SIENTIAPDE-1273

Enhance MLFlowRepository and Activities classes with new methods and metrics

- Added `check_artifact_exists` method to MLFlowRepository for verifying artifact presence in the MLflow Model Registry.
- Implemented `get_prediction_data` method in MLFlowRepository to retrieve prediction data from models.
- Updated Activities class to integrate ModelMetrics for improved metrics handling.
- Enhanced tests for artifact existence checks and prediction data retrieval, ensuring robust coverage for new functionalities.
- Updated various workflows to include `transform_table_name` in input data for better data handling.

laborious/activities/mlflow.py

@@ -1,3 +1,4 @@
+from typing import Hashable
 from temporalio import activity, workflow
 
 with workflow.unsafe.imports_passed_through():
@@ -418,3 +419,36 @@ class MLFlow(SientiaMonitoring):
             )
             self.error(trace, metadata=metadata)
             raise e
+
+
+    @activity.defn(name='get_reference_data')
+    async def get_reference_data(self, input_data: dict[str, Any]) -> dict[Hashable, Any] | None:
+        """
+        Get reference data from the MLflow Model Registry.
+
+        Args:
+            input_data (dict): Input data containing:
+                - metadata (dict): Workflow execution metadata
+                - model_name (str): Name of the MLFlow model to get reference data from
+
+        Returns:
+            dict[Hashable, Any] | None: Reference data from the MLflow Model Registry.
+
+        """
+
+        metadata = input_data['metadata']
+        model_name = input_data['model_name']
+        artifact = "evaluation_data.csv"
+
+        reference_data = await self.model_monitoring_repository.load_artifact_dataframe(
+            model_name=model_name, artifact_path=artifact, metadata=metadata
+        )
+
+        if reference_data is None:
+            self.warning(f'Reference data not found for model {model_name}', metadata)
+            return None
+
+        reference_data['timestamp'] = to_datetime(reference_data['timestamp'])
+        reference_data['timestamp'] = reference_data['timestamp'].dt.strftime(DATETIME_FORMAT)
+
+        return reference_data.to_dict()