Merge branch 'main' into type-transpose

Author: MarcoGorelli

.github/workflows/comment_commands.yml

@@ -36,13 +36,16 @@ jobs:
             })
             core.setOutput('sha', pr.data.head.sha)
             core.setOutput('branch', pr.data.head.ref)
+            core.setOutput('repository', pr.data.head.repo.full_name)
 
       - name: Checkout code on the correct branch
         uses: actions/checkout@v4
         with:
           # context is not aware which branch to checkout so it would otherwise
-          # default to main
+          # default to main (we also need repo name to source from the right user
+          # otherwise it will look for the branch in pandas-stubs repo)
           ref: ${{ steps.get-branch-info.outputs.branch }}
+          repository: ${{ steps.get-branch-info.outputs.repository }}
 
       - name: Install project dependencies
         uses: ./.github/setup

pandas-stubs/core/frame.pyi

@@ -720,7 +720,7 @@ class DataFrame(NDFrame, OpsMixin, _GetItemHack):
     def insert(
         self,
         loc: int,
-        column,
+        column: Hashable,
         value: Scalar | ListLikeU | None,
         allow_duplicates: _bool = ...,
     ) -> None: ...
@@ -1025,7 +1025,7 @@ class DataFrame(NDFrame, OpsMixin, _GetItemHack):
         self,
         other: DataFrame,
         func: Callable,
-        fill_value=...,
+        fill_value: Scalar | None = ...,
         overwrite: _bool = ...,
     ) -> Self: ...
     def combine_first(self, other: DataFrame) -> Self: ...

pandas-stubs/core/groupby/generic.pyi

@@ -3,7 +3,6 @@ from collections.abc import (
     Hashable,
     Iterable,
     Iterator,
-    Mapping,
     Sequence,
 )
 from typing import (
@@ -29,14 +28,11 @@ from typing_extensions import (
     TypeAlias,
 )
 
-from pandas._libs.lib import NoDefault
 from pandas._libs.tslibs.timestamps import Timestamp
 from pandas._typing import (
     S1,
     AggFuncTypeBase,
     AggFuncTypeFrame,
-    ArrayLike,
-    Axis,
     ByT,
     CorrelationMethod,
     Dtype,
@@ -113,26 +109,13 @@ class SeriesGroupBy(GroupBy[Series[S1]], Generic[S1, ByT]):
         bins: int | Sequence[int] | None = ...,
         dropna: bool = ...,
     ) -> Series[float]: ...
-    def fillna(
-        self,
-        value: (
-            Scalar | ArrayLike | Series | DataFrame | Mapping[Hashable, Scalar] | None
-        ) = ...,
-        method: Literal["bfill", "ffill"] | None = ...,
-        axis: Axis | None | NoDefault = ...,
-        inplace: bool = ...,
-        limit: int | None = ...,
-        downcast: dict | None | NoDefault = ...,
-    ) -> Series[S1] | None: ...
     def take(
         self,
         indices: TakeIndexer,
-        axis: Axis | NoDefault = ...,
         **kwargs,
     ) -> Series[S1]: ...
     def skew(
         self,
-        axis: Axis | NoDefault = ...,
         skipna: bool = ...,
         numeric_only: bool = ...,
         **kwargs,
@@ -145,8 +128,8 @@ class SeriesGroupBy(GroupBy[Series[S1]], Generic[S1, ByT]):
     def nsmallest(
         self, n: int = ..., keep: Literal["first", "last", "all"] = ...
     ) -> Series[S1]: ...
-    def idxmin(self, axis: Axis | NoDefault = ..., skipna: bool = ...) -> Series: ...
-    def idxmax(self, axis: Axis | NoDefault = ..., skipna: bool = ...) -> Series: ...
+    def idxmin(self, skipna: bool = ...) -> Series: ...
+    def idxmax(self, skipna: bool = ...) -> Series: ...
     def corr(
         self,
         other: Series,
@@ -242,13 +225,11 @@ class DataFrameGroupBy(GroupBy[DataFrame], Generic[ByT, _TT]):
     def nunique(self, dropna: bool = ...) -> DataFrame: ...
     def idxmax(
         self,
-        axis: Axis | None | NoDefault = ...,
         skipna: bool = ...,
         numeric_only: bool = ...,
     ) -> DataFrame: ...
     def idxmin(
         self,
-        axis: Axis | None | NoDefault = ...,
         skipna: bool = ...,
         numeric_only: bool = ...,
     ) -> DataFrame: ...
@@ -336,13 +317,10 @@ class DataFrameGroupBy(GroupBy[DataFrame], Generic[ByT, _TT]):
         ascending: bool = ...,
         dropna: bool = ...,
     ) -> DataFrame: ...
-    def take(
-        self, indices: TakeIndexer, axis: Axis | None | NoDefault = ..., **kwargs
-    ) -> DataFrame: ...
+    def take(self, indices: TakeIndexer, **kwargs) -> DataFrame: ...
     @overload
     def skew(
         self,
-        axis: Axis | None | NoDefault = ...,
         skipna: bool = ...,
         numeric_only: bool = ...,
         *,
@@ -352,7 +330,6 @@ class DataFrameGroupBy(GroupBy[DataFrame], Generic[ByT, _TT]):
     @overload
     def skew(
         self,
-        axis: Axis | None | NoDefault = ...,
         skipna: bool = ...,
         numeric_only: bool = ...,
         *,
@@ -394,14 +371,6 @@ class DataFrameGroupBy(GroupBy[DataFrame], Generic[ByT, _TT]):
     ) -> Series: ...  # Series[Axes] but this is not allowed
     @property
     def dtypes(self) -> Series: ...
-    def corrwith(
-        self,
-        other: DataFrame | Series,
-        axis: Axis | NoDefault = ...,
-        drop: bool = ...,
-        method: CorrelationMethod = ...,
-        numeric_only: bool = ...,
-    ) -> DataFrame: ...
     def __getattr__(self, name: str) -> SeriesGroupBy[Any, ByT]: ...
     # Overrides that provide more precise return types over the GroupBy class
     @final  # type: ignore[misc]

