update samples - test

Author: vizhur

configuration.ipynb

@@ -103,7 +103,7 @@
       "source": [
         "import azureml.core\n",
         "\n",
-        "print(\"This notebook was created using version 1.0.72 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version 1.0.72.1 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/README.md

@@ -154,6 +154,12 @@ jupyter notebook
 - [auto-ml-continuous-retraining.ipynb](continuous-retraining/auto-ml-continuous-retraining.ipynb)
     - Continous retraining using Pipelines and Time-Series TabularDataset
 
+- [auto-ml-classification-text-dnn.ipynb](classification-text-dnn/auto-ml-classification-text-dnn.ipynb)
+    - Classification with text data using deep learning in AutoML
+    - AutoML highlights here include using deep neural networks (DNNs) to create embedded features from text data.
+    - Depending on the compute cluster the user provides, AutoML tried out Bidirectional Encoder Representations from Transformers (BERT) when a GPU compute is used.
+    - Bidirectional Long-Short Term neural network (BiLSTM) when a CPU compute is used, thereby optimizing the choice of DNN for the uesr's setup.
+
 <a name="documentation"></a>
 See [Configure automated machine learning experiments](https://docs.microsoft.com/azure/machine-learning/service/how-to-configure-auto-train) to learn how more about the the settings and features available for automated machine learning experiments.
 

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

@@ -14,7 +14,9 @@ dependencies:
 - pandas>=0.22.0,<=0.23.4
 - py-xgboost<=0.80
 - pyarrow>=0.11.0
-- conda-forge::fbprophet==0.5
+- fbprophet==0.5
+- pytorch=1.1.0
+- cudatoolkit=9.0
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
@@ -23,6 +25,14 @@ dependencies:
   - azureml-train
   - azureml-widgets
   - azureml-explain-model
+  - azureml-pipeline
   - azureml-contrib-interpret
   - pandas_ml
-  
+  - pytorch-transformers==1.0.0
+  - spacy==2.1.8
+  - joblib
+  - https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz
+
+channels:
+- conda-forge
+- pytorch

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

@@ -15,7 +15,9 @@ dependencies:
 - pandas>=0.22.0,<0.23.0
 - py-xgboost<=0.80
 - pyarrow>=0.11.0
-- conda-forge::fbprophet==0.5
+- fbprophet==0.5
+- pytorch=1.1.0
+- cudatoolkit=9.0
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
@@ -24,6 +26,14 @@ dependencies:
   - azureml-train
   - azureml-widgets
   - azureml-explain-model
+  - azureml-pipeline
   - azureml-contrib-interpret
   - pandas_ml
-  
+  - pytorch-transformers==1.0.0
+  - spacy==2.1.8
+  - joblib
+  - https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz  
+
+channels:
+- conda-forge
+- pytorch

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

@@ -382,6 +382,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
+        "# Wait for the remote run to complete\n",
         "remote_run.wait_for_completion()"
       ]
     },
@@ -463,8 +464,31 @@
       "metadata": {},
       "source": [
         "### Retrieve the Best Model's explanation\n",
-        "Retrieve the explanation from the best_run which includes explanations for engineered features and raw features.\n",
+        "Retrieve the explanation from the best_run which includes explanations for engineered features and raw features. Make sure that the run for generating explanations for the best model is completed."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Wait for the best model explanation run to complete\n",
+        "from azureml.train.automl.run import AutoMLRun\n",
+        "model_explainability_run_id = remote_run.get_properties().get('ModelExplainRunId')\n",
+        "print(model_explainability_run_id)\n",
+        "if model_explainability_run_id is not None:\n",
+        "    model_explainability_run = AutoMLRun(experiment=experiment, run_id=model_explainability_run_id)\n",
+        "    model_explainability_run.wait_for_completion()\n",
         "\n",
+        "# Get the best run object\n",
+        "best_run, fitted_model = remote_run.get_output()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
         "#### Download engineered feature importance from artifact store\n",
         "You can use ExplanationClient to download the engineered feature explanations from the artifact store of the best_run."
       ]
@@ -475,13 +499,32 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "best_run, fitted_model = remote_run.get_output()\n",
         "client = ExplanationClient.from_run(best_run)\n",
         "engineered_explanations = client.download_model_explanation(raw=False)\n",
         "exp_data = engineered_explanations.get_feature_importance_dict()\n",
         "exp_data"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Download raw feature importance from artifact store\n",
+        "You can use ExplanationClient to download the raw feature explanations from the artifact store of the best_run."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "client = ExplanationClient.from_run(best_run)\n",
+        "engineered_explanations = client.download_model_explanation(raw=True)\n",
+        "exp_data = engineered_explanations.get_feature_importance_dict()\n",
+        "exp_data"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -524,7 +567,8 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Predict with the ONNX model, using onnxruntime package"
+        "### Predict with the ONNX model, using onnxruntime package\n",
+        "#### Note: The code will install the onnxruntime==0.4.0 if not installed. Newer versions of the onnxruntime have compatibility issues."
       ]
     },
     {
@@ -552,12 +596,21 @@
         "else:\n",
         "    python_version_compatible = False\n",
         "\n",
+        "onnxrt_present = False\n",
         "try:\n",
         "    import onnxruntime\n",
         "    from azureml.automl.core.onnx_convert import OnnxInferenceHelper    \n",
-        "    onnxrt_present = True\n",
+        "    from onnxruntime import __version__ as ORT_VER\n",
+        "    if ORT_VER == '0.4.0':\n",
+        "        onnxrt_present = True\n",
         "except ImportError:\n",
         "    onnxrt_present = False\n",
+        "    \n",
+        "# Install the onnxruntime if the version 0.4.0 is not installed.\n",
+        "if not onnxrt_present:\n",
+        "    print(\"Installing the onnxruntime version 0.4.0.\")\n",
+        "    !{sys.executable} -m pip install --user --force-reinstall onnxruntime==0.4.0\n",
+        "    onnxrt_present = True\n",
         "\n",
         "def get_onnx_res(run):\n",
         "    res_path = 'onnx_resource.json'\n",
@@ -826,13 +879,6 @@
         "\n",
         "[Moro et al., 2014] S. Moro, P. Cortez and P. Rita. A Data-Driven Approach to Predict the Success of Bank Telemarketing. Decision Support Systems, Elsevier, 62:22-31, June 2014"
       ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": []
     }
   ],
   "metadata": {

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

@@ -8,6 +8,6 @@ dependencies:
   - azureml-widgets
   - matplotlib
   - pandas_ml
-  - onnxruntime
+  - onnxruntime==0.4.0
   - azureml-explain-model
   - azureml-contrib-interpret