Address PR comments: reference YAML instead of hard-coding it

Author: JKirsch1

articles/machine-learning/how-to-monitor-model-performance.md

@@ -922,79 +922,7 @@ After you register your production data and preprocessing component, you can set
     - For the `target_column` value, use the name of the output column that contains values that the model predicts.
     - Under `emails`, list the email addresses that you want to use for notifications.
 
-    ```yml
-    # model-monitoring-with-collected-data.yaml
-    $schema:  http://azureml/sdk-2-0/Schedule.json
-    name: fraud_detection_model_monitoring
-    display_name: Fraud detection model monitoring
-    description: Fraud detection model monitoring with your own production data
-
-    trigger:
-    # perform model monitoring activity daily at 3:15am
-    type: recurrence
-    frequency: day # Possible frequency values include "minute," "hour," "day," "week," and "month."
-    interval: 1 # Monitoring runs every day when you use the value 1.
-    schedule: 
-        hours: 3 # Monitoring starts sometime in the hour after 3:00 AM.
-        minutes: 15 # Monitoring starts 15 minutes after the scheduled hour.
-
-    create_monitor:
-    compute: 
-        instance_type: standard_e4s_v3
-        runtime_version: "3.3"
-    monitoring_target:
-        ml_task: classification
-        endpoint_deployment_id: azureml:fraud-detection-endpoint:fraud-detection-deployment
-    
-    monitoring_signals:
-
-        advanced_data_drift: # This term is the monitoring signal name. You can use any user-defined name.
-        type: data_drift
-        # Define a production data asset that contains your collected data.
-        production_data:
-            input_data:
-            path: azureml:my_production_inference_data_model_inputs:1  # Your collected data is registered as an Azure Machine Learning asset.
-            type: uri_folder
-            data_context: model_inputs
-            pre_processing_component: azureml:production_data_preprocessing:1.0.0
-        reference_data:
-            input_data:
-            path: azureml:my_model_training_data:1 # Use training data as a comparison baseline.
-            type: mltable
-            data_context: training
-            data_column_names:
-            target_column: is_fraud
-        features: 
-            top_n_feature_importance: 20 # Monitor drift for the top 20 features.
-        metric_thresholds:
-            numerical:
-            jensen_shannon_distance: 0.01
-            categorical:
-            pearsons_chi_squared_test: 0.02
-
-        advanced_prediction_drift: # This term is the monitoring signal name. You can use any user-defined name.
-        type: prediction_drift
-        # Define a production data asset that contains your collected data.
-        production_data:
-            input_data:
-            path: azureml:my_production_inference_data_model_outputs:1  # Your collected data is registered as an Azure Machine Learning asset.
-            type: uri_folder
-            data_context: model_outputs
-            pre_processing_component: azureml:production_data_preprocessing:1.0.0
-        reference_data:
-            input_data:
-            path: azureml:my_model_validation_data:1 # Use training data as a comparison reference data asset.
-            type: mltable
-            data_context: validation
-        metric_thresholds:
-            categorical:
-            pearsons_chi_squared_test: 0.02
-    
-    alert_notification:
-        emails:
-        - [email protected]
-        - [email protected]
-    ```
+    :::code language="yaml" source="~/azureml-examples-main/cli/monitoring/model-monitoring-with-collected-data.yaml":::
 
 1. Run the following command to create the model.