Merge branch 'main' into pd-cut-doc

Author: chaarvii

doc/source/user_guide/text.rst

@@ -204,7 +204,7 @@ and replacing any remaining whitespaces with underscores:
 
 .. warning::
 
-    The type of the Series is inferred and the allowed types (i.e. strings).
+    The type of the Series is inferred and is one among the allowed types (i.e. strings).
 
     Generally speaking, the ``.str`` accessor is intended to work only on strings. With very few
     exceptions, other uses are not supported, and may be disabled at a later point.

pandas/_typing.py

@@ -526,3 +526,5 @@ def closed(self) -> bool:
 
 # maintaine the sub-type of any hashable sequence
 SequenceT = TypeVar("SequenceT", bound=Sequence[Hashable])
+
+SliceType = Optional[Hashable]

pandas/core/generic.py

@@ -1491,14 +1491,12 @@ def __invert__(self) -> Self:
         return res.__finalize__(self, method="__invert__")
 
     @final
-    def __nonzero__(self) -> NoReturn:
+    def __bool__(self) -> NoReturn:
         raise ValueError(
             f"The truth value of a {type(self).__name__} is ambiguous. "
             "Use a.empty, a.bool(), a.item(), a.any() or a.all()."
         )
 
-    __bool__ = __nonzero__
-
     @final
     def abs(self) -> Self:
         """

pandas/core/indexes/base.py

@@ -45,7 +45,9 @@
     ArrayLike,
     Axes,
     Axis,
+    AxisInt,
     DropKeep,
+    Dtype,
     DtypeObj,
     F,
     IgnoreRaise,
@@ -57,6 +59,7 @@
     ReindexMethod,
     Self,
     Shape,
+    SliceType,
     npt,
 )
 from pandas.compat.numpy import function as nv
@@ -1087,7 +1090,7 @@ def view(self, cls=None):
             result._id = self._id
         return result
 
-    def astype(self, dtype, copy: bool = True):
+    def astype(self, dtype: Dtype, copy: bool = True):
         """
         Create an Index with values cast to dtypes.
 
@@ -2907,14 +2910,12 @@ def __iadd__(self, other):
         return self + other
 
     @final
-    def __nonzero__(self) -> NoReturn:
+    def __bool__(self) -> NoReturn:
         raise ValueError(
             f"The truth value of a {type(self).__name__} is ambiguous. "
             "Use a.empty, a.bool(), a.item(), a.any() or a.all()."
         )
 
-    __bool__ = __nonzero__
-
     # --------------------------------------------------------------------
     # Set Operation Methods
 
@@ -2957,7 +2958,7 @@ def _dti_setop_align_tzs(self, other: Index, setop: str_t) -> tuple[Index, Index
         return self, other
 
     @final
-    def union(self, other, sort=None):
+    def union(self, other, sort: bool | None = None):
         """
         Form the union of two Index objects.
 
@@ -3334,7 +3335,7 @@ def _intersection_via_get_indexer(
         return result
 
     @final
-    def difference(self, other, sort=None):
+    def difference(self, other, sort: bool | None = None):
         """
         Return a new Index with elements of index not in `other`.
 
@@ -3420,7 +3421,12 @@ def _wrap_difference_result(self, other, result):
         # We will override for MultiIndex to handle empty results
         return self._wrap_setop_result(other, result)
 
-    def symmetric_difference(self, other, result_name=None, sort=None):
+    def symmetric_difference(
+        self,
+        other,
+        result_name: abc.Hashable | None = None,
+        sort: bool | None = None,
+    ):
         """
         Compute the symmetric difference of two Index objects.
 
@@ -6389,7 +6395,7 @@ def _transform_index(self, func, *, level=None) -> Index:
             items = [func(x) for x in self]
             return Index(items, name=self.name, tupleize_cols=False)
 
-    def isin(self, values, level=None) -> npt.NDArray[np.bool_]:
+    def isin(self, values, level: str_t | int | None = None) -> npt.NDArray[np.bool_]:
         """
         Return a boolean array where the index values are in `values`.
 
@@ -6687,7 +6693,12 @@ def get_slice_bound(self, label, side: Literal["left", "right"]) -> int:
             else:
                 return slc
 
-    def slice_locs(self, start=None, end=None, step=None) -> tuple[int, int]:
+    def slice_locs(
+        self,
+        start: SliceType = None,
+        end: SliceType = None,
+        step: int | None = None,
+    ) -> tuple[int, int]:
         """
         Compute slice locations for input labels.
 
@@ -6781,7 +6792,9 @@ def slice_locs(self, start=None, end=None, step=None) -> tuple[int, int]:
 
         return start_slice, end_slice
 
-    def delete(self, loc) -> Self:
+    def delete(
+        self, loc: int | np.integer | list[int] | npt.NDArray[np.integer]
+    ) -> Self:
         """
         Make new Index with passed location(-s) deleted.
 
@@ -7227,7 +7240,9 @@ def _maybe_disable_logical_methods(self, opname: str_t) -> None:
             raise TypeError(f"cannot perform {opname} with {type(self).__name__}")
 
     @Appender(IndexOpsMixin.argmin.__doc__)
-    def argmin(self, axis=None, skipna: bool = True, *args, **kwargs) -> int:
+    def argmin(
+        self, axis: AxisInt | None = None, skipna: bool = True, *args, **kwargs
+    ) -> int:
         nv.validate_argmin(args, kwargs)
         nv.validate_minmax_axis(axis)
 
@@ -7240,7 +7255,9 @@ def argmin(self, axis=None, skipna: bool = True, *args, **kwargs) -> int:
         return super().argmin(skipna=skipna)
 
     @Appender(IndexOpsMixin.argmax.__doc__)
-    def argmax(self, axis=None, skipna: bool = True, *args, **kwargs) -> int:
+    def argmax(
+        self, axis: AxisInt | None = None, skipna: bool = True, *args, **kwargs
+    ) -> int:
         nv.validate_argmax(args, kwargs)
         nv.validate_minmax_axis(axis)
 
@@ -7251,7 +7268,7 @@ def argmax(self, axis=None, skipna: bool = True, *args, **kwargs) -> int:
                 raise ValueError("Encountered all NA values")
         return super().argmax(skipna=skipna)
 
-    def min(self, axis=None, skipna: bool = True, *args, **kwargs):
+    def min(self, axis: AxisInt | None = None, skipna: bool = True, *args, **kwargs):
         """
         Return the minimum value of the Index.
 
