Merge remote-tracking branch 'upstream/main' into missing-source-link

Author: fbourgey

ci/code_checks.sh

@@ -92,7 +92,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.dt.day_name PR01,PR02" \
         -i "pandas.Series.dt.floor PR01,PR02" \
         -i "pandas.Series.dt.freq GL08" \
-        -i "pandas.Series.dt.microseconds SA01" \
         -i "pandas.Series.dt.month_name PR01,PR02" \
         -i "pandas.Series.dt.nanoseconds SA01" \
         -i "pandas.Series.dt.normalize PR01" \
@@ -113,12 +112,9 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timedelta.max PR02" \
         -i "pandas.Timedelta.min PR02" \
         -i "pandas.Timedelta.resolution PR02" \
-        -i "pandas.Timedelta.to_numpy PR01" \
         -i "pandas.Timedelta.to_timedelta64 SA01" \
         -i "pandas.Timedelta.total_seconds SA01" \
         -i "pandas.Timedelta.view SA01" \
-        -i "pandas.TimedeltaIndex.components SA01" \
-        -i "pandas.TimedeltaIndex.microseconds SA01" \
         -i "pandas.TimedeltaIndex.nanoseconds SA01" \
         -i "pandas.TimedeltaIndex.seconds SA01" \
         -i "pandas.TimedeltaIndex.to_pytimedelta RT03,SA01" \

doc/source/whatsnew/v3.0.0.rst

@@ -528,6 +528,7 @@ Performance improvements
 - Performance improvement in :meth:`RangeIndex.reindex` returning a :class:`RangeIndex` instead of a :class:`Index` when possible. (:issue:`57647`, :issue:`57752`)
 - Performance improvement in :meth:`RangeIndex.take` returning a :class:`RangeIndex` instead of a :class:`Index` when possible. (:issue:`57445`, :issue:`57752`)
 - Performance improvement in :func:`merge` if hash-join can be used (:issue:`57970`)
+- Performance improvement in :meth:`CategoricalDtype.update_dtype` when ``dtype`` is a :class:`CategoricalDtype` with non ``None`` categories and ordered (:issue:`59647`)
 - Performance improvement in :meth:`to_hdf` avoid unnecessary reopenings of the HDF5 file to speedup data addition to files with a very large number of groups . (:issue:`58248`)
 - Performance improvement in ``DataFrameGroupBy.__len__`` and ``SeriesGroupBy.__len__`` (:issue:`57595`)
 - Performance improvement in indexing operations for string dtypes (:issue:`56997`)

pandas/_libs/tslibs/timedeltas.pyx

@@ -1421,9 +1421,16 @@ cdef class _Timedelta(timedelta):
         """
         Convert the Timedelta to a NumPy timedelta64.
 
-        This is an alias method for `Timedelta.to_timedelta64()`. The dtype and
-        copy parameters are available here only for compatibility. Their values
-        will not affect the return value.
+        This is an alias method for `Timedelta.to_timedelta64()`.
+
+        Parameters
+        ----------
+        dtype : NoneType
+            It is available here only for compatibility. Its value will not
+            affect the return value.
+        copy : bool, default False
+            It is available here only for compatibility. Its value will not
+            affect the return value.
 
         Returns
         -------

pandas/core/arrays/_arrow_string_mixins.py

@@ -190,3 +190,18 @@ def _str_istitle(self):
     def _str_isupper(self):
         result = pc.utf8_is_upper(self._pa_array)
         return self._convert_bool_result(result)
+
+    def _str_contains(
+        self, pat, case: bool = True, flags: int = 0, na=None, regex: bool = True
+    ):
+        if flags:
+            raise NotImplementedError(f"contains not implemented with {flags=}")
+
+        if regex:
+            pa_contains = pc.match_substring_regex
+        else:
+            pa_contains = pc.match_substring
+        result = pa_contains(self._pa_array, pat, ignore_case=not case)
+        if not isna(na):  # pyright: ignore [reportGeneralTypeIssues]
+            result = result.fill_null(na)
+        return self._convert_bool_result(result)

pandas/core/arrays/arrow/array.py

@@ -2322,21 +2322,6 @@ def _str_count(self, pat: str, flags: int = 0) -> Self:
             raise NotImplementedError(f"count not implemented with {flags=}")
         return type(self)(pc.count_substring_regex(self._pa_array, pat))
 
