workbench 0.8.201__py3-none-any.whl → 0.8.203__py3-none-any.whl

workbench/core/transforms/pandas_transforms/pandas_to_features.py

@@ -68,6 +68,15 @@ class PandasToFeatures(Transform):
         self.output_df = input_df.copy()
         self.one_hot_columns = one_hot_columns or []
 
+        # Warn about known AWS Iceberg bug with event_time_column
+        if event_time_column is not None:
+            self.log.warning(
+                f"event_time_column='{event_time_column}' specified. Note: AWS has a known bug with "
+                "Iceberg FeatureGroups where varying event times across multiple days can cause "
+                "duplicate rows in the offline store. Setting event_time_column=None."
+            )
+            self.event_time_column = None
+
         # Now Prepare the DataFrame for its journey into an AWS FeatureGroup
         self.prep_dataframe()
 
@@ -400,7 +409,7 @@ class PandasToFeatures(Transform):
 
         # Set Hold Out Ids (if we got them during creation)
         if self.incoming_hold_out_ids:
-            self.output_feature_set.set_training_holdouts(self.id_column, self.incoming_hold_out_ids)
+            self.output_feature_set.set_training_holdouts(self.incoming_hold_out_ids)
 
     def ensure_feature_group_created(self, feature_group):
         status = feature_group.describe().get("FeatureGroupStatus")
@@ -462,7 +471,7 @@ if __name__ == "__main__":
 
     # Create my DF to Feature Set Transform (with one-hot encoding)
     df_to_features = PandasToFeatures("test_features")
-    df_to_features.set_input(data_df, id_column="id", one_hot_columns=["food"])
+    df_to_features.set_input(data_df, id_column="id", event_time_column="date", one_hot_columns=["food"])
     df_to_features.set_output_tags(["test", "small"])
     df_to_features.transform()