Merge branch 'main' into bugfix-spss-kwargs

astronights · web-flow · commit 186b4573f664 · 2024-01-30T08:25:37.000+08:00
diff --git a/.github/workflows/wheels.yml b/.github/workflows/wheels.yml
@@ -139,7 +139,7 @@ jobs:
 
       - name: Build normal wheels
         if: ${{ (env.IS_SCHEDULE_DISPATCH != 'true' || env.IS_PUSH == 'true') }}
-        uses: pypa/cibuildwheel@v2.16.2
+        uses: pypa/cibuildwheel@v2.16.4
         with:
          package-dir: ./dist/${{ matrix.buildplat[1] == 'macosx_*' && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:
@@ -148,7 +148,7 @@ jobs:
 
       - name: Build nightly wheels (with NumPy pre-release)
         if: ${{ (env.IS_SCHEDULE_DISPATCH == 'true' && env.IS_PUSH != 'true') }}
-        uses: pypa/cibuildwheel@v2.16.2
+        uses: pypa/cibuildwheel@v2.16.4
         with:
          package-dir: ./dist/${{ matrix.buildplat[1] == 'macosx_*' && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:
diff --git a/ci/code_checks.sh b/ci/code_checks.sh
@@ -95,7 +95,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.PeriodIndex.strftime\
         pandas.Series.clip\
         pandas.Series.rename_axis\
-        pandas.Series.interpolate\
         pandas.Series.dt.to_period\
         pandas.Series.dt.tz_localize\
         pandas.Series.dt.tz_convert\
@@ -162,9 +161,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.tseries.offsets.Milli\
         pandas.tseries.offsets.Micro\
         pandas.tseries.offsets.Nano\
-        pandas.describe_option\
-        pandas.reset_option\
-        pandas.get_option\
         pandas.set_option\
         pandas.Timestamp.max\
         pandas.Timestamp.min\
@@ -186,8 +182,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.core.groupby.DataFrameGroupBy.hist\
         pandas.core.groupby.DataFrameGroupBy.plot\
         pandas.core.groupby.SeriesGroupBy.plot\
-        pandas.read_hdf\
-        pandas.HDFStore.append\
         pandas.core.window.rolling.Rolling.quantile\
         pandas.core.window.expanding.Expanding.quantile\
         pandas.api.extensions.ExtensionArray.argsort # There should be no backslash in the final line, please keep this comment in the last ignored function
diff --git a/doc/source/user_guide/missing_data.rst b/doc/source/user_guide/missing_data.rst
@@ -30,7 +30,7 @@ use :class:`api.types.NaTType`.
    pd.Series(["2020", "2020"], dtype=pd.PeriodDtype("D")).reindex([0, 1, 2])
 
 :class:`NA` for :class:`StringDtype`, :class:`Int64Dtype` (and other bit widths),
-:class:`Float64Dtype`(and other bit widths), :class:`BooleanDtype` and :class:`ArrowDtype`.
+:class:`Float64Dtype` (and other bit widths), :class:`BooleanDtype` and :class:`ArrowDtype`.
 These types will maintain the original data type of the data.
 For typing applications, use :class:`api.types.NAType`.
 
diff --git a/doc/source/whatsnew/v2.2.1.rst b/doc/source/whatsnew/v2.2.1.rst
@@ -19,6 +19,7 @@ Fixed regressions
 - Fixed regression in :func:`wide_to_long` raising an ``AttributeError`` for string columns (:issue:`57066`)
 - Fixed regression in :meth:`DataFrameGroupBy.idxmin`, :meth:`DataFrameGroupBy.idxmax`, :meth:`SeriesGroupBy.idxmin`, :meth:`SeriesGroupBy.idxmax` ignoring the ``skipna`` argument (:issue:`57040`)
 - Fixed regression in :meth:`DataFrameGroupBy.idxmin`, :meth:`DataFrameGroupBy.idxmax`, :meth:`SeriesGroupBy.idxmin`, :meth:`SeriesGroupBy.idxmax` where values containing the minimum or maximum value for the dtype could produce incorrect results (:issue:`57040`)
+- Fixed regression in :meth:`Index.join` raising ``TypeError`` when joining an empty index to a non-empty index containing mixed dtype values (:issue:`57048`)
 - Fixed regression in :meth:`Series.pct_change` raising a ``ValueError`` for an empty :class:`Series` (:issue:`57056`)
 
