Merge branch 'main' into fix-interval_range-dtype

Author: Nithurshen

.github/PULL_REQUEST_TEMPLATE.md

@@ -3,3 +3,4 @@
 - [ ] All [code checks passed](https://pandas.pydata.org/pandas-docs/dev/development/contributing_codebase.html#pre-commit).
 - [ ] Added [type annotations](https://pandas.pydata.org/pandas-docs/dev/development/contributing_codebase.html#type-hints) to new arguments/methods/functions.
 - [ ] Added an entry in the latest `doc/source/whatsnew/vX.X.X.rst` file if fixing a bug or adding a new feature.
+- [ ] If I used AI to develop this pull request, I prompted it to follow `AGENTS.md`.

AGENTS.md

@@ -0,0 +1,48 @@
+# pandas Agent Instructions
+
+## Project Overview
+`pandas` is an open source, BSD-licensed library providing high-performance, easy-to-use data structures and data analysis tools for the Python programming language.
+
+## Purpose
+- Assist contributors by suggesting code changes, tests, and documentation edits for the pandas repository while preserving stability and compatibility.
+
+## Persona & Tone
+- Concise, neutral, code-focused. Prioritize correctness, readability, and tests.
+
+## Project Guidelines
+- Be sure to follow all guidelines for contributing to the codebase specified at https://pandas.pydata.org/docs/development/contributing_codebase.html
+- These guidelines are also available in the following local files, which should be loaded into context and adhered to
+    - doc/source/development/contributing_codebase.rst
+    - doc/source/development/contributing_docstring.rst
+    - doc/source/development/contributing_documentation.rst
+    - doc/source/development/contributing.rst
+
+## Decision heuristics
+- Favor small, backward-compatible changes with tests.
+- If a change would be breaking, propose it behind a deprecation path and document the rationale.
+- Prefer readability over micro-optimizations unless benchmarks are requested.
+- Add tests for behavioral changes; update docs only after code change is final.
+
+## Type hints guidance (summary)
+- Prefer PEP 484 style and types in pandas._typing when appropriate.
+- Avoid unnecessary use of typing.cast; prefer refactors that convey types to type-checkers.
+- Use builtin generics (list, dict) when possible.
+
+## Docstring guidance (summary)
+- Follow NumPy / numpydoc conventions used across the repo: short summary, extended summary, Parameters, Returns/Yields, See Also, Notes, Examples.
+- Ensure examples are deterministic, import numpy/pandas as documented, and pass doctest rules used by docs validation.
+- Preserve formatting rules: triple double-quotes, no blank line before/after docstring, parameter formatting ("name : type, default ..."), types and examples conventions.
+
+## Pull Requests (summary)
+- Pull request titles should be descriptive and include one of the following prefixes:
+    - 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
+- Pull request descriptions should follow the template, and **succinctly** describe the change being made. Usually a few sentences is sufficient.
+- Pull requests which are resolving an existing Github Issue should include a link to the issue in the PR Description.
+- Do not add summaries or additional comments to individual commit messages. The single PR description is sufficient.

doc/source/whatsnew/v3.0.0.rst

@@ -1032,13 +1032,13 @@ Bug fixes
 Categorical
 ^^^^^^^^^^^
 - Bug in :class:`Categorical` where constructing from a pandas :class:`Series` or :class:`Index` with ``dtype='object'`` did not preserve the categories' dtype as ``object``; now the ``categories.dtype`` is preserved as ``object`` for these cases, while numpy arrays and Python sequences with ``dtype='object'`` continue to infer the most specific dtype (for example, ``str`` if all elements are strings) (:issue:`61778`)
+- Bug in :class:`pandas.Categorical` displaying string categories without quotes when using "string" dtype (:issue:`63045`)
 - Bug in :func:`Series.apply` where ``nan`` was ignored for :class:`CategoricalDtype` (:issue:`59938`)
 - Bug in :func:`bdate_range` raising ``ValueError`` with frequency ``freq="cbh"`` (:issue:`62849`)
 - Bug in :func:`testing.assert_index_equal` raising ``TypeError`` instead of ``AssertionError`` for incomparable ``CategoricalIndex`` when ``check_categorical=True`` and ``exact=False`` (:issue:`61935`)
 - Bug in :meth:`Categorical.astype` where ``copy=False`` would still trigger a copy of the codes (:issue:`62000`)
 - Bug in :meth:`DataFrame.pivot` and :meth:`DataFrame.set_index` raising an ``ArrowNotImplementedError`` for columns with pyarrow dictionary dtype (:issue:`53051`)
 - Bug in :meth:`Series.convert_dtypes` with ``dtype_backend="pyarrow"`` where empty :class:`CategoricalDtype` :class:`Series` raised an error or got converted to ``null[pyarrow]`` (:issue:`59934`)
--
 
