Merge remote-tracking branch 'upstream/main' into better-msg-delta-series_timestamp

Author: KevsterAmp

.gitattributes

@@ -85,4 +85,5 @@ pandas/tests/io/parser/data export-ignore
 
 # Include cibw script in sdist since it's needed for building wheels
 scripts/cibw_before_build.sh -export-ignore
-scripts/cibw_before_test.sh -export-ignore
+scripts/cibw_before_build_windows.sh -export-ignore
+scripts/cibw_before_test_windows.sh -export-ignore

.github/workflows/unit-tests.yml

@@ -387,8 +387,8 @@ jobs:
       - name: Build Environment
         run: |
           python --version
-          python -m pip install --upgrade pip setuptools wheel meson[ninja]==1.2.1 meson-python==0.13.1
-          python -m pip install --pre --extra-index-url https://pypi.anaconda.org/scientific-python-nightly-wheels/simple numpy cython
+          python -m pip install --upgrade pip setuptools wheel numpy meson[ninja]==1.2.1 meson-python==0.13.1
+          python -m pip install --pre --extra-index-url https://pypi.anaconda.org/scientific-python-nightly-wheels/simple cython
           python -m pip install versioneer[toml]
           python -m pip install python-dateutil pytz tzdata hypothesis>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0 pytest-cov
           python -m pip install -ve . --no-build-isolation --no-index --no-deps -Csetup-args="--werror"

.github/workflows/wheels.yml

@@ -111,10 +111,6 @@ jobs:
         - buildplat: [ubuntu-22.04, pyodide_wasm32]
           python: ["cp312", "3.12"]
           cibw_build_frontend: 'build'
-        # TODO: Build free-threaded wheels for Windows
-        exclude:
-        - buildplat: [windows-2022, win_amd64]
-          python: ["cp313t", "3.13"]
 
     env:
       IS_PUSH: ${{ github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v') }}
@@ -181,20 +177,6 @@ jobs:
         shell: bash -el {0}
         run: for whl in $(ls wheelhouse); do wheel unpack wheelhouse/$whl -d /tmp; done
 
-      # Testing on windowsservercore instead of GHA runner to fail on missing DLLs
-      - name: Test Windows Wheels
-        if: ${{ matrix.buildplat[1] == 'win_amd64' }}
-        shell: pwsh
-        run: |
-          $TST_CMD = @"
-          python -m pip install hypothesis>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0;
-          python -m pip install `$(Get-Item pandas\wheelhouse\*.whl);
-          python -c `'import pandas as pd; pd.test(extra_args=[`\"--no-strict-data-files`\", `\"-m not clipboard and not single_cpu and not slow and not network and not db`\"])`';
-          "@
-          # add rc to the end of the image name if the Python version is unreleased
-          docker pull python:${{ matrix.python[1] == '3.13' && '3.13-rc' || format('{0}-windowsservercore', matrix.python[1]) }}
-          docker run --env PANDAS_CI='1' -v ${PWD}:C:\pandas python:${{ matrix.python[1] == '3.13' && '3.13-rc' || format('{0}-windowsservercore', matrix.python[1]) }} powershell -Command $TST_CMD
-
       - uses: actions/upload-artifact@v4
         with:
           name: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}

MANIFEST.in

@@ -65,3 +65,5 @@ graft pandas/_libs/include
 
 # Include cibw script in sdist since it's needed for building wheels
 include scripts/cibw_before_build.sh
+include scripts/cibw_before_build_windows.sh
+include scripts/cibw_before_test_windows.sh

ci/code_checks.sh

@@ -84,7 +84,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timestamp.resolution PR02" \
         -i "pandas.Timestamp.tzinfo GL08" \
         -i "pandas.api.types.is_re_compilable PR07,SA01" \
-        -i "pandas.api.types.pandas_dtype PR07,RT03,SA01" \
         -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \
         -i "pandas.arrays.IntegerArray SA01" \
         -i "pandas.arrays.IntervalArray.length SA01" \

doc/source/whatsnew/v2.3.0.rst

@@ -106,10 +106,10 @@ Conversion
 Strings
 ^^^^^^^
 - Bug in :meth:`Series.rank` for :class:`StringDtype` with ``storage="pyarrow"`` incorrectly returning integer results in case of ``method="average"`` and raising an error if it would truncate results (:issue:`59768`)
+- Bug in :meth:`Series.replace` with :class:`StringDtype` when replacing with a non-string value was not upcasting to ``object`` dtype (:issue:`60282`)
 - Bug in :meth:`Series.str.replace` when ``n < 0`` for :class:`StringDtype` with ``storage="pyarrow"`` (:issue:`59628`)
 - Bug in ``ser.str.slice`` with negative ``step`` with :class:`ArrowDtype` and :class:`StringDtype` with ``storage="pyarrow"`` giving incorrect results (:issue:`59710`)
 - Bug in the ``center`` method on :class:`Series` and :class:`Index` object ``str`` accessors with pyarrow-backed dtype not matching the python behavior in corner cases with an odd number of fill characters (:issue:`54792`)
--
 
