Add support for predict_proba in classification notebook (#3531)

* modify to support predict_proba

* fix code style

Author: iamrk04

sdk/python/jobs/automl-standalone-jobs/automl-classification-task-bankmarketing/automl-classification-task-bankmarketing.ipynb

@@ -655,15 +655,19 @@
    "outputs": [],
    "source": [
     "model_name = \"bankmarketing-model\"\n",
+    "\n",
     "model = Model(\n",
-    "    path=f\"azureml://jobs/{best_run.info.run_id}/outputs/artifacts/outputs/mlflow-model/\",\n",
+    "    path=f\"azureml://jobs/{best_run.info.run_id}/outputs/artifacts/outputs/model.pkl\",\n",
     "    name=model_name,\n",
     "    description=\"my sample classification model\",\n",
-    "    type=AssetTypes.MLFLOW_MODEL,\n",
     ")\n",
     "\n",
-    "# for downloaded file\n",
-    "# model = Model(path=\"artifact_downloads/outputs/model.pkl\", name=model_name)\n",
+    "env = Environment(\n",
+    "    name=\"automl-tabular-env\",\n",
+    "    description=\"environment for automl inference\",\n",
+    "    image=\"mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu20.04:latest\",\n",
+    "    conda_file=\"artifact_downloads/outputs/conda_env_v_1_0_0.yml\",\n",
+    ")\n",
     "\n",
     "registered_model = ml_client.models.create_or_update(model)"
    ]
@@ -690,26 +694,18 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "code_configuration = CodeConfiguration(\n",
+    "    code=\"artifact_downloads/outputs/\", scoring_script=\"scoring_file_v_2_0_0.py\"\n",
+    ")\n",
+    "\n",
     "deployment = ManagedOnlineDeployment(\n",
     "    name=\"bankmarketing-deploy\",\n",
     "    endpoint_name=online_endpoint_name,\n",
     "    model=registered_model.id,\n",
     "    instance_type=\"Standard_DS2_V2\",\n",
     "    instance_count=1,\n",
-    "    liveness_probe=ProbeSettings(\n",
-    "        failure_threshold=30,\n",
-    "        success_threshold=1,\n",
-    "        timeout=2,\n",
-    "        period=10,\n",
-    "        initial_delay=2000,\n",
-    "    ),\n",
-    "    readiness_probe=ProbeSettings(\n",
-    "        failure_threshold=10,\n",
-    "        success_threshold=1,\n",
-    "        timeout=10,\n",
-    "        period=10,\n",
-    "        initial_delay=2000,\n",
-    "    ),\n",
+    "    code_configuration=code_configuration,\n",
+    "    environment=env,\n",
     ")"
    ]
   },
@@ -753,29 +749,32 @@
    "source": [
     "# test the blue deployment with some sample data\n",
     "import pandas as pd\n",
+    "import json\n",
     "\n",
     "test_data = pd.read_csv(\"./data/test-mltable-folder/bank_marketing_test_data.csv\")\n",
     "\n",
     "test_data = test_data.drop(\"y\", axis=1)\n",
     "\n",
     "test_data_json = test_data.to_json(orient=\"records\", indent=4)\n",
-    "data = (\n",
-    "    '{ \\\n",
-    "          \"input_data\": {\"data\": '\n",
-    "    + test_data_json\n",
-    "    + \"}}\"\n",
-    ")\n",
+    "\n",
+    "data = {\n",
+    "    \"Inputs\": {\"data\": json.loads(test_data_json)},\n",
+    "    \"GlobalParameters\": {\n",
+    "        \"method\": \"predict_proba\"  # use method \"predict\" when probability is not needed\n",
+    "    },\n",
+    "}\n",
     "\n",
     "request_file_name = \"sample-request-bankmarketing.json\"\n",
     "\n",
     "with open(request_file_name, \"w\") as request_file:\n",
-    "    request_file.write(data)\n",
+    "    json.dump(data, request_file)\n",
     "\n",
-    "ml_client.online_endpoints.invoke(\n",
+    "res = ml_client.online_endpoints.invoke(\n",
     "    endpoint_name=online_endpoint_name,\n",
     "    deployment_name=\"bankmarketing-deploy\",\n",
     "    request_file=request_file_name,\n",
-    ")"
+    ")\n",
+    "res"
    ]
   },
   {