Skip to content

Add validations when materializing from file sources #1615

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
feast-ci-bot merged 2 commits into from
Jun 3, 2021
Merged

Add validations when materializing from file sources #1615

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
88d2abf
Validate join keys when materializing from file sources
achals Jun 2, 2021
f5e62a2
Dedupe columns when extracting from the dataframe
achals Jun 2, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 9 additions & 3 deletions sdk/python/feast/infra/offline_stores/file.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -212,6 +212,13 @@ def pull_latest_from_table_or_query(
created_timestamp_column
].apply(lambda x: x if x.tzinfo is not None else x.replace(tzinfo=pytz.utc))

source_columns = set(source_df.columns)
if not set(join_key_columns).issubset(source_columns):
raise ValueError(
f"The DataFrame must have at least {set(join_key_columns)} columns present, "
f"but these were missing: {set(join_key_columns)- source_columns} "
)

ts_columns = (
[event_timestamp_column, created_timestamp_column]
if created_timestamp_column
Expand All @@ -229,8 +236,7 @@ def pull_latest_from_table_or_query(
# make driver_id a normal column again
last_values_df.reset_index(inplace=True)

table = pyarrow.Table.from_pandas(
last_values_df[join_key_columns + feature_name_columns + ts_columns]
)
columns_to_extract = set(join_key_columns + feature_name_columns + ts_columns)
table = pyarrow.Table.from_pandas(last_values_df[columns_to_extract])

return table
2 changes: 1 addition & 1 deletion sdk/python/feast/registry.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -132,7 +132,7 @@ def get_entity(self, name: str, project: str, allow_cache: bool = False) -> Enti
for entity_proto in registry_proto.entities:
if entity_proto.spec.name == name and entity_proto.spec.project == project:
return Entity.from_proto(entity_proto)
raise EntityNotFoundException(project, name)
raise EntityNotFoundException(name, project=project)

def apply_feature_table(self, feature_table: FeatureTable, project: str):
"""
Expand Down