Merge branch 'main' into cln/tests

Author: mroeschke

.github/workflows/wheels.yml

@@ -162,7 +162,7 @@ jobs:
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v3.1.4
+        uses: pypa/cibuildwheel@v3.2.0
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:

doc/source/whatsnew/v0.21.0.rst

@@ -635,22 +635,17 @@ Previous behavior:
 
 New behavior:
 
-.. code-block:: ipython
+.. ipython:: python
 
-   In [1]: pi = pd.period_range('2017-01', periods=12, freq='M')
+   pi = pd.period_range('2017-01', periods=12, freq='M')
 
-   In [2]: s = pd.Series(np.arange(12), index=pi)
+   s = pd.Series(np.arange(12), index=pi)
 
-   In [3]: resampled = s.resample('2Q').mean()
+   resampled = s.resample('2Q').mean()
 
-   In [4]: resampled
-   Out[4]:
-   2017Q1    2.5
-   2017Q3    8.5
-   Freq: 2Q-DEC, dtype: float64
+   resampled
 
-   In [5]: resampled.index
-   Out[5]: PeriodIndex(['2017Q1', '2017Q3'], dtype='period[2Q-DEC]')
+   resampled.index
 
 Upsampling and calling ``.ohlc()`` previously returned a ``Series``, basically identical to calling ``.asfreq()``. OHLC upsampling now returns a DataFrame with columns ``open``, ``high``, ``low`` and ``close`` (:issue:`13083`). This is consistent with downsampling and ``DatetimeIndex`` behavior.
 

doc/source/whatsnew/v2.2.0.rst

@@ -664,7 +664,7 @@ Other Deprecations
 - Deprecated :meth:`DatetimeArray.__init__` and :meth:`TimedeltaArray.__init__`, use :func:`array` instead (:issue:`55623`)
 - Deprecated :meth:`Index.format`, use ``index.astype(str)`` or ``index.map(formatter)`` instead (:issue:`55413`)
 - Deprecated :meth:`Series.ravel`, the underlying array is already 1D, so ravel is not necessary (:issue:`52511`)
-- Deprecated :meth:`Series.resample` and :meth:`DataFrame.resample` with a :class:`PeriodIndex` (and the 'convention' keyword), convert to :class:`DatetimeIndex` (with ``.to_timestamp()``) before resampling instead (:issue:`53481`)
+- Deprecated :meth:`Series.resample` and :meth:`DataFrame.resample` with a :class:`PeriodIndex` (and the 'convention' keyword), convert to :class:`DatetimeIndex` (with ``.to_timestamp()``) before resampling instead (:issue:`53481`). Note: this deprecation was later undone in pandas 2.3.3 (:issue:`57033`)
 - Deprecated :meth:`Series.view`, use :meth:`Series.astype` instead to change the dtype (:issue:`20251`)
 - Deprecated :meth:`offsets.Tick.is_anchored`, use ``False`` instead (:issue:`55388`)
 - Deprecated ``core.internals`` members ``Block``, ``ExtensionBlock``, and ``DatetimeTZBlock``, use public APIs instead (:issue:`55139`)

doc/source/whatsnew/v2.3.3.rst

@@ -47,7 +47,8 @@ Bug fixes
 - Fix regression in ``~Series.str.contains``, ``~Series.str.match`` and ``~Series.str.fullmatch``
   with a compiled regex and custom flags (:issue:`62240`)
 - Fix :meth:`Series.str.match` and :meth:`Series.str.fullmatch` not matching patterns with groups correctly for the Arrow-backed string dtype (:issue:`61072`)
-
+- Fix comparing a :class:`StringDtype` Series with mixed objects raising an error (:issue:`60228`)
+- Fix error being raised when using a numpy ufunc with a Python-backed string array (:issue:`40800`)
 
 Improvements and fixes for Copy-on-Write
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -57,6 +58,14 @@ Bug fixes
 
 - The :meth:`DataFrame.iloc` now works correctly with ``copy_on_write`` option when assigning values after subsetting the columns of a homogeneous DataFrame (:issue:`60309`)
 
+Other changes
+~~~~~~~~~~~~~
+
+- The deprecation of using :meth:`Series.resample` and :meth:`DataFrame.resample`
+  with a :class:`PeriodIndex` (and the 'convention' keyword) has been undone.
+  Resampling with a :class:`PeriodIndex` is supported again, but a subset of
+  methods that return incorrect results will raise an error in pandas 3.0 (:issue:`57033`)
+
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_233.contributors:

pandas/_typing.py

@@ -83,8 +83,7 @@
 
     # numpy compatible types
     NumpyValueArrayLike: TypeAlias = ScalarLike_co | npt.ArrayLike
-    # Name "npt._ArrayLikeInt_co" is not defined  [name-defined]
-    NumpySorter: TypeAlias = npt._ArrayLikeInt_co | None  # type: ignore[name-defined]
+    NumpySorter: TypeAlias = npt._ArrayLikeInt_co | None
 
 
 P = ParamSpec("P")

pandas/core/algorithms.py

@@ -215,14 +215,15 @@ def _reconstruct_data(
         #  that values.dtype == dtype
         cls = dtype.construct_array_type()
 
