Merge remote-tracking branch 'upstream/main' into anno2

simonjayhawkins · simonjayhawkins · commit a33515ebf1ea · 2025-09-12T11:36:04.000+01:00
diff --git a/.github/workflows/unit-tests.yml b/.github/workflows/unit-tests.yml
@@ -313,7 +313,7 @@ jobs:
     #    To freeze this file, uncomment out the ``if: false`` condition, and migrate the jobs
     #    to the corresponding posix/windows-macos/sdist etc. workflows.
     # Feel free to modify this comment as necessary.
-    if: false
+    # if: false
     defaults:
       run:
         shell: bash -eou pipefail {0}
@@ -345,7 +345,7 @@ jobs:
       - name: Set up Python Dev Version
         uses: actions/setup-python@v6
         with:
-          python-version: '3.13-dev'
+          python-version: '3.14-dev'
 
       - name: Build Environment
         run: |
@@ -358,6 +358,8 @@ jobs:
 
       - name: Run Tests
         uses: ./.github/actions/run-tests
+        # TEMP allow this to fail until we fixed all test failures (related to chained assignment warnings)
+        continue-on-error: true
 
   # NOTE: this job must be kept in sync with the Pyodide build job in wheels.yml
   emscripten:
diff --git a/README.md b/README.md
@@ -11,7 +11,7 @@
 | --- | --- |
 | Testing | [![CI - Test](https://github.com/pandas-dev/pandas/actions/workflows/unit-tests.yml/badge.svg)](https://github.com/pandas-dev/pandas/actions/workflows/unit-tests.yml) [![Coverage](https://codecov.io/github/pandas-dev/pandas/coverage.svg?branch=main)](https://codecov.io/gh/pandas-dev/pandas) |
 | Package | [![PyPI Latest Release](https://img.shields.io/pypi/v/pandas.svg)](https://pypi.org/project/pandas/) [![PyPI Downloads](https://img.shields.io/pypi/dm/pandas.svg?label=PyPI%20downloads)](https://pypi.org/project/pandas/) [![Conda Latest Release](https://anaconda.org/conda-forge/pandas/badges/version.svg)](https://anaconda.org/conda-forge/pandas) [![Conda Downloads](https://img.shields.io/conda/dn/conda-forge/pandas.svg?label=Conda%20downloads)](https://anaconda.org/conda-forge/pandas) |
-| Meta | [![Powered by NumFOCUS](https://img.shields.io/badge/powered%20by-NumFOCUS-orange.svg?style=flat&colorA=E1523D&colorB=007D8A)](https://numfocus.org) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.3509134.svg)](https://doi.org/10.5281/zenodo.3509134) [![License - BSD 3-Clause](https://img.shields.io/pypi/l/pandas.svg)](https://github.com/pandas-dev/pandas/blob/main/LICENSE) [![Slack](https://img.shields.io/badge/join_Slack-information-brightgreen.svg?logo=slack)](https://pandas.pydata.org/docs/dev/development/community.html?highlight=slack#community-slack) |
+| Meta | [![Powered by NumFOCUS](https://img.shields.io/badge/powered%20by-NumFOCUS-orange.svg?style=flat&colorA=E1523D&colorB=007D8A)](https://numfocus.org) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.3509134.svg)](https://doi.org/10.5281/zenodo.3509134) [![License - BSD 3-Clause](https://img.shields.io/pypi/l/pandas.svg)](https://github.com/pandas-dev/pandas/blob/main/LICENSE) [![Slack](https://img.shields.io/badge/join_Slack-information-brightgreen.svg?logo=slack)](https://pandas.pydata.org/docs/dev/development/community.html?highlight=slack#community-slack) [![LFX Health Score](https://insights.linuxfoundation.org/api/badge/health-score?project=pandas-dev-pandas)](https://insights.linuxfoundation.org/project/pandas-dev-pandas) |
 