 .. ---------------------------------------------------------------------------
diff --git a/pandas/_config/config.py b/pandas/_config/config.py
@@ -54,14 +54,17 @@
     ContextDecorator,
     contextmanager,
 )
+from inspect import signature
 import re
 from typing import (
     TYPE_CHECKING,
     Any,
     Callable,
     Generic,
+    Literal,
     NamedTuple,
     cast,
+    overload,
 )
 import warnings
 
@@ -270,6 +273,7 @@ class CallableDynamicDoc(Generic[T]):
     def __init__(self, func: Callable[..., T], doc_tmpl: str) -> None:
         self.__doc_tmpl__ = doc_tmpl
         self.__func__ = func
+        self.__signature__ = signature(func)
 
     def __call__(self, *args, **kwds) -> T:
         return self.__func__(*args, **kwds)
@@ -740,7 +744,23 @@ def _build_option_description(k: str) -> str:
     return s
 
 
-def pp_options_list(keys: Iterable[str], width: int = 80, _print: bool = False):
+@overload
+def pp_options_list(
+    keys: Iterable[str], *, width: int = ..., _print: Literal[False] = ...
+) -> str:
+    ...
+
+
+@overload
+def pp_options_list(
+    keys: Iterable[str], *, width: int = ..., _print: Literal[True]
+) -> None:
+    ...
+
+
+def pp_options_list(
+    keys: Iterable[str], *, width: int = 80, _print: bool = False
+) -> str | None:
     """Builds a concise listing of available options, grouped by prefix"""
     from itertools import groupby
     from textwrap import wrap
@@ -770,8 +790,7 @@ def pp(name: str, ks: Iterable[str]) -> list[str]:
     s = "\n".join(ls)
     if _print:
         print(s)
-    else:
-        return s
+    return s
 
 
 #
diff --git a/pandas/_libs/arrays.pyi b/pandas/_libs/arrays.pyi
@@ -14,9 +14,9 @@ class NDArrayBacked:
     _ndarray: np.ndarray
     def __init__(self, values: np.ndarray, dtype: DtypeObj) -> None: ...
     @classmethod
-    def _simple_new(cls, values: np.ndarray, dtype: DtypeObj): ...
-    def _from_backing_data(self, values: np.ndarray): ...
-    def __setstate__(self, state): ...
+    def _simple_new(cls, values: np.ndarray, dtype: DtypeObj) -> Self: ...
+    def _from_backing_data(self, values: np.ndarray) -> Self: ...
+    def __setstate__(self, state) -> None: ...
     def __len__(self) -> int: ...
     @property
     def shape(self) -> Shape: ...
@@ -26,14 +26,14 @@ class NDArrayBacked:
     def size(self) -> int: ...
     @property
     def nbytes(self) -> int: ...
-    def copy(self, order=...): ...
-    def delete(self, loc, axis=...): ...
-    def swapaxes(self, axis1, axis2): ...
-    def repeat(self, repeats: int | Sequence[int], axis: int | None = ...): ...
-    def reshape(self, *args, **kwargs): ...
-    def ravel(self, order=...): ...
+    def copy(self, order=...) -> Self: ...
+    def delete(self, loc, axis=...) -> Self: ...
+    def swapaxes(self, axis1, axis2) -> Self: ...
+    def repeat(self, repeats: int | Sequence[int], axis: int | None = ...) -> Self: ...
+    def reshape(self, *args, **kwargs) -> Self: ...
+    def ravel(self, order=...) -> Self: ...
     @property
-    def T(self): ...
+    def T(self) -> Self: ...
     @classmethod
     def _concat_same_type(
         cls, to_concat: Sequence[Self], axis: AxisInt = ...
diff --git a/pandas/_libs/testing.pyi b/pandas/_libs/testing.pyi
@@ -1,4 +1,6 @@
-def assert_dict_equal(a, b, compare_keys: bool = ...): ...
+from typing import Mapping
+
+def assert_dict_equal(a: Mapping, b: Mapping, compare_keys: bool = ...) -> bool: ...
 def assert_almost_equal(
     a,
     b,
@@ -9,4 +11,4 @@ def assert_almost_equal(
     lobj=...,
     robj=...,
     index_values=...,
-): ...
+) -> bool: ...
diff --git a/pandas/_libs/tslibs/dtypes.pyi b/pandas/_libs/tslibs/dtypes.pyi
@@ -1,5 +1,7 @@
 from enum import Enum
 
