Merge branch 'main' into gh-62717

Author: heoh

.github/workflows/unit-tests.yml

@@ -181,8 +181,7 @@ jobs:
     timeout-minutes: 90
     strategy:
       matrix:
-        # Note: Don't use macOS latest since macos 14 appears to be arm64 only
-        os: [macos-13, macos-14, windows-2025]
+        os: [macos-15-intel, macos-15, windows-2025]
         env_file: [actions-311.yaml, actions-312.yaml, actions-313.yaml]
       fail-fast: false
     runs-on: ${{ matrix.os }}
@@ -399,7 +398,7 @@ jobs:
           pyodide build
 
       - name: Set up Node.js
-        uses: actions/setup-node@v5
+        uses: actions/setup-node@v6
         with:
           node-version: '20'
 

.github/workflows/wheels.yml

@@ -98,10 +98,9 @@ jobs:
         - [ubuntu-24.04, musllinux_x86_64]
         - [ubuntu-24.04-arm, manylinux_aarch64]
         - [ubuntu-24.04-arm, musllinux_aarch64]
-        - [macos-13, macosx_x86_64]
-        # Note: M1 images on Github Actions start from macOS 14
-        - [macos-14, macosx_arm64]
-        - [windows-2022, win_amd64]
+        - [macos-15-intel, macosx_x86_64]
+        - [macos-15, macosx_arm64]
+        - [windows-2025, win_amd64]
         - [windows-11-arm, win_arm64]
         python: [["cp311", "3.11"], ["cp312", "3.12"], ["cp313", "3.13"], ["cp313t", "3.13"], ["cp314", "3.14"], ["cp314t", "3.14"]]
         include:

asv_bench/benchmarks/ctors.py

@@ -23,7 +23,7 @@ def gen_of_str(arr):
 
 
 def arr_dict(arr):
-    return dict(zip(range(len(arr)), arr))
+    return dict(zip(range(len(arr)), arr, strict=True))
 
 
 def list_of_tuples(arr):

asv_bench/benchmarks/series_methods.py

@@ -16,7 +16,7 @@ def setup(self):
         self.idx = date_range(
             start=datetime(2015, 10, 26), end=datetime(2016, 1, 1), freq="50s"
         )
-        self.data = dict(zip(self.idx, range(len(self.idx))))
+        self.data = dict(zip(self.idx, range(len(self.idx)), strict=True))
         self.array = np.array([1, 2, 3])
         self.idx2 = Index(["a", "b", "c"])
 
@@ -407,7 +407,9 @@ def setup(self, num_to_replace):
         self.to_replace_list = np.random.choice(self.arr, num_to_replace)
         self.values_list = np.random.choice(self.arr1, num_to_replace)
 
-        self.replace_dict = dict(zip(self.to_replace_list, self.values_list))
+        self.replace_dict = dict(
+            zip(self.to_replace_list, self.values_list, strict=True)
+        )
 
     def time_replace_dict(self, num_to_replace):
         self.ser.replace(self.replace_dict)

doc/source/whatsnew/v3.0.0.rst

@@ -515,6 +515,22 @@ If we had passed ``pd.Int64Dtype()`` or ``"int64[pyarrow]"`` for the dtype in th
 
 With ``"mode.nan_is_na"`` set to ``False``, ``ser.to_numpy()`` (and ``frame.values`` and ``np.asarray(obj)``) will convert to ``object`` dtype if :class:`NA` entries are present, where before they would coerce to ``NaN``.  To retain a float numpy dtype, explicitly pass ``na_value=np.nan`` to :meth:`Series.to_numpy`.
 
+The ``__module__`` attribute now points to public modules
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The ``__module__`` attribute on functions and classes in the public API has been
+updated to refer to the preferred public module from which to access the object,
+rather than the module in which the object happens to be defined (:issue:`55178`).
+
+This produces more informative displays in the Python console for classes, e.g.,
+instead of ``<class 'pandas.core.frame.DataFrame'>`` you now see
+``<class 'pandas.DataFrame'>``, and in interactive tools such as IPython, e.g.,
+instead of ``<function pandas.io.parsers.readers.read_csv(...)>`` you now see
+``<function pandas.read_csv(...)>``.
+
+This may break code that relies on the previous ``__module__`` values (e.g.
+doctests inspecting the ``type()`` of a DataFrame object).
+
 .. _whatsnew_300.api_breaking.deps:
 