 
 ## What is it?
diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst
@@ -649,6 +649,7 @@ Other Deprecations
 - Deprecated ``pd.core.internals.api.maybe_infer_ndim`` (:issue:`40226`)
 - Deprecated allowing constructing or casting to :class:`Categorical` with non-NA values that are not present in specified ``dtype.categories`` (:issue:`40996`)
 - Deprecated allowing non-keyword arguments in :meth:`DataFrame.all`, :meth:`DataFrame.min`, :meth:`DataFrame.max`, :meth:`DataFrame.sum`, :meth:`DataFrame.prod`, :meth:`DataFrame.mean`, :meth:`DataFrame.median`, :meth:`DataFrame.sem`, :meth:`DataFrame.var`, :meth:`DataFrame.std`, :meth:`DataFrame.skew`, :meth:`DataFrame.kurt`, :meth:`Series.all`,  :meth:`Series.min`, :meth:`Series.max`, :meth:`Series.sum`, :meth:`Series.prod`, :meth:`Series.mean`, :meth:`Series.median`, :meth:`Series.sem`, :meth:`Series.var`, :meth:`Series.std`, :meth:`Series.skew`, and :meth:`Series.kurt`. (:issue:`57087`)
+- Deprecated allowing non-keyword arguments in :meth:`DataFrame.groupby` and :meth:`Series.groupby` except ``by`` and ``level``. (:issue:`62102`)
 - Deprecated allowing non-keyword arguments in :meth:`Series.to_markdown` except ``buf``. (:issue:`57280`)
 - Deprecated allowing non-keyword arguments in :meth:`Series.to_string` except ``buf``. (:issue:`57280`)
 - Deprecated behavior of :meth:`.DataFrameGroupBy.groups` and :meth:`.SeriesGroupBy.groups`, in a future version ``groups`` by one element list will return tuple instead of scalar. (:issue:`58858`)
diff --git a/pandas/_libs/sparse.pyi b/pandas/_libs/sparse.pyi
@@ -1,9 +1,11 @@
-from collections.abc import Sequence
 from typing import Self
 
 import numpy as np
 
-from pandas._typing import npt
+from pandas._typing import (
+    TakeIndexer,
+    npt,
+)
 
 class SparseIndex:
     length: int
@@ -26,7 +28,7 @@ class SparseIndex:
 class IntIndex(SparseIndex):
     indices: npt.NDArray[np.int32]
     def __init__(
-        self, length: int, indices: Sequence[int], check_integrity: bool = ...
+        self, length: int, indices: TakeIndexer, check_integrity: bool = ...
     ) -> None: ...
 
 class BlockIndex(SparseIndex):
diff --git a/pandas/compat/__init__.py b/pandas/compat/__init__.py
@@ -19,6 +19,7 @@
     IS64,
     ISMUSL,
     PY312,
+    PY314,
     PYPY,
     WASM,
 )
@@ -154,6 +155,7 @@ def is_ci_environment() -> bool:
     "IS64",
     "ISMUSL",
     "PY312",
+    "PY314",
     "PYARROW_MIN_VERSION",
     "PYPY",
     "WASM",
diff --git a/pandas/compat/_constants.py b/pandas/compat/_constants.py
@@ -14,6 +14,7 @@
 IS64 = sys.maxsize > 2**32
 
 PY312 = sys.version_info >= (3, 12)
+PY314 = sys.version_info >= (3, 14)
 PYPY = platform.python_implementation() == "PyPy"
 WASM = (sys.platform == "emscripten") or (platform.machine() in ["wasm32", "wasm64"])
 ISMUSL = "musl" in (sysconfig.get_config_var("HOST_GNU_TYPE") or "")
@@ -23,6 +24,7 @@
     "IS64",
     "ISMUSL",
     "PY312",
+    "PY314",
     "PYPY",
     "WASM",
 ]
diff --git a/pandas/core/arrays/sparse/accessor.py b/pandas/core/arrays/sparse/accessor.py
@@ -440,10 +440,10 @@ def to_coo(self) -> spmatrix:
             rows.append(row)
             data.append(sp_arr.sp_values.astype(dtype, copy=False))
 
-        cols = np.concatenate(cols)
-        rows = np.concatenate(rows)
-        data = np.concatenate(data)
-        return coo_matrix((data, (rows, cols)), shape=self._parent.shape)
+        cols_arr = np.concatenate(cols)
+        rows_arr = np.concatenate(rows)
+        data_arr = np.concatenate(data)
+        return coo_matrix((data_arr, (rows_arr, cols_arr)), shape=self._parent.shape)
 
     @property
     def density(self) -> float:
diff --git a/pandas/core/arrays/sparse/array.py b/pandas/core/arrays/sparse/array.py
@@ -92,13 +92,26 @@
         Sequence,
     )
     from enum import Enum
+    from typing import (
+        Protocol,
+        type_check_only,
+    )
 
     class ellipsis(Enum):
         Ellipsis = "..."
 