+from pandas._typing import Self
+
 OFFSET_TO_PERIOD_FREQSTR: dict[str, str]
 
 def periods_per_day(reso: int = ...) -> int: ...
@@ -12,7 +14,7 @@ class PeriodDtypeBase:
     _n: int
 
     # actually __cinit__
-    def __new__(cls, code: int, n: int): ...
+    def __new__(cls, code: int, n: int) -> Self: ...
     @property
     def _freq_group_code(self) -> int: ...
     @property
diff --git a/pandas/_libs/tslibs/offsets.pyi b/pandas/_libs/tslibs/offsets.pyi
@@ -64,15 +64,15 @@ class BaseOffset:
     @overload
     def __rsub__(self, other: npt.NDArray[np.object_]) -> npt.NDArray[np.object_]: ...
     @overload
-    def __rsub__(self, other: BaseOffset): ...
+    def __rsub__(self, other: BaseOffset) -> Self: ...
     @overload
     def __rsub__(self, other: _DatetimeT) -> _DatetimeT: ...
     @overload
     def __rsub__(self, other: _TimedeltaT) -> _TimedeltaT: ...
     @overload
     def __mul__(self, other: np.ndarray) -> np.ndarray: ...
     @overload
-    def __mul__(self, other: int): ...
+    def __mul__(self, other: int) -> Self: ...
     @overload
     def __rmul__(self, other: np.ndarray) -> np.ndarray: ...
     @overload
@@ -100,7 +100,7 @@ def _get_offset(name: str) -> BaseOffset: ...
 
 class SingleConstructorOffset(BaseOffset):
     @classmethod
-    def _from_name(cls, suffix: None = ...): ...
+    def _from_name(cls, suffix: None = ...) -> Self: ...
     def __reduce__(self): ...
 
 @overload
diff --git a/pandas/_testing/__init__.py b/pandas/_testing/__init__.py
@@ -482,7 +482,7 @@ def iat(x):
 _UNITS = ["s", "ms", "us", "ns"]
 
 
-def get_finest_unit(left: str, right: str):
+def get_finest_unit(left: str, right: str) -> str:
     """
     Find the higher of two datetime64 units.
     """
diff --git a/pandas/_typing.py b/pandas/_typing.py
@@ -332,7 +332,7 @@ def readline(self) -> AnyStr_co:
 
     @property
     def closed(self) -> bool:
-        # for enine=pyarrow
+        # for engine=pyarrow
         ...
 
 
diff --git a/pandas/conftest.py b/pandas/conftest.py
@@ -190,10 +190,6 @@ def pytest_collection_modifyitems(items, config) -> None:
 
     if is_doctest:
         for item in items:
-            # autouse=True for the add_doctest_imports can lead to expensive teardowns
-            # since doctest_namespace is a session fixture
-            item.add_marker(pytest.mark.usefixtures("add_doctest_imports"))
-
             for path, message in ignored_doctest_warnings:
                 ignore_doctest_warning(item, path, message)
 
