Merge branch 'main' into enh-list-arith

Author: jbrockmendel

.github/workflows/docbuild-and-upload.yml

@@ -93,7 +93,7 @@ jobs:
       run: mv doc/build/html web/build/docs
 
     - name: Save website as an artifact
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v5
       with:
         name: website
         path: web/build

.github/workflows/wheels.yml

@@ -64,7 +64,7 @@ jobs:
           python -m pip install build
           python -m build --sdist
 
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v5
         with:
           name: sdist
           path: ./dist/*
@@ -138,7 +138,7 @@ jobs:
       # removes unnecessary files from the release
       - name: Download sdist (not macOS)
         #if: ${{ matrix.buildplat[1] != 'macosx_*' }}
-        uses: actions/download-artifact@v5
+        uses: actions/download-artifact@v6
         with:
           name: sdist
           path: ./dist
@@ -196,7 +196,7 @@ jobs:
         shell: bash -el {0}
         run: for whl in $(ls wheelhouse); do wheel unpack wheelhouse/$whl -d /tmp; done
 
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v5
         with:
           name: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
           path: ./wheelhouse/*.whl
@@ -238,11 +238,11 @@ jobs:
 
     steps:
       - name: Download all artefacts
-        uses: actions/download-artifact@v5
+        uses: actions/download-artifact@v6
         with:
           path: dist          # everything lands in ./dist/**
 
-      # TODO: This step can be probably be achieved by actions/download-artifact@v5
+      # TODO: This step can be probably be achieved by actions/download-artifact@v6
       # by specifying merge-multiple: true, and a glob pattern
       - name: Collect files
         run: |

doc/source/reference/aliases.rst

@@ -65,7 +65,7 @@ Alias                                Meaning
 :py:type:`NaPosition`                Argument type for ``na_position`` in :meth:`sort_index` and :meth:`sort_values`
 :py:type:`NsmallestNlargestKeep`     Argument type for ``keep`` in :meth:`nlargest` and :meth:`nsmallest`
 :py:type:`OpenFileErrors`            Argument type for ``errors`` in :meth:`to_hdf` and :meth:`to_csv`
-:py:type:`Ordered`                   Return type for :py:attr:`ordered`` in :class:`CategoricalDtype` and :class:`Categorical`
+:py:type:`Ordered`                   Return type for :py:attr:`ordered` in :class:`CategoricalDtype` and :class:`Categorical`
 :py:type:`ParquetCompressionOptions` Argument type for ``compression`` in :meth:`DataFrame.to_parquet`
 :py:type:`QuantileInterpolation`     Argument type for ``interpolation`` in :meth:`quantile`
 :py:type:`ReadBuffer`                Additional argument type corresponding to buffers for various file reading methods
@@ -89,7 +89,7 @@ Alias                                Meaning
 :py:type:`ToTimestampHow`            Argument type for ``how`` in :meth:`to_timestamp` and ``convention`` in :meth:`resample`
 :py:type:`UpdateJoin`                Argument type for ``join`` in :meth:`DataFrame.update`
 :py:type:`UsecolsArgType`            Argument type for ``usecols`` in :meth:`pandas.read_clipboard`, :meth:`pandas.read_csv` and :meth:`pandas.read_excel`
-:py:type:`WindowingRankType`         Argument type for ``method`` in :meth:`rank`` in rolling and expanding window operations
+:py:type:`WindowingRankType`         Argument type for ``method`` in :meth:`rank` in rolling and expanding window operations
 :py:type:`WriteBuffer`               Additional argument type corresponding to buffers for various file output methods
 :py:type:`WriteExcelBuffer`          Additional argument type corresponding to buffers for :meth:`to_excel`
 :py:type:`XMLParsers`                Argument type for ``parser`` in :meth:`DataFrame.to_xml` and :meth:`pandas.read_xml`

doc/source/user_guide/io.rst

@@ -2366,52 +2366,7 @@ Read a URL with no options:
 
    The data from the above URL changes every Monday so the resulting data above may be slightly different.
 
-Read a URL while passing headers alongside the HTTP request:
-
-.. code-block:: ipython
-
-   In [322]: url = 'https://www.sump.org/notes/request/' # HTTP request reflector
-
-   In [323]: pd.read_html(url)
-   Out[323]:
-   [                   0                    1
-    0     Remote Socket:  51.15.105.256:51760
-    1  Protocol Version:             HTTP/1.1
-    2    Request Method:                  GET
-    3       Request URI:      /notes/request/
-    4     Request Query:                  NaN,
-    0   Accept-Encoding:             identity
-    1              Host:         www.sump.org
-    2        User-Agent:    Python-urllib/3.8
-    3        Connection:                close]
-
-   In [324]: headers = {
-      .....:    'User-Agent':'Mozilla Firefox v14.0',
-      .....:    'Accept':'application/json',
-      .....:    'Connection':'keep-alive',
-      .....:    'Auth':'Bearer 2*/f3+fe68df*4'
-      .....: }
-
-   In [325]: pd.read_html(url, storage_options=headers)
-   Out[325]:
-   [                   0                    1
-    0     Remote Socket:  51.15.105.256:51760
-    1  Protocol Version:             HTTP/1.1
-    2    Request Method:                  GET
-    3       Request URI:      /notes/request/
-    4     Request Query:                  NaN,
-    0        User-Agent: Mozilla Firefox v14.0
-    1    AcceptEncoding:   gzip,  deflate,  br
-    2            Accept:      application/json
-    3        Connection:             keep-alive
-    4              Auth:  Bearer 2*/f3+fe68df*4]
-
-.. note::
-
-   We see above that the headers we passed are reflected in the HTTP request.
-
-Read in the content of the file from the above URL and pass it to ``read_html``
-as a string:
+Read in HTML content from a file using ``read_html``:
 
