Skip to content

fix: Fix single row broadcast with null index #1803

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 2 commits into from
Jun 10, 2025
Merged

fix: Fix single row broadcast with null index #1803

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
a2f6b68
fix: Fix single row broadcast with null index
TrevorBergeron Jun 9, 2025
def5d13
Merge branch 'main' into index_name_null
TrevorBergeron Jun 10, 2025
File filter

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: 1 addition & 1 deletion bigframes/core/blocks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2895,7 +2895,7 @@ def join_with_single_row(
combined_expr,
index_columns=index_cols_post_join,
column_labels=left.column_labels.append(single_row_block.column_labels),
index_labels=[left.index.name],
index_labels=left.index.names,
)
return (
block,
Expand Down
31 changes: 27 additions & 4 deletions tests/system/small/test_dataframe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2657,16 +2657,16 @@ def test_listlike_binop_axis_1_bf_index(scalars_dfs):
assert_pandas_df_equal(bf_result, pd_result, check_dtype=False)


def test_binop_with_self_aggregate(session, scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
def test_binop_with_self_aggregate(scalars_dfs_maybe_ordered):
scalars_df, scalars_pandas_df = scalars_dfs_maybe_ordered

df_columns = ["int64_col", "float64_col", "int64_too"]

# Ensure that this takes the optimized single-query path by counting executions
execution_count_before = session._metrics.execution_count
execution_count_before = scalars_df._session._metrics.execution_count
bf_df = scalars_df[df_columns]
bf_result = (bf_df - bf_df.mean()).to_pandas()
execution_count_after = session._metrics.execution_count
execution_count_after = scalars_df._session._metrics.execution_count

pd_df = scalars_pandas_df[df_columns]
pd_result = pd_df - pd_df.mean()
Expand All @@ -2677,6 +2677,29 @@ def test_binop_with_self_aggregate(session, scalars_dfs):
assert_pandas_df_equal(bf_result, pd_result, check_dtype=False)


def test_binop_with_self_aggregate_w_index_reset(scalars_dfs_maybe_ordered):
scalars_df, scalars_pandas_df = scalars_dfs_maybe_ordered

df_columns = ["int64_col", "float64_col", "int64_too"]

# Ensure that this takes the optimized single-query path by counting executions
execution_count_before = scalars_df._session._metrics.execution_count
bf_df = scalars_df[df_columns].reset_index(drop=True)
bf_result = (bf_df - bf_df.mean()).to_pandas()
execution_count_after = scalars_df._session._metrics.execution_count

pd_df = scalars_pandas_df[df_columns].reset_index(drop=True)
pd_result = pd_df - pd_df.mean()

executions = execution_count_after - execution_count_before

assert executions == 1
pd_result.index = pd_result.index.astype("Int64")
assert_pandas_df_equal(
bf_result, pd_result, check_dtype=False, check_index_type=False
)


@pytest.mark.parametrize(
("left_labels", "right_labels"),
[
Expand Down