Skip to content

feat: _read_gbq_colab creates hybrid session #1901

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
merged 6 commits into from
Jul 24, 2025
Merged

feat: _read_gbq_colab creates hybrid session #1901

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
921fb7a
feat: _read_gbq_colab creates hybrid session
TrevorBergeron Jul 11, 2025
dd29572
skip test if no polars
TrevorBergeron Jul 11, 2025
83eeb97
Merge remote-tracking branch 'github/main' into colab_hybrid
TrevorBergeron Jul 20, 2025
4c968b7
disable hybrid engine unless flag set
TrevorBergeron Jul 20, 2025
02c8035
Revert "disable hybrid engine unless flag set"
TrevorBergeron Jul 23, 2025
62ae03f
Merge remote-tracking branch 'github/main' into colab_hybrid
TrevorBergeron Jul 23, 2025
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
2 changes: 2 additions & 0 deletions bigframes/pandas/io/api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -345,6 +345,8 @@ def _read_gbq_colab(
dry_run=True,
)
_set_default_session_location_if_possible_deferred_query(create_query)
if not config.options.bigquery._session_started:
config.options.bigquery.enable_polars_execution = True

return global_session.with_default_session(
bigframes.session.Session._read_gbq_colab,
Expand Down
30 changes: 30 additions & 0 deletions tests/system/small/session/test_read_gbq_colab.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,11 @@
import pandas.testing
import pytest

import bigframes
import bigframes.pandas

pytest.importorskip("polars")


def test_read_gbq_colab_to_pandas_batches_preserves_order_by(maybe_ordered_session):
# This query should return enough results to be too big to fit in a single
Expand Down Expand Up @@ -59,6 +64,31 @@ def test_read_gbq_colab_to_pandas_batches_preserves_order_by(maybe_ordered_sessi
assert executions_after == executions_before_python == executions_before_sql + 1


def test_read_gbq_colab_fresh_session_is_hybrid():
bigframes.close_session()
df = bigframes.pandas._read_gbq_colab(
"""
SELECT
name,
SUM(number) AS total
FROM
`bigquery-public-data.usa_names.usa_1910_2013`
WHERE state LIKE 'W%'
GROUP BY name
ORDER BY total DESC
LIMIT 300
"""
)
session = df._session
executions_before_python = session._metrics.execution_count
result = df.sort_values("name").peek(100)
executions_after = session._metrics.execution_count

assert len(result) == 100
assert session._executor._enable_polars_execution is True # type: ignore
assert executions_after == executions_before_python == 1


def test_read_gbq_colab_peek_avoids_requery(maybe_ordered_session):
executions_before_sql = maybe_ordered_session._metrics.execution_count
df = maybe_ordered_session._read_gbq_colab(
Expand Down