Merge branch 'main' into nsorted

Author: MartinBraquet

.pre-commit-config.yaml

@@ -140,7 +140,7 @@ repos:
         pass_filenames: false
         types: [python]
         stages: [manual]
-    -   id: mypy
+    -   id: stubtest
         # note: assumes python env is setup and activated
         # note: requires pandas dev to be installed
         name: mypy (stubtest)

doc/source/whatsnew/v2.3.0.rst

@@ -50,10 +50,20 @@ Notable bug fixes
 
 These are bug fixes that might have notable behavior changes.
 
-.. _whatsnew_230.notable_bug_fixes.notable_bug_fix1:
+.. _whatsnew_230.notable_bug_fixes.string_comparisons:
 
-notable_bug_fix1
-^^^^^^^^^^^^^^^^
+Comparisons between different string dtypes
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+In previous versions, comparing Series of different string dtypes (e.g. ``pd.StringDtype("pyarrow", na_value=pd.NA)`` against ``pd.StringDtype("python", na_value=np.nan)``) would result in inconsistent resulting dtype or incorrectly raise. pandas will now use the hierarchy
+
+    object < (python, NaN) < (pyarrow, NaN) < (python, NA) < (pyarrow, NA)
+
+in determining the result dtype when there are different string dtypes compared. Some examples:
+
+- When ``pd.StringDtype("pyarrow", na_value=pd.NA)`` is compared against any other string dtype, the result will always be ``boolean[pyarrow]``.
+- When ``pd.StringDtype("python", na_value=pd.NA)`` is compared against ``pd.StringDtype("pyarrow", na_value=np.nan)``, the result will be ``boolean``, the NumPy-backed nullable extension array.
+- When ``pd.StringDtype("python", na_value=pd.NA)`` is compared against ``pd.StringDtype("python", na_value=np.nan)``, the result will be ``boolean``, the NumPy-backed nullable extension array.
 
 .. _whatsnew_230.api_changes:
 

doc/source/whatsnew/v3.0.0.rst

@@ -905,6 +905,7 @@ Other
 - Bug in ``Series.list`` methods not preserving the original name. (:issue:`60522`)
 - Bug in printing a :class:`DataFrame` with a :class:`DataFrame` stored in :attr:`DataFrame.attrs` raised a ``ValueError`` (:issue:`60455`)
 - Bug in printing a :class:`Series` with a :class:`DataFrame` stored in :attr:`Series.attrs` raised a ``ValueError`` (:issue:`60568`)
+- Fixed bug where the :class:`DataFrame` constructor misclassified array-like objects with a ``.name`` attribute as :class:`Series` or :class:`Index` (:issue:`61443`)
 - Fixed regression in :meth:`DataFrame.from_records` not initializing subclasses properly (:issue:`57008`)
 
 .. ***DO NOT USE THIS SECTION***

pandas/_libs/arrays.pyi

@@ -1,4 +1,4 @@
-from typing import Sequence
+from collections.abc import Sequence
 
 import numpy as np
 

pandas/_libs/hashtable.pyi

@@ -1,6 +1,6 @@
+from collections.abc import Hashable
 from typing import (
     Any,
-    Hashable,
     Literal,
     overload,
 )

pandas/_libs/internals.pyi

@@ -1,6 +1,8 @@
-from typing import (
+from collections.abc import (
     Iterator,
     Sequence,
+)
+from typing import (
     final,
     overload,
 )

pandas/_libs/json.pyi

@@ -1,6 +1,6 @@
+from collections.abc import Callable
 from typing import (
     Any,
-    Callable,
 )
 
 def ujson_dumps(

pandas/_libs/lib.pyi

@@ -1,12 +1,14 @@
 # TODO(npdtypes): Many types specified here can be made more specific/accurate;
 #  the more specific versions are specified in comments
+from collections.abc import (
+    Callable,
+    Generator,
+    Hashable,
+)
 from decimal import Decimal
 from typing import (
     Any,
-    Callable,
     Final,
-    Generator,
-    Hashable,
     Literal,
     TypeAlias,
     overload,

pandas/_libs/ops.pyi

@@ -1,7 +1,9 @@
-from typing import (
-    Any,
+from collections.abc import (
     Callable,
     Iterable,
+)
+from typing import (
+    Any,
     Literal,
     TypeAlias,
     overload,

pandas/_libs/parsers.pyi

@@ -1,5 +1,5 @@
+from collections.abc import Hashable
 from typing import (
-    Hashable,
     Literal,
 )