Merge branch 'main' into BUG-#61583,to_stata

Author: eicchen

README.md

@@ -5,7 +5,7 @@
 
 -----------------
 
-# pandas: powerful Python data analysis toolkit
+# pandas: A Powerful Python Data Analysis Toolkit
 
 | | |
 | --- | --- |

ci/deps/actions-310-minimum_versions.yaml

@@ -18,7 +18,7 @@ dependencies:
   - pytest-xdist>=3.4.0
   - pytest-localserver>=0.8.1
   - pytest-qt>=4.4.0
-  - boto3
+  - boto3=1.37.3
 
   # required dependencies
   - python-dateutil=2.8.2

ci/deps/actions-310.yaml

@@ -16,7 +16,7 @@ dependencies:
   - pytest-xdist>=3.4.0
   - pytest-localserver>=0.8.1
   - pytest-qt>=4.4.0
-  - boto3
+  - boto3=1.37.3
 
   # required dependencies
   - python-dateutil

ci/deps/actions-311-downstream_compat.yaml

@@ -17,7 +17,7 @@ dependencies:
   - pytest-xdist>=3.4.0
   - pytest-localserver>=0.8.1
   - pytest-qt>=4.4.0
-  - boto3
+  - boto3=1.37.3
 
   # required dependencies
   - python-dateutil

ci/deps/actions-311.yaml

@@ -16,7 +16,7 @@ dependencies:
   - pytest-xdist>=3.4.0
   - pytest-localserver>=0.8.1
   - pytest-qt>=4.4.0
-  - boto3
+  - boto3=1.37.3
 
   # required dependencies
   - python-dateutil

ci/deps/actions-312.yaml

@@ -16,7 +16,7 @@ dependencies:
   - pytest-xdist>=3.4.0
   - pytest-localserver>=0.8.1
   - pytest-qt>=4.4.0
-  - boto3
+  - boto3=1.37.3
 
   # required dependencies
   - python-dateutil

ci/deps/actions-313.yaml

@@ -16,7 +16,7 @@ dependencies:
   - pytest-xdist>=3.4.0
   - pytest-localserver>=0.8.1
   - pytest-qt>=4.4.0
-  - boto3
+  - boto3=1.37.3
 
   # required dependencies
   - python-dateutil

doc/source/development/community.rst

@@ -77,7 +77,7 @@ Any community member can open issues to:
 - Ask questions, e.g. "I noticed the behavior of a certain function
   changed between versions. Is this expected?".
 
-    Ideally, your questions should be related to how pandas works rather
+  - Ideally, your questions should be related to how pandas works rather
     than how you use pandas. `StackOverflow <https://stackoverflow.com/>`_ is
     better suited for answering usage questions, and we ask that all usage
     questions are first asked on StackOverflow. Thank you for respecting our

doc/source/development/contributing.rst

@@ -234,14 +234,14 @@ and merged into project to appear the in the next release. To submit a pull requ
 #. Write a descriptive title that includes prefixes. pandas uses a convention for title
    prefixes. Here are some common ones along with general guidelines for when to use them:
 
-    * ENH: Enhancement, new functionality
-    * BUG: Bug fix
-    * DOC: Additions/updates to documentation
-    * TST: Additions/updates to tests
-    * BLD: Updates to the build process/scripts
-    * PERF: Performance improvement
-    * TYP: Type annotations
-    * CLN: Code cleanup
+   * ENH: Enhancement, new functionality
+   * BUG: Bug fix
+   * DOC: Additions/updates to documentation
+   * TST: Additions/updates to tests
+   * BLD: Updates to the build process/scripts
+   * PERF: Performance improvement
+   * TYP: Type annotations
+   * CLN: Code cleanup
 
 #. Write a description of your changes in the ``Preview Discussion`` tab
 #. Click ``Send Pull Request``.

doc/source/development/contributing_codebase.rst

@@ -444,11 +444,11 @@ be located.
                result = ser.loc[[3, 4]]
                tm.assert_series_equal(result, expected)
 
-    In cases like this, the test location should be based on the *underlying*
-    method being tested.  Or in the case of a test for a bugfix, the location
-    of the actual bug.  So in this example, we know that ``Series.__getitem__``
-    calls ``Series.loc.__getitem__``, so this is *really* a test for
-    ``loc.__getitem__``.  So this test belongs in ``tests.indexing.test_loc``.
+      In cases like this, the test location should be based on the *underlying*
+      method being tested.  Or in the case of a test for a bugfix, the location
+      of the actual bug.  So in this example, we know that ``Series.__getitem__``
+      calls ``Series.loc.__getitem__``, so this is *really* a test for
+      ``loc.__getitem__``.  So this test belongs in ``tests.indexing.test_loc``.
 
