SIENTIAPDE-1712

SIENTIAPDE-1712 Refactor debug logging for DataFrames across multiple classes. Introduced a new method to log DataFrame content conditionally based on row count in Gates, MLFlow, ModelMetrics, and MLFlowRepository classes, improving debugging capabilities while managing log output effectively.

laborious/activities/mlflow.py

@@ -20,6 +20,7 @@ with workflow.unsafe.imports_passed_through():
     from sientia_do.utils.formatters import create_sample_dict
 
     from laborious.utils.models.minio_dataframe_payload import MinioDataFramePayload
+    from laborious.utils.dataframe_debug import build_dataframe_debug_message
     from laborious.utils.repository.minio_manager import MinioManager
     from laborious.utils.repository.model_repository import MLFlowRepository
 
@@ -104,19 +105,11 @@ class MLFlow(MinioManager):
          - data (Any): Dataframe-like object expected to expose shape and to_csv
          - metadata (dict[str, Any]): Workflow metadata for contextual logging
         """
-        if not hasattr(data, 'shape') or not hasattr(data, 'to_csv'):
-            self.debug(f'{message}\n{data}', metadata)
-            return
-
-        rows = data.shape[0]
-        if rows <= self._MAX_DEBUG_DATAFRAME_ROWS:
-            self.debug(f'{message}\n{data.to_csv()}', metadata)
-            return
-
         self.debug(
-            (
-                f'{message} skipped because dataframe has {rows} rows '
-                f'(max: {self._MAX_DEBUG_DATAFRAME_ROWS}). Shape: {data.shape}'
+            build_dataframe_debug_message(
+                message=message,
+                data=data,
+                max_rows=self._MAX_DEBUG_DATAFRAME_ROWS,
             ),
             metadata,
         )