Skip to content

Type DataFrame methods: __setitem__, asof, set_axis #1473

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

Open
wants to merge 7 commits into
base: main
Choose a base branch
from
+94 −12
Open

Type DataFrame methods: __setitem__, asof, set_axis #1473

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
0b17616
type asof
MarcoGorelli Nov 6, 2025
a05e17f
type setitem
MarcoGorelli Nov 6, 2025
b66d0c8
wip#
MarcoGorelli Nov 6, 2025
c0f4536
Merge remote-tracking branch 'upstream/main' into even-more-dataframe
MarcoGorelli Nov 11, 2025
6c91caa
fixup setitem
MarcoGorelli Nov 11, 2025
9538b55
remove invalid case
MarcoGorelli Nov 11, 2025
02f940a
remove test case which adds extra columns (thus making subsequent tes…
MarcoGorelli Nov 11, 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
91 changes: 85 additions & 6 deletions pandas-stubs/core/frame.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,7 @@ from pandas import (
Timestamp,
)
from pandas.core.arraylike import OpsMixin
from pandas.core.base import IndexOpsMixin
from pandas.core.generic import NDFrame
from pandas.core.groupby.generic import DataFrameGroupBy
from pandas.core.indexers import BaseIndexer
Expand Down Expand Up @@ -92,6 +93,7 @@ from pandas._typing import (
ArrayLike,
AstypeArg,
Axes,
AxesData,
Axis,
AxisColumn,
AxisIndex,
Expand Down Expand Up @@ -197,6 +199,8 @@ class _iLocIndexerFrame(_iLocIndexer, Generic[_T]):
| tuple[slice]
),
) -> _T: ...

# Keep in sync with `DataFrame.__setitem__`
def __setitem__(
self,
idx: (
Expand All @@ -209,7 +213,7 @@ class _iLocIndexerFrame(_iLocIndexer, Generic[_T]):
),
value: (
Scalar
| Series
| IndexOpsMixin
| DataFrame
| np_ndarray
| NAType
Expand Down Expand Up @@ -273,6 +277,8 @@ class _LocIndexerFrame(_LocIndexer, Generic[_T]):
) -> Series: ...
@overload
def __getitem__(self, idx: tuple[Scalar, slice]) -> Series | _T: ...

# Keep in sync with `DataFrame.__setitem__`
@overload
def __setitem__(
self,
Expand All @@ -284,7 +290,7 @@ class _LocIndexerFrame(_LocIndexer, Generic[_T]):
| NAType
| NaTType
| ArrayLike
| Series
| IndexOpsMixin
| DataFrame
| list
| Mapping[Hashable, Scalar | NAType | NaTType]
Expand Down Expand Up @@ -328,7 +334,7 @@ class _AtIndexerFrame(_AtIndexer):
| NAType
| NaTType
| ArrayLike
| Series
| IndexOpsMixin
| DataFrame
| list
| Mapping[Hashable, Scalar | NAType | NaTType]
Expand Down Expand Up @@ -800,7 +806,74 @@ class DataFrame(NDFrame, OpsMixin, _GetItemHack):
def isetitem(
self, loc: int | Sequence[int], value: Scalar | ArrayLike | list[Any]
) -> None: ...
def __setitem__(self, key, value) -> None: ...

# Keep in sync with `_iLocIndexerFrame.__setitem__`
@overload
def __setitem__(
self,
idx: (
int
| IndexType
| tuple[int, int]
| tuple[IndexType, int]
| tuple[IndexType, IndexType]
| tuple[int, IndexType]
),
value: (
Scalar
| IndexOpsMixin
| Sequence[Scalar]
| DataFrame
| np.ndarray
Copy link
Contributor

@cmp0xff cmp0xff Nov 11, 2025

Choose a reason for hiding this comment

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

np.ndarray does not have default values, adding complaints to pyright_strict.

Suggested change
| np.ndarray
| np_ndarray

| NAType
| NaTType
| Mapping[Hashable, Scalar | NAType | NaTType]
| None
),
) -> None: ...
# Keep in sync with `_LocIndexerFrame.__setitem__`
@overload
def __setitem__(
self,
idx: (
MaskType | StrLike | _IndexSliceTuple | list[ScalarT] | IndexingInt | slice
),
value: (
Scalar
| NAType
| NaTType
| ArrayLike
| IndexOpsMixin
| Sequence[Scalar]
| DataFrame
| list
Copy link
Contributor

@cmp0xff cmp0xff Nov 11, 2025

Choose a reason for hiding this comment

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

Why extra list? Maybe

Suggested change
| list

Copy link
Member Author

@MarcoGorelli MarcoGorelli Nov 11, 2025

Choose a reason for hiding this comment

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

Because without it

df[["col1", "col2"]] = [[1, 2], [3, 4]]

would raise, as list is not assignable to Scalar

Copy link
Contributor

@cmp0xff cmp0xff Nov 11, 2025

Choose a reason for hiding this comment

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

The following works

>>> import pandas as pd
>>> df = pd.DataFrame(columns=["a", 'b'])
>>> df[["a", "b"]] = ((1, 2), (3, 4))

so maybe

Suggested change
| list
| Sequence[Sequence[Scalar]]

| Mapping[Hashable, Scalar | NAType | NaTType]
| None
),
) -> None: ...
@overload
def __setitem__(
self,
idx: tuple[_IndexSliceTuple, Hashable],
value: (
Scalar
| NAType
| NaTType
| ArrayLike
| IndexOpsMixin
| Sequence[Scalar]
| dict
Copy link
Contributor

@cmp0xff cmp0xff Nov 11, 2025

Choose a reason for hiding this comment

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

Could it be the following?

