Skip to content

GH1074 Add type hint Series[list[str]] for Series.str.split with expand=False #1075

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 8 commits into from
Dec 18, 2024
Merged

GH1074 Add type hint Series[list[str]] for Series.str.split with expand=False #1075

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
7b43a93
GH1074 Add type hint Series[list[str]] for Series.str.split with expa…
pan-vlados Dec 18, 2024
bb3e78f
Updates:
pan-vlados Dec 18, 2024
f77583c
Update tests/test_indexes.py
pan-vlados Dec 18, 2024
d93390d
Update tests/test_series.py
pan-vlados Dec 18, 2024
577d375
Update tests/test_series.py
pan-vlados Dec 18, 2024
e46842a
Updates:
pan-vlados Dec 18, 2024
7ba4a45
pre-commit fixes
pan-vlados Dec 18, 2024
667cef3
Add type hints and tests for str.rsplit() for expand=False
pan-vlados Dec 18, 2024
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
6 changes: 4 additions & 2 deletions pandas-stubs/_typing.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -547,7 +547,8 @@ S1 = TypeVar(
| Period
| Interval
| CategoricalDtype
| BaseOffset,
| BaseOffset
| list[str],
)

S2 = TypeVar(
Expand All @@ -566,7 +567,8 @@ S2 = TypeVar(
| Period
| Interval
| CategoricalDtype
| BaseOffset,
| BaseOffset
| list[str],
)

IndexingInt: TypeAlias = (
Expand Down
6 changes: 3 additions & 3 deletions pandas-stubs/core/series.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -242,15 +242,15 @@ class Series(IndexOpsMixin[S1], NDFrame):
copy: bool = ...,
) -> Series[float]: ...
@overload
def __new__( # type: ignore[overload-overlap]
def __new__(
cls,
data: Sequence[Never],
data: Sequence[str],
index: Axes | None = ...,
*,
dtype: Dtype = ...,
name: Hashable = ...,
copy: bool = ...,
) -> Series[Any]: ...
) -> Series[str]: ...
@overload
def __new__(
cls,
Expand Down
4 changes: 4 additions & 0 deletions pandas-stubs/core/strings.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,6 +65,10 @@ class StringMethods(NoNewAttributesMixin, Generic[T, _TS, _TM]):
self, pat: str = ..., *, n: int = ..., expand: Literal[True], regex: bool = ...
) -> _TS: ...
@overload
def split(
self, pat: str = ..., *, n: int = ..., expand: Literal[False], regex: bool = ...
) -> Series[list[str]]: ...
@overload
def split(
self, pat: str = ..., *, n: int = ..., expand: bool = ..., regex: bool = ...
) -> T: ...
Expand Down
6 changes: 3 additions & 3 deletions tests/test_frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3767,9 +3767,9 @@ class MyDict(TypedDict):


def test_series_empty_dtype() -> None:
"""Test for the creation of a Series from an empty list GH571 to map to a Series[Any]."""
"""Test for the creation of a Series from an empty list GH571 to map to a Series[str]."""
new_tab: Sequence[Never] = [] # need to be typehinted to please mypy
check(assert_type(pd.Series(new_tab), "pd.Series[Any]"), pd.Series)
check(assert_type(pd.Series([]), "pd.Series[Any]"), pd.Series)
check(assert_type(pd.Series(new_tab), "pd.Series[str]"), pd.Series)
check(assert_type(pd.Series([]), "pd.Series[str]"), pd.Series)
# ensure that an empty string does not get matched to Sequence[Never]
check(assert_type(pd.Series(""), "pd.Series[str]"), pd.Series)
3 changes: 3 additions & 0 deletions tests/test_series.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1556,6 +1556,9 @@ def test_string_accessors():
check(assert_type(s.str.split("a"), pd.Series), pd.Series)
# GH 194
check(assert_type(s.str.split("a", expand=True), pd.DataFrame), pd.DataFrame)
check(
assert_type(s.str.split("a", expand=False), "pd.Series[list[str]]"), pd.Series
)
check(assert_type(s.str.startswith("a"), "pd.Series[bool]"), pd.Series, np.bool_)
check(
assert_type(s.str.startswith(("a", "b")), "pd.Series[bool]"),
Expand Down