-        # error: Incompatible types in assignment (expression has type
-        # "ExtensionArray", variable has type "ndarray[Any, Any]")
-        values = cls._from_sequence(values, dtype=dtype)  # type: ignore[assignment]
-
-    else:
-        values = values.astype(dtype, copy=False)
-
-    return values
+        # error: Incompatible return value type
+        # (got "ExtensionArray",
+        # expected "ndarray[tuple[Any, ...], dtype[Any]]")
+        return cls._from_sequence(values, dtype=dtype)  # type: ignore[return-value]
+
+    # error: Incompatible return value type
+    # (got "ndarray[tuple[Any, ...], dtype[Any]]",
+    # expected "ExtensionArray")
+    return values.astype(dtype, copy=False)  # type: ignore[return-value]
 
 
 def _ensure_arraylike(values, func_name: str) -> ArrayLike:

pandas/core/array_algos/quantile.py

@@ -102,7 +102,7 @@ def quantile_with_mask(
             interpolation=interpolation,
         )
 
-        result = np.asarray(result)  # type: ignore[assignment]
+        result = np.asarray(result)
         result = result.T
 
     return result

pandas/core/arrays/_mixins.py

@@ -151,7 +151,9 @@ def view(self, dtype: Dtype | None = None) -> ArrayLike:
 
             td64_values = arr.view(dtype)
             return TimedeltaArray._simple_new(td64_values, dtype=dtype)
-        return arr.view(dtype=dtype)
+        # error: Argument "dtype" to "view" of "ndarray" has incompatible type
+        # "ExtensionDtype | dtype[Any]"; expected "dtype[Any] | _HasDType[dtype[Any]]"
+        return arr.view(dtype=dtype)  # type: ignore[arg-type]
 
     def take(
         self,

pandas/core/arrays/arrow/_arrow_utils.py

@@ -44,7 +44,7 @@ def pyarrow_array_to_numpy_and_mask(
         mask = pyarrow.BooleanArray.from_buffers(
             pyarrow.bool_(), len(arr), [None, bitmask], offset=arr.offset
         )
-        mask = np.asarray(mask)  # type: ignore[assignment]
+        mask = np.asarray(mask)
     else:
         mask = np.ones(len(arr), dtype=bool)
     return data, mask

pandas/core/arrays/arrow/array.py

@@ -657,7 +657,7 @@ def _box_pa_array(
             ):
                 arr_value = np.asarray(value, dtype=object)
                 # similar to isna(value) but exclude NaN, NaT, nat-like, nan-like
-                mask = is_pdna_or_none(arr_value)  # type: ignore[assignment]
+                mask = is_pdna_or_none(arr_value)
 
             try:
                 pa_array = pa.array(value, type=pa_type, mask=mask)
@@ -883,22 +883,27 @@ def _cmp_method(self, other, op) -> ArrowExtensionArray:
         ltype = self._pa_array.type
 
         if isinstance(other, (ExtensionArray, np.ndarray, list)):
-            boxed = self._box_pa(other)
-            rtype = boxed.type
-            if (pa.types.is_timestamp(ltype) and pa.types.is_date(rtype)) or (
-                pa.types.is_timestamp(rtype) and pa.types.is_date(ltype)
-            ):
-                # GH#62157 match non-pyarrow behavior
-                result = ops.invalid_comparison(self, other, op)
-                result = pa.array(result, type=pa.bool_())
+            try:
+                boxed = self._box_pa(other)
+            except pa.lib.ArrowInvalid:
+                # e.g. GH#60228 [1, "b"] we have to operate pointwise
+                res_values = [op(x, y) for x, y in zip(self, other)]
+                result = pa.array(res_values, type=pa.bool_(), from_pandas=True)
             else:
-                try:
-                    result = pc_func(self._pa_array, boxed)
-                except pa.ArrowNotImplementedError:
-                    # TODO: could this be wrong if other is object dtype?
-                    #  in which case we need to operate pointwise?
+                rtype = boxed.type
+                if (pa.types.is_timestamp(ltype) and pa.types.is_date(rtype)) or (
+                    pa.types.is_timestamp(rtype) and pa.types.is_date(ltype)
+                ):
+                    # GH#62157 match non-pyarrow behavior
                     result = ops.invalid_comparison(self, other, op)
                     result = pa.array(result, type=pa.bool_())
+                else:
+                    try:
+                        result = pc_func(self._pa_array, boxed)
+                    except pa.ArrowNotImplementedError:
+                        result = ops.invalid_comparison(self, other, op)
+                        result = pa.array(result, type=pa.bool_())
+
         elif is_scalar(other):
             if (isinstance(other, datetime) and pa.types.is_date(ltype)) or (
                 type(other) is date and pa.types.is_timestamp(ltype)
@@ -2738,7 +2743,7 @@ def _str_get_dummies(self, sep: str = "|", dtype: NpDtype | None = None):
             dummies_dtype = np.bool_
         dummies = np.zeros(n_rows * n_cols, dtype=dummies_dtype)
         dummies[indices] = True
-        dummies = dummies.reshape((n_rows, n_cols))  # type: ignore[assignment]
+        dummies = dummies.reshape((n_rows, n_cols))
         result = self._from_pyarrow_array(pa.array(list(dummies)))
         return result, uniques_sorted.to_pylist()