Suggested change
| dict
| Mapping[Hashable, Scalar | NAType | NaTType]

| None
),
) -> None: ...
# Extra cases not supported by `_LocIndexerFrame.__setitem__` /
# `_iLocIndexerFrame.__setitem__`.
@overload
def __setitem__(
self,
idx: IndexOpsMixin | DataFrame,
value: Scalar | NAType | NaTType | ArrayLike | Series | list | dict | None,
Copy link
Contributor

@cmp0xff cmp0xff Nov 11, 2025

Choose a reason for hiding this comment

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

Could it be something like the following?

Suggested change
value: Scalar | NAType | NaTType | ArrayLike | Series | list | dict | None,
value: Scalar | NAType | NaTType | ArrayLike | Series | Sequence[Scalar | NAType | NaTType] | Mapping[Hashable, Scalar | NAType | NaTType] | None,

Copy link
Member Author

@MarcoGorelli MarcoGorelli Nov 11, 2025

Choose a reason for hiding this comment

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

the dict part sure, the list part i don't think so #1473 (comment)

): ...
Copy link
Contributor

@cmp0xff cmp0xff Nov 11, 2025

Choose a reason for hiding this comment

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

Suggested change
): ...
) -> None: ...

@overload
def query(
self,
Expand Down Expand Up @@ -1917,7 +1990,11 @@ class DataFrame(NDFrame, OpsMixin, _GetItemHack):
**kwargs: Any,
) -> Series[_bool]: ...
@final
def asof(self, where, subset: _str | list[_str] | None = None) -> Self: ...
def asof(
self,
where: Scalar | AnyArrayLike | Sequence[Scalar],
subset: Hashable | list[Hashable] | None = None,
) -> Self: ...
@final
def asfreq(
self,
Expand Down Expand Up @@ -2454,7 +2531,9 @@ class DataFrame(NDFrame, OpsMixin, _GetItemHack):
**kwargs: Any,
) -> Series: ...
# Not actually positional, but used to handle removal of deprecated
def set_axis(self, labels, *, axis: Axis = ..., copy: _bool = ...) -> Self: ...
def set_axis(
self, labels: AxesData, *, axis: Axis = 0, copy: _bool = ...
) -> Self: ...
def skew(
self,
axis: Axis | None = ...,
Expand Down
4 changes: 2 additions & 2 deletions pandas-stubs/core/indexing.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ from typing import (
TypeVar,
)

from pandas.core.indexes.api import Index
from pandas.core.base import IndexOpsMixin

from pandas._libs.indexing import _NDFrameIndexerBase
from pandas._typing import (
Expand All @@ -13,7 +13,7 @@ from pandas._typing import (
)

_IndexSliceTuple: TypeAlias = tuple[
Index | MaskType | Scalar | list[ScalarT] | slice | tuple[Scalar, ...], ...
IndexOpsMixin | MaskType | Scalar | list[ScalarT] | slice | tuple[Scalar, ...], ...
Copy link
Contributor

@cmp0xff cmp0xff Nov 11, 2025

Choose a reason for hiding this comment

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

Could it be the following?

Suggested change
IndexOpsMixin | MaskType | Scalar | list[ScalarT] | slice | tuple[Scalar, ...], ...
IndexOpsMixin | MaskType | Scalar | Sequence[ScalarT] | slice, ...

]

_IndexSliceUnion: TypeAlias = slice | _IndexSliceTuple
Expand Down
8 changes: 4 additions & 4 deletions pandas-stubs/core/series.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -557,14 +557,14 @@ class Series(IndexOpsMixin[S1], ElementOpsMixin[S1], NDFrame):
@final
def __getattr__(self, name: _str) -> S1: ...

# Keep in sync with `iLocIndexerSeries.__getitem__`
# Keep in sync with `_iLocIndexerSeries.__getitem__`
@overload
def __getitem__(self, idx: IndexingInt) -> S1: ...
@overload
def __getitem__(
self, idx: Index | Series | slice | np_ndarray_anyint
) -> Series[S1]: ...
# Keep in sync with `LocIndexerSeries.__getitem__`
# Keep in sync with `_LocIndexerSeries.__getitem__`
@overload
def __getitem__( # type: ignore[overload-overlap] # pyright: ignore[reportOverlappingOverload]
self,
Expand Down Expand Up @@ -1546,8 +1546,8 @@ class Series(IndexOpsMixin[S1], ElementOpsMixin[S1], NDFrame):
@final
def asof(
self,
where: Scalar | Sequence[Scalar],
subset: _str | Sequence[_str] | None = None,
where: Scalar | AnyArrayLike | Sequence[Scalar],
subset: None = None,
) -> Scalar | Series[S1]: ...
@overload
def clip( # pyright: ignore[reportOverlappingOverload]
Expand Down
3 changes: 3 additions & 0 deletions tests/test_frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -292,6 +292,9 @@ def test_types_setitem() -> None:
df[5] = [5, 6]
df[["col1", "col2"]] = [[1, 2], [3, 4]]
df[s] = [5, 6]
df.loc[:, s] = [5, 6]
df["col1"] = [5, 6]
df[df["col1"] > 1] = [5, 6, 7]
df[a] = [[1, 2], [3, 4]]
df[i] = [8, 9]

Expand Down