 Increased minimum version for Python
@@ -938,6 +954,7 @@ 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 :func:`Series.apply` where ``nan`` was ignored for :class:`CategoricalDtype` (:issue:`59938`)
 - 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`)
@@ -1041,6 +1058,7 @@ Indexing
 - Bug in reindexing of :class:`DataFrame` with :class:`PeriodDtype` columns in case of consolidated block (:issue:`60980`, :issue:`60273`)
 - Bug in :meth:`DataFrame.loc.__getitem__` and :meth:`DataFrame.iloc.__getitem__` with a :class:`CategoricalDtype` column with integer categories raising when trying to index a row containing a ``NaN`` entry (:issue:`58954`)
 - Bug in :meth:`Index.__getitem__` incorrectly raising with a 0-dim ``np.ndarray`` key (:issue:`55601`)
+- Bug in :meth:`Index.get_indexer` not casting missing values correctly for new string datatype (:issue:`55833`)
 - Bug in adding new rows with :meth:`DataFrame.loc.__setitem__` or :class:`Series.loc.__setitem__` which failed to retain dtype on the object's index in some cases (:issue:`41626`)
 - Bug in indexing on a :class:`DatetimeIndex` with a ``timestamp[pyarrow]`` dtype or on a :class:`TimedeltaIndex` with a ``duration[pyarrow]`` dtype (:issue:`62277`)
 
@@ -1086,6 +1104,7 @@ I/O
 - Bug in :meth:`HDFStore.select` causing queries on categorical string columns to return unexpected results (:issue:`57608`)
 - Bug in :meth:`MultiIndex.factorize` incorrectly raising on length-0 indexes (:issue:`57517`)
 - Bug in :meth:`read_csv` causing segmentation fault when ``encoding_errors`` is not a string. (:issue:`59059`)
+- Bug in :meth:`read_csv` for the ``c`` and ``python`` engines where parsing numbers with large exponents caused overflows. Now, numbers with large positive exponents are parsed as ``inf`` or ``-inf`` depending on the sign of the mantissa, while those with large negative exponents are parsed as ``0.0`` (:issue:`62617`, :issue:`38794`, :issue:`62740`)
 - Bug in :meth:`read_csv` raising ``TypeError`` when ``index_col`` is specified and ``na_values`` is a dict containing the key ``None``. (:issue:`57547`)
 - Bug in :meth:`read_csv` raising ``TypeError`` when ``nrows`` and ``iterator`` are specified without specifying a ``chunksize``. (:issue:`59079`)
 - Bug in :meth:`read_csv` where the order of the ``na_values`` makes an inconsistency when ``na_values`` is a list non-string values. (:issue:`59303`)
@@ -1147,7 +1166,6 @@ Groupby/resample/rolling
 - Bug in :meth:`Rolling.apply` for ``method="table"`` where column order was not being respected due to the columns getting sorted by default. (:issue:`59666`)
 - Bug in :meth:`Rolling.apply` where the applied function could be called on fewer than ``min_period`` periods if ``method="table"``. (:issue:`58868`)
 - Bug in :meth:`Series.resample` could raise when the date range ended shortly before a non-existent time. (:issue:`58380`)
-- Bug in :meth:`Series.rolling.var` and :meth:`Series.rolling.std` where the end of window was not indexed correctly. (:issue:`47721`, :issue:`52407`, :issue:`54518`, :issue:`55343`)
 
 Reshaping
 ^^^^^^^^^

pandas/_config/config.py

@@ -944,3 +944,11 @@ def is_callable(obj: object) -> bool:
     if not callable(obj):
         raise ValueError("Value must be a callable")
     return True
+
+
+# import set_module here would cause circular import
+get_option.__module__ = "pandas"
+set_option.__module__ = "pandas"
+describe_option.__module__ = "pandas"
+reset_option.__module__ = "pandas"
+option_context.__module__ = "pandas"

pandas/_libs/include/pandas/portable.h

@@ -35,3 +35,51 @@ The full license is in the LICENSE file, distributed with this software.
   do {                                                                         \
   } while (0) /* fallthrough */
 #endif
+
+#if defined(_WIN32)
+#ifndef ENABLE_INTSAFE_SIGNED_FUNCTIONS
+#define ENABLE_INTSAFE_SIGNED_FUNCTIONS
+#endif
+#include <intsafe.h>
+#define checked_add(a, b, res)                                                 \
+  _Generic((res),                                                              \
+      int *: IntAdd,                                                           \
+      unsigned int *: UIntAdd,                                                 \
+      long *: LongAdd,                                                         \
+      unsigned long *: ULongAdd,                                               \
+      long long *: LongLongAdd,                                                \
+      unsigned long long *: ULongLongAdd,                                      \
+      short *: ShortAdd,                                                       \
+      unsigned short *: UShortAdd)(a, b, res)
+
+#define checked_sub(a, b, res)                                                 \
+  _Generic((res),                                                              \
+      int *: IntSub,                                                           \
+      unsigned int *: UIntSub,                                                 \
+      long *: LongSub,                                                         \
+      unsigned long *: ULongSub,                                               \
+      long long *: LongLongSub,                                                \
+      unsigned long long *: ULongLongSub,                                      \
+      short *: ShortSub,                                                       \
+      unsigned short *: UShortSub)(a, b, res)
+
+#define checked_mul(a, b, res)                                                 \
+  _Generic((res),                                                              \
+      int *: IntMult,                                                          \
+      unsigned int *: UIntMult,                                                \
+      long *: LongMult,                                                        \
+      unsigned long *: ULongMult,                                              \
+      long long *: LongLongMult,                                               \
+      unsigned long long *: ULongLongMult,                                     \
+      short *: ShortMult,                                                      \
+      unsigned short *: UShortMult)(a, b, res)
+
+#elif (defined(__has_builtin) && __has_builtin(__builtin_add_overflow)) ||     \
+    __GNUC__ > 7
+#define checked_add(a, b, res) __builtin_add_overflow(a, b, res)
+#define checked_sub(a, b, res) __builtin_sub_overflow(a, b, res)
+#define checked_mul(a, b, res) __builtin_mul_overflow(a, b, res)
+#else
+_Static_assert(0,
+               "Overflow checking not detected; please try a newer compiler");
+#endif

pandas/_libs/lib.pyx

@@ -41,6 +41,7 @@ from cython cimport (
 from pandas._config import using_string_dtype
 
 from pandas._libs.missing import check_na_tuples_nonequal
+from pandas.util._decorators import set_module
 
 import_datetime()
 
@@ -154,6 +155,7 @@ def memory_usage_of_objects(arr: object[:]) -> int64_t:
 # ----------------------------------------------------------------------
 
 
+@set_module("pandas.api.types")
 def is_scalar(val: object) -> bool:
     """
     Return True if given object is scalar.
@@ -255,6 +257,7 @@ cdef int64_t get_itemsize(object val):
         return -1
 
 
+@set_module("pandas.api.types")
 def is_iterator(obj: object) -> bool:
     """
     Check if the object is an iterator.
@@ -1095,6 +1098,7 @@ def indices_fast(ndarray[intp_t, ndim=1] index, const int64_t[:] labels, list ke
 
 # core.common import for fast inference checks
 
+@set_module("pandas.api.types")
 def is_float(obj: object) -> bool:
     """
     Return True if given object is float.
@@ -1128,6 +1132,7 @@ def is_float(obj: object) -> bool:
     return util.is_float_object(obj)
 
 
+@set_module("pandas.api.types")
 def is_integer(obj: object) -> bool:
     """
     Return True if given object is integer.
@@ -1172,6 +1177,7 @@ def is_int_or_none(obj) -> bool:
     return obj is None or util.is_integer_object(obj)
 
 
+@set_module("pandas.api.types")
 def is_bool(obj: object) -> bool:
     """
     Return True if given object is boolean.
@@ -1202,6 +1208,7 @@ def is_bool(obj: object) -> bool:
     return util.is_bool_object(obj)
 
 
+@set_module("pandas.api.types")
 def is_complex(obj: object) -> bool:
     """
     Return True if given object is complex.
@@ -1237,6 +1244,7 @@ cpdef bint is_decimal(object obj):
     return isinstance(obj, Decimal)
 
 
+@set_module("pandas.api.types")
 def is_list_like(obj: object, allow_sets: bool = True) -> bool:
     """
     Check if the object is list-like.
@@ -1520,6 +1528,7 @@ cdef object _try_infer_map(object dtype):
     return None
 
 
+@set_module("pandas.api.types")
 def infer_dtype(value: object, skipna: bool = True) -> str:
     """
     Return a string label of the type of the elements in a list-like input.