Removal of unnecessary checks & made both dates timezone aware

Signed-off-by: Aniket Paluskar <apaluska@redhat.com>
feast-dev · ntkathole · Dec 8, 2025 · Nov 11, 2025 · Nov 11, 2025 · Nov 12, 2025
commit b28ea1911e1379ce9dc97e241961bf53ea428bbc
@@ -37,7 +37,7 @@
 from feast.on_demand_feature_view import OnDemandFeatureView
 from feast.repo_config import FeastConfigBaseModel, RepoConfig
 from feast.saved_dataset import SavedDatasetStorage
-from feast.utils import _get_requested_feature_views_to_features_dict
+from feast.utils import _get_requested_feature_views_to_features_dict, make_tzaware
 
 # DaskRetrievalJob will cast string objects to string[pyarrow] from dask version 2023.7.1
 # This is not the desired behavior for our use case, so we set the convert-string option to False
@@ -152,7 +152,9 @@ def get_historical_features(
 
         if non_entity_mode:
             # Default end_date to current time (UTC) to keep behavior predictable without extra parameters.
-            end_date = end_date or datetime.now(timezone.utc)
+            end_date = (
+                make_tzaware(end_date) if end_date else datetime.now(timezone.utc)
+            )
 
             # When start_date is not provided, choose a conservative lower bound using max TTL, otherwise fall back.
             if start_date is None:
@@ -167,6 +169,7 @@ def get_historical_features(
                 else:
                     # Keep default window bounded to avoid unbounded scans by default.
                     start_date = end_date - timedelta(days=30)
+            start_date = make_tzaware(start_date)
 
-            # When start_date is not provided, choose a conservative lower bound using max TTL, otherwise fall back.
-            if start_date is None:
-                max_ttl_seconds = 0
-                for fv in feature_views:
-                    if fv.ttl and isinstance(fv.ttl, timedelta):
-                        max_ttl_seconds = max(
-                            max_ttl_seconds, int(fv.ttl.total_seconds())
-                        )
-                if max_ttl_seconds > 0:
-                    start_date = end_date - timedelta(seconds=max_ttl_seconds)
-                else:
-                    # Keep default window bounded to avoid unbounded scans by default.
-                    start_date = end_date - timedelta(days=30)
+            # Compute TTL-based lower bound for start_date.
+            max_ttl_seconds = 0
+            for fv in feature_views:
+                if fv.ttl and isinstance(fv.ttl, timedelta):
+                    max_ttl_seconds = max(
+                        max_ttl_seconds, int(fv.ttl.total_seconds())
+                    )
+            if max_ttl_seconds > 0:
+                ttl_lower_bound = end_date - timedelta(seconds=max_ttl_seconds)
+            else:
+                # Keep default window bounded to avoid unbounded scans by default.
+                ttl_lower_bound = end_date - timedelta(days=30)
+
+            # If user provided start_date, use the max of user start_date and ttl_lower_bound.
+            if start_date is not None:
+                if start_date < ttl_lower_bound:
+                    import warnings
+                    warnings.warn(
+                        f"Provided start_date ({start_date}) is earlier than TTL-based lower bound ({ttl_lower_bound}). Overriding start_date to {ttl_lower_bound}."
+                    )
+                start_date = max(start_date, ttl_lower_bound)
+            else:
+                start_date = ttl_lower_bound
-            # When start_date is not provided, choose a conservative lower bound using max TTL, otherwise fall back.
-            if start_date is None:
-                max_ttl_seconds = 0
-                for fv in feature_views:
-                    if fv.ttl and isinstance(fv.ttl, timedelta):
-                        max_ttl_seconds = max(
-                            max_ttl_seconds, int(fv.ttl.total_seconds())
-                        )
-                if max_ttl_seconds > 0:
-                    start_date = end_date - timedelta(seconds=max_ttl_seconds)
-                else:
-                    # Keep default window bounded to avoid unbounded scans by default.
-                    start_date = end_date - timedelta(days=30)
+            # Compute TTL-based lower bound for start_date.
+            max_ttl_seconds = 0
+            for fv in feature_views:
+                if fv.ttl and isinstance(fv.ttl, timedelta):
+                    max_ttl_seconds = max(
+                        max_ttl_seconds, int(fv.ttl.total_seconds())
+                    )
+            if max_ttl_seconds > 0:
+                ttl_lower_bound = end_date - timedelta(seconds=max_ttl_seconds)
+            else:
+                # Keep default window bounded to avoid unbounded scans by default.
+                ttl_lower_bound = end_date - timedelta(days=30)
+
+            # If user provided start_date, use the max of user start_date and ttl_lower_bound.
+            if start_date is not None:
+                if start_date < ttl_lower_bound:
+                    import warnings
+                    warnings.warn(
+                        f"Provided start_date ({start_date}) is earlier than TTL-based lower bound ({ttl_lower_bound}). Overriding start_date to {ttl_lower_bound}."
+                    )
+                start_date = max(start_date, ttl_lower_bound)
+            else:
+                start_date = ttl_lower_bound
             # Minimal synthetic entity_df: one timestamp row; join keys are not materialized here on purpose to avoid
             # accidental dependence on specific feature view schemas at this layer.
@@ -178,7 +181,7 @@ def get_historical_features(
                 entity_df, dd.DataFrame
             ):
                 raise ValueError(
-                    f"Please provide an entity_df of type {type(pd.DataFrame)} or dask.dataframe instead of type {type(entity_df)}"
+                    f"Please provide an entity_df of type pd.DataFrame or dask.dataframe.DataFrame instead of type {type(entity_df)}"
                 )
         entity_df_event_timestamp_col = DEFAULT_ENTITY_DF_EVENT_TIMESTAMP_COL  # local modifiable copy of global variable
         if entity_df_event_timestamp_col not in entity_df.columns:
@@ -296,15 +299,11 @@ def evaluate_historical_retrieval():
                     full_feature_names,
                 )
 
-                # df_to_join = _merge(entity_df_with_features, df_to_join, join_keys)
-
                 # In non-entity mode, if the synthetic entity_df lacks join keys, cross join to build a snapshot
                 # of all entities as-of the requested timestamp, then rely on TTL and deduplication to select
                 # the appropriate latest rows per entity.
                 current_join_keys = join_keys
-                if non_entity_mode and any(
-                    k not in entity_df_with_features.columns for k in join_keys
-                ):
+                if non_entity_mode:
                     current_join_keys = []
 
                 df_to_join = _merge(