 .. ipython:: python
 

doc/source/whatsnew/v3.0.0.rst

@@ -981,6 +981,7 @@ Datetimelike
 - Bug in :meth:`DatetimeIndex.is_year_start` and :meth:`DatetimeIndex.is_quarter_start` does not raise on Custom business days frequencies bigger then "1C" (:issue:`58664`)
 - Bug in :meth:`DatetimeIndex.is_year_start` and :meth:`DatetimeIndex.is_quarter_start` returning ``False`` on double-digit frequencies (:issue:`58523`)
 - Bug in :meth:`DatetimeIndex.union` and :meth:`DatetimeIndex.intersection` when ``unit`` was non-nanosecond (:issue:`59036`)
+- Bug in :meth:`DatetimeIndex.where` and :meth:`TimedeltaIndex.where` failing to set ``freq=None`` in some cases (:issue:`24555`)
 - Bug in :meth:`Index.union` with a ``pyarrow`` timestamp dtype incorrectly returning ``object`` dtype (:issue:`58421`)
 - Bug in :meth:`Series.dt.microsecond` producing incorrect results for pyarrow backed :class:`Series`. (:issue:`59154`)
 - Bug in :meth:`Timestamp.normalize` and :meth:`DatetimeArray.normalize` returning incorrect results instead of raising on integer overflow for very small (distant past) values (:issue:`60583`)
@@ -997,7 +998,6 @@ Datetimelike
 - Bug in constructing arrays with a timezone-aware :class:`ArrowDtype` from timezone-naive datetime objects incorrectly treating those as UTC times instead of wall times like :class:`DatetimeTZDtype` (:issue:`61775`)
 - Bug in setting scalar values with mismatched resolution into arrays with non-nanosecond ``datetime64``, ``timedelta64`` or :class:`DatetimeTZDtype` incorrectly truncating those scalars (:issue:`56410`)
 
-
 Timedelta
 ^^^^^^^^^
 - Accuracy improvement in :meth:`Timedelta.to_pytimedelta` to round microseconds consistently for large nanosecond based Timedelta (:issue:`57841`)
@@ -1036,6 +1036,7 @@ Conversion
 
 Strings
 ^^^^^^^
+- Bug in :meth:`Series.str.replace` raising an error on valid group references (``\1``, ``\2``, etc.) on series converted to PyArrow backend dtype (:issue:`62653`)
 - Bug in :meth:`Series.str.zfill` raising ``AttributeError`` for :class:`ArrowDtype` (:issue:`61485`)
 - Bug in :meth:`Series.value_counts` would not respect ``sort=False`` for series having ``string`` dtype (:issue:`55224`)
 - Bug in multiplication with a :class:`StringDtype` incorrectly allowing multiplying by bools; explicitly cast to integers instead (:issue:`62595`)
@@ -1152,6 +1153,7 @@ Groupby/resample/rolling
 - Bug in :meth:`.DataFrameGroupBy.groups` and :meth:`.SeriesGroupby.groups` that would not respect groupby argument ``dropna`` (:issue:`55919`)
 - Bug in :meth:`.DataFrameGroupBy.median` where nat values gave an incorrect result. (:issue:`57926`)
 - Bug in :meth:`.DataFrameGroupBy.quantile` when ``interpolation="nearest"`` is inconsistent with :meth:`DataFrame.quantile` (:issue:`47942`)
+- Bug in :meth:`.DataFrameGroupBy` reductions where non-Boolean values were allowed for the ``numeric_only`` argument; passing a non-Boolean value will now raise (:issue:`62778`)
 - Bug in :meth:`.Resampler.interpolate` on a :class:`DataFrame` with non-uniform sampling and/or indices not aligning with the resulting resampled index would result in wrong interpolation (:issue:`21351`)
 - Bug in :meth:`.Series.rolling` when used with a :class:`.BaseIndexer` subclass and computing min/max (:issue:`46726`)
 - Bug in :meth:`DataFrame.ewm` and :meth:`Series.ewm` when passed ``times`` and aggregation functions other than mean (:issue:`51695`)
@@ -1208,6 +1210,7 @@ ExtensionArray
 - Bug in comparison between object with :class:`ArrowDtype` and incompatible-dtyped (e.g. string vs bool) incorrectly raising instead of returning all-``False`` (for ``==``) or all-``True`` (for ``!=``) (:issue:`59505`)
 - Bug in constructing pandas data structures when passing into ``dtype`` a string of the type followed by ``[pyarrow]`` while PyArrow is not installed would raise ``NameError`` rather than ``ImportError`` (:issue:`57928`)
 - Bug in various :class:`DataFrame` reductions for pyarrow temporal dtypes returning incorrect dtype when result was null (:issue:`59234`)
+- Fixed flex arithmetic with :class:`ExtensionArray` operands raising when ``fill_value`` was passed. (:issue:`62467`)
 
