Skip to content

fix: Preserve pandas column name attribute #2363

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.

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 25 commits into from
May 16, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
25 commits
Select commit Hold shift + click to select a range
feaad95
concat
FBruzzesi Apr 8, 2025
f28599f
seems to work
FBruzzesi Apr 8, 2025
fc982d3
copy=False
FBruzzesi Apr 8, 2025
f557dd5
ok pandas 3
FBruzzesi Apr 9, 2025
46c29e7
Merge branch 'main' into fix/maintain-pandas-column-index-name
FBruzzesi Apr 9, 2025
d5fea77
do not HACK non-pandas codepath
FBruzzesi Apr 9, 2025
f3b4cf9
mypy
FBruzzesi Apr 9, 2025
9f3c415
Merge branch 'main' into fix/maintain-pandas-column-index-name
FBruzzesi Apr 10, 2025
bd7fd09
refactor: `utils.horizontal_concat` -> `Namespace._horizontal_concat`
dangotbanned Apr 10, 2025
987a688
revert: undo last commit
dangotbanned Apr 10, 2025
7f39ada
re-solve conflicts
FBruzzesi Apr 17, 2025
0d105a3
re-solve conflicts
FBruzzesi Apr 17, 2025
13166e7
fix pandas utils
FBruzzesi Apr 17, 2025
afaa9ec
Merge branch 'main' into fix/maintain-pandas-column-index-name
FBruzzesi Apr 18, 2025
2cf041c
Merge branch 'main' into fix/maintain-pandas-column-index-name
FBruzzesi Apr 19, 2025
984a57b
Merge branch 'main' into fix/maintain-pandas-column-index-name
FBruzzesi Apr 20, 2025
823293b
Merge branch 'main' into fix/maintain-pandas-column-index-name
FBruzzesi Apr 21, 2025
788bc1f
Merge branch 'main' into fix/maintain-pandas-column-index-name
FBruzzesi Apr 29, 2025
1e745d4
merge main
FBruzzesi May 2, 2025
e1ef8b5
Merge branch 'main' into fix/maintain-pandas-column-index-name
FBruzzesi May 3, 2025
28795f2
Merge remote-tracking branch 'upstream/main' into fix/maintain-pandas…
MarcoGorelli May 16, 2025
5efaff2
keep it simpler, dont trust pandas for rename_axis
MarcoGorelli May 16, 2025
f202c57
remove unintended file
MarcoGorelli May 16, 2025
e024c54
reduce diff
MarcoGorelli May 16, 2025
5387649
reduce diff
MarcoGorelli May 16, 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
4 changes: 4 additions & 0 deletions narwhals/_pandas_like/dataframe.py
Original file line number Diff line number Diff line change
Expand Up @@ -422,6 +422,8 @@ def select(self: PandasLikeDataFrame, *exprs: PandasLikeExpr) -> PandasLikeDataF
new_series = align_series_full_broadcast(*new_series)
namespace = self.__narwhals_namespace__()
df = namespace._concat_horizontal([s.native for s in new_series])
# `concat` creates a new object, so fine to modify `.columns.name` inplace.
df.columns.name = self.native.columns.name
return self._with_native(df, validate_column_names=True)

def drop_nulls(
Expand Down Expand Up @@ -480,6 +482,8 @@ def with_columns(
to_concat.extend(self._extract_comparand(s) for s in name_columns.values())
namespace = self.__narwhals_namespace__()
df = namespace._concat_horizontal(to_concat)
# `concat` creates a new object, so fine to modify `.columns.name` inplace.
df.columns.name = self.native.columns.name
return self._with_native(df, validate_column_names=False)

def rename(self, mapping: Mapping[str, str]) -> Self:
Expand Down
12 changes: 7 additions & 5 deletions tests/frame/join_test.py
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,6 @@
import pytest

import narwhals as nw
from narwhals.utils import Implementation
from tests.utils import DUCKDB_VERSION
from tests.utils import PANDAS_VERSION
from tests.utils import POLARS_VERSION
Expand Down Expand Up @@ -242,11 +241,14 @@ def test_cross_join_suffix(constructor: Constructor, suffix: str) -> None:


def test_cross_join_non_pandas() -> None:
_ = pytest.importorskip("modin")

import modin.pandas as mpd

data = {"antananarivo": [1, 3, 2]}
df = nw.from_native(pd.DataFrame(data))
# HACK to force testing for a non-pandas codepath
df._compliant_frame._implementation = Implementation.MODIN
result = df.join(df, how="cross")
df1 = nw.from_native(mpd.DataFrame(pd.DataFrame(data)), eager_only=True)
df2 = nw.from_native(mpd.DataFrame(pd.DataFrame(data)), eager_only=True)
result = df1.join(df2, how="cross")
expected = {
"antananarivo": [1, 1, 1, 3, 3, 3, 2, 2, 2],
"antananarivo_right": [1, 3, 2, 1, 3, 2, 1, 3, 2],
Expand Down
33 changes: 33 additions & 0 deletions tests/preserve_pandas_like_columns_name_attr_test.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,33 @@
from __future__ import annotations

from typing import TYPE_CHECKING

import pytest

import narwhals.stable.v1 as nw

if TYPE_CHECKING:
from tests.utils import Constructor


def test_ops_preserve_column_index_name(
constructor: Constructor, request: pytest.FixtureRequest
) -> None:
if not any(x in str(constructor) for x in ("pandas", "modin", "cudf", "dask")):
pytest.skip(
reason="Dataframe columns is a list and do not have a `name` like a pandas Index does"
)
if "dask" in str(constructor):
# https://github.com/dask/dask/issues/11874
request.applymarker(pytest.mark.xfail)

data = {"a": [1, 3, 2], "b": [4, 4, 6], "z": [7.0, 8.0, 9.0]}
df_native = constructor(data)
df_native.columns.name = "foo" # type: ignore[union-attr]

df = nw.from_native(df_native)

result = df.with_columns(b=nw.col("a") + 1, c=nw.col("a") * 2).select("c", "b")
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I wanted to concatenate two methods here, mostly for the sake of it.
Might be worth reparametrizing it


assert result.to_native().columns.name == "foo" # type: ignore[union-attr]
assert result.lazy().collect(backend="pandas").to_native().columns.name == "foo"
Loading