update samples from Release-170 as a part of 1.51 SDK stable release

Author: amlrelsa-ms

README.md

@@ -1,13 +1,8 @@
 # Azure Machine Learning Python SDK notebooks
 
-### **With the introduction of AzureML SDK v2, this samples repository for the v1 SDK is now deprecated and will not be monitored or updated. Users are encouraged to visit the [v2 SDK samples repository](https://github.com/Azure/azureml-examples) instead for up-to-date and enhanced examples of how to build, train, and deploy machine learning models with AzureML's newest features.**
-
--------------------------
-Welcome to the Azure Machine Learning Python SDK notebooks repository!
-
-
 > a community-driven repository of examples using mlflow for tracking can be found at https://github.com/Azure/azureml-examples
 
+Welcome to the Azure Machine Learning Python SDK notebooks repository!
 
 ## Getting started
 

configuration.ipynb

@@ -103,7 +103,7 @@
       "source": [
         "import azureml.core\n",
         "\n",
-        "print(\"This notebook was created using version 1.50.0 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version 1.51 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.yml

@@ -6,7 +6,7 @@ dependencies:
   - fairlearn>=0.6.2
   - joblib
   - liac-arff
-  - raiwidgets~=0.26.0
+  - raiwidgets~=0.27.0
   - itsdangerous==2.0.1
   - markupsafe<2.1.0
   - protobuf==3.20.0

contrib/fairness/upload-fairness-dashboard.yml

@@ -6,7 +6,7 @@ dependencies:
   - fairlearn>=0.6.2
   - joblib
   - liac-arff
-  - raiwidgets~=0.26.0
+  - raiwidgets~=0.27.0
   - itsdangerous==2.0.1
   - markupsafe<2.1.0
   - protobuf==3.20.0

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

@@ -12,13 +12,13 @@ dependencies:
 - pandas==1.1.5
 - scipy==1.5.3
 - Cython==0.29.14
-- tqdm==4.64.1
+- tqdm==4.65.0
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
-  - azureml-widgets~=1.50.0
-  - azureml-defaults~=1.50.0
-  - -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.50.0/validated_win32_requirements.txt [--no-deps]
+  - azureml-widgets~=1.51
+  - azureml-defaults~=1.51
+  - -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.51/validated_win32_requirements.txt [--no-deps]
   - matplotlib==3.6.2
   - xgboost==1.3.3
   - cmdstanpy==0.9.5

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

@@ -23,10 +23,10 @@ dependencies:
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
-  - azureml-widgets~=1.50.0
-  - azureml-defaults~=1.50.0
+  - azureml-widgets~=1.51
+  - azureml-defaults~=1.51
   - 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/1.50.0/validated_linux_requirements.txt [--no-deps]
+  - -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.51/validated_linux_requirements.txt [--no-deps]

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

@@ -16,17 +16,17 @@ dependencies:
 - scikit-learn==0.22.1
 - py-xgboost<=1.3.3
 - holidays==0.10.3
-- conda-forge::fbprophet==0.7.1
 - pytorch::pytorch=1.11.0
 - cudatoolkit=9.0
 - notebook
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
-  - azureml-widgets~=1.50.0
-  - azureml-defaults~=1.50.0
+  - azureml-widgets~=1.51
+  - azureml-defaults~=1.51
   - pytorch-transformers==1.0.0
   - spacy==2.2.4
   - pystan==2.19.1.1
+  - fbprophet==0.7.1
   - https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz
-  - -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.50.0/validated_darwin_requirements.txt [--no-deps]
+  - -r https://automlsdkdataresources.blob.core.windows.net/validated-requirements/1.51/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

@@ -712,7 +712,9 @@
         "from azureml.core.model import Model\n",
         "from azureml.core.environment import Environment\n",
         "\n",
-        "inference_config = InferenceConfig(entry_script=script_file_name)\n",
+        "inference_config = InferenceConfig(\n",
+        "    environment=best_run.get_environment(), entry_script=script_file_name\n",
+        ")\n",
         "\n",
         "aciconfig = AciWebservice.deploy_configuration(\n",
         "    cpu_cores=2,\n",

how-to-use-azureml/automated-machine-learning/experimental/autofeaturization-codegen/codegen-for-autofeaturization.ipynb

@@ -97,7 +97,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "print(\"This notebook was created using version 1.50.0 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version 1.51 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/experimental/autofeaturization-custom-model-training/custom-model-training-from-autofeaturization-run.ipynb