 Styler
 ^^^^^^

pandas/conftest.py

@@ -1447,6 +1447,9 @@ def any_string_dtype(request):
         return pd.StringDtype(storage, na_value)
 
 
+any_string_dtype2 = any_string_dtype
+
+
 @pytest.fixture(params=tm.DATETIME64_DTYPES)
 def datetime64_dtype(request):
     """

pandas/core/arrays/_arrow_string_mixins.py

@@ -173,15 +173,12 @@ def _str_replace(
             or callable(repl)
             or not case
             or flags
-            or (
-                isinstance(repl, str)
-                and (r"\g<" in repl or re.search(r"\\\d", repl) is not None)
-            )
+            or (isinstance(repl, str) and r"\g<" in repl)
         ):
             raise NotImplementedError(
                 "replace is not supported with a re.Pattern, callable repl, "
                 "case=False, flags!=0, or when the replacement string contains "
-                "named group references (\\g<...>, \\d+)"
+                "named group references (\\g<...>)"
             )
 
         func = pc.replace_substring_regex if regex else pc.replace_substring

pandas/core/arrays/datetimelike.py

@@ -393,7 +393,9 @@ def __getitem__(self, key: PositionalIndexer2D) -> Self | DTScalarOrNaT:
         else:
             # At this point we know the result is an array.
             result = cast(Self, result)
-        result._freq = self._get_getitem_freq(key)
+        # error: Incompatible types in assignment (expression has type
+        # "BaseOffset | None", variable has type "None")
+        result._freq = self._get_getitem_freq(key)  # type: ignore[assignment]
         return result
 
     def _get_getitem_freq(self, key) -> BaseOffset | None:
@@ -527,6 +529,10 @@ def view(self, dtype: Dtype | None = None) -> ArrayLike:
         #  are present in this file.
         return super().view(dtype)
 
+    def _putmask(self, mask: npt.NDArray[np.bool_], value) -> None:
+        super()._putmask(mask, value)
+        self._freq = None  # GH#24555
+
     # ------------------------------------------------------------------
     # Validation Methods
     # TODO: try to de-duplicate these, ensure identical behavior
@@ -2042,7 +2048,7 @@ def _maybe_pin_freq(self, freq, validate_kwds: dict) -> None:
             if self._freq is None:
                 # Set _freq directly to bypass duplicative _validate_frequency
                 # check.
-                self._freq = to_offset(self.inferred_freq)
+                self._freq = to_offset(self.inferred_freq)  # type: ignore[assignment]
         elif freq is lib.no_default:
             # user did not specify anything, keep inferred freq if the original
             #  data had one, otherwise do nothing
@@ -2442,7 +2448,7 @@ def take(
 
         if isinstance(maybe_slice, slice):
             freq = self._get_getitem_freq(maybe_slice)
-            result._freq = freq
+            result._freq = freq  # type: ignore[assignment]
 
         return result
 

pandas/core/arrays/string_arrow.py

@@ -425,8 +425,7 @@ def _str_replace(
             or flags
             or (  # substitution contains a named group pattern
                 # https://docs.python.org/3/library/re.html
-                isinstance(repl, str)
-                and (r"\g<" in repl or re.search(r"\\\d", repl) is not None)
+                isinstance(repl, str) and r"\g<" in repl
             )
         ):
             return super()._str_replace(pat, repl, n, case, flags, regex)

pandas/core/frame.py

@@ -11554,6 +11554,15 @@ def _dict_round(df: DataFrame, decimals) -> Iterator[Series]:
         def _series_round(ser: Series, decimals: int) -> Series:
             if is_integer_dtype(ser.dtype) or is_float_dtype(ser.dtype):
                 return ser.round(decimals)
+            elif isinstance(ser._values, (DatetimeArray, TimedeltaArray, PeriodArray)):
+                # GH#57781
+                # TODO: also the ArrowDtype analogues?
+                warnings.warn(
+                    "obj.round has no effect with datetime, timedelta, "
+                    "or period dtypes. Use obj.dt.round(...) instead.",
+                    UserWarning,
+                    stacklevel=find_stack_level(),
+                )
             return ser
 
         nv.validate_round(args, kwargs)