SIENTIAPDE-1478

Enhance MLFlow logging and add skip_transform option in MLFlowRepository

- Updated logging in mlflow.py to output processed input data as CSV.
- Introduced skip_transform parameter in MLFlowRepository to conditionally bypass data transformation.
- Improved logging in model_repository.py to display data in a more structured format (to_dict) for predictions and transformations.

laborious/activities/mlflow.py

@@ -157,8 +157,8 @@ class MLFlow(SientiaMonitoring):
         data.columns.name = None
         data.index.name = None
 
-        self.debug('Processed input data:', metadata)
+        self.debug(f'Processed input data: \n {data.to_csv()}', metadata)
-        self.debug(data.head(5).to_string(), metadata)
+
 
         # Request transformation from MLFlow model
         response_data = await self.model_monitoring_repository.transform(

laborious/utils/repository/model_repository.py

@@ -752,6 +752,7 @@ class MLFlowRepository(SientiaMonitoring):
         latest_production_id: str,
         metadata: dict,
         transform_flavor: str = 'sklearn',
+        skip_transform: bool = False,
         predict_flavor: str = 'sklearn',
         target_name: str | None = None,
     ) -> dict[str, Any]:
@@ -812,7 +813,10 @@ class MLFlowRepository(SientiaMonitoring):
             load_wrapper=load_predict_wrapper,
         )
 
-        treated_data_candidate = data_model.fit(data)
+        if not skip_transform:
+            treated_data_candidate = data_model.fit(data)
+        else:
+            treated_data_candidate = data_model
 
         if not isinstance(treated_data_candidate, pd.DataFrame):
             data_model = treated_data_candidate
@@ -1164,7 +1168,7 @@ class MLFlowRepository(SientiaMonitoring):
                       and returned in the response structure rather than propagated.
         """
 
-        self.debug(f'Data received for model transformation: {data.head(5).to_csv()}', metadata)
+        self.debug(f'Data received for model transformation: {data.to_csv()}', metadata)
 
         # data.to_csv(
         #     f"tmp/data_{model_name}.csv", index=True)
@@ -1250,7 +1254,7 @@ class MLFlowRepository(SientiaMonitoring):
             input_index = data.index
             start_time = datetime.now()
 
-            self.debug(f'Data received for model prediction: {data.head(5).to_csv()}', metadata)
+            self.debug(f'Data received for model prediction: {data.to_dict(orient="records")}', metadata)
 
             # data.to_csv(
             #     f"tmp/treated_data_{model_name}.csv", index=True)
@@ -1268,7 +1272,7 @@ class MLFlowRepository(SientiaMonitoring):
 
             if isinstance(predict_data, pd.DataFrame):
                 self.debug(
-                    f'Data received from model prediction: {data.head(5).to_csv()}', metadata
+                    f'Data received from model prediction: {predict_data.to_dict(orient="records")}', metadata
                 )
 
                 # predict_data.to_csv(
@@ -1343,6 +1347,7 @@ class MLFlowRepository(SientiaMonitoring):
 
         transform_flavor = model_config.get('transform_flavor', 'sklearn')
         predict_flavor = model_config.get('predict_flavor', 'sklearn')
+        skip_transform = model_config.get('skip_transform', False)
 
         self.debug(
             f'Model configuration - transform_flavor: {transform_flavor}, predict_flavor: {predict_flavor}, target_name: {target_name}',
@@ -1356,6 +1361,7 @@ class MLFlowRepository(SientiaMonitoring):
                 model_name=model_name,
                 data=data,
                 transform_flavor=transform_flavor,
+                skip_transform=skip_transform,
                 predict_flavor=predict_flavor,
                 target_name=target_name,
                 metadata=metadata,