 Datetimelike
 ^^^^^^^^^^^^

pandas/_libs/internals.pyi

@@ -94,3 +94,7 @@ class BlockValuesRefs:
     def add_reference(self, blk: Block) -> None: ...
     def add_index_reference(self, index: Index) -> None: ...
     def has_reference(self) -> bool: ...
+
+class SetitemMixin:
+    def __setitem__(self, key, value) -> None: ...
+    def __delitem__(self, key) -> None: ...

pandas/_libs/internals.pyx

@@ -1,6 +1,9 @@
 from collections import defaultdict
+import sys
+import warnings
 
 cimport cython
+from cpython cimport PY_VERSION_HEX
 from cpython.object cimport PyObject
 from cpython.pyport cimport PY_SSIZE_T_MAX
 from cpython.slice cimport PySlice_GetIndicesEx
@@ -20,6 +23,9 @@ from numpy cimport (
 cnp.import_array()
 
 from pandas._libs.algos import ensure_int64
+from pandas.compat import CHAINED_WARNING_DISABLED
+from pandas.errors import ChainedAssignmentError
+from pandas.errors.cow import _chained_assignment_msg
 
 from pandas._libs.util cimport (
     is_array,
@@ -996,3 +1002,43 @@ cdef class BlockValuesRefs:
                 return self._has_reference_maybe_locked()
         ELSE:
             return self._has_reference_maybe_locked()
+
+
+cdef extern from "Python.h":
+    """
+    #if PY_VERSION_HEX < 0x030E0000
+    int __Pyx_PyUnstable_Object_IsUniqueReferencedTemporary(PyObject *ref);
+    #else
+    #define __Pyx_PyUnstable_Object_IsUniqueReferencedTemporary \
+        PyUnstable_Object_IsUniqueReferencedTemporary
+    #endif
+    """
+    int PyUnstable_Object_IsUniqueReferencedTemporary\
+        "__Pyx_PyUnstable_Object_IsUniqueReferencedTemporary"(object o) except -1
+
+
+# Python version compatibility for PyUnstable_Object_IsUniqueReferencedTemporary
+cdef inline bint _is_unique_referenced_temporary(object obj) except -1:
+    if PY_VERSION_HEX >= 0x030E0000:
+        # Python 3.14+ has PyUnstable_Object_IsUniqueReferencedTemporary
+        return PyUnstable_Object_IsUniqueReferencedTemporary(obj)
+    else:
+        # Fallback for older Python versions using sys.getrefcount
+        return sys.getrefcount(obj) <= 1
+
+
+cdef class SetitemMixin:
+    # class used in DataFrame and Series for checking for chained assignment
+
+    def __setitem__(self, key, value) -> None:
+        cdef bint is_unique = 0
+        if not CHAINED_WARNING_DISABLED:
+            is_unique = _is_unique_referenced_temporary(self)
+            if is_unique:
+                warnings.warn(
+                    _chained_assignment_msg, ChainedAssignmentError, stacklevel=1
+                )
+        self._setitem(key, value)
+
+    def __delitem__(self, key) -> None:
+        self._delitem(key)

pandas/_libs/lib.pyx

@@ -322,7 +322,7 @@ def item_from_zerodim(val: object) -> object:
     >>> item_from_zerodim(np.array([1]))
     array([1])
     """
-    if cnp.PyArray_IsZeroDim(val):
+    if cnp.PyArray_IsZeroDim(val) and cnp.PyArray_CheckExact(val):
         return cnp.PyArray_ToScalar(cnp.PyArray_DATA(val), val)
     return val
 
