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

Jump to bottom

feat(ingest/profiling): allow unique count queries to be combined #10322

Merged
merged 1 commit into from
Apr 18, 2024
Merged

feat(ingest/profiling): allow unique count queries to be combined #10322

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
23 changes: 17 additions & 6 deletions metadata-ingestion/src/datahub/ingestion/source/ge_data_profiler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -142,21 +142,25 @@ class GEProfilerRequest:
batch_kwargs: dict


def get_column_unique_count_patch(self: SqlAlchemyDataset, column: str) -> int:
def get_column_unique_count_dh_patch(self: SqlAlchemyDataset, column: str) -> int:
if self.engine.dialect.name.lower() == REDSHIFT:
element_values = self.engine.execute(
sa.select(
[sa.text(f'APPROXIMATE count(distinct "{column}")')] # type:ignore
[
# We use coalesce here to force SQL Alchemy to see this
# as a column expression.
sa.func.coalesce(
sa.text(f'APPROXIMATE count(distinct "{column}")')
),
]
).select_from(self._table)
)
return convert_to_json_serializable(element_values.fetchone()[0])
elif self.engine.dialect.name.lower() == BIGQUERY:
element_values = self.engine.execute(
sa.select(
[
sa.text( # type:ignore
f"APPROX_COUNT_DISTINCT(`{column}`)"
)
sa.func.coalesce(sa.text(f"APPROX_COUNT_DISTINCT(`{column}`)")),
]
).select_from(self._table)
)
Expand Down Expand Up @@ -233,9 +237,16 @@ def _is_single_row_query_method(query: Any) -> bool:
"unexpected_count",
]

FIRST_PARTY_SINGLE_ROW_QUERY_METHODS = {
"get_column_unique_count_dh_patch",
}

# We'll do this the inefficient way since the arrays are pretty small.
stack = traceback.extract_stack()
for frame in reversed(stack):
if frame.name in FIRST_PARTY_SINGLE_ROW_QUERY_METHODS:
return True

if not any(frame.filename.endswith(file) for file in SINGLE_ROW_QUERY_FILES):
continue

Expand Down Expand Up @@ -1010,7 +1021,7 @@ def generate_profiles(

with PerfTimer() as timer, unittest.mock.patch(
"great_expectations.dataset.sqlalchemy_dataset.SqlAlchemyDataset.get_column_unique_count",
get_column_unique_count_patch,
get_column_unique_count_dh_patch,
), unittest.mock.patch(
"great_expectations.dataset.sqlalchemy_dataset.SqlAlchemyDataset._get_column_quantiles_bigquery",
_get_column_quantiles_bigquery_patch,
Expand Down
Loading