 Interval
 ^^^^^^^^
@@ -118,7 +118,7 @@ Interval
 
 Indexing
 ^^^^^^^^
--
+- Fixed bug in :meth:`Index.get_indexer` round-tripping through string dtype when ``infer_string`` is enabled (:issue:`55834`)
 -
 
 Missing

doc/source/whatsnew/v3.0.0.rst

@@ -702,6 +702,8 @@ I/O
 - Bug in :meth:`read_stata` raising ``KeyError`` when input file is stored in big-endian format and contains strL data. (:issue:`58638`)
 - Bug in :meth:`read_stata` where extreme value integers were incorrectly interpreted as missing for format versions 111 and prior (:issue:`58130`)
 - Bug in :meth:`read_stata` where the missing code for double was not recognised for format versions 105 and prior (:issue:`58149`)
+- Bug in :meth:`set_option` where setting the pandas option ``display.html.use_mathjax`` to ``False`` has no effect (:issue:`59884`)
+- Bug in :meth:`to_excel` where :class:`MultiIndex` columns would be merged to a single row when ``merge_cells=False`` is passed (:issue:`60274`)
 
 Period
 ^^^^^^

pandas/core/array_algos/replace.py

@@ -151,4 +151,6 @@ def re_replacer(s):
     if mask is None:
         values[:] = f(values)
     else:
+        if values.ndim != mask.ndim:
+            mask = np.broadcast_to(mask, values.shape)
         values[mask] = f(values[mask])

pandas/core/arrays/arrow/array.py

@@ -1644,7 +1644,11 @@ def _accumulate(
             else:
                 data_to_accum = data_to_accum.cast(pa.int64())
 
-        result = pyarrow_meth(data_to_accum, skip_nulls=skipna, **kwargs)
+        try:
+            result = pyarrow_meth(data_to_accum, skip_nulls=skipna, **kwargs)
+        except pa.ArrowNotImplementedError as err:
+            msg = f"operation '{name}' not supported for dtype '{self.dtype}'"
+            raise TypeError(msg) from err
 
         if convert_to_int:
             result = result.cast(pa_dtype)

pandas/core/arrays/string_.py

@@ -730,20 +730,9 @@ def _values_for_factorize(self) -> tuple[np.ndarray, libmissing.NAType | float]:
 
         return arr, self.dtype.na_value
 
-    def __setitem__(self, key, value) -> None:
-        value = extract_array(value, extract_numpy=True)
-        if isinstance(value, type(self)):
-            # extract_array doesn't extract NumpyExtensionArray subclasses
-            value = value._ndarray
-
-        key = check_array_indexer(self, key)
-        scalar_key = lib.is_scalar(key)
-        scalar_value = lib.is_scalar(value)
-        if scalar_key and not scalar_value:
-            raise ValueError("setting an array element with a sequence.")
-
-        # validate new items
-        if scalar_value:
+    def _maybe_convert_setitem_value(self, value):
+        """Maybe convert value to be pyarrow compatible."""
+        if lib.is_scalar(value):
             if isna(value):
                 value = self.dtype.na_value
             elif not isinstance(value, str):
@@ -753,8 +742,11 @@ def __setitem__(self, key, value) -> None:
                     "instead."
                 )
         else:
+            value = extract_array(value, extract_numpy=True)
             if not is_array_like(value):
                 value = np.asarray(value, dtype=object)
+            elif isinstance(value.dtype, type(self.dtype)):
+                return value
             else:
                 # cast categories and friends to arrays to see if values are
                 # compatible, compatibility with arrow backed strings
@@ -764,11 +756,26 @@ def __setitem__(self, key, value) -> None:
                     "Invalid value for dtype 'str'. Value should be a "
                     "string or missing value (or array of those)."
                 )
+        return value
 
-            mask = isna(value)
-            if mask.any():
-                value = value.copy()
-                value[isna(value)] = self.dtype.na_value
+    def __setitem__(self, key, value) -> None:
+        value = self._maybe_convert_setitem_value(value)
+
+        key = check_array_indexer(self, key)
+        scalar_key = lib.is_scalar(key)
+        scalar_value = lib.is_scalar(value)
+        if scalar_key and not scalar_value:
+            raise ValueError("setting an array element with a sequence.")
+
+        if not scalar_value:
+            if value.dtype == self.dtype:
+                value = value._ndarray
+            else:
+                value = np.asarray(value)
+                mask = isna(value)
+                if mask.any():
+                    value = value.copy()
+                    value[isna(value)] = self.dtype.na_value
 
         super().__setitem__(key, value)