     Ellipsis = ellipsis.Ellipsis
 
-    from scipy.sparse import spmatrix
+    from scipy.sparse import (
+        csc_array,
+        csc_matrix,
+    )
+
+    @type_check_only
+    class _SparseMatrixLike(Protocol):
+        @property
+        def shape(self, /) -> tuple[int, int]: ...
+        def tocsc(self, /) -> csc_array | csc_matrix: ...
 
     from pandas._typing import NumpySorter
 
@@ -120,6 +133,7 @@ class ellipsis(Enum):
 
     from pandas import Series
 
+
 else:
     ellipsis = type(Ellipsis)
 
@@ -511,7 +525,7 @@ def _simple_new(
         return new
 
     @classmethod
-    def from_spmatrix(cls, data: spmatrix) -> Self:
+    def from_spmatrix(cls, data: _SparseMatrixLike) -> Self:
         """
         Create a SparseArray from a scipy.sparse matrix.
 
@@ -543,10 +557,10 @@ def from_spmatrix(cls, data: spmatrix) -> Self:
 
         # our sparse index classes require that the positions be strictly
         # increasing. So we need to sort loc, and arr accordingly.
-        data = data.tocsc()
-        data.sort_indices()
-        arr = data.data
-        idx = data.indices
+        data_csc = data.tocsc()
+        data_csc.sort_indices()
+        arr = data_csc.data
+        idx = data_csc.indices
 
         zero = np.array(0, dtype=arr.dtype).item()
         dtype = SparseDtype(arr.dtype, zero)
@@ -1217,10 +1231,7 @@ def _concat_same_type(cls, to_concat: Sequence[Self]) -> Self:
 
             data = np.concatenate(values)
             indices_arr = np.concatenate(indices)
-            # error: Argument 2 to "IntIndex" has incompatible type
-            # "ndarray[Any, dtype[signedinteger[_32Bit]]]";
-            # expected "Sequence[int]"
-            sp_index = IntIndex(length, indices_arr)  # type: ignore[arg-type]
+            sp_index = IntIndex(length, indices_arr)
 
         else:
             # when concatenating block indices, we don't claim that you'll
diff --git a/pandas/core/frame.py b/pandas/core/frame.py
@@ -9374,6 +9374,9 @@ def update(
         )
     )
     @Appender(_shared_docs["groupby"] % _shared_doc_kwargs)
+    @deprecate_nonkeyword_arguments(
+        Pandas4Warning, allowed_args=["self", "by", "level"], name="groupby"
+    )
     def groupby(
         self,
         by=None,
diff --git a/pandas/core/series.py b/pandas/core/series.py
@@ -1961,6 +1961,9 @@ def _set_name(
         )
     )
     @Appender(_shared_docs["groupby"] % _shared_doc_kwargs)
+    @deprecate_nonkeyword_arguments(
+        Pandas4Warning, allowed_args=["self", "by", "level"], name="groupby"
+    )
     def groupby(
         self,
         by=None,
diff --git a/pandas/tests/arrays/sparse/test_libsparse.py b/pandas/tests/arrays/sparse/test_libsparse.py
@@ -209,12 +209,10 @@ def test_intersect_empty(self):
     @pytest.mark.parametrize(
         "case",
         [
-            # Argument 2 to "IntIndex" has incompatible type "ndarray[Any,
-            # dtype[signedinteger[_32Bit]]]"; expected "Sequence[int]"
-            IntIndex(5, np.array([1, 2], dtype=np.int32)),  # type: ignore[arg-type]
-            IntIndex(5, np.array([0, 2, 4], dtype=np.int32)),  # type: ignore[arg-type]
-            IntIndex(0, np.array([], dtype=np.int32)),  # type: ignore[arg-type]
-            IntIndex(5, np.array([], dtype=np.int32)),  # type: ignore[arg-type]
+            IntIndex(5, np.array([1, 2], dtype=np.int32)),
+            IntIndex(5, np.array([0, 2, 4], dtype=np.int32)),
+            IntIndex(0, np.array([], dtype=np.int32)),
+            IntIndex(5, np.array([], dtype=np.int32)),
         ],
     )
     def test_intersect_identical(self, case):
diff --git a/pandas/tests/frame/test_query_eval.py b/pandas/tests/frame/test_query_eval.py
@@ -168,7 +168,7 @@ def test_query_duplicate_column_name(self, engine, parser):
             }
         ).rename(columns={"B": "A"})
 