 6. Is your test for a DataFrame or Series method?
 

doc/source/development/contributing_gitpod.rst

@@ -158,8 +158,8 @@ Option 1: using Liveserve
    file and click on **Open with Live Serve**. Alternatively, you can open the
    file in the editor and click on the **Go live** button on the status bar.
 
-    .. image:: ./gitpod-imgs/vscode-statusbar.png
-        :alt: Gitpod workspace VSCode start live serve screenshot
+   .. image:: ./gitpod-imgs/vscode-statusbar.png
+      :alt: Gitpod workspace VSCode start live serve screenshot
 
 #. A simple browser will open to the right-hand side of the editor. We recommend
    closing it and click on the **Open in browser** button in the pop-up.
@@ -182,13 +182,13 @@ uses the rst extension with docutils.
    :kbd:`Ctrl-Shift-P` in Linux and Windows. Start typing "restructured"
    and choose either "Open preview" or "Open preview to the Side".
 
-    .. image:: ./gitpod-imgs/vscode-rst.png
-        :alt: Gitpod workspace VSCode open rst screenshot
+   .. image:: ./gitpod-imgs/vscode-rst.png
+      :alt: Gitpod workspace VSCode open rst screenshot
 
 #. As you work on the document, you will see a live rendering of it on the editor.
 
-    .. image:: ./gitpod-imgs/rst-rendering.png
-        :alt: Gitpod workspace VSCode rst rendering screenshot
+   .. image:: ./gitpod-imgs/rst-rendering.png
+      :alt: Gitpod workspace VSCode rst rendering screenshot
 
 If you want to see the final output with the ``html`` theme you will need to
 rebuild the docs with ``make html`` and use Live Serve as described in option 1.

doc/source/development/debugging_extensions.rst

@@ -10,9 +10,9 @@ pandas uses Cython and C/C++ `extension modules <https://docs.python.org/3/exten
 
 For Python developers with limited or no C/C++ experience this can seem a daunting task. Core developer Will Ayd has written a 3 part blog series to help guide you from the standard Python debugger into these other tools:
 
-  1. `Fundamental Python Debugging Part 1 - Python <https://willayd.com/fundamental-python-debugging-part-1-python.html>`_
-  2. `Fundamental Python Debugging Part 2 - Python Extensions <https://willayd.com/fundamental-python-debugging-part-2-python-extensions.html>`_
-  3. `Fundamental Python Debugging Part 3 - Cython Extensions <https://willayd.com/fundamental-python-debugging-part-3-cython-extensions.html>`_
+1. `Fundamental Python Debugging Part 1 - Python <https://willayd.com/fundamental-python-debugging-part-1-python.html>`_
+2. `Fundamental Python Debugging Part 2 - Python Extensions <https://willayd.com/fundamental-python-debugging-part-2-python-extensions.html>`_
+3. `Fundamental Python Debugging Part 3 - Cython Extensions <https://willayd.com/fundamental-python-debugging-part-3-cython-extensions.html>`_
 
 Debugging locally
 -----------------

doc/source/development/developer.rst

@@ -116,19 +116,19 @@ The ``metadata`` field is ``None`` except for:
   omitted it is assumed to be nanoseconds.
 * ``categorical``: ``{'num_categories': K, 'ordered': is_ordered, 'type': $TYPE}``
 
-    * Here ``'type'`` is optional, and can be a nested pandas type specification
-      here (but not categorical)
+  * Here ``'type'`` is optional, and can be a nested pandas type specification
+    here (but not categorical)
 
 * ``unicode``: ``{'encoding': encoding}``
 
-    * The encoding is optional, and if not present is UTF-8
+  * The encoding is optional, and if not present is UTF-8
 
 * ``object``: ``{'encoding': encoding}``. Objects can be serialized and stored
   in ``BYTE_ARRAY`` Parquet columns. The encoding can be one of:
 
