Skip to content

fix: handle multi-level columns for df aggregates properly #305

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
Jan 10, 2024
Merged

fix: handle multi-level columns for df aggregates properly #305

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
c4ba614
fix: handle multi-level columns for df aggregates properly
TrevorBergeron Jan 5, 2024
c09e5b7
skip legacy pandas for new test
TrevorBergeron Jan 5, 2024
bfaa284
Merge remote-tracking branch 'github/main' into lostmultifix
TrevorBergeron Jan 5, 2024
a15e13b
Merge branch 'main' into lostmultifix
TrevorBergeron Jan 8, 2024
b009b39
Merge branch 'main' into lostmultifix
TrevorBergeron Jan 9, 2024
94dac87
Merge branch 'main' into lostmultifix
gcf-merge-on-green[bot] Jan 10, 2024
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
12 changes: 10 additions & 2 deletions bigframes/core/blocks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -855,13 +855,21 @@ def aggregate_all_and_stack(
aggregations = [
(col_id, operation, col_id) for col_id in self.value_columns
]
index_col_ids = [
guid.generate_guid() for i in range(self.column_labels.nlevels)
]
result_expr = self.expr.aggregate(aggregations, dropna=dropna).unpivot(
row_labels=self.column_labels.to_list(),
index_col_ids=["index"],
index_col_ids=index_col_ids,
unpivot_columns=tuple([(value_col_id, tuple(self.value_columns))]),
dtype=dtype,
)
return Block(result_expr, index_columns=["index"], column_labels=[None])
return Block(
result_expr,
index_columns=index_col_ids,
column_labels=[None],
index_labels=self.column_labels.names,
)
else: # axis_n == 1
# using offsets as identity to group on.
# TODO: Allow to promote identity/total_order columns instead for better perf
Expand Down
20 changes: 20 additions & 0 deletions tests/system/small/test_multiindex.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -713,6 +713,26 @@ def test_column_multi_index_binary_op(scalars_df_index, scalars_pandas_df_index)
pandas.testing.assert_series_equal(bf_result, pd_result)


@skip_legacy_pandas
def test_column_multi_index_any():
columns = pandas.MultiIndex.from_tuples(
[("col0", "col00"), ("col0", "col00"), ("col1", "col11")]
)
pd_df = pandas.DataFrame(
[[0, 1, 2], [0, 1, 2], [0, 1, 2], [0, 1, 2]], columns=columns
)
bf_df = bpd.DataFrame(pd_df)

pd_result = pd_df.isna().any()
bf_result = bf_df.isna().any().to_pandas()

pandas.testing.assert_frame_equal(
bf_result.reset_index(drop=False),
pd_result.reset_index(drop=False),
check_dtype=False,
)


def test_column_multi_index_agg(scalars_df_index, scalars_pandas_df_index):
columns = ["int64_too", "int64_col", "float64_col"]
multi_columns = pandas.MultiIndex.from_tuples(zip(["a", "b", "a"], ["a", "b", "b"]))
Expand Down