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/utils/dataframe_debug.py

@@ -0,0 +1,34 @@
+from typing import Any
+
+from pandas import DataFrame
+
+DEFAULT_MAX_DEBUG_DATAFRAME_ROWS = 100
+
+
+def build_dataframe_debug_message(
+    message: str,
+    data: Any,
+    max_rows: int = DEFAULT_MAX_DEBUG_DATAFRAME_ROWS,
+) -> str:
+    """
+    Build a safe debug message for dataframe payloads
+
+    Args:
+     - message (str): Base message to identify the logged payload
+     - data (Any): Payload to evaluate for dataframe-aware logging
+     - max_rows (int): Maximum dataframe row count allowed for full payload logging
+
+    Return:
+     Formatted debug message with full dataframe content or compact summary
+    """
+    if not isinstance(data, DataFrame):
+        return f'{message} {data}'
+
+    rows = data.shape[0]
+    if rows <= max_rows:
+        return f'{message}\n{data.to_csv()}'
+
+    return (
+        f'{message} skipped because dataframe has {rows} rows '
+        f'(max: {max_rows}). Shape: {data.shape}'
+    )

laborious/utils/repository/model_repository.py

@@ -36,6 +36,7 @@ from sientia_do.observability.sientia_monitoring import SientiaMonitoring
 from sientia_do.temporal.constants import DATETIME_FORMAT_WITH_TZ
 
 from laborious import metrics
+from laborious.utils.dataframe_debug import build_dataframe_debug_message
 
 ARTIFACTS_PATH = './tmp/artifacts'
 TRANSFORMED_COMPRESSED_PATH = 'artifacts/training_transformer.pkl'
@@ -105,19 +106,11 @@ class MLFlowRepository(SientiaMonitoring):
          - data (Any): Dataframe-like object expected to expose shape and to_csv
          - metadata (dict[str, Any]): Metadata for contextual logging
         """
-        if not isinstance(data, pd.DataFrame):
-            self.debug(f'{message} {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,
         )