Merge pull request Azure#1489 from Azure/release_update/Release-97

update samples from Release-97 as a part of  SDK  1.29.0 release

Author: harneetvirk

configuration.ipynb

@@ -103,7 +103,7 @@
       "source": [
         "import azureml.core\n",
         "\n",
-        "print(\"This notebook was created using version 1.28.0 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version 1.29.0 of the Azure ML SDK\")\n",
         "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },

contrib/fairness/fairlearn-azureml-mitigation.ipynb

@@ -46,9 +46,10 @@
         "Please see the [configuration notebook](../../configuration.ipynb) for information about creating one, if required.\n",
         "This notebook also requires the following packages:\n",
         "* `azureml-contrib-fairness`\n",
-        "* `fairlearn==0.4.6` (v0.5.0 will work with minor modifications)\n",
+        "* `fairlearn>=0.6.2` (pre-v0.5.0 will work with minor modifications)\n",
         "* `joblib`\n",
         "* `liac-arff`\n",
+        "* `raiwidgets==0.4.0`\n",
         "\n",
         "Fairlearn relies on features introduced in v0.22.1 of `scikit-learn`. If you have an older version already installed, please uncomment and run the following cell:"
       ]
@@ -85,7 +86,7 @@
       "outputs": [],
       "source": [
         "from fairlearn.reductions import GridSearch, DemographicParity, ErrorRate\n",
-        "from fairlearn.widget import FairlearnDashboard\n",
+        "from raiwidgets import FairnessDashboard\n",
         "\n",
         "from sklearn.compose import ColumnTransformer\n",
         "from sklearn.impute import SimpleImputer\n",
@@ -256,9 +257,9 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "FairlearnDashboard(sensitive_features=A_test, sensitive_feature_names=['Sex', 'Race'],\n",
-        "                   y_true=y_test,\n",
-        "                   y_pred={\"unmitigated\": unmitigated_predictor.predict(X_test)})"
+        "FairnessDashboard(sensitive_features=A_test,\n",
+        "                  y_true=y_test,\n",
+        "                  y_pred={\"unmitigated\": unmitigated_predictor.predict(X_test)})"
       ]
     },
     {
@@ -311,8 +312,8 @@
         "sweep.fit(X_train, y_train,\n",
         "          sensitive_features=A_train.sex)\n",
         "\n",
-        "# For Fairlearn v0.5.0, need sweep.predictors_\n",
-        "predictors = sweep._predictors"
+        "# For Fairlearn pre-v0.5.0, need sweep._predictors\n",
+        "predictors = sweep.predictors_"
       ]
     },
     {
@@ -329,16 +330,14 @@
       "outputs": [],
       "source": [
         "errors, disparities = [], []\n",
-        "for m in predictors:\n",
-        "    classifier = lambda X: m.predict(X)\n",
-        "    \n",
+        "for predictor in predictors:\n",
         "    error = ErrorRate()\n",
         "    error.load_data(X_train, pd.Series(y_train), sensitive_features=A_train.sex)\n",
         "    disparity = DemographicParity()\n",
         "    disparity.load_data(X_train, pd.Series(y_train), sensitive_features=A_train.sex)\n",
         "    \n",
-        "    errors.append(error.gamma(classifier)[0])\n",
-        "    disparities.append(disparity.gamma(classifier).max())\n",
+        "    errors.append(error.gamma(predictor.predict)[0])\n",
+        "    disparities.append(disparity.gamma(predictor.predict).max())\n",
         "    \n",
         "all_results = pd.DataFrame( {\"predictor\": predictors, \"error\": errors, \"disparity\": disparities})\n",
         "\n",
@@ -387,10 +386,9 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "FairlearnDashboard(sensitive_features=A_test, \n",
-        "                   sensitive_feature_names=['Sex', 'Race'],\n",
-        "                   y_true=y_test.tolist(),\n",
-        "                   y_pred=predictions_dominant)"
+        "FairnessDashboard(sensitive_features=A_test, \n",
+        "                  y_true=y_test.tolist(),\n",
+        "                  y_pred=predictions_dominant)"
       ]
     },
     {
@@ -409,7 +407,7 @@
         "<a id=\"AzureUpload\"></a>\n",
         "## Uploading a Fairness Dashboard to Azure\n",
         "\n",
-        "Uploading a fairness dashboard to Azure is a two stage process. The `FairlearnDashboard` invoked in the previous section relies on the underlying Python kernel to compute metrics on demand. This is obviously not available when the fairness dashboard is rendered in AzureML Studio. By default, the dashboard in Azure Machine Learning Studio also requires the models to be registered. The required stages are therefore:\n",
+        "Uploading a fairness dashboard to Azure is a two stage process. The `FairnessDashboard` invoked in the previous section relies on the underlying Python kernel to compute metrics on demand. This is obviously not available when the fairness dashboard is rendered in AzureML Studio. By default, the dashboard in Azure Machine Learning Studio also requires the models to be registered. The required stages are therefore:\n",
         "1. Register the dominant models\n",
         "1. Precompute all the required metrics\n",
         "1. Upload to Azure\n",

