Merge remote-tracking branch 'upstream/main' into typevar-default

Author: MarcoGorelli

.pre-commit-config.yaml

@@ -11,7 +11,7 @@ repos:
     hooks:
     -   id: isort
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.11.5
+    rev: v0.11.13
     hooks:
     -   id: ruff
         args: [

pandas-stubs/_typing.pyi

@@ -847,6 +847,7 @@ SeriesDType: TypeAlias = (
 S1 = TypeVar("S1", bound=SeriesDType, default=Any)
 # Like S1, but without `default=Any`.
 S2 = TypeVar("S2", bound=SeriesDType)
+S3 = TypeVar("S3", bound=SeriesDType)
 
 IndexingInt: TypeAlias = (
     int | np.int_ | np.integer | np.unsignedinteger | np.signedinteger | np.int8
@@ -995,7 +996,12 @@ TimeZones: TypeAlias = str | tzinfo | None | int
 
 # Evaluates to a DataFrame column in DataFrame.assign context.
 IntoColumn: TypeAlias = (
-    AnyArrayLike | Scalar | Callable[[DataFrame], AnyArrayLike | Scalar] | None
+    AnyArrayLike
+    | Scalar
+    | Callable[[DataFrame], AnyArrayLike | Scalar | list[Scalar] | range]
+    | list[Scalar]
+    | range
+    | None
 )
 
 DatetimeLike: TypeAlias = datetime.datetime | np.datetime64 | Timestamp

pandas-stubs/core/frame.pyi

@@ -2276,7 +2276,7 @@ class DataFrame(NDFrame, OpsMixin, _GetItemHack):
         replace: _bool = ...,
         weights: _str | ListLike | None = ...,
         random_state: RandomState | None = ...,
-        axis: AxisIndex | None = ...,
+        axis: Axis | None = ...,
         ignore_index: _bool = ...,
     ) -> Self: ...
     def sem(

pandas-stubs/core/groupby/base.pyi

@@ -1,7 +1,56 @@
 from collections.abc import Hashable
 import dataclasses
+from typing import (
+    Literal,
+    TypeAlias,
+)
 
 @dataclasses.dataclass(order=True, frozen=True)
 class OutputKey:
     label: Hashable
     position: int
+
+ReductionKernelType: TypeAlias = Literal[
+    "all",
+    "any",
+    "corrwith",
+    "count",
+    "first",
+    "idxmax",
+    "idxmin",
+    "last",
+    "max",
+    "mean",
+    "median",
+    "min",
+    "nunique",
+    "prod",
+    # as long as `quantile`'s signature accepts only
+    # a single quantile value, it's a reduction.
+    # GH#27526 might change that.
+    "quantile",
+    "sem",
+    "size",
+    "skew",
+    "std",
+    "sum",
+    "var",
+]
+
+TransformationKernelType: TypeAlias = Literal[
+    "bfill",
+    "cumcount",
+    "cummax",
+    "cummin",
+    "cumprod",
+    "cumsum",
+    "diff",
+    "ffill",
+    "fillna",
+    "ngroup",
+    "pct_change",
+    "rank",
+    "shift",
+]
+
+TransformReductionListType: TypeAlias = ReductionKernelType | TransformationKernelType

pandas-stubs/core/groupby/generic.pyi

@@ -7,6 +7,7 @@ from collections.abc import (
 )
 from typing import (
     Any,
+    Concatenate,
     Generic,
     Literal,
     NamedTuple,
@@ -18,6 +19,7 @@ from typing import (
 from matplotlib.axes import Axes as PlotAxes
 import numpy as np
 from pandas.core.frame import DataFrame
+from pandas.core.groupby.base import TransformReductionListType
 from pandas.core.groupby.groupby import (
     GroupBy,
     GroupByPlot,
@@ -31,6 +33,7 @@ from typing_extensions import (
 from pandas._libs.tslibs.timestamps import Timestamp
 from pandas._typing import (
     S2,
+    S3,
     AggFuncTypeBase,
     AggFuncTypeFrame,
     ByT,
@@ -40,6 +43,7 @@ from pandas._typing import (
     Level,
     ListLike,
     NsmallestNlargestKeep,
+    P,
     Scalar,
     TakeIndexer,
     WindowingEngine,
@@ -53,10 +57,30 @@ class NamedAgg(NamedTuple):
     aggfunc: AggScalar
 