@@ -250,7 +246,14 @@ def pytest_collection_modifyitems(items, config) -> None:
     )
 
 
-@pytest.fixture
+# ----------------------------------------------------------------
+# Autouse fixtures
+# ----------------------------------------------------------------
+
+
+# https://github.com/pytest-dev/pytest/issues/11873
+# Would like to avoid autouse=True, but cannot as of pytest 8.0.0
+@pytest.fixture(autouse=True)
 def add_doctest_imports(doctest_namespace) -> None:
     """
     Make `np` and `pd` names available for doctests.
@@ -259,9 +262,6 @@ def add_doctest_imports(doctest_namespace) -> None:
     doctest_namespace["pd"] = pd
 
 
-# ----------------------------------------------------------------
-# Autouse fixtures
-# ----------------------------------------------------------------
 @pytest.fixture(autouse=True)
 def configure_tests() -> None:
     """
diff --git a/pandas/core/arrays/_mixins.py b/pandas/core/arrays/_mixins.py
@@ -89,7 +89,9 @@ def method(self, *args, **kwargs):
     return cast(F, method)
 
 
-class NDArrayBackedExtensionArray(NDArrayBacked, ExtensionArray):
+# error: Definition of "delete/ravel/T/repeat/copy" in base class "NDArrayBacked"
+# is incompatible with definition in base class "ExtensionArray"
+class NDArrayBackedExtensionArray(NDArrayBacked, ExtensionArray):  # type: ignore[misc]
     """
     ExtensionArray that is backed by a single NumPy ndarray.
     """
@@ -386,7 +388,7 @@ def fillna(
     # ------------------------------------------------------------------------
     # Reductions
 
-    def _wrap_reduction_result(self, axis: AxisInt | None, result):
+    def _wrap_reduction_result(self, axis: AxisInt | None, result) -> Any:
         if axis is None or self.ndim == 1:
             return self._box_func(result)
         return self._from_backing_data(result)
diff --git a/pandas/core/arrays/base.py b/pandas/core/arrays/base.py
@@ -1781,7 +1781,7 @@ def _formatter(self, boxed: bool = False) -> Callable[[Any], str | None]:
     # Reshaping
     # ------------------------------------------------------------------------
 
-    def transpose(self, *axes: int) -> ExtensionArray:
+    def transpose(self, *axes: int) -> Self:
         """
         Return a transposed view on this array.
 
@@ -1802,10 +1802,10 @@ def transpose(self, *axes: int) -> ExtensionArray:
         return self[:]
 
     @property
-    def T(self) -> ExtensionArray:
+    def T(self) -> Self:
         return self.transpose()
 
-    def ravel(self, order: Literal["C", "F", "A", "K"] | None = "C") -> ExtensionArray:
+    def ravel(self, order: Literal["C", "F", "A", "K"] | None = "C") -> Self:
         """
         Return a flattened view on this array.
 
diff --git a/pandas/core/arrays/categorical.py b/pandas/core/arrays/categorical.py
@@ -243,7 +243,9 @@ def contains(cat, key, container) -> bool:
         return any(loc_ in container for loc_ in loc)
 
 
-class Categorical(NDArrayBackedExtensionArray, PandasObject, ObjectStringArrayMixin):
+# error: Definition of "delete/ravel/T/repeat/copy" in base class "NDArrayBacked"
+# is incompatible with definition in base class "ExtensionArray"
+class Categorical(NDArrayBackedExtensionArray, PandasObject, ObjectStringArrayMixin):  # type: ignore[misc]
     """
     Represent a categorical variable in classic R / S-plus fashion.
 
