Merge remote-tracking branch 'upstream/main' into issue_61889

Author: jorisvandenbossche

README.md

@@ -115,7 +115,7 @@ details, see the commit logs at https://github.com/pandas-dev/pandas.
 ## Dependencies
 - [NumPy - Adds support for large, multi-dimensional arrays, matrices and high-level mathematical functions to operate on these arrays](https://www.numpy.org)
 - [python-dateutil - Provides powerful extensions to the standard datetime module](https://dateutil.readthedocs.io/en/stable/index.html)
-- [pytz - Brings the Olson tz database into Python which allows accurate and cross platform timezone calculations](https://github.com/stub42/pytz)
+- [tzdata - Provides an IANA time zone database](https://tzdata.readthedocs.io/en/latest/)
 
 See the [full installation instructions](https://pandas.pydata.org/pandas-docs/stable/install.html#dependencies) for minimum supported versions of required, recommended and optional dependencies.
 

ci/deps/actions-311-downstream_compat.yaml

@@ -50,8 +50,7 @@ dependencies:
   - pytz>=2023.4
   - pyxlsb>=1.0.10
   - s3fs>=2023.12.2
-  # TEMP upper pin for scipy (https://github.com/statsmodels/statsmodels/issues/9584)
-  - scipy>=1.12.0,<1.16
+  - scipy>=1.12.0
   - sqlalchemy>=2.0.0
   - tabulate>=0.9.0
   - xarray>=2024.1.1

doc/source/whatsnew/index.rst

@@ -24,6 +24,7 @@ Version 2.3
 .. toctree::
    :maxdepth: 2
 
+   v2.3.2
    v2.3.1
    v2.3.0
 

doc/source/whatsnew/v2.3.2.rst

@@ -0,0 +1,31 @@
+.. _whatsnew_232:
+
+What's new in 2.3.2 (August XX, 2025)
+-------------------------------------
+
+These are the changes in pandas 2.3.2. See :ref:`release` for a full changelog
+including other versions of pandas.
+
+{{ header }}
+
+.. ---------------------------------------------------------------------------
+.. _whatsnew_232.string_fixes:
+
+Improvements and fixes for the StringDtype
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Most changes in this release are related to :class:`StringDtype` which will
+become the default string dtype in pandas 3.0. See
+:ref:`whatsnew_230.upcoming_changes` for more details.
+
+.. _whatsnew_232.string_fixes.bugs:
+
+Bug fixes
+^^^^^^^^^
+-
+
+.. ---------------------------------------------------------------------------
+.. _whatsnew_232.contributors:
+
+Contributors
+~~~~~~~~~~~~

pandas/core/algorithms.py

@@ -751,7 +751,7 @@ def factorize(
     array([0, 0, 1])
     >>> uniques
     ['a', 'c']
-    Categories (3, object): ['a', 'b', 'c']
+    Categories (3, str): [a, b, c]
 
     Notice that ``'b'`` is in ``uniques.categories``, despite not being
     present in ``cat.values``.
@@ -764,7 +764,7 @@ def factorize(
     >>> codes
     array([0, 0, 1])
     >>> uniques
-    Index(['a', 'c'], dtype='object')
+    Index(['a', 'c'], dtype='str')
 
     If NaN is in the values, and we want to include NaN in the uniques of the
     values, it can be achieved by setting ``use_na_sentinel=False``.

pandas/core/arrays/categorical.py

@@ -2233,8 +2233,16 @@ def _repr_categories(self) -> list[str]:
         )
         from pandas.io.formats import format as fmt
 
+        formatter = None
+        if self.categories.dtype == "str":
+            # the extension array formatter defaults to boxed=True in format_array
+            # override here to boxed=False to be consistent with QUOTE_NONNUMERIC
+            formatter = cast(ExtensionArray, self.categories._values)._formatter(
+                boxed=False
+            )
+
         format_array = partial(
-            fmt.format_array, formatter=None, quoting=QUOTE_NONNUMERIC
+            fmt.format_array, formatter=formatter, quoting=QUOTE_NONNUMERIC
         )
         if len(self.categories) > max_categories:
             num = max_categories // 2

pandas/core/base.py

@@ -323,12 +323,12 @@ def transpose(self, *args, **kwargs) -> Self:
         0     Ant
         1    Bear
         2     Cow
-        dtype: object
+        dtype: str
         >>> s.T
         0     Ant
         1    Bear
         2     Cow
-        dtype: object
+        dtype: str
 
         For Index:
 
@@ -383,7 +383,7 @@ def ndim(self) -> int:
         0     Ant
         1    Bear
         2     Cow
-        dtype: object
+        dtype: str
         >>> s.ndim
         1
 
@@ -452,9 +452,9 @@ def nbytes(self) -> int:
         0     Ant
         1    Bear
         2     Cow
-        dtype: object
+        dtype: str
         >>> s.nbytes
-        24
+        34
 
         For Index:
 
@@ -487,7 +487,7 @@ def size(self) -> int:
         0     Ant
         1    Bear
         2     Cow
-        dtype: object
+        dtype: str
         >>> s.size
         3
 
@@ -567,7 +567,7 @@ def array(self) -> ExtensionArray:
         >>> ser = pd.Series(pd.Categorical(["a", "b", "a"]))
         >>> ser.array
         ['a', 'b', 'a']
-        Categories (2, object): ['a', 'b']
+        Categories (2, str): [a, b]
         """
         raise AbstractMethodError(self)
 
@@ -1076,15 +1076,15 @@ def value_counts(
 
         >>> df.dtypes
         a    category
-        b      object
+        b      str
         c    category
         d    category
         dtype: object
 
         >>> df.dtypes.value_counts()
         category    2
         category    1
-        object      1
+        str         1
         Name: count, dtype: int64
         """
         return algorithms.value_counts_internal(
@@ -1386,7 +1386,7 @@ def factorize(
         ... )
         >>> ser
         ['apple', 'bread', 'bread', 'cheese', 'milk']
-        Categories (4, object): ['apple' < 'bread' < 'cheese' < 'milk']
+        Categories (4, str): [apple < bread < cheese < milk]
 
         >>> ser.searchsorted('bread')
         np.int64(1)