Skip to content

Make DataFrame#loc return Series or DataFrame if a scalar is given #866

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 1 commit into from
Feb 12, 2024
Merged

Make DataFrame#loc return Series or DataFrame if a scalar is given #866

Show file tree
Hide file tree
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
5 changes: 3 additions & 2 deletions pandas-stubs/core/frame.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,6 +156,8 @@ class _iLocIndexerFrame(_iLocIndexer):
) -> None: ...

class _LocIndexerFrame(_LocIndexer):
@overload
def __getitem__(self, idx: Scalar) -> Series | DataFrame: ...
@overload
def __getitem__(
self,
Expand Down Expand Up @@ -184,8 +186,7 @@ class _LocIndexerFrame(_LocIndexer):
@overload
def __getitem__(
self,
idx: ScalarT
| Callable[[DataFrame], ScalarT]
idx: Callable[[DataFrame], ScalarT]
| tuple[
IndexType
| MaskType
Expand Down
31 changes: 20 additions & 11 deletions tests/test_frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2199,16 +2199,16 @@ def test_frame_scalars_slice() -> None:

# Note: bool_ cannot be tested since the index is object and pandas does not
# support boolean access using loc except when the index is boolean
check(assert_type(df.loc[str_], pd.Series), pd.Series)
check(assert_type(df.loc[bytes_], pd.Series), pd.Series)
check(assert_type(df.loc[date], pd.Series), pd.Series)
check(assert_type(df.loc[datetime_], pd.Series), pd.Series)
check(assert_type(df.loc[timedelta], pd.Series), pd.Series)
check(assert_type(df.loc[int_], pd.Series), pd.Series)
check(assert_type(df.loc[float_], pd.Series), pd.Series)
check(assert_type(df.loc[complex_], pd.Series), pd.Series)
check(assert_type(df.loc[timestamp], pd.Series), pd.Series)
check(assert_type(df.loc[pd_timedelta], pd.Series), pd.Series)
check(assert_type(df.loc[str_], Union[pd.Series, pd.DataFrame]), pd.Series)
check(assert_type(df.loc[bytes_], Union[pd.Series, pd.DataFrame]), pd.Series)
check(assert_type(df.loc[date], Union[pd.Series, pd.DataFrame]), pd.Series)
check(assert_type(df.loc[datetime_], Union[pd.Series, pd.DataFrame]), pd.Series)
check(assert_type(df.loc[timedelta], Union[pd.Series, pd.DataFrame]), pd.Series)
check(assert_type(df.loc[int_], Union[pd.Series, pd.DataFrame]), pd.Series)
check(assert_type(df.loc[float_], Union[pd.Series, pd.DataFrame]), pd.Series)
check(assert_type(df.loc[complex_], Union[pd.Series, pd.DataFrame]), pd.Series)
check(assert_type(df.loc[timestamp], Union[pd.Series, pd.DataFrame]), pd.Series)
check(assert_type(df.loc[pd_timedelta], Union[pd.Series, pd.DataFrame]), pd.Series)
check(assert_type(df.loc[none], pd.Series), pd.Series)

check(assert_type(df.loc[:, str_], pd.Series), pd.Series)
Expand All @@ -2223,11 +2223,20 @@ def test_frame_scalars_slice() -> None:
check(assert_type(df.loc[:, pd_timedelta], pd.Series), pd.Series)
check(assert_type(df.loc[:, none], pd.Series), pd.Series)

# GH749

multi_idx = pd.MultiIndex.from_product([["a", "b"], [1, 2]], names=["alpha", "num"])
df2 = pd.DataFrame({"col1": range(4)}, index=multi_idx)
check(assert_type(df2.loc[str_], Union[pd.Series, pd.DataFrame]), pd.DataFrame)

df3 = pd.DataFrame({"x": range(2)}, index=pd.Index(["a", "b"]))
check(assert_type(df3.loc[str_], Union[pd.Series, pd.DataFrame]), pd.Series)


def test_boolean_loc() -> None:
# Booleans can only be used in loc when the index is boolean
df = pd.DataFrame([[0, 1], [1, 0]], columns=[True, False], index=[True, False])
check(assert_type(df.loc[True], pd.Series), pd.Series)
check(assert_type(df.loc[True], Union[pd.Series, pd.DataFrame]), pd.Series)
check(assert_type(df.loc[:, False], pd.Series), pd.Series)


Expand Down