 class SeriesGroupBy(GroupBy[Series[S2]], Generic[S2, ByT]):
+    @overload
+    def aggregate(
+        self,
+        func: Callable[Concatenate[Series[S2], P], S3],
+        /,
+        *args,
+        engine: WindowingEngine = ...,
+        engine_kwargs: WindowingEngineKwargs = ...,
+        **kwargs,
+    ) -> Series[S3]: ...
+    @overload
+    def aggregate(
+        self,
+        func: Callable[[Series], S3],
+        *args,
+        engine: WindowingEngine = ...,
+        engine_kwargs: WindowingEngineKwargs = ...,
+        **kwargs,
+    ) -> Series[S3]: ...
     @overload
     def aggregate(
         self,
         func: list[AggFuncTypeBase],
+        /,
         *args,
         engine: WindowingEngine = ...,
         engine_kwargs: WindowingEngineKwargs = ...,
@@ -66,19 +90,33 @@ class SeriesGroupBy(GroupBy[Series[S2]], Generic[S2, ByT]):
     def aggregate(
         self,
         func: AggFuncTypeBase | None = ...,
+        /,
         *args,
         engine: WindowingEngine = ...,
         engine_kwargs: WindowingEngineKwargs = ...,
         **kwargs,
     ) -> Series: ...
     agg = aggregate
+    @overload
     def transform(
         self,
-        func: Callable | str,
-        *args,
+        func: Callable[Concatenate[Series[S2], P], Series[S3]],
+        /,
+        *args: Any,
         engine: WindowingEngine = ...,
         engine_kwargs: WindowingEngineKwargs = ...,
-        **kwargs,
+        **kwargs: Any,
+    ) -> Series[S3]: ...
+    @overload
+    def transform(
+        self,
+        func: Callable,
+        *args: Any,
+        **kwargs: Any,
+    ) -> Series: ...
+    @overload
+    def transform(
+        self, func: TransformReductionListType, *args, **kwargs
     ) -> Series: ...
     def filter(
         self, func: Callable | str, dropna: bool = ..., *args, **kwargs
@@ -206,13 +244,25 @@ class DataFrameGroupBy(GroupBy[DataFrame], Generic[ByT, _TT]):
         **kwargs,
     ) -> DataFrame: ...
     agg = aggregate
+    @overload
     def transform(
         self,
-        func: Callable | str,
-        *args,
+        func: Callable[Concatenate[DataFrame, P], DataFrame],
+        *args: Any,
         engine: WindowingEngine = ...,
         engine_kwargs: WindowingEngineKwargs = ...,
-        **kwargs,
+        **kwargs: Any,
+    ) -> DataFrame: ...
+    @overload
+    def transform(
+        self,
+        func: Callable,
+        *args: Any,
+        **kwargs: Any,
+    ) -> DataFrame: ...
+    @overload
+    def transform(
+        self, func: TransformReductionListType, *args, **kwargs
     ) -> DataFrame: ...
     def filter(
         self, func: Callable, dropna: bool = ..., *args, **kwargs

pandas-stubs/core/indexes/multi.pyi

@@ -54,7 +54,7 @@ class MultiIndex(Index):
     @classmethod
     def from_product(
         cls,
-        iterables: Sequence[SequenceNotStr[Hashable]],
+        iterables: Sequence[SequenceNotStr[Hashable] | pd.Series | pd.Index],
         sortorder: int | None = ...,
         names: SequenceNotStr[Hashable] = ...,
     ) -> Self: ...

pyproject.toml

@@ -37,7 +37,7 @@ ty = "^0.0.1a8"
 
 [tool.poetry.group.dev.dependencies]
 mypy = "1.16.0"
-pandas = "2.2.3"
+pandas = "2.3.0"
 pyarrow = ">=10.0.1"
 pytest = ">=7.1.2"
 pyright = ">=1.1.400"

tests/__init__.py

@@ -50,7 +50,7 @@
 
 TYPE_CHECKING_INVALID_USAGE: Final = TYPE_CHECKING
 WINDOWS = os.name == "nt" or "cygwin" in platform.system().lower()
-PD_LTE_22 = Version(pd.__version__) < Version("2.2.999")
+PD_LTE_23 = Version(pd.__version__) < Version("2.3.999")
 NUMPY20 = np.lib.NumpyVersion(np.__version__) >= "2.0.0"
 
 

tests/test_errors.py

@@ -4,7 +4,7 @@
 import pytest
 
 from tests import (
-    PD_LTE_22,
+    PD_LTE_23,
     WINDOWS,
 )
 
@@ -108,13 +108,13 @@ def test_specification_error() -> None:
 
 
 def test_setting_with_copy_error() -> None:
-    if PD_LTE_22:
+    if PD_LTE_23:
         with pytest.raises(errors.SettingWithCopyError):
             raise errors.SettingWithCopyError()
 
 
 def test_setting_with_copy_warning() -> None:
-    if PD_LTE_22:
+    if PD_LTE_23:
         with pytest.warns(errors.SettingWithCopyWarning):
             warnings.warn("", errors.SettingWithCopyWarning)