-    * ``'pickle'``
-    * ``'bson'``
-    * ``'json'``
+  * ``'pickle'``
+  * ``'bson'``
+  * ``'json'``
 
 * ``timedelta``: ``{'unit': 'ns'}``. The ``'unit'`` is optional, and if omitted
   it is assumed to be nanoseconds. This metadata is optional altogether

doc/source/development/maintaining.rst

@@ -218,11 +218,11 @@ pandas supports point releases (e.g. ``1.4.3``) that aim to:
 
 1. Fix bugs in new features introduced in the first minor version release.
 
-  * e.g. If a new feature was added in ``1.4`` and contains a bug, a fix can be applied in ``1.4.3``
+   * e.g. If a new feature was added in ``1.4`` and contains a bug, a fix can be applied in ``1.4.3``
 
 2. Fix bugs that used to work in a few minor releases prior. There should be agreement between core team members that a backport is appropriate.
 
-  * e.g. If a feature worked in ``1.2`` and stopped working since ``1.3``, a fix can be applied in ``1.4.3``.
+   * e.g. If a feature worked in ``1.2`` and stopped working since ``1.3``, a fix can be applied in ``1.4.3``.
 
 Since pandas minor releases are based on GitHub branches (e.g. point release of ``1.4`` are based off the ``1.4.x`` branch),
 "backporting" means merging a pull request fix to the ``main`` branch and correct minor branch associated with the next point release.
@@ -289,8 +289,8 @@ The required steps for adding a maintainer are:
 1. Contact the contributor and ask their interest to join.
 2. Add the contributor to the appropriate `GitHub Team <https://github.com/orgs/pandas-dev/teams>`_ if accepted the invitation.
 
-  * ``pandas-core`` is for core team members
-  * ``pandas-triage`` is for pandas triage members
+   * ``pandas-core`` is for core team members
+   * ``pandas-triage`` is for pandas triage members
 
 If adding to ``pandas-core``, there are two additional steps:
 
@@ -467,10 +467,10 @@ Post-Release
    patch releases. The exact instructions are (replace the example version numbers by
    the appropriate ones for the version you are releasing):
 
-    - Log in to the server and use the correct user.
-    - ``cd /var/www/html/pandas-docs/``
-    - ``ln -sfn version/2.1 stable`` (for a major or minor release)
-    - ``ln -sfn version/2.0.3 version/2.0`` (for a patch release)
+   - Log in to the server and use the correct user.
+   - ``cd /var/www/html/pandas-docs/``
+   - ``ln -sfn version/2.1 stable`` (for a major or minor release)
+   - ``ln -sfn version/2.0.3 version/2.0`` (for a patch release)
 
 2. If releasing a major or minor release, open a PR in our source code to update
    ``web/pandas/versions.json``, to have the desired versions in the documentation
@@ -487,8 +487,8 @@ Post-Release
 6. Announce the new release in the official channels (use previous announcements
    for reference):
 
-    - The pandas-dev and pydata mailing lists
-    - X, Mastodon, Telegram and LinkedIn
+   - The pandas-dev and pydata mailing lists
+   - X, Mastodon, Telegram and LinkedIn
 
