in minutes that all iterations combined can take before the experiment terminates.|\n",
+        "|**experiment_timeout_hours**| Maximum amount of time in hours that all iterations combined can take before the experiment terminates.|\n",
         "|**enable_early_stopping**| Flag to enble early termination if the score is not improving in the short term.|\n",
         "|**featurization**| 'auto' / 'off' / FeaturizationConfig Indicator for whether featurization step should be done automatically or not, or whether customized featurization should be used. Note: If the input data is sparse, featurization cannot be turned on.|\n",
         "|**n_cross_validations**|Number of cross validation splits.|\n",
@@ -262,7 +262,7 @@
       "source": [
         "automl_settings = {\n",
         "    \"enable_early_stopping\": True, \n",
-        "    \"experiment_timeout_minutes\" : 10,\n",
+        "    \"experiment_timeout_hours\" : 0.2,\n",
         "    \"max_concurrent_iterations\": 4,\n",
         "    \"max_cores_per_iteration\": -1,\n",
         "    \"n_cross_validations\": 5,\n",

how-to-use-azureml/automated-machine-learning/regression-hardware-performance-explanation-and-featurization/auto-ml-regression-hardware-performance-explanation-and-featurization.yml

@@ -2,12 +2,3 @@ name: auto-ml-regression-hardware-performance-explanation-and-featurization
 dependencies:
 - pip:
   - azureml-sdk
-  - interpret
-  - azureml-defaults
-  - azureml-explain-model
-  - azureml-train-automl
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml
-  - azureml-explain-model
-  - azureml-contrib-interpret

how-to-use-azureml/automated-machine-learning/regression/auto-ml-regression.ipynb

@@ -188,15 +188,19 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "metadata": {},
+      "metadata": {
+        "tags": [
+          "automlconfig-remarks-sample"
+        ]
+      },
       "outputs": [],
       "source": [
         "automl_settings = {\n",
         "    \"n_cross_validations\": 3,\n",
         "    \"primary_metric\": 'r2_score',\n",
         "    \"preprocess\": True,\n",
         "    \"enable_early_stopping\": True, \n",
-        "    \"experiment_timeout_minutes\": 20, #for real scenarios we reccommend a timeout of at least one hour \n",
+        "    \"experiment_timeout_hours\": 0.3, #for real scenarios we reccommend a timeout of at least one hour \n",
         "    \"max_concurrent_iterations\": 4,\n",
         "    \"max_cores_per_iteration\": -1,\n",
         "    \"verbosity\": logging.INFO,\n",