@@ -561,6 +563,7 @@ def astype(self, dtype: AstypeArg, copy: bool = True) -> ArrayLike:
             object is returned.
         """
         dtype = pandas_dtype(dtype)
+        result: Categorical | np.ndarray
         if self.dtype is dtype:
             result = self.copy() if copy else self
 
@@ -1818,10 +1821,14 @@ def value_counts(self, dropna: bool = True) -> Series:
             ix = np.append(ix, -1)
 
         ix = coerce_indexer_dtype(ix, self.dtype.categories)
-        ix = self._from_backing_data(ix)
+        ix_categorical = self._from_backing_data(ix)
 
         return Series(
-            count, index=CategoricalIndex(ix), dtype="int64", name="count", copy=False
+            count,
+            index=CategoricalIndex(ix_categorical),
+            dtype="int64",
+            name="count",
+            copy=False,
         )
 
     # error: Argument 2 of "_empty" is incompatible with supertype
@@ -2526,7 +2533,9 @@ def _concat_same_type(cls, to_concat: Sequence[Self], axis: AxisInt = 0) -> Self
             result = res_flat.reshape(len(first), -1, order="F")
             return result
 
-        result = union_categoricals(to_concat)
+        # error: Incompatible types in assignment (expression has type "Categorical",
+        # variable has type "Self")
+        result = union_categoricals(to_concat)  # type: ignore[assignment]
         return result
 
     # ------------------------------------------------------------------
@@ -2666,11 +2675,11 @@ def _replace(self, *, to_replace, value, inplace: bool = False) -> Self | None:
 
         new_categories = ser.take(locs)
         new_categories = new_categories.drop_duplicates(keep="first")
-        new_categories = Index(new_categories)
+        index_categories = Index(new_categories)
         new_codes = recode_for_categories(
-            cat._codes, all_values, new_categories, copy=False
+            cat._codes, all_values, index_categories, copy=False
         )
-        new_dtype = CategoricalDtype(new_categories, ordered=self.dtype.ordered)
+        new_dtype = CategoricalDtype(index_categories, ordered=self.dtype.ordered)
         NDArrayBacked.__init__(cat, new_codes, new_dtype)
 
         if new_dtype != orig_dtype:
diff --git a/pandas/core/arrays/interval.py b/pandas/core/arrays/interval.py
@@ -1727,6 +1727,8 @@ def insert(self, loc: int, item: Interval) -> Self:
         return self._shallow_copy(new_left, new_right)
 
     def delete(self, loc) -> Self:
+        new_left: np.ndarray | DatetimeArray | TimedeltaArray
+        new_right: np.ndarray | DatetimeArray | TimedeltaArray
         if isinstance(self._left, np.ndarray):
             new_left = np.delete(self._left, loc)
             assert isinstance(self._right, np.ndarray)
diff --git a/pandas/core/arrays/string_.py b/pandas/core/arrays/string_.py
@@ -499,10 +499,10 @@ def astype(self, dtype, copy: bool = True):
             values = arr.astype(dtype.numpy_dtype)
             return IntegerArray(values, mask, copy=False)
         elif isinstance(dtype, FloatingDtype):
-            arr = self.copy()
+            arr_ea = self.copy()
             mask = self.isna()
-            arr[mask] = "0"
-            values = arr.astype(dtype.numpy_dtype)
+            arr_ea[mask] = "0"
+            values = arr_ea.astype(dtype.numpy_dtype)
             return FloatingArray(values, mask, copy=False)
         elif isinstance(dtype, ExtensionDtype):
             # Skip the NumpyExtensionArray.astype method
diff --git a/pandas/core/generic.py b/pandas/core/generic.py
diff --git a/pandas/core/indexes/base.py b/pandas/core/indexes/base.py
diff --git a/pandas/io/pytables.py b/pandas/io/pytables.py
diff --git a/pandas/plotting/_core.py b/pandas/plotting/_core.py
diff --git a/pandas/plotting/_matplotlib/core.py b/pandas/plotting/_matplotlib/core.py
diff --git a/pandas/tests/reshape/merge/test_join.py b/pandas/tests/reshape/merge/test_join.py
diff --git a/pandas/tseries/holiday.py b/pandas/tseries/holiday.py
diff --git a/pandas/util/_doctools.py b/pandas/util/_doctools.py
