Resolve merge conflict in whatsnew/v3.0.0.rst

Author: cmjcharlton

ci/code_checks.sh

@@ -83,7 +83,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.DataFrame.__iter__ SA01" \
         -i "pandas.DataFrame.assign SA01" \
         -i "pandas.DataFrame.at_time PR01" \
-        -i "pandas.DataFrame.axes SA01" \
         -i "pandas.DataFrame.bfill SA01" \
         -i "pandas.DataFrame.columns SA01" \
         -i "pandas.DataFrame.copy SA01" \

doc/source/whatsnew/v2.2.1.rst

@@ -87,4 +87,4 @@ Other
 Contributors
 ~~~~~~~~~~~~
 
-.. contributors:: v2.2.0..v2.2.1|HEAD
+.. contributors:: v2.2.0..v2.2.1

doc/source/whatsnew/v2.2.2.rst

@@ -1,6 +1,6 @@
 .. _whatsnew_222:
 
-What's new in 2.2.2 (April XX, 2024)
+What's new in 2.2.2 (April 10, 2024)
 ---------------------------------------
 
 These are the changes in pandas 2.2.2. See :ref:`release` for a full changelog
@@ -9,6 +9,21 @@ including other versions of pandas.
 {{ header }}
 
 .. ---------------------------------------------------------------------------
+
+.. _whatsnew_220.np2_compat:
+
+Pandas 2.2.2 is now compatible with numpy 2.0
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Pandas 2.2.2 is the first version of pandas that is generally compatible with the upcoming
+numpy 2.0 release, and wheels for pandas 2.2.2 will work with both numpy 1.x and 2.x.
+
+One major caveat is that arrays created with numpy 2.0's new ``StringDtype`` will convert
+to ``object`` dtyped arrays upon :class:`Series`/:class:`DataFrame` creation.
+Full support for numpy 2.0's StringDtype is expected to land in pandas 3.0.
+
+As usual please report any bugs discovered to our `issue tracker <https://github.com/pandas-dev/pandas/issues/new/choose>`_
+
 .. _whatsnew_222.regressions:
 
 Fixed regressions
@@ -40,3 +55,5 @@ Other
 
 Contributors
 ~~~~~~~~~~~~
+
+.. contributors:: v2.2.1..v2.2.2|HEAD

doc/source/whatsnew/v3.0.0.rst

@@ -36,6 +36,7 @@ Other enhancements
 - Support reading value labels from Stata 108-format (Stata 6) and earlier files (:issue:`58154`)
 - Users can globally disable any ``PerformanceWarning`` by setting the option ``mode.performance_warnings`` to ``False`` (:issue:`56920`)
 - :meth:`Styler.format_index_names` can now be used to format the index and column names (:issue:`48936` and :issue:`47489`)
+- :meth:`DataFrame.cummin`, :meth:`DataFrame.cummax`, :meth:`DataFrame.cumprod` and :meth:`DataFrame.cumsum` methods now have a ``numeric_only`` parameter (:issue:`53072`)
 - Support reading Stata 110-format (Stata 7) dta files (:issue:`47176`)
 -
 
