Skip to content
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

fix: Snowflake remote storage #3574

Merged
merged 5 commits into from
Apr 3, 2023
Merged

fix: Snowflake remote storage #3574

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
41516f5
fix: Snowflake remote storage
adamschmidt Mar 28, 2023
934bfdf
fix: lint
adamschmidt Mar 28, 2023
ca5d4ce
fix: field string build
adamschmidt Mar 29, 2023
d1d4c0d
fix: join typo
adamschmidt Mar 29, 2023
bfa5b31
fix: formatting
adamschmidt Mar 29, 2023
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
30 changes: 28 additions & 2 deletions sdk/python/feast/infra/offline_stores/snowflake.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,6 +109,9 @@ class SnowflakeOfflineStoreConfig(FeastConfigBaseModel):
blob_export_location: Optional[str] = None
""" Location (in S3, Google storage or Azure storage) where data is offloaded """

convert_timestamp_columns: Optional[bool] = None
""" Convert timestamp columns on export to a Parquet-supported format """

class Config:
allow_population_by_field_name = True

Expand Down Expand Up @@ -152,6 +155,29 @@ def pull_latest_from_table_or_query(
+ '"'
)

if config.offline_store.convert_timestamp_columns:
select_fields = list(
map(
lambda field_name: f'"{field_name}"',
join_key_columns + feature_name_columns,
)
)
select_timestamps = list(
map(
lambda field_name: f"to_varchar({field_name}, 'YYYY-MM-DD\"T\"HH24:MI:SS.FFTZH:TZM') as {field_name}",
timestamp_columns,
)
)
inner_field_string = ", ".join(select_fields + select_timestamps)
else:
select_fields = list(
map(
lambda field_name: f'"{field_name}"',
join_key_columns + feature_name_columns + timestamp_columns,
)
)
inner_field_string = ", ".join(select_fields)

if data_source.snowflake_options.warehouse:
config.offline_store.warehouse = data_source.snowflake_options.warehouse

Expand All @@ -166,7 +192,7 @@ def pull_latest_from_table_or_query(
{field_string}
{f''', TRIM({repr(DUMMY_ENTITY_VAL)}::VARIANT,'"') AS "{DUMMY_ENTITY_ID}"''' if not join_key_columns else ""}
FROM (
SELECT {field_string},
SELECT {inner_field_string},
ROW_NUMBER() OVER({partition_by_join_key_string} ORDER BY {timestamp_desc_string}) AS "_feast_row"
FROM {from_expression}
WHERE "{timestamp_field}" BETWEEN TIMESTAMP '{start_date}' AND TIMESTAMP '{end_date}'
Expand Down Expand Up @@ -533,7 +559,7 @@ def to_remote_storage(self) -> List[str]:
self.to_snowflake(table)

query = f"""
COPY INTO '{self.config.offline_store.blob_export_location}/{table}' FROM "{self.config.offline_store.database}"."{self.config.offline_store.schema_}"."{table}"\n
COPY INTO '{self.export_path}/{table}' FROM "{self.config.offline_store.database}"."{self.config.offline_store.schema_}"."{table}"\n
STORAGE_INTEGRATION = {self.config.offline_store.storage_integration_name}\n
FILE_FORMAT = (TYPE = PARQUET)
DETAILED_OUTPUT = TRUE
Expand Down