@@ -2716,18 +2716,16 @@ def maybe_convert_objects(ndarray[object] objects,
             if convert_non_numeric:
                 if getattr(val, "tzinfo", None) is not None:
                     seen.datetimetz_ = True
-                    break
                 else:
                     seen.datetime_ = True
                     try:
                         convert_to_tsobject(val, None, None, 0, 0)
                     except OutOfBoundsDatetime:
                         # e.g. test_out_of_s_bounds_datetime64
                         seen.object_ = True
-                        break
             else:
                 seen.object_ = True
-                break
+            break
         elif is_period_object(val):
             if convert_non_numeric:
                 seen.period_ = True

pandas/_libs/tslibs/timestamps.pyx

@@ -3492,7 +3492,7 @@ default 'raise'
             year -= 1
             month += 12
         return (day +
-                np.fix((153 * month - 457) / 5) +
+                np.trunc((153 * month - 457) / 5) +
                 365 * year +
                 np.floor(year / 4) -
                 np.floor(year / 100) +

pandas/_testing/contexts.py

@@ -13,8 +13,8 @@
 import uuid
 
 from pandas.compat import (
-    PYPY,
-    WARNING_CHECK_DISABLED,
+    CHAINED_WARNING_DISABLED,
+    CHAINED_WARNING_DISABLED_INPLACE_METHOD,
 )
 from pandas.errors import ChainedAssignmentError
 
@@ -163,10 +163,18 @@ def with_csv_dialect(name: str, **kwargs) -> Generator[None]:
         csv.unregister_dialect(name)
 
 
-def raises_chained_assignment_error(extra_warnings=(), extra_match=()):
+def raises_chained_assignment_error(
+    extra_warnings=(), extra_match=(), inplace_method=False
+):
     from pandas._testing import assert_produces_warning
 
-    if PYPY or WARNING_CHECK_DISABLED:
+    WARNING_DISABLED = (
+        CHAINED_WARNING_DISABLED_INPLACE_METHOD
+        if inplace_method
+        else CHAINED_WARNING_DISABLED
+    )
+
+    if WARNING_DISABLED:
         if not extra_warnings:
             from contextlib import nullcontext
 

pandas/compat/__init__.py

@@ -16,12 +16,13 @@
 from typing import TYPE_CHECKING
 
 from pandas.compat._constants import (
+    CHAINED_WARNING_DISABLED,
+    CHAINED_WARNING_DISABLED_INPLACE_METHOD,
     IS64,
     ISMUSL,
     PY312,
     PY314,
     PYPY,
-    WARNING_CHECK_DISABLED,
     WASM,
 )
 from pandas.compat.numpy import is_numpy_dev
@@ -152,14 +153,15 @@ def is_ci_environment() -> bool:
 
 
 __all__ = [
+    "CHAINED_WARNING_DISABLED",
+    "CHAINED_WARNING_DISABLED_INPLACE_METHOD",
     "HAS_PYARROW",
     "IS64",
     "ISMUSL",
     "PY312",
     "PY314",
     "PYARROW_MIN_VERSION",
     "PYPY",
-    "WARNING_CHECK_DISABLED",
     "WASM",
     "is_numpy_dev",
     "pa_version_under14p0",

pandas/compat/_constants.py

@@ -19,7 +19,8 @@
 WASM = (sys.platform == "emscripten") or (platform.machine() in ["wasm32", "wasm64"])
 ISMUSL = "musl" in (sysconfig.get_config_var("HOST_GNU_TYPE") or "")
 REF_COUNT = 2
-WARNING_CHECK_DISABLED = PY314
+CHAINED_WARNING_DISABLED = PYPY or (PY314 and not sys._is_gil_enabled())  # type: ignore[attr-defined]
+CHAINED_WARNING_DISABLED_INPLACE_METHOD = PYPY or PY314
 
 
 __all__ = [