def materialize_single_feature_view(
self,
feature_view: FeatureView,
start_date: datetime,
end_date: datetime,
registry: Registry,
project: str,
tqdm_builder: Callable[[int], tqdm],
) -> None:
entities = []
for entity_name in feature_view.entities:
entities.append(registry.get_entity(entity_name, project))
(
join_key_columns,
feature_name_columns,
event_timestamp_column,
created_timestamp_column,
) = _get_column_names(feature_view, entities)
start_date = utils.make_tzaware(start_date)
end_date = utils.make_tzaware(end_date)
offline_store = get_offline_store_from_sources([feature_view.input])
table = offline_store.pull_latest_from_table_or_query(
data_source=feature_view.input,
join_key_columns=join_key_columns,
feature_name_columns=feature_name_columns,
event_timestamp_column=event_timestamp_column,
created_timestamp_column=created_timestamp_column,
start_date=start_date,
end_date=end_date,
)
if feature_view.input.field_mapping is not None:
table = _run_field_mapping(table, feature_view.input.field_mapping)
join_keys = [entity.join_key for entity in entities]
rows_to_write = _convert_arrow_to_proto(table, feature_view, join_keys)
with tqdm_builder(len(rows_to_write)) as pbar:
self.online_write_batch(project, feature_view, rows_to_write,
lambda x: pbar.update(x))
feature_view.materialization_intervals.append((start_date, end_date))
registry.apply_feature_view(feature_view, project)
def get_historical_features(
config: RepoConfig,
feature_views: List[FeatureView],
feature_refs: List[str],
entity_df: Union[pd.DataFrame, str],
registry: Registry,
project: str,
) -> RetrievalJob:
offline_store = get_offline_store_from_sources(
[feature_view.input for feature_view in feature_views])
return offline_store.get_historical_features(
config=config,
feature_views=feature_views,
feature_refs=feature_refs,
entity_df=entity_df,
registry=registry,
project=project,
)