@@ -148,7 +149,6 @@ See :ref:`install.dependencies` and :ref:`install.optional_dependencies` for mor
 Other API changes
 ^^^^^^^^^^^^^^^^^
 - 3rd party ``py.path`` objects are no longer explicitly supported in IO methods. Use :py:class:`pathlib.Path` objects instead (:issue:`57091`)
-- :attr:`MultiIndex.codes`, :attr:`MultiIndex.levels`, and :attr:`MultiIndex.names` now returns a ``tuple`` instead of a ``FrozenList`` (:issue:`53531`)
 - :func:`read_table`'s ``parse_dates`` argument defaults to ``None`` to improve consistency with :func:`read_csv` (:issue:`57476`)
 - Made ``dtype`` a required argument in :meth:`ExtensionArray._from_sequence_of_strings` (:issue:`56519`)
 - Updated :meth:`DataFrame.to_excel` so that the output spreadsheet has no styling. Custom styling can still be done using :meth:`Styler.to_excel` (:issue:`54154`)
@@ -210,6 +210,8 @@ Removal of prior version deprecations/changes
 - :meth:`SeriesGroupBy.agg` no longer pins the name of the group to the input passed to the provided ``func`` (:issue:`51703`)
 - All arguments except ``name`` in :meth:`Index.rename` are now keyword only (:issue:`56493`)
 - All arguments except the first ``path``-like argument in IO writers are now keyword only (:issue:`54229`)
+- Disallow allowing logical operations (``||``, ``&``, ``^``) between pandas objects and dtype-less sequences (e.g. ``list``, ``tuple``); wrap the objects in :class:`Series`, :class:`Index`, or ``np.array`` first instead (:issue:`52264`)
+- Disallow automatic casting to object in :class:`Series` logical operations (``&``, ``^``, ``||``) between series with mismatched indexes and dtypes other than ``object`` or ``bool`` (:issue:`52538`)
 - Disallow calling :meth:`Series.replace` or :meth:`DataFrame.replace` without a ``value`` and with non-dict-like ``to_replace`` (:issue:`33302`)
 - Disallow constructing a :class:`arrays.SparseArray` with scalar data (:issue:`53039`)
 - Disallow non-standard (``np.ndarray``, :class:`Index`, :class:`ExtensionArray`, or :class:`Series`) to :func:`isin`, :func:`unique`, :func:`factorize` (:issue:`52986`)

pandas/_libs/hashtable_class_helper.pxi.in

@@ -3,7 +3,7 @@ Template for each `dtype` helper function for hashtable
 
 WARNING: DO NOT edit .pxi FILE directly, .pxi is generated from .pxi.in
 """
-
+from cpython.unicode cimport PyUnicode_AsUTF8
 
 {{py:
 
@@ -98,7 +98,6 @@ from pandas._libs.khash cimport (
 # VectorData
 # ----------------------------------------------------------------------
 
-from pandas._libs.tslibs.util cimport get_c_string
 from pandas._libs.missing cimport C_NA
 
 
@@ -998,7 +997,7 @@ cdef class StringHashTable(HashTable):
         cdef:
             khiter_t k
             const char *v
-        v = get_c_string(val)
+        v = PyUnicode_AsUTF8(val)
 
         k = kh_get_str(self.table, v)
         if k != self.table.n_buckets:
@@ -1012,7 +1011,7 @@ cdef class StringHashTable(HashTable):
             int ret = 0
             const char *v
 
-        v = get_c_string(key)
+        v = PyUnicode_AsUTF8(key)
 
         k = kh_put_str(self.table, v, &ret)
         if kh_exist_str(self.table, k):
@@ -1037,7 +1036,7 @@ cdef class StringHashTable(HashTable):
             raise MemoryError()
         for i in range(n):
             val = values[i]
-            v = get_c_string(val)
+            v = PyUnicode_AsUTF8(val)
             vecs[i] = v
 
         with nogil:
@@ -1071,11 +1070,11 @@ cdef class StringHashTable(HashTable):
             val = values[i]
 
             if isinstance(val, str):
-                # GH#31499 if we have a np.str_ get_c_string won't recognize
+                # GH#31499 if we have a np.str_ PyUnicode_AsUTF8 won't recognize
                 #  it as a str, even though isinstance does.
-                v = get_c_string(<str>val)
+                v = PyUnicode_AsUTF8(<str>val)
             else:
-                v = get_c_string(self.na_string_sentinel)
+                v = PyUnicode_AsUTF8(self.na_string_sentinel)
             vecs[i] = v
 
         with nogil:
@@ -1109,11 +1108,11 @@ cdef class StringHashTable(HashTable):
             val = values[i]
 
             if isinstance(val, str):
-                # GH#31499 if we have a np.str_ get_c_string won't recognize
+                # GH#31499 if we have a np.str_ PyUnicode_AsUTF8 won't recognize
                 #  it as a str, even though isinstance does.
-                v = get_c_string(<str>val)
+                v = PyUnicode_AsUTF8(<str>val)
             else:
-                v = get_c_string(self.na_string_sentinel)
+                v = PyUnicode_AsUTF8(self.na_string_sentinel)
             vecs[i] = v
 
         with nogil:
@@ -1195,9 +1194,9 @@ cdef class StringHashTable(HashTable):
             else:
                 # if ignore_na is False, we also stringify NaN/None/etc.
                 try:
-                    v = get_c_string(<str>val)
+                    v = PyUnicode_AsUTF8(<str>val)
                 except UnicodeEncodeError:
-                    v = get_c_string(<str>repr(val))
+                    v = PyUnicode_AsUTF8(<str>repr(val))
                 vecs[i] = v
 