@@ -7314,7 +7331,7 @@ def min(self, axis=None, skipna: bool = True, *args, **kwargs):
 
         return nanops.nanmin(self._values, skipna=skipna)
 
-    def max(self, axis=None, skipna: bool = True, *args, **kwargs):
+    def max(self, axis: AxisInt | None = None, skipna: bool = True, *args, **kwargs):
         """
         Return the maximum value of the Index.
 

pandas/core/indexes/category.py

@@ -377,8 +377,13 @@ def __contains__(self, key: Any) -> bool:
         # if key is a NaN, check if any NaN is in self.
         if is_valid_na_for_dtype(key, self.categories.dtype):
             return self.hasnans
-
-        return contains(self, key, container=self._engine)
+        if self.categories._typ == "rangeindex":
+            container: Index | libindex.IndexEngine | libindex.ExtensionEngine = (
+                self.categories
+            )
+        else:
+            container = self._engine
+        return contains(self, key, container=container)
 
     def reindex(
         self, target, method=None, level=None, limit: int | None = None, tolerance=None

pandas/core/internals/managers.py

@@ -263,12 +263,9 @@ def make_empty(self, axes=None) -> Self:
             blocks = []
         return type(self).from_blocks(blocks, axes)
 
-    def __nonzero__(self) -> bool:
+    def __bool__(self) -> bool:
         return True
 
-    # Python3 compat
-    __bool__ = __nonzero__
-
     def set_axis(self, axis: AxisInt, new_labels: Index) -> None:
         # Caller is responsible for ensuring we have an Index object.
         self._validate_set_axis(axis, new_labels)

pandas/tests/indexes/categorical/test_category.py

@@ -21,6 +21,9 @@
 class TestCategoricalIndex:
     @pytest.fixture
     def simple_index(self) -> CategoricalIndex:
+        """
+        Fixture that provides a CategoricalIndex.
+        """
         return CategoricalIndex(list("aabbca"), categories=list("cab"), ordered=False)
 
     def test_can_hold_identifiers(self):
@@ -392,3 +395,10 @@ def test_remove_maintains_order(self):
                 ["a", "b", np.nan, "d", "d", "a"], categories=list("dba"), ordered=True
             ),
         )
+
+
+def test_contains_rangeindex_categories_no_engine():
+    ci = CategoricalIndex(range(3))
+    assert 2 in ci
+    assert 5 not in ci
+    assert "_engine" not in ci._cache

pandas/tests/indexes/interval/test_constructors.py

@@ -210,6 +210,7 @@ class TestFromArrays(ConstructorTests):
 
     @pytest.fixture
     def constructor(self):
+        """Fixture for IntervalIndex.from_arrays constructor"""
         return IntervalIndex.from_arrays
 
     def get_kwargs_from_breaks(self, breaks, closed="right"):
@@ -282,6 +283,7 @@ class TestFromBreaks(ConstructorTests):
 
     @pytest.fixture
     def constructor(self):
+        """Fixture for IntervalIndex.from_breaks constructor"""
         return IntervalIndex.from_breaks
 
     def get_kwargs_from_breaks(self, breaks, closed="right"):
@@ -320,6 +322,7 @@ class TestFromTuples(ConstructorTests):
 
     @pytest.fixture
     def constructor(self):
+        """Fixture for IntervalIndex.from_tuples constructor"""
         return IntervalIndex.from_tuples
 
     def get_kwargs_from_breaks(self, breaks, closed="right"):
@@ -370,6 +373,7 @@ class TestClassConstructors(ConstructorTests):
 
     @pytest.fixture
     def constructor(self):
+        """Fixture for IntervalIndex class constructor"""
         return IntervalIndex
 
     def get_kwargs_from_breaks(self, breaks, closed="right"):

pandas/tests/indexing/interval/test_interval_new.py

@@ -17,6 +17,9 @@
 class TestIntervalIndex:
     @pytest.fixture
     def series_with_interval_index(self):
+        """
+        Fixture providing a Series with an IntervalIndex.
+        """
         return Series(np.arange(5), IntervalIndex.from_breaks(np.arange(6)))
 
     def test_loc_with_interval(self, series_with_interval_index, indexer_sl):

pandas/tests/io/json/test_json_table_schema_ext_dtype.py

@@ -97,18 +97,22 @@ def test_as_json_table_type_ext_integer_dtype(self):
 class TestTableOrient:
     @pytest.fixture
     def da(self):
+        """Fixture for creating a DateArray."""
         return DateArray([dt.date(2021, 10, 10)])
 
     @pytest.fixture
     def dc(self):
+        """Fixture for creating a DecimalArray."""
         return DecimalArray([decimal.Decimal(10)])
 
     @pytest.fixture
     def sa(self):
+        """Fixture for creating a StringDtype array."""
         return array(["pandas"], dtype="string")
 
     @pytest.fixture
     def ia(self):
+        """Fixture for creating an Int64Dtype array."""
         return array([10], dtype="Int64")
 
     def test_build_date_series(self, da):