-        res = df.query('C == 1', engine=engine, parser=parser)
+        res = df.query("C == 1", engine=engine, parser=parser)
 
         expect = DataFrame(
             [[1, 1, 1]],
@@ -1411,7 +1411,7 @@ def test_expr_with_column_name_with_backtick_and_hash(self):
     def test_expr_with_column_name_with_backtick(self):
         # GH 59285
         df = DataFrame({"a`b": (1, 2, 3), "ab": (4, 5, 6)})
-        result = df.query("`a``b` < 2")  # noqa
+        result = df.query("`a``b` < 2")
         # Note: Formatting checks may wrongly consider the above ``inline code``.
         expected = df[df["a`b"] < 2]
         tm.assert_frame_equal(result, expected)
diff --git a/pandas/tests/indexes/test_indexing.py b/pandas/tests/indexes/test_indexing.py
@@ -18,6 +18,7 @@
 import numpy as np
 import pytest
 
+from pandas.compat import PY314
 from pandas.errors import InvalidIndexError
 
 from pandas.core.dtypes.common import (
@@ -160,13 +161,19 @@ def test_contains_requires_hashable_raises(self, index):
         with pytest.raises(TypeError, match=msg):
             [] in index
 
+        if PY314:
+            container_or_iterable = "a container or iterable"
+        else:
+            container_or_iterable = "iterable"
+
         msg = "|".join(
             [
                 r"unhashable type: 'dict'",
                 r"must be real number, not dict",
                 r"an integer is required",
                 r"\{\}",
-                r"pandas\._libs\.interval\.IntervalTree' is not iterable",
+                r"pandas\._libs\.interval\.IntervalTree' is not "
+                f"{container_or_iterable}",
             ]
         )
         with pytest.raises(TypeError, match=msg):
diff --git a/pandas/tests/io/parser/test_quoting.py b/pandas/tests/io/parser/test_quoting.py
@@ -8,6 +8,7 @@
 
 import pytest
 
+from pandas.compat import PY314
 from pandas.errors import ParserError
 
 from pandas import DataFrame
@@ -20,15 +21,24 @@
 skip_pyarrow = pytest.mark.usefixtures("pyarrow_skip")
 
 
+if PY314:
+    # TODO: write a regex that works with all new possitibilities here
+    MSG1 = ""
+    MSG2 = r"[\s\S]*"
+else:
+    MSG1 = "a(n)? 1-character string"
+    MSG2 = "string( or None)?"
+
+
 @pytest.mark.parametrize(
     "kwargs,msg",
     [
-        ({"quotechar": "foo"}, '"quotechar" must be a(n)? 1-character string'),
+        ({"quotechar": "foo"}, f'"quotechar" must be {MSG1}'),
         (
             {"quotechar": None, "quoting": csv.QUOTE_MINIMAL},
             "quotechar must be set if quoting enabled",
         ),
-        ({"quotechar": 2}, '"quotechar" must be string( or None)?, not int'),
+        ({"quotechar": 2}, f'"quotechar" must be {MSG2}, not int'),
     ],
 )
 @skip_pyarrow  # ParserError: CSV parse error: Empty CSV file or block
@@ -87,8 +97,12 @@ def test_null_quote_char(all_parsers, quoting, quote_char):
 
     if quoting != csv.QUOTE_NONE:
         # Sanity checking.
+        if not PY314:
+            msg = "1-character string"
+        else:
+            msg = "unicode character or None"
         msg = (
-            '"quotechar" must be a 1-character string'
+            f'"quotechar" must be a {msg}'
             if all_parsers.engine == "python" and quote_char == ""
             else "quotechar must be set if quoting enabled"
         )
diff --git a/pandas/tests/reshape/merge/test_merge.py b/pandas/tests/reshape/merge/test_merge.py
@@ -8,6 +8,8 @@
 import numpy as np
 import pytest
 
+from pandas.compat import PY314
+
 from pandas.core.dtypes.common import (
     is_object_dtype,
     is_string_dtype,
@@ -2420,10 +2422,18 @@ def test_merge_suffix_raises(suffixes):
         merge(a, b, left_index=True, right_index=True, suffixes=suffixes)
 