         # compute

pandas/_libs/index.pyi

@@ -73,13 +73,13 @@ class MaskedUInt8Engine(MaskedIndexEngine): ...
 class MaskedBoolEngine(MaskedUInt8Engine): ...
 
 class BaseMultiIndexCodesEngine:
-    levels: tuple[np.ndarray]
+    levels: list[np.ndarray]
     offsets: np.ndarray  # ndarray[uint64_t, ndim=1]
 
     def __init__(
         self,
-        levels: tuple[Index, ...],  # all entries hashable
-        labels: tuple[np.ndarray],  # all entries integer-dtyped
+        levels: list[Index],  # all entries hashable
+        labels: list[np.ndarray],  # all entries integer-dtyped
         offsets: np.ndarray,  # np.ndarray[np.uint64, ndim=1]
     ) -> None: ...
     def get_indexer(self, target: npt.NDArray[np.object_]) -> npt.NDArray[np.intp]: ...

pandas/_libs/lib.pyi

@@ -67,7 +67,6 @@ def fast_multiget(
     default=...,
 ) -> ArrayLike: ...
 def fast_unique_multiple_list_gen(gen: Generator, sort: bool = ...) -> list: ...
-def fast_unique_multiple_list(lists: list, sort: bool | None = ...) -> list: ...
 @overload
 def map_infer(
     arr: np.ndarray,

pandas/_libs/lib.pyx

@@ -312,34 +312,6 @@ def item_from_zerodim(val: object) -> object:
     return val
 
 
-@cython.wraparound(False)
-@cython.boundscheck(False)
-def fast_unique_multiple_list(lists: list, sort: bool | None = True) -> list:
-    cdef:
-        list buf
-        Py_ssize_t k = len(lists)
-        Py_ssize_t i, j, n
-        list uniques = []
-        dict table = {}
-        object val, stub = 0
-
-    for i in range(k):
-        buf = lists[i]
-        n = len(buf)
-        for j in range(n):
-            val = buf[j]
-            if val not in table:
-                table[val] = stub
-                uniques.append(val)
-    if sort:
-        try:
-            uniques.sort()
-        except TypeError:
-            pass
-
-    return uniques
-
-
 @cython.wraparound(False)
 @cython.boundscheck(False)
 def fast_unique_multiple_list_gen(object gen, bint sort=True) -> list:
@@ -361,15 +333,15 @@ def fast_unique_multiple_list_gen(object gen, bint sort=True) -> list:
         list buf
         Py_ssize_t j, n
         list uniques = []
-        dict table = {}
-        object val, stub = 0
+        set table = set()
+        object val
 
     for buf in gen:
         n = len(buf)
         for j in range(n):
             val = buf[j]
             if val not in table:
-                table[val] = stub
+                table.add(val)
                 uniques.append(val)
     if sort:
         try:

pandas/_libs/tslibs/np_datetime.pyx

@@ -18,6 +18,7 @@ from cpython.object cimport (
     Py_LT,
     Py_NE,
 )
+from cpython.unicode cimport PyUnicode_AsUTF8AndSize
 from libc.stdint cimport INT64_MAX
 
 import_datetime()
@@ -44,7 +45,6 @@ from pandas._libs.tslibs.dtypes cimport (
     npy_unit_to_abbrev,
     npy_unit_to_attrname,
 )
-from pandas._libs.tslibs.util cimport get_c_string_buf_and_size
 
 
 cdef extern from "pandas/datetime/pd_datetime.h":
@@ -341,13 +341,13 @@ cdef int string_to_dts(
         const char* format_buf
         FormatRequirement format_requirement
 