-    def _str_contains(
-        self, pat, case: bool = True, flags: int = 0, na=None, regex: bool = True
-    ) -> Self:
-        if flags:
-            raise NotImplementedError(f"contains not implemented with {flags=}")
-
-        if regex:
-            pa_contains = pc.match_substring_regex
-        else:
-            pa_contains = pc.match_substring
-        result = pa_contains(self._pa_array, pat, ignore_case=not case)
-        if not isna(na):
-            result = result.fill_null(na)
-        return type(self)(result)
-
     def _result_converter(self, result):
         return type(self)(result)
 

pandas/core/arrays/string_arrow.py

@@ -223,10 +223,8 @@ def insert(self, loc: int, item) -> ArrowStringArray:
             raise TypeError("Scalar must be NA or str")
         return super().insert(loc, item)
 
-    def _convert_bool_result(self, values, na=None):
+    def _convert_bool_result(self, values):
         if self.dtype.na_value is np.nan:
-            if not isna(na):
-                values = values.fill_null(bool(na))
             return ArrowExtensionArray(values).to_numpy(na_value=np.nan)
         return BooleanDtype().__from_arrow__(values)
 
@@ -304,11 +302,6 @@ def _str_contains(
                 fallback_performancewarning()
             return super()._str_contains(pat, case, flags, na, regex)
 
-        if regex:
-            result = pc.match_substring_regex(self._pa_array, pat, ignore_case=not case)
-        else:
-            result = pc.match_substring(self._pa_array, pat, ignore_case=not case)
-        result = self._convert_bool_result(result, na=na)
         if not isna(na):
             if not isinstance(na, bool):
                 # GH#59561
@@ -318,8 +311,9 @@ def _str_contains(
                     FutureWarning,
                     stacklevel=find_stack_level(),
                 )
-            result[isna(result)] = bool(na)
-        return result
+                na = bool(na)
+
+        return ArrowStringArrayMixin._str_contains(self, pat, case, flags, na, regex)
 
     def _str_replace(
         self,

pandas/core/arrays/timedeltas.py

@@ -876,6 +876,12 @@ def to_pytimedelta(self) -> npt.NDArray[np.object_]:
     microseconds_docstring = textwrap.dedent(
         """Number of microseconds (>= 0 and less than 1 second) for each element.
 
+    See Also
+    --------
+    pd.Timedelta.microseconds : Number of microseconds (>= 0 and less than 1 second).
+    pd.Timedelta.to_pytimedelta.microseconds : Number of microseconds (>= 0 and less
+        than 1 second) of a datetime.timedelta.
+
     Examples
     --------
     For Series:
@@ -955,6 +961,12 @@ def components(self) -> DataFrame:
         -------
         DataFrame
 
+        See Also
+        --------
+        TimedeltaIndex.total_seconds : Return total duration expressed in seconds.
+        Timedelta.components : Return a components namedtuple-like of a single
+            timedelta.
+
         Examples
         --------
         >>> tdelta_idx = pd.to_timedelta(["1 day 3 min 2 us 42 ns"])

pandas/core/dtypes/dtypes.py

@@ -611,6 +611,13 @@ def update_dtype(self, dtype: str_type | CategoricalDtype) -> CategoricalDtype:
             dtype = cast(CategoricalDtype, dtype)
 
         # update categories/ordered unless they've been explicitly passed as None
+        if (
+            isinstance(dtype, CategoricalDtype)
+            and dtype.categories is not None
+            and dtype.ordered is not None
+        ):
+            # Avoid re-validation in CategoricalDtype constructor
+            return dtype
         new_categories = (
             dtype.categories if dtype.categories is not None else self.categories
         )

pandas/tests/arrays/boolean/test_logical.py

@@ -60,19 +60,20 @@ def test_eq_mismatched_type(self, other):
         expected = pd.array([True, True])
         tm.assert_extension_array_equal(result, expected)
 
-    def test_logical_length_mismatch_raises(self, all_logical_operators):
+    @pytest.mark.parametrize("other", [[True, False], [True, False, True, False]])
+    def test_logical_length_mismatch_raises(self, other, all_logical_operators):
         op_name = all_logical_operators
         a = pd.array([True, False, None], dtype="boolean")
         msg = "Lengths must match"
 
         with pytest.raises(ValueError, match=msg):
-            getattr(a, op_name)([True, False])
+            getattr(a, op_name)(other)
 
         with pytest.raises(ValueError, match=msg):
-            getattr(a, op_name)(np.array([True, False]))
+            getattr(a, op_name)(np.array(other))
 
         with pytest.raises(ValueError, match=msg):
-            getattr(a, op_name)(pd.array([True, False], dtype="boolean"))
+            getattr(a, op_name)(pd.array(other, dtype="boolean"))
 
     def test_logical_nan_raises(self, all_logical_operators):
         op_name = all_logical_operators