Merge branch 'main' into bug-json-normalize

Author: parthava-adabala

.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/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

@@ -1035,6 +1035,7 @@ 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`)
@@ -1208,6 +1209,7 @@ 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/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/indexes/range.py

@@ -27,7 +27,6 @@
 from pandas.compat.numpy import function as nv
 from pandas.util._decorators import (
     cache_readonly,
-    doc,
     set_module,
 )
 
@@ -473,8 +472,51 @@ def inferred_type(self) -> str:
     # --------------------------------------------------------------------
     # Indexing Methods
 
-    @doc(Index.get_loc)
     def get_loc(self, key) -> int:
+        """
+        Get integer location for requested label.
+
+        Parameters
+        ----------
+        key : int or float
+            Label to locate. Integer-like floats (e.g. 3.0) are accepted and
+            treated as the corresponding integer. Non-integer floats and other
+            non-integer labels are not valid and will raise KeyError or
+            InvalidIndexError.
+
+        Returns
+        -------
+        int
+            Integer location of the label within the RangeIndex.
+
+        Raises
+        ------
+        KeyError
+            If the label is not present in the RangeIndex or the label is a
+            non-integer value.
+        InvalidIndexError
+            If the label is of an invalid type for the RangeIndex.
+
+        See Also
+        --------
+        RangeIndex.get_slice_bound : Calculate slice bound that corresponds to
+            given label.
+        RangeIndex.get_indexer : Computes indexer and mask for new index given
+            the current index.
+        RangeIndex.get_non_unique : Returns indexer and masks for new index given
+            the current index.
+        RangeIndex.get_indexer_for : Returns an indexer even when non-unique.
+
+        Examples
+        --------
+        >>> idx = pd.RangeIndex(5)
+        >>> idx.get_loc(3)
+        3
+
+        >>> idx = pd.RangeIndex(2, 10, 2)  # values [2, 4, 6, 8]
+        >>> idx.get_loc(6)
+        2
+        """
         if is_integer(key) or (is_float(key) and key.is_integer()):
             new_key = int(key)
             try:
@@ -528,12 +570,39 @@ def _should_fallback_to_positional(self) -> bool:
     def tolist(self) -> list[int]:
         return list(self._range)
 
-    @doc(Index.__iter__)
     def __iter__(self) -> Iterator[int]:
+        """
+        Return an iterator of the values.
+
+        Returns
+        -------
+        iterator
+            An iterator yielding ints from the RangeIndex.
+
+        Examples
+        --------
+        >>> idx = pd.RangeIndex(3)
+        >>> for x in idx:
+        ...     print(x)
+        0
+        1
+        2
+        """
         yield from self._range
 
-    @doc(Index._shallow_copy)
     def _shallow_copy(self, values, name: Hashable = no_default):
+        """
+        Create a new RangeIndex with the same class as the caller, don't copy the
+        data, use the same object attributes with passed in attributes taking
+        precedence.
+
+        *this is an internal non-public method*
+
+        Parameters
+        ----------
+        values : the values to create the new RangeIndex, optional
+        name : Label, defaults to self.name
+        """
         name = self._name if name is no_default else name
 
         if values.dtype.kind == "f":
@@ -560,8 +629,42 @@ def _wrap_reindex_result(self, target, indexer, preserve_names: bool):
             target = self._shallow_copy(target._values, name=target.name)
         return super()._wrap_reindex_result(target, indexer, preserve_names)
 
-    @doc(Index.copy)
     def copy(self, name: Hashable | None = None, deep: bool = False) -> Self:
+        """
+        Make a copy of this object.
+
+        Name is set on the new object.
+
+        Parameters
+        ----------
+        name : Label, optional
+            Set name for new object.
+        deep : bool, default False
+            If True attempts to make a deep copy of the RangeIndex.
+                Else makes a shallow copy.
+
+        Returns
+        -------
+        RangeIndex
+            RangeIndex refer to new object which is a copy of this object.
+
+        See Also
+        --------
+        RangeIndex.delete: Make new RangeIndex with passed location(-s) deleted.
+        RangeIndex.drop: Make new RangeIndex with passed list of labels deleted.
+
+        Notes
+        -----
+        In most cases, there should be no functional difference from using
+        ``deep``, but if ``deep`` is passed it will attempt to deepcopy.
+
+        Examples
+        --------
+        >>> idx = pd.RangeIndex(3)
+        >>> new_idx = idx.copy()
+        >>> idx is new_idx
+        False
+        """
         name = self._validate_names(name=name, deep=deep)[0]
         new_index = self._rename(name=name)
         return new_index

pandas/core/resample.py

@@ -850,7 +850,6 @@ def interpolate(
         inplace: bool = False,
         limit_direction: Literal["forward", "backward", "both"] = "forward",
         limit_area=None,
-        downcast=lib.no_default,
         **kwargs,
     ):
         """
@@ -907,11 +906,6 @@ def interpolate(
               (interpolate).
             * 'outside': Only fill NaNs outside valid values (extrapolate).
 
-        downcast : optional, 'infer' or None, defaults to None
-            Downcast dtypes if possible.
-
-            .. deprecated:: 2.1.0
-
         **kwargs : optional
             Keyword arguments to pass on to the interpolating function.
 
@@ -993,7 +987,6 @@ def interpolate(
         Note that the series correctly decreases between two anchors
         ``07:00:00`` and ``07:00:02``.
         """
-        assert downcast is lib.no_default  # just checking coverage
         result = self._upsample("asfreq")
 
         # If the original data has timestamps which are not aligned with the
@@ -1030,7 +1023,6 @@ def interpolate(
             inplace=inplace,
             limit_direction=limit_direction,
             limit_area=limit_area,
-            downcast=downcast,
             **kwargs,
         )
 

pandas/core/series.py

@@ -6738,7 +6738,7 @@ def _flex_method(self, other, op, *, level=None, fill_value=None, axis: Axis = 0
 
         if isinstance(other, Series):
             return self._binop(other, op, level=level, fill_value=fill_value)
-        elif isinstance(other, (np.ndarray, list, tuple)):
+        elif isinstance(other, (np.ndarray, list, tuple, ExtensionArray)):
             if len(other) != len(self):
                 raise ValueError("Lengths must be equal")
             other = self._constructor(other, self.index, copy=False)