-    buf = get_c_string_buf_and_size(val, &length)
+    buf = PyUnicode_AsUTF8AndSize(val, &length)
     if format is None:
         format_buf = b""
         format_length = 0
         format_requirement = INFER_FORMAT
     else:
-        format_buf = get_c_string_buf_and_size(format, &format_length)
+        format_buf = PyUnicode_AsUTF8AndSize(format, &format_length)
         format_requirement = <FormatRequirement>exact
     return parse_iso_8601_datetime(buf, length, want_exc,
                                    dts, out_bestunit, out_local, out_tzoffset,

pandas/_libs/tslibs/parsing.pyx

@@ -19,6 +19,7 @@ from cpython.datetime cimport (
 from datetime import timezone
 
 from cpython.object cimport PyObject_Str
+from cpython.unicode cimport PyUnicode_AsUTF8AndSize
 from cython cimport Py_ssize_t
 from libc.string cimport strchr
 
@@ -74,10 +75,7 @@ import_pandas_datetime()
 
 from pandas._libs.tslibs.strptime import array_strptime
 
-from pandas._libs.tslibs.util cimport (
-    get_c_string_buf_and_size,
-    is_array,
-)
+from pandas._libs.tslibs.util cimport is_array
 
 
 cdef extern from "pandas/portable.h":
@@ -175,7 +173,7 @@ cdef datetime _parse_delimited_date(
         int day = 1, month = 1, year
         bint can_swap = 0
 
-    buf = get_c_string_buf_and_size(date_string, &length)
+    buf = PyUnicode_AsUTF8AndSize(date_string, &length)
     if length == 10 and _is_delimiter(buf[2]) and _is_delimiter(buf[5]):
         # parsing MM?DD?YYYY and DD?MM?YYYY dates
         month = _parse_2digit(buf)
@@ -251,7 +249,7 @@ cdef bint _does_string_look_like_time(str parse_string):
         Py_ssize_t length
         int hour = -1, minute = -1
 
-    buf = get_c_string_buf_and_size(parse_string, &length)
+    buf = PyUnicode_AsUTF8AndSize(parse_string, &length)
     if length >= 4:
         if buf[1] == b":":
             # h:MM format
@@ -467,7 +465,7 @@ cpdef bint _does_string_look_like_datetime(str py_string):
         char first
         int error = 0
 
-    buf = get_c_string_buf_and_size(py_string, &length)
+    buf = PyUnicode_AsUTF8AndSize(py_string, &length)
     if length >= 1:
         first = buf[0]
         if first == b"0":
@@ -521,7 +519,7 @@ cdef datetime _parse_dateabbr_string(str date_string, datetime default,
             pass
 
     if 4 <= date_len <= 7:
-        buf = get_c_string_buf_and_size(date_string, &date_len)
+        buf = PyUnicode_AsUTF8AndSize(date_string, &date_len)
         try:
             i = date_string.index("Q", 1, 6)
             if i == 1:

pandas/_libs/tslibs/util.pxd

@@ -1,6 +1,5 @@
 
 from cpython.object cimport PyTypeObject
-from cpython.unicode cimport PyUnicode_AsUTF8AndSize
 
 
 cdef extern from "Python.h":
@@ -155,36 +154,6 @@ cdef inline bint is_nan(object val):
     return is_complex_object(val) and val != val
 
 
-cdef inline const char* get_c_string_buf_and_size(str py_string,
-                                                  Py_ssize_t *length) except NULL:
-    """
-    Extract internal char* buffer of unicode or bytes object `py_string` with
-    getting length of this internal buffer saved in `length`.
-
-    Notes
-    -----
-    Python object owns memory, thus returned char* must not be freed.
-    `length` can be NULL if getting buffer length is not needed.
-
-    Parameters
-    ----------
-    py_string : str
-    length : Py_ssize_t*
-
-    Returns
-    -------
-    buf : const char*
-    """
-    # Note PyUnicode_AsUTF8AndSize() can
-    #  potentially allocate memory inside in unlikely case of when underlying
-    #  unicode object was stored as non-utf8 and utf8 wasn't requested before.
-    return PyUnicode_AsUTF8AndSize(py_string, length)
-
-
-cdef inline const char* get_c_string(str py_string) except NULL:
-    return get_c_string_buf_and_size(py_string, NULL)
-
-
 cdef inline bytes string_encode_locale(str py_string):
     """As opposed to PyUnicode_Encode, use current system locale to encode."""
     return PyUnicode_EncodeLocale(py_string, NULL)