contrib/fairness/fairlearn-azureml-mitigation.yml

@@ -3,6 +3,7 @@ dependencies:
 - pip:
   - azureml-sdk
   - azureml-contrib-fairness
-  - fairlearn==0.4.6
+  - fairlearn>=0.6.2
   - joblib
   - liac-arff
+  - raiwidgets==0.4.0

contrib/fairness/fairness_nb_utils.py

@@ -21,7 +21,7 @@ def fetch_openml_with_retries(data_id, max_retries=4, retry_delay=60):
             print("Download attempt {0} of {1}".format(i + 1, max_retries))
             data = fetch_openml(data_id=data_id, as_frame=True)
             break
-        except Exception as e:
+        except Exception as e:  # noqa: B902
             print("Download attempt failed with exception:")
             print(e)
             if i + 1 != max_retries:
@@ -47,7 +47,7 @@ def fetch_openml_with_retries(data_id, max_retries=4, retry_delay=60):
 
 
 def fetch_census_dataset():
-    """Fetch the Adult Census Dataset
+    """Fetch the Adult Census Dataset.
 
     This uses a particular URL for the Adult Census dataset. The code
     is a simplified version of fetch_openml() in sklearn.
@@ -63,17 +63,35 @@ def fetch_census_dataset():
 
     filename = "1595261.gz"
     data_url = "https://rainotebookscdn.blob.core.windows.net/datasets/"
-    urlretrieve(data_url + filename, filename)
 
-    http_stream = gzip.GzipFile(filename=filename, mode='rb')
-
-    with closing(http_stream):
-        def _stream_generator(response):
-            for line in response:
-                yield line.decode('utf-8')
-
-        stream = _stream_generator(http_stream)
-        data = arff.load(stream)
+    remaining_attempts = 5
+    sleep_duration = 10
+    while remaining_attempts > 0:
+        try:
+            urlretrieve(data_url + filename, filename)
+
+            http_stream = gzip.GzipFile(filename=filename, mode='rb')
+
+            with closing(http_stream):
+                def _stream_generator(response):
+                    for line in response:
+                        yield line.decode('utf-8')
+
+                stream = _stream_generator(http_stream)
+                data = arff.load(stream)
+        except Exception as exc:  # noqa: B902
+            remaining_attempts -= 1
+            print("Error downloading dataset from {} ({} attempt(s) remaining)"
+                  .format(data_url, remaining_attempts))
+            print(exc)
+            time.sleep(sleep_duration)
+            sleep_duration *= 2
+            continue
+        else:
+            # dataset successfully downloaded
+            break
+    else:
+        raise Exception("Could not retrieve dataset from {}.".format(data_url))
 
     attributes = OrderedDict(data['attributes'])
     arff_columns = list(attributes)

