Merge branch 'main' into add_prefix_feature

Author: zhangbowen-coder

doc/source/whatsnew/v2.3.4.rst

@@ -13,6 +13,7 @@ including other versions of pandas.
 Bug fixes
 ^^^^^^^^^
 - Bug in :meth:`DataFrame.__getitem__` returning modified columns when called with ``slice`` in Python 3.12 (:issue:`57500`)
+- Bug in :meth:`Series.str.replace` raising an error on valid group references (``\1``, ``\2``, etc.) on series converted to PyArrow backend dtype (:issue:`62653`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_234.contributors:

doc/source/whatsnew/v3.0.0.rst

@@ -1124,7 +1124,6 @@ Conversion
 Strings
 ^^^^^^^
 - Bug in :meth:`Series.str.match` failing to raise when given a compiled ``re.Pattern`` object and conflicting ``case`` or ``flags`` arguments (:issue:`62240`)
-- Bug in :meth:`Series.str.replace` raising an error on valid group references (``\1``, ``\2``, etc.) on series converted to PyArrow backend dtype (:issue:`62653`)
 - Bug in :meth:`Series.str.zfill` raising ``AttributeError`` for :class:`ArrowDtype` (:issue:`61485`)
 - Bug in :meth:`Series.value_counts` would not respect ``sort=False`` for series having ``string`` dtype (:issue:`55224`)
 - Bug in multiplication with a :class:`StringDtype` incorrectly allowing multiplying by bools; explicitly cast to integers instead (:issue:`62595`)

pandas/_libs/internals.pyx

@@ -1006,8 +1006,12 @@ cdef class BlockValuesRefs:
 
 cdef extern from "Python.h":
     """
+    // python version < 3.14
     #if PY_VERSION_HEX < 0x030E0000
-    int __Pyx_PyUnstable_Object_IsUniqueReferencedTemporary(PyObject *ref);
+    // This function is unused and is declared to avoid a build warning
+    int __Pyx_PyUnstable_Object_IsUniqueReferencedTemporary(PyObject *ref) {
+        return Py_REFCNT(ref) == 1;
+    }
     #else
     #define __Pyx_PyUnstable_Object_IsUniqueReferencedTemporary \
         PyUnstable_Object_IsUniqueReferencedTemporary

pandas/core/arrays/datetimelike.py

@@ -2342,6 +2342,9 @@ def _with_freq(self, freq) -> Self:
 
     def _values_for_json(self) -> np.ndarray:
         # Small performance bump vs the base class which calls np.asarray(self)
+        if self.unit != "ns":
+            # GH#55827
+            return self.as_unit("ns")._values_for_json()
         if isinstance(self.dtype, np.dtype):
             return self._ndarray
         return super()._values_for_json()

pandas/tests/io/json/test_pandas.py

@@ -135,12 +135,6 @@ def test_frame_non_unique_index_raises(self, orient):
         ],
     )
     def test_frame_non_unique_columns(self, orient, data, request):
-        if isinstance(data[0][0], Timestamp) and orient == "split":
-            mark = pytest.mark.xfail(
-                reason="GH#55827 non-nanosecond dt64 fails to round-trip"
-            )
-            request.applymarker(mark)
-
         df = DataFrame(data, index=[1, 2], columns=["x", "x"])
 
         expected_warning = None
@@ -162,10 +156,14 @@ def test_frame_non_unique_columns(self, orient, data, request):
                 # in milliseconds; these are internally stored in nanosecond,
                 # so divide to get where we need
                 # TODO: a to_epoch method would also solve; see GH 14772
-                expected.isetitem(0, expected.iloc[:, 0].astype(np.int64) // 1000000)
+                dta = expected.iloc[:, 0]._values
+                dta = dta.as_unit("ns")  # GH#55827
+                expected.isetitem(0, dta.astype(np.int64) // 1_000_000)
         elif orient == "split":
             expected = df
             expected.columns = ["x", "x.1"]
+            if expected["x"].dtype.kind == "M":
+                expected["x"] = expected["x"].astype("M8[ns]")  # GH#55827
 
         tm.assert_frame_equal(result, expected)