 
+TWO_GOT_THREE = "2, got 3" if PY314 else "2"
+
+
 @pytest.mark.parametrize(
     "col1, col2, suffixes, msg",
     [
-        ("a", "a", ("a", "b", "c"), r"too many values to unpack \(expected 2\)"),
+        (
+            "a",
+            "a",
+            ("a", "b", "c"),
+            (rf"too many values to unpack \(expected {TWO_GOT_THREE}\)"),
+        ),
         ("a", "a", tuple("a"), r"not enough values to unpack \(expected 2, got 1\)"),
     ],
 )
diff --git a/pandas/tests/scalar/period/test_period.py b/pandas/tests/scalar/period/test_period.py
@@ -16,6 +16,7 @@
 from pandas._libs.tslibs.np_datetime import OutOfBoundsDatetime
 from pandas._libs.tslibs.parsing import DateParseError
 from pandas._libs.tslibs.period import INVALID_FREQ_ERR_MSG
+from pandas.compat import PY314
 from pandas.errors import Pandas4Warning
 
 from pandas import (
@@ -347,7 +348,10 @@ def test_invalid_arguments(self):
         msg = '^Given date string "-2000" not likely a datetime$'
         with pytest.raises(ValueError, match=msg):
             Period("-2000", "Y")
-        msg = "day is out of range for month"
+        if PY314:
+            msg = "day 0 must be in range 1..31 for month 1 in year 1: 0"
+        else:
+            msg = "day is out of range for month"
         with pytest.raises(DateParseError, match=msg):
             Period("0", "Y")
         msg = "Unknown datetime string format, unable to parse"
diff --git a/pandas/tests/scalar/timestamp/test_constructors.py b/pandas/tests/scalar/timestamp/test_constructors.py
@@ -17,6 +17,7 @@
 import pytest
 
 from pandas._libs.tslibs.dtypes import NpyDatetimeUnit
+from pandas.compat import PY314
 from pandas.errors import (
     OutOfBoundsDatetime,
     Pandas4Warning,
@@ -221,7 +222,10 @@ def test_constructor_positional(self):
         with pytest.raises(ValueError, match=msg):
             Timestamp(2000, 13, 1)
 
-        msg = "day is out of range for month"
+        if PY314:
+            msg = "must be in range 1..31 for month 1 in year 2000"
+        else:
+            msg = "day is out of range for month"
         with pytest.raises(ValueError, match=msg):
             Timestamp(2000, 1, 0)
         with pytest.raises(ValueError, match=msg):
@@ -245,7 +249,10 @@ def test_constructor_keyword(self):
         with pytest.raises(ValueError, match=msg):
             Timestamp(year=2000, month=13, day=1)
 
-        msg = "day is out of range for month"
+        if PY314:
+            msg = "must be in range 1..31 for month 1 in year 2000"
+        else:
+            msg = "day is out of range for month"
         with pytest.raises(ValueError, match=msg):
             Timestamp(year=2000, month=1, day=0)
         with pytest.raises(ValueError, match=msg):
diff --git a/pandas/tests/tools/test_to_datetime.py b/pandas/tests/tools/test_to_datetime.py

Original file line number	Diff line number	Diff line change
`@@ -9374,6 +9374,9 @@ def update(`
`9374`	`9374`	`)`
`9375`	`9375`	`)`
`9376`	`9376`	`@Appender(_shared_docs["groupby"] % _shared_doc_kwargs)`
	`9377`	`+ @deprecate_nonkeyword_arguments(`
	`9378`	`+ Pandas4Warning, allowed_args=["self", "by", "level"], name="groupby"`
	`9379`	`+ )`
`9377`	`9380`	`def groupby(`
`9378`	`9381`	`self,`
`9379`	`9382`	`by=None,`
Original file line number	Diff line number	Diff line change
`@@ -1961,6 +1961,9 @@ def _set_name(`
`1961`	`1961`	`)`
`1962`	`1962`	`)`
`1963`	`1963`	`@Appender(_shared_docs["groupby"] % _shared_doc_kwargs)`
	`1964`	`+ @deprecate_nonkeyword_arguments(`
	`1965`	`+ Pandas4Warning, allowed_args=["self", "by", "level"], name="groupby"`
	`1966`	`+ )`
`1964`	`1967`	`def groupby(`
`1965`	`1968`	`self,`
`1966`	`1969`	`by=None,`