@@ -97,7 +97,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "print(\"This notebook was created using version 1.50.0 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version 1.51 of the Azure ML SDK\")\n",
         "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },
@@ -454,10 +454,13 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "**Note:** Not all datasets produce a y_transformer. The dataset used in the current notebook requires a transformer as the y column data is categorical."
+        "**Note:** Not all datasets produce a y_transformer. The dataset used in the current notebook requires a transformer as the y column data is categorical. \n",
+        "\n",
+        "We will go ahead and download the mlflow transformer model and use it to transform test data that can be used for further experimentation below. To run the commented code, make sure the environment requirement is satisfied. You can go ahead and create the environment from the `conda.yaml` file under `/outputs/featurization/pipeline/` and run the given code in it."
       ]
     },
     {
@@ -466,22 +469,23 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.automl.core.shared.constants import Transformers\n",
+        "''' from azureml.automl.core.shared.constants import Transformers\n",
         "\n",
         "transformers = mlflow.sklearn.load_model(uri) # Using method 1\n",
         "data_transformers = transformers.get_transformers()\n",
         "x_transformer = data_transformers[Transformers.X_TRANSFORMER]\n",
         "y_transformer = data_transformers[Transformers.Y_TRANSFORMER]\n",
         "\n",
         "X_test = x_transformer.transform(X_test_data)\n",
-        "y_test = y_transformer.transform(y_test_data)"
+        "y_test = y_transformer.transform(y_test_data) '''"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Run the following cell to see the featurization summary of X and y transformers.  "
+        "Run the following cell to see the featurization summary of X and y transformers. Uncomment to use.  "
       ]
     },
     {
@@ -490,10 +494,10 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "X_data_summary = x_transformer.get_featurization_summary(is_user_friendly=False)\n",
+        "''' X_data_summary = x_transformer.get_featurization_summary(is_user_friendly=False)\n",
         "\n",
         "summary_df = pd.DataFrame.from_records(X_data_summary)\n",
-        "summary_df"
+        "summary_df '''"
       ]
     },
     {
@@ -544,10 +548,11 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Another way to load the data is to go to the above autofeaturization experiment and check for the featurized dataset ids under `Output datasets`. Uncomment and replace them accordingly below to use."
+        "Another way to load the data is to go to the above autofeaturization experiment and check for the featurized dataset ids under `Output datasets`. Uncomment and replace them accordingly below, to use."
       ]
     },
     {
@@ -597,10 +602,20 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Here we are passing our training data to the lightgbm classifier, any custom model can be used with your data."
+        "Here we are passing our training data to the lightgbm classifier, any custom model can be used with your data. Let us first install lightgbm."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "! pip install lightgbm"
       ]
     },
     {
@@ -612,21 +627,15 @@
         "import lightgbm as lgb\n",
         "\n",
         "model = lgb.LGBMClassifier(learning_rate=0.08,max_depth=-5,random_state=42)\n",
-        "model.fit(X_train, y_train, sample_weight=sample_weight, eval_set=[(X_test, y_test),(X_train, y_train)],\n",
-        "          verbose=20,eval_metric='logloss')\n",
-        "\n",
-        "print('Training accuracy {:.4f}'.format(model.score(X_train, y_train)))\n",
-        "print('Testing accuracy {:.4f}'.format(model.score(X_test, y_test)))"
+        "model.fit(X_train, y_train, sample_weight=sample_weight)"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "<a id='Results'></a>\n",
-        "## Analyze results\n",
-        "\n",
-        "### Retrieve the Model"
+        "Once training is done, the test data obtained after transforming from the above downloaded transformer can be used to calculate the accuracy "
       ]
     },
     {
@@ -635,17 +644,20 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "model"
+        "print('Training accuracy {:.4f}'.format(model.score(X_train, y_train)))\n",
+        "\n",
+        "# Uncomment below to test the model on test data \n",
+        "# print('Testing accuracy {:.4f}'.format(model.score(X_test, y_test)))"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "<a id='Test'></a>\n",
-        "## Test the fitted model\n",
+        "<a id='Results'></a>\n",
+        "## Analyze results\n",
         "\n",
-        "Now that the model is trained, split the data in the same way the data was split for training (The difference here is the data is being split locally) and then run the test data through the trained model to get the predicted values."
+        "### Retrieve the Model"
       ]
     },
     {
@@ -654,17 +666,17 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "y_pred = model.predict(X_test)"
+        "model"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Calculate metrics for the prediction\n",
+        "<a id='Test'></a>\n",
+        "## Test the fitted model\n",
         "\n",
-        "Now visualize the data on a scatter plot to show what our truth (actual) values are compared to the predicted values \n",
-        "from the trained model that was returned."
+        "Now that the model is trained, split the data in the same way the data was split for training (The difference here is the data is being split locally) and then run the test data through the trained model to get the predicted values."
       ]
     },
     {
@@ -673,26 +685,8 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from sklearn.metrics import confusion_matrix\n",
-        "from matplotlib import pyplot as plt\n",
-        "import numpy as np\n",
-        "import itertools\n",
-        "\n",
-        "cf =confusion_matrix(y_test,y_pred)\n",
-        "plt.imshow(cf,cmap=plt.cm.Blues,interpolation='nearest')\n",
-        "plt.colorbar()\n",
-        "plt.title('Confusion Matrix')\n",
-        "plt.xlabel('Predicted')\n",
-        "plt.ylabel('Actual')\n",
-        "class_labels = ['False','True']\n",
-        "tick_marks = np.arange(len(class_labels))\n",
-        "plt.xticks(tick_marks,class_labels)\n",
-        "plt.yticks([-0.5,0,1,1.5],['','False','True',''])\n",
-        "# plotting text value inside cells\n",
-        "thresh = cf.max() / 2.\n",
-        "for i,j in itertools.product(range(cf.shape[0]),range(cf.shape[1])):\n",
-        "    plt.text(j,i,format(cf[i,j],'d'),horizontalalignment='center',color='white' if cf[i,j] >thresh else 'black')\n",
-        "plt.show()"
+        "# Uncomment below to test the model on test data\n",
+        "# y_pred = model.predict(X_test)"
       ]
     },
     {