def _ingest_single_batch(
data_frame: DataFrame,
feature_group_name: str,
sagemaker_session: Session,
start_index: int,
end_index: int,
):
"""Ingest a single batch of DataFrame rows into FeatureStore.
Args:
data_frame (DataFrame): source DataFrame to be ingested.
feature_group_name (str): name of the Feature Group.
sagemaker_session (Session): session instance to perform boto calls.
start_index (int): starting position to ingest in this batch.
end_index (int): ending position to ingest in this batch.
"""
logger.info("Started ingesting index %d to %d", start_index, end_index)
for row in data_frame[start_index:end_index].itertuples(index=False):
record = [
FeatureValue(feature_name=data_frame.columns[index],
value_as_string=str(row[index]))
for index in range(len(row))
]
sagemaker_session.put_record(
feature_group_name=feature_group_name,
record=[value.to_dict() for value in record])
def _ingest_single_batch(
data_frame: DataFrame,
feature_group_name: str,
sagemaker_session: Session,
start_index: int,
end_index: int,
) -> List[int]:
"""Ingest a single batch of DataFrame rows into FeatureStore.
Args:
data_frame (DataFrame): source DataFrame to be ingested.
feature_group_name (str): name of the Feature Group.
sagemaker_session (Session): session instance to perform boto calls.
start_index (int): starting position to ingest in this batch.
end_index (int): ending position to ingest in this batch.
Returns:
List of row indices that failed to be ingested.
"""
logger.info("Started ingesting index %d to %d", start_index, end_index)
failed_rows = list()
for row in data_frame[start_index:end_index].itertuples():
record = [
FeatureValue(feature_name=data_frame.columns[index - 1],
value_as_string=str(row[index]))
for index in range(1, len(row)) if pd.notna(row[index])
]
try:
sagemaker_session.put_record(
feature_group_name=feature_group_name,
record=[value.to_dict() for value in record],
)
except Exception as e: # pylint: disable=broad-except
logger.error("Failed to ingest row %d: %s", row[0], e)
failed_rows.append(row[0])
return failed_rows