 7. Update this release instructions to fix anything incorrect and to update about any
    change since the last release.

doc/source/whatsnew/v3.0.0.rst

@@ -64,6 +64,9 @@ Other enhancements
 - :meth:`Series.nlargest` uses a 'stable' sort internally and will preserve original ordering.
 - :class:`ArrowDtype` now supports ``pyarrow.JsonType`` (:issue:`60958`)
 - :class:`DataFrameGroupBy` and :class:`SeriesGroupBy` methods ``sum``, ``mean``, ``median``, ``prod``, ``min``, ``max``, ``std``, ``var`` and ``sem`` now accept ``skipna`` parameter (:issue:`15675`)
+- :class:`Easter` has gained a new constructor argument ``method`` which specifies the method used to calculate Easter — for example, Orthodox Easter (:issue:`61665`)
+- :class:`Holiday` constructor argument ``days_of_week`` will raise a ``ValueError`` when type is something other than ``None`` or ``tuple`` (:issue:`61658`)
+- :class:`Holiday` has gained the constructor argument and field ``exclude_dates`` to exclude specific datetimes from a custom holiday calendar (:issue:`54382`)
 - :class:`Rolling` and :class:`Expanding` now support ``nunique`` (:issue:`26958`)
 - :class:`Rolling` and :class:`Expanding` now support aggregations ``first`` and ``last`` (:issue:`33155`)
 - :func:`read_parquet` accepts ``to_pandas_kwargs`` which are forwarded to :meth:`pyarrow.Table.to_pandas` which enables passing additional keywords to customize the conversion to pandas, such as ``maps_as_pydicts`` to read the Parquet map data type as python dictionaries (:issue:`56842`)
@@ -715,6 +718,7 @@ Numeric
 - Bug in :meth:`DataFrame.cov` raises a ``TypeError`` instead of returning potentially incorrect results or other errors (:issue:`53115`)
 - Bug in :meth:`DataFrame.quantile` where the column type was not preserved when ``numeric_only=True`` with a list-like ``q`` produced an empty result (:issue:`59035`)
 - Bug in :meth:`Series.dot` returning ``object`` dtype for :class:`ArrowDtype` and nullable-dtype data (:issue:`61375`)
+- Bug in :meth:`Series.std` and :meth:`Series.var` when using complex-valued data (:issue:`61645`)
 - Bug in ``np.matmul`` with :class:`Index` inputs raising a ``TypeError`` (:issue:`57079`)
 
 Conversion
@@ -885,6 +889,7 @@ Other
 - Bug in :func:`eval` with ``engine="numexpr"`` returning unexpected result for float division. (:issue:`59736`)
 - Bug in :func:`to_numeric` raising ``TypeError`` when ``arg`` is a :class:`Timedelta` or :class:`Timestamp` scalar. (:issue:`59944`)
 - Bug in :func:`unique` on :class:`Index` not always returning :class:`Index` (:issue:`57043`)
+- Bug in :meth:`DataFrame.apply` raising ``RecursionError`` when passing ``func=list[int]``. (:issue:`61565`)
 - Bug in :meth:`DataFrame.apply` where passing ``engine="numba"`` ignored ``args`` passed to the applied function (:issue:`58712`)
 - Bug in :meth:`DataFrame.eval` and :meth:`DataFrame.query` which caused an exception when using NumPy attributes via ``@`` notation, e.g., ``df.eval("@np.floor(a)")``. (:issue:`58041`)
 - Bug in :meth:`DataFrame.eval` and :meth:`DataFrame.query` which did not allow to use ``tan`` function. (:issue:`55091`)

pandas/_libs/lib.pyx

@@ -2,6 +2,7 @@ from collections import abc
 from decimal import Decimal
 from enum import Enum
 from sys import getsizeof
+from types import GenericAlias
 from typing import (
     Literal,
     _GenericAlias,
@@ -1298,7 +1299,7 @@ cdef bint c_is_list_like(object obj, bint allow_sets) except -1:
         getattr(obj, "__iter__", None) is not None and not isinstance(obj, type)
         # we do not count strings/unicode/bytes as list-like
         # exclude Generic types that have __iter__
-        and not isinstance(obj, (str, bytes, _GenericAlias))
+        and not isinstance(obj, (str, bytes, _GenericAlias, GenericAlias))
         # exclude zero-dimensional duck-arrays, effectively scalars
         and not (hasattr(obj, "ndim") and obj.ndim == 0)
         # exclude sets if allow_sets is False

pandas/_libs/tslibs/offsets.pyi

@@ -230,7 +230,13 @@ class FY5253Quarter(FY5253Mixin):
         variation: Literal["nearest", "last"] = ...,
     ) -> None: ...
 
-class Easter(SingleConstructorOffset): ...
+class Easter(SingleConstructorOffset):
+    def __init__(
+        self,
+        n: int = ...,
+        normalize: bool = ...,
+        method: int = ...,
+    ) -> None: ...
 
 class _CustomBusinessMonth(BusinessMixin):
     def __init__(

pandas/_libs/tslibs/offsets.pyx

@@ -4520,6 +4520,12 @@ cdef class Easter(SingleConstructorOffset):
         The number of years represented.
     normalize : bool, default False
         Normalize start/end dates to midnight before generating date range.
+    method : int, default 3
+        The method used to calculate the date of Easter. Valid options are:
+        - 1 (EASTER_JULIAN): Original calculation in Julian calendar
+        - 2 (EASTER_ORTHODOX): Original method, date converted to Gregorian calendar
+        - 3 (EASTER_WESTERN): Revised method, in Gregorian calendar
+        These constants are defined in the `dateutil.easter` module.
 