pandas-stubs/core/indexes/base.pyi

@@ -67,7 +67,7 @@ class Index(IndexOpsMixin[S1]):
     __hash__: ClassVar[None]  # type: ignore[assignment]
     # overloads with additional dtypes
     @overload
-    def __new__(
+    def __new__(  # pyright: ignore[reportOverlappingOverload]
         cls,
         data: Sequence[int | np.integer] | IndexOpsMixin[int] | np_ndarray_anyint,
         *,

pandas-stubs/core/series.pyi

@@ -249,7 +249,7 @@ class Series(IndexOpsMixin[S1], NDFrame):
         copy: bool = ...,
     ) -> Series[float]: ...
     @overload
-    def __new__(  # type: ignore[overload-overlap]
+    def __new__(  # type: ignore[overload-overlap] # pyright: ignore[reportOverlappingOverload]
         cls,
         data: Sequence[Never],
         index: Axes | None = ...,

pandas-stubs/io/formats/style.pyi

@@ -11,6 +11,7 @@ from typing import (
 
 from matplotlib.colors import Colormap
 import numpy as np
+from pandas import Index
 from pandas.core.frame import DataFrame
 from pandas.core.series import Series
 
@@ -52,6 +53,10 @@ class _DataFrameFunc(Protocol):
     ) -> npt.NDArray | DataFrame: ...
 
 class Styler(StylerRenderer):
+    @property
+    def columns(self) -> Index[Any]: ...
+    @property
+    def index(self) -> Index[Any]: ...
     def __init__(
         self,
         data: DataFrame | Series,

pyproject.toml

@@ -34,11 +34,11 @@ types-pytz = ">= 2022.1.1"
 numpy = ">= 1.23.5"
 
 [tool.poetry.group.dev.dependencies]
-mypy = "1.14.1"
+mypy = "1.15.0"
 pandas = "2.2.3"
 pyarrow = ">=10.0.1"
 pytest = ">=7.1.2"
-pyright = ">= 1.1.393"
+pyright = ">=1.1.396"
 poethepoet = ">=0.16.5"
 loguru = ">=0.6.0"
 typing-extensions = ">=4.4.0"

tests/test_frame.py

@@ -4007,3 +4007,15 @@ def test_transpose() -> None:
     check(assert_type(df.transpose(), pd.DataFrame), pd.DataFrame)
     check(assert_type(df.transpose(None), pd.DataFrame), pd.DataFrame)
     check(assert_type(df.transpose(copy=True), pd.DataFrame), pd.DataFrame)
+
+
+def test_combine() -> None:
+    df1 = pd.DataFrame({"A": [0, 0], "B": [4, 4]})
+    df2 = pd.DataFrame({"A": [1, 1], "B": [3, 3]})
+    take_smaller = lambda s1, s2: s1 if s1.sum() < s2.sum() else s2
+    assert_type(
+        check(
+            df1.combine(df2, take_smaller, fill_value=0, overwrite=False), pd.DataFrame
+        ),
+        pd.DataFrame,
+    )

tests/test_styler.py

@@ -13,6 +13,7 @@
 import numpy.typing as npt
 from pandas import (
     DataFrame,
+    Index,
     Series,
 )
 from pandas._testing import ensure_clean
@@ -224,3 +225,9 @@ def test_subset() -> None:
     check(assert_type(DF.style.highlight_min(subset=IndexSlice[1:2]), Styler), Styler)
     check(assert_type(DF.style.highlight_min(subset=[1]), Styler), Styler)
     check(assert_type(DF.style.highlight_min(subset=DF.columns[1:]), Styler), Styler)
+
+
+def test_styler_columns_and_index() -> None:
+    styler = DF.style
+    check(assert_type(styler.columns, Index), Index)
+    check(assert_type(styler.index, Index), Index)