SIENTIAPDE-1273

Refactor data handling in various modules to ensure DataFrame consistency

- Replaced direct DataFrame instantiation with `ensure_dataframe` utility in Gates, MLFlow, OPC, and ModelMetrics classes to standardize data handling.
- Updated return types in several asynchronous methods to return DataFrames instead of dictionaries for improved usability.
- Adjusted data export processes in workflows to convert DataFrames to dictionaries with `to_dict(orient='records')` for compatibility with downstream systems.

laborious/activities/mlflow.py

@@ -20,6 +20,7 @@ with workflow.unsafe.imports_passed_through():
         now,
     )
 
+    from laborious.utils.dataframe_utils import ensure_dataframe
     from laborious.utils.repository.minio_repository import MinioRepository
     from laborious.utils.repository.model_repository import MLFlowRepository
 
@@ -139,7 +140,7 @@ class MLFlow(SientiaMonitoring):
         """
         metadata = input_data['metadata']
         self.info('Transforming data...', metadata)
-        data = DataFrame(input_data['data'])
+        data = ensure_dataframe(input_data['data'])
         model_name = input_data['model_name']
         model_config = input_data.get('model_config', {})
 
@@ -211,7 +212,7 @@ class MLFlow(SientiaMonitoring):
         """
         metadata = input_data['metadata']
         self.info('Predicting data...', metadata)
-        data = DataFrame(input_data['data'])
+        data = ensure_dataframe(input_data['data'])
         model_name = input_data['model_name']
         model_config = input_data.get('model_config', {})
 
@@ -422,7 +423,7 @@ class MLFlow(SientiaMonitoring):
 
 
     @activity.defn(name='get_reference_data')
-    async def get_reference_data(self, input_data: dict[str, Any]) -> dict[Hashable, Any] | None:
+    async def get_reference_data(self, input_data: dict[str, Any]) -> DataFrame | None:
         """
         Get reference data from the MLflow Model Registry.
 
@@ -451,4 +452,4 @@ class MLFlow(SientiaMonitoring):
         reference_data['timestamp'] = to_datetime(reference_data['timestamp'])
         reference_data['timestamp'] = reference_data['timestamp'].dt.strftime(DATETIME_FORMAT)
 
-        return reference_data.to_dict()
+        return reference_data