     See Also
     --------
@@ -4532,15 +4538,32 @@ cdef class Easter(SingleConstructorOffset):
     Timestamp('2022-04-17 00:00:00')
     """
 
+    _attributes = tuple(["n", "normalize", "method"])
+
+    cdef readonly:
+        int method
+
+    from dateutil.easter import EASTER_WESTERN
+
+    def __init__(self, n=1, normalize=False, method=EASTER_WESTERN):
+        BaseOffset.__init__(self, n, normalize)
+
+        self.method = method
+
+        if method < 1 or method > 3:
+            raise ValueError(f"Method must be 1<=method<=3, got {method}")
+
     cpdef __setstate__(self, state):
+        from dateutil.easter import EASTER_WESTERN
         self.n = state.pop("n")
         self.normalize = state.pop("normalize")
+        self.method = state.pop("method", EASTER_WESTERN)
 
     @apply_wraps
     def _apply(self, other: datetime) -> datetime:
         from dateutil.easter import easter
 
-        current_easter = easter(other.year)
+        current_easter = easter(other.year, method=self.method)
         current_easter = datetime(
             current_easter.year, current_easter.month, current_easter.day
         )
@@ -4555,7 +4578,7 @@ cdef class Easter(SingleConstructorOffset):
 
         # NOTE: easter returns a datetime.date so we have to convert to type of
         # other
-        new = easter(other.year + n)
+        new = easter(other.year + n, method=self.method)
         new = datetime(
             new.year,
             new.month,
@@ -4573,7 +4596,7 @@ cdef class Easter(SingleConstructorOffset):
 
         from dateutil.easter import easter
 
-        return date(dt.year, dt.month, dt.day) == easter(dt.year)
+        return date(dt.year, dt.month, dt.day) == easter(dt.year, method=self.method)
 
 
 # ----------------------------------------------------------------------

pandas/core/nanops.py

@@ -1014,7 +1014,11 @@ def nanvar(
     avg = _ensure_numeric(values.sum(axis=axis, dtype=np.float64)) / count
     if axis is not None:
         avg = np.expand_dims(avg, axis)
-    sqr = _ensure_numeric((avg - values) ** 2)
+    if values.dtype.kind == "c":
+        # Need to use absolute value for complex numbers.
+        sqr = _ensure_numeric(abs(avg - values) ** 2)
+    else:
+        sqr = _ensure_numeric((avg - values) ** 2)
     if mask is not None:
         np.putmask(sqr, mask, 0)
     result = sqr.sum(axis=axis, dtype=np.float64) / d

pandas/tests/dtypes/test_inference.py

@@ -250,6 +250,15 @@ class MyDataFrame(DataFrame, Generic[T]): ...
     assert inference.is_list_like(tst)
 
 
+def test_is_list_like_native_container_types():
+    # GH 61565
+    # is_list_like was yielding false positives for native container types
+    assert not inference.is_list_like(list[int])
+    assert not inference.is_list_like(list[str])
+    assert not inference.is_list_like(tuple[int])
+    assert not inference.is_list_like(tuple[str])
+
+
 def test_is_sequence():
     is_seq = inference.is_sequence
     assert is_seq((1, 2))

pandas/tests/extension/base/setitem.py

@@ -440,11 +440,11 @@ def test_delitem_series(self, data):
         tm.assert_series_equal(ser, expected)
 
     def test_setitem_invalid(self, data, invalid_scalar):
-        msg = ""  # messages vary by subclass, so we do not test it
-        with pytest.raises((ValueError, TypeError), match=msg):
+        # messages vary by subclass, so we do not test it
+        with pytest.raises((ValueError, TypeError), match=None):
             data[0] = invalid_scalar
 
-        with pytest.raises((ValueError, TypeError), match=msg):
+        with pytest.raises((ValueError, TypeError), match=None):
             data[:] = invalid_scalar
 
     def test_setitem_2d_values(self, data):