Merge branch 'main' into tst-string-xfails

Author: jbrockmendel

.github/workflows/unit-tests.yml

@@ -140,9 +140,6 @@ jobs:
 
       moto:
         image: motoserver/moto:5.0.27
-        env:
-          AWS_ACCESS_KEY_ID: foobar_key
-          AWS_SECRET_ACCESS_KEY: foobar_secret
         ports:
           - 5000:5000
 

environment.yml

@@ -64,9 +64,8 @@ dependencies:
   - dask-core
   - seaborn-base
 
-  # local testing dependencies
+  # Mocking s3 tests
   - moto
-  - flask
 
   # benchmarks
   - asv>=0.6.1

pandas/conftest.py

@@ -2116,3 +2116,9 @@ def temp_file(tmp_path):
     file_path = tmp_path / str(uuid.uuid4())
     file_path.touch()
     return file_path
+
+
+@pytest.fixture(scope="session")
+def monkeysession():
+    with pytest.MonkeyPatch.context() as mp:
+        yield mp

pandas/core/apply.py

@@ -10,6 +10,7 @@
     TYPE_CHECKING,
     Any,
     Literal,
+    TypeAlias,
     cast,
 )
 
@@ -71,7 +72,7 @@
     from pandas.core.resample import Resampler
     from pandas.core.window.rolling import BaseWindow
 
-ResType = dict[int, Any]
+ResType: TypeAlias = dict[int, Any]
 
 
 class BaseExecutionEngine(abc.ABC):

pandas/core/arrays/datetimelike.py

@@ -10,6 +10,7 @@
     TYPE_CHECKING,
     Any,
     Literal,
+    TypeAlias,
     Union,
     cast,
     final,
@@ -161,7 +162,7 @@
         TimedeltaArray,
     )
 
-DTScalarOrNaT = Union[DatetimeLikeScalar, NaTType]
+DTScalarOrNaT: TypeAlias = DatetimeLikeScalar | NaTType
 
 
 def _make_unpacked_invalid_op(op_name: str):
@@ -386,7 +387,7 @@ def __getitem__(self, key: PositionalIndexer2D) -> Self | DTScalarOrNaT:
         # Use cast as we know we will get back a DatetimeLikeArray or DTScalar,
         # but skip evaluating the Union at runtime for performance
         # (see https://github.com/pandas-dev/pandas/pull/44624)
-        result = cast("Union[Self, DTScalarOrNaT]", super().__getitem__(key))
+        result = cast(Union[Self, DTScalarOrNaT], super().__getitem__(key))
         if lib.is_scalar(result):
             return result
         else:

pandas/core/arrays/interval.py

@@ -9,7 +9,7 @@
 from typing import (
     TYPE_CHECKING,
     Literal,
-    Union,
+    TypeAlias,
     overload,
 )
 
@@ -109,8 +109,8 @@
     )
 
 
-IntervalSide = Union[TimeArrayLike, np.ndarray]
-IntervalOrNA = Union[Interval, float]
+IntervalSide: TypeAlias = TimeArrayLike | np.ndarray
+IntervalOrNA: TypeAlias = Interval | float
 
 _interval_shared_docs: dict[str, str] = {}
 

pandas/core/arrays/string_arrow.py

@@ -4,7 +4,6 @@
 import re
 from typing import (
     TYPE_CHECKING,
-    Union,
 )
 import warnings
 
@@ -63,9 +62,6 @@
     from pandas import Series
 
 
-ArrowStringScalarOrNAT = Union[str, libmissing.NAType]
-
-
 def _chk_pyarrow_available() -> None:
     if pa_version_under10p1:
         msg = "pyarrow>=10.0.1 is required for PyArrow backed ArrowExtensionArray."

pandas/core/groupby/generic.py

@@ -17,8 +17,8 @@
     Any,
     Literal,
     NamedTuple,
+    TypeAlias,
     TypeVar,
-    Union,
     cast,
 )
 import warnings
@@ -102,7 +102,7 @@
     from pandas.core.generic import NDFrame
 
 # TODO(typing) the return value on this callable should be any *scalar*.
-AggScalar = Union[str, Callable[..., Any]]
+AggScalar: TypeAlias = str | Callable[..., Any]
 # TODO: validate types on ScalarResult and move to _typing
 # Blocked from using by https://github.com/python/mypy/issues/1484
 # See note at _mangle_lambda_list

pandas/core/groupby/groupby.py

@@ -26,6 +26,7 @@ class providing the base-class of operations.
 from typing import (
     TYPE_CHECKING,
     Literal,
+    TypeAlias,
     TypeVar,
     Union,
     cast,
@@ -449,13 +450,13 @@ def f(self):
         return attr
 
 
-_KeysArgType = Union[
-    Hashable,
-    list[Hashable],
-    Callable[[Hashable], Hashable],
-    list[Callable[[Hashable], Hashable]],
-    Mapping[Hashable, Hashable],
-]
+_KeysArgType: TypeAlias = (
+    Hashable
+    | list[Hashable]
+    | Callable[[Hashable], Hashable]
+    | list[Callable[[Hashable], Hashable]]
+    | Mapping[Hashable, Hashable]
+)
 
 
 class BaseGroupBy(PandasObject, SelectionMixin[NDFrameT], GroupByIndexingMixin):
@@ -957,9 +958,8 @@ def __iter__(self) -> Iterator[tuple[Hashable, NDFrameT]]:
         level = self.level
         result = self._grouper.get_iterator(self._selected_obj)
         # mypy: Argument 1 to "len" has incompatible type "Hashable"; expected "Sized"
-        if (
-            (is_list_like(level) and len(level) == 1)  # type: ignore[arg-type]
-            or (isinstance(keys, list) and len(keys) == 1)
+        if (is_list_like(level) and len(level) == 1) or (  # type: ignore[arg-type]
+            isinstance(keys, list) and len(keys) == 1
         ):
             # GH#42795 - when keys is a list, return tuples even when length is 1
             result = (((key,), group) for key, group in result)

pandas/core/indexing.py

@@ -5,7 +5,6 @@
 from typing import (
     TYPE_CHECKING,
     Any,
-    TypeVar,
     cast,
     final,
 )
@@ -83,6 +82,7 @@
         Axis,
         AxisInt,
         Self,
+        T,
         npt,
     )
 
@@ -91,7 +91,6 @@
         Series,
     )
 
-T = TypeVar("T")
 # "null slice"
 _NS = slice(None, None)
 _one_ellipsis_message = "indexer may only contain one '...' entry"