contrib/fairness/upload-fairness-dashboard.ipynb

@@ -30,7 +30,7 @@
         "1. [Training Models](#TrainingModels)\n",
         "1. [Logging in to AzureML](#LoginAzureML)\n",
         "1. [Registering the Models](#RegisterModels)\n",
-        "1. [Using the Fairlearn Dashboard](#LocalDashboard)\n",
+        "1. [Using the Fairness Dashboard](#LocalDashboard)\n",
         "1. [Uploading a Fairness Dashboard to Azure](#AzureUpload)\n",
         "    1. Computing Fairness Metrics\n",
         "    1. Uploading to Azure\n",
@@ -48,9 +48,10 @@
         "Please see the [configuration notebook](../../configuration.ipynb) for information about creating one, if required.\n",
         "This notebook also requires the following packages:\n",
         "* `azureml-contrib-fairness`\n",
-        "* `fairlearn==0.4.6` (should also work with v0.5.0)\n",
+        "* `fairlearn>=0.6.2` (also works for pre-v0.5.0 with slight modifications)\n",
         "* `joblib`\n",
         "* `liac-arff`\n",
+        "* `raiwidgets==0.4.0`\n",
         "\n",
         "Fairlearn relies on features introduced in v0.22.1 of `scikit-learn`. If you have an older version already installed, please uncomment and run the following cell:"
       ]
@@ -388,12 +389,11 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from fairlearn.widget import FairlearnDashboard\n",
+        "from raiwidgets import FairnessDashboard\n",
         "\n",
-        "FairlearnDashboard(sensitive_features=A_test, \n",
-        "                   sensitive_feature_names=['Sex', 'Race'],\n",
-        "                   y_true=y_test.tolist(),\n",
-        "                   y_pred=ys_pred)"
+        "FairnessDashboard(sensitive_features=A_test, \n",
+        "                  y_true=y_test.tolist(),\n",
+        "                  y_pred=ys_pred)"
       ]
     },
     {
@@ -403,7 +403,7 @@
         "<a id=\"AzureUpload\"></a>\n",
         "## Uploading a Fairness Dashboard to Azure\n",
         "\n",
-        "Uploading a fairness dashboard to Azure is a two stage process. The `FairlearnDashboard` invoked in the previous section relies on the underlying Python kernel to compute metrics on demand. This is obviously not available when the fairness dashboard is rendered in AzureML Studio. The required stages are therefore:\n",
+        "Uploading a fairness dashboard to Azure is a two stage process. The `FairnessDashboard` invoked in the previous section relies on the underlying Python kernel to compute metrics on demand. This is obviously not available when the fairness dashboard is rendered in AzureML Studio. The required stages are therefore:\n",
         "1. Precompute all the required metrics\n",
         "1. Upload to Azure\n",
         "\n",

contrib/fairness/upload-fairness-dashboard.yml

@@ -3,6 +3,7 @@ dependencies:
 - pip:
   - azureml-sdk
   - azureml-contrib-fairness
-  - fairlearn==0.4.6
+  - fairlearn>=0.6.2
   - joblib
   - liac-arff
+  - raiwidgets==0.4.0

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

@@ -21,8 +21,8 @@ dependencies:
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
-  - azureml-widgets~=1.28.0
+  - azureml-widgets~=1.29.0
   - pytorch-transformers==1.0.0
   - spacy==2.1.8
   - https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz
-  - -r https://automlresources-prod.azureedge.net/validated-requirements/1.28.0/validated_win32_requirements.txt [--no-deps]
+  - -r https://automlresources-prod.azureedge.net/validated-requirements/1.29.0/validated_win32_requirements.txt [--no-deps]

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

@@ -21,8 +21,8 @@ dependencies:
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
-  - azureml-widgets~=1.28.0
+  - azureml-widgets~=1.29.0
   - pytorch-transformers==1.0.0
   - spacy==2.1.8
   - https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz
-  - -r https://automlresources-prod.azureedge.net/validated-requirements/1.28.0/validated_linux_requirements.txt [--no-deps]
+  - -r https://automlresources-prod.azureedge.net/validated-requirements/1.29.0/validated_linux_requirements.txt [--no-deps]

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

@@ -22,8 +22,8 @@ dependencies:
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
-  - azureml-widgets~=1.28.0
+  - azureml-widgets~=1.29.0
   - pytorch-transformers==1.0.0
   - spacy==2.1.8
   - https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz
-  - -r https://automlresources-prod.azureedge.net/validated-requirements/1.28.0/validated_darwin_requirements.txt [--no-deps]
+  - -r https://automlresources-prod.azureedge.net/validated-requirements/1.29.0/validated_darwin_requirements.txt [--no-deps]

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

@@ -105,7 +105,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "print(\"This notebook was created using version 1.28.0 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version 1.29.0 of the Azure ML SDK\")\n",
         "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },