Merge remote-tracking branch 'upstream/main' into ref/concat

Author: mroeschke

.pre-commit-config.yaml

@@ -19,7 +19,7 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.4.7
+    rev: v0.5.0
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -73,7 +73,7 @@ repos:
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v3.15.2
+    rev: v3.16.0
     hooks:
     -   id: pyupgrade
         args: [--py310-plus]
@@ -93,7 +93,7 @@ repos:
     - id: sphinx-lint
       args: ["--enable", "all", "--disable", "line-too-long"]
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v18.1.5
+    rev: v18.1.8
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include

ci/code_checks.sh

@@ -244,13 +244,11 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timestamp.month_name SA01" \
         -i "pandas.Timestamp.nanosecond GL08" \
         -i "pandas.Timestamp.normalize SA01" \
-        -i "pandas.Timestamp.now SA01" \
         -i "pandas.Timestamp.quarter SA01" \
         -i "pandas.Timestamp.replace PR07,SA01" \
         -i "pandas.Timestamp.resolution PR02" \
         -i "pandas.Timestamp.second GL08" \
         -i "pandas.Timestamp.strptime PR01,SA01" \
-        -i "pandas.Timestamp.time SA01" \
         -i "pandas.Timestamp.timestamp SA01" \
         -i "pandas.Timestamp.timetuple SA01" \
         -i "pandas.Timestamp.timetz SA01" \

doc/source/whatsnew/v3.0.0.rst

@@ -563,8 +563,8 @@ I/O
 - 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_excel` raising ``ValueError`` when passing array of boolean values when ``dtype="boolean"``. (:issue:`58159`)
+- Bug in :meth:`read_json` not validating the ``typ`` argument to not be exactly ``"frame"`` or ``"series"`` (:issue:`59124`)
 - Bug in :meth:`read_stata` raising ``KeyError`` when input file is stored in big-endian format and contains strL data. (:issue:`58638`)
--
 
 Period
 ^^^^^^
@@ -596,6 +596,7 @@ Reshaping
 ^^^^^^^^^
 - Bug in :meth:`DataFrame.join` inconsistently setting result index name (:issue:`55815`)
 - Bug in :meth:`DataFrame.unstack` producing incorrect results when ``sort=False`` (:issue:`54987`, :issue:`55516`)
+- Bug in :meth:`DataFrame.unstack` producing incorrect results when manipulating empty :class:`DataFrame` with an :class:`ExtentionDtype` (:issue:`59123`)
 
 Sparse
 ^^^^^^
@@ -615,6 +616,7 @@ Other
 ^^^^^
 - Bug in :class:`DataFrame` when passing a ``dict`` with a NA scalar and ``columns`` that would always return ``np.nan`` (:issue:`57205`)
 - Bug in :func:`eval` on :class:`ExtensionArray` on including division ``/`` failed with a ``TypeError``. (:issue:`58748`)
+- Bug in :func:`eval` on :class:`complex` including division ``/`` discards imaginary part. (:issue:`21374`)
 - Bug in :func:`eval` where the names of the :class:`Series` were not preserved when using ``engine="numexpr"``. (:issue:`10239`)
 - Bug in :func:`unique` on :class:`Index` not always returning :class:`Index` (:issue:`57043`)
 - Bug in :meth:`DataFrame.apply` where passing ``engine="numba"`` ignored ``args`` passed to the applied function (:issue:`58712`)

pandas/_libs/src/datetime/pd_datetime.c

@@ -245,7 +245,12 @@ static int pandas_datetime_exec(PyObject *Py_UNUSED(module)) {
 }
 
 static PyModuleDef_Slot pandas_datetime_slots[] = {
-    {Py_mod_exec, pandas_datetime_exec}, {0, NULL}};
+    {Py_mod_exec, pandas_datetime_exec},
+#if PY_VERSION_HEX >= 0x030D0000
+    {Py_mod_gil, Py_MOD_GIL_NOT_USED},
+#endif
+    {0, NULL},
+};
 
 static struct PyModuleDef pandas_datetimemodule = {
     PyModuleDef_HEAD_INIT,

pandas/_libs/src/parser/pd_parser.c

@@ -161,7 +161,12 @@ static int pandas_parser_exec(PyObject *Py_UNUSED(module)) {
 }
 
 static PyModuleDef_Slot pandas_parser_slots[] = {
-    {Py_mod_exec, pandas_parser_exec}, {0, NULL}};
+    {Py_mod_exec, pandas_parser_exec},
+#if PY_VERSION_HEX >= 0x030D0000
+    {Py_mod_gil, Py_MOD_GIL_NOT_USED},
+#endif
+    {0, NULL},
+};
 
 static struct PyModuleDef pandas_parsermodule = {
     PyModuleDef_HEAD_INIT,

pandas/_libs/tslibs/nattype.pyx

@@ -633,6 +633,16 @@ class NaTType(_NaT):
         """
         Return time object with same time but with tzinfo=None.
 
+        This method extracts the time part of the `Timestamp` object, excluding any
+        timezone information. It returns a `datetime.time` object which only represents
+        the time (hours, minutes, seconds, and microseconds).
+
+        See Also
+        --------
+        Timestamp.date : Return date object with same year, month and day.
+        Timestamp.tz_convert : Convert timezone-aware Timestamp to another time zone.
+        Timestamp.tz_localize : Localize the Timestamp to a timezone.
+
         Examples
         --------
         >>> ts = pd.Timestamp('2023-01-01 10:00:00')
@@ -957,11 +967,21 @@ class NaTType(_NaT):
         """
         Return new Timestamp object representing current time local to tz.
 
+        This method returns a new `Timestamp` object that represents the current time.
+        If a timezone is provided, the current time will be localized to that timezone.
+        Otherwise, it returns the current local time.
+
         Parameters
         ----------
         tz : str or timezone object, default None
             Timezone to localize to.
 
+        See Also
+        --------
+        to_datetime : Convert argument to datetime.
+        Timestamp.utcnow : Return a new Timestamp representing UTC day and time.
+        Timestamp.today : Return the current time in the local timezone.
+
         Examples
         --------
         >>> pd.Timestamp.now()  # doctest: +SKIP

pandas/_libs/tslibs/timestamps.pyx

@@ -1465,11 +1465,21 @@ class Timestamp(_Timestamp):
         """
         Return new Timestamp object representing current time local to tz.
 
+        This method returns a new `Timestamp` object that represents the current time.
+        If a timezone is provided, the current time will be localized to that timezone.
+        Otherwise, it returns the current local time.
+
         Parameters
         ----------
         tz : str or timezone object, default None
             Timezone to localize to.
 
+        See Also
+        --------
+        to_datetime : Convert argument to datetime.
+        Timestamp.utcnow : Return a new Timestamp representing UTC day and time.
+        Timestamp.today : Return the current time in the local timezone.
+
         Examples
         --------
         >>> pd.Timestamp.now()  # doctest: +SKIP
@@ -1768,6 +1778,16 @@ class Timestamp(_Timestamp):
         """
         Return time object with same time but with tzinfo=None.
 
+        This method extracts the time part of the `Timestamp` object, excluding any
+        timezone information. It returns a `datetime.time` object which only represents
+        the time (hours, minutes, seconds, and microseconds).
+
+        See Also
+        --------
+        Timestamp.date : Return date object with same year, month and day.
+        Timestamp.tz_convert : Convert timezone-aware Timestamp to another time zone.
+        Timestamp.tz_localize : Localize the Timestamp to a timezone.
+
         Examples
         --------
         >>> ts = pd.Timestamp('2023-01-01 10:00:00')

pandas/_testing/__init__.py

@@ -107,6 +107,7 @@
 
 COMPLEX_DTYPES: list[Dtype] = [complex, "complex64", "complex128"]
 STRING_DTYPES: list[Dtype] = [str, "str", "U"]
+COMPLEX_FLOAT_DTYPES: list[Dtype] = [*COMPLEX_DTYPES, *FLOAT_NUMPY_DTYPES]
 
 DATETIME64_DTYPES: list[Dtype] = ["datetime64[ns]", "M8[ns]"]
 TIMEDELTA64_DTYPES: list[Dtype] = ["timedelta64[ns]", "m8[ns]"]

pandas/conftest.py

@@ -1448,6 +1448,21 @@ def complex_dtype(request):
     return request.param
 
 
+@pytest.fixture(params=tm.COMPLEX_FLOAT_DTYPES)
+def complex_or_float_dtype(request):
+    """
+    Parameterized fixture for complex and numpy float dtypes.
+
+    * complex
+    * 'complex64'
+    * 'complex128'
+    * float
+    * 'float32'
+    * 'float64'
+    """
+    return request.param
+
+
 @pytest.fixture(params=tm.SIGNED_INT_NUMPY_DTYPES)
 def any_signed_int_numpy_dtype(request):
     """

pandas/core/common.py

@@ -145,7 +145,7 @@ def is_bool_indexer(key: Any) -> bool:
     elif isinstance(key, list):
         # check if np.array(key).dtype would be bool
         if len(key) > 0:
-            if type(key) is not list:  # noqa: E721
+            if type(key) is not list:
                 # GH#42461 cython will raise TypeError if we pass a subclass
                 key = list(key)
             return lib.is_bool_list(key)