use TypeAlias. Make internal types private

Author: Dr-Irv

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):
@@ -934,7 +935,7 @@ def validate_values_for_numba(self) -> None:
 
     @abc.abstractmethod
     def wrap_results_for_axis(
-        self, results: ResType, res_index: Index
+        self, results: _ResType, res_index: Index
     ) -> DataFrame | Series:
         pass
 
@@ -1163,7 +1164,7 @@ def apply_standard(self):
         # wrap results
         return self.wrap_results(results, res_index)
 
-    def apply_series_generator(self) -> tuple[ResType, Index]:
+    def apply_series_generator(self) -> tuple[_ResType, Index]:
         assert callable(self.func)
 
         series_gen = self.series_generator
@@ -1193,7 +1194,7 @@ def apply_series_numba(self):
         results = self.apply_with_numba()
         return results, self.result_index
 
-    def wrap_results(self, results: ResType, res_index: Index) -> DataFrame | Series:
+    def wrap_results(self, results: _ResType, res_index: Index) -> DataFrame | Series:
         from pandas import Series
 
         # see if we can infer the results
@@ -1289,7 +1290,7 @@ def result_columns(self) -> Index:
         return self.index
 
     def wrap_results_for_axis(
-        self, results: ResType, res_index: Index
+        self, results: _ResType, res_index: Index
     ) -> DataFrame | Series:
         """return the results for the rows"""
 
@@ -1433,7 +1434,7 @@ def result_columns(self) -> Index:
         return self.columns
 
     def wrap_results_for_axis(
-        self, results: ResType, res_index: Index
+        self, results: _ResType, res_index: Index
     ) -> DataFrame | Series:
         """return the results for the columns"""
         result: DataFrame | Series
@@ -1453,7 +1454,7 @@ def wrap_results_for_axis(
 
         return result
 
-    def infer_to_same_shape(self, results: ResType, res_index: Index) -> DataFrame:
+    def infer_to_same_shape(self, results: _ResType, res_index: Index) -> DataFrame:
         """infer the results to the same shape as the input object"""
         result = self.obj._constructor(data=results)
         result = result.T

pandas/core/arrays/datetimelike.py

@@ -10,6 +10,7 @@
     TYPE_CHECKING,
     Any,
     Literal,
+    TypeAlias,
     Union,
     cast,
     final,
@@ -161,7 +162,8 @@
         TimedeltaArray,
     )
 
-DTScalarOrNaT = Union[DatetimeLikeScalar, NaTType]
+# underscore at end because of rule PYI043 that private types should not end with 'T'
+_DTScalarOrNaT_: TypeAlias = DatetimeLikeScalar | NaTType
 
 
 def _make_unpacked_invalid_op(op_name: str):
@@ -236,7 +238,7 @@ def _scalar_type(self) -> type[DatetimeLikeScalar]:
         """
         raise AbstractMethodError(self)
 
-    def _scalar_from_string(self, value: str) -> DTScalarOrNaT:
+    def _scalar_from_string(self, value: str) -> _DTScalarOrNaT_:
         """
         Construct a scalar type from a string.
 
@@ -257,7 +259,7 @@ def _scalar_from_string(self, value: str) -> DTScalarOrNaT:
         raise AbstractMethodError(self)
 
     def _unbox_scalar(
-        self, value: DTScalarOrNaT
+        self, value: _DTScalarOrNaT_
     ) -> np.int64 | np.datetime64 | np.timedelta64:
         """
         Unbox the integer value of a scalar `value`.
@@ -279,7 +281,7 @@ def _unbox_scalar(
         """
         raise AbstractMethodError(self)
 
-    def _check_compatible_with(self, other: DTScalarOrNaT) -> None:
+    def _check_compatible_with(self, other: _DTScalarOrNaT_) -> None:
         """
         Verify that `self` and `other` are compatible.
 
@@ -370,23 +372,23 @@ def __array__(
         return self._ndarray
 
     @overload
-    def __getitem__(self, key: ScalarIndexer) -> DTScalarOrNaT: ...
+    def __getitem__(self, key: ScalarIndexer) -> _DTScalarOrNaT_: ...
 
     @overload
     def __getitem__(
         self,
         key: SequenceIndexer | PositionalIndexerTuple,
     ) -> Self: ...
 
-    def __getitem__(self, key: PositionalIndexer2D) -> Self | DTScalarOrNaT:
+    def __getitem__(self, key: PositionalIndexer2D) -> Self | _DTScalarOrNaT_:
         """
         This getitem defers to the underlying array, which by-definition can
         only handle list-likes, slices, and integer scalars
         """
         # 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] = {}
 
@@ -216,8 +216,8 @@ def ndim(self) -> Literal[1]:
         return 1
 
     # To make mypy recognize the fields
-    _left: IntervalSide
-    _right: IntervalSide
+    _left: _IntervalSide
+    _right: _IntervalSide
     _dtype: IntervalDtype
 
     # ---------------------------------------------------------------------
@@ -234,8 +234,8 @@ def __new__(
         data = extract_array(data, extract_numpy=True)
 
         if isinstance(data, cls):
-            left: IntervalSide = data._left
-            right: IntervalSide = data._right
+            left: _IntervalSide = data._left
+            right: _IntervalSide = data._right
             closed = closed or data.closed
             dtype = IntervalDtype(left.dtype, closed=closed)
         else:
@@ -277,8 +277,8 @@ def __new__(
     @classmethod
     def _simple_new(
         cls,
-        left: IntervalSide,
-        right: IntervalSide,
+        left: _IntervalSide,
+        right: _IntervalSide,
         dtype: IntervalDtype,
     ) -> Self:
         result = IntervalMixin.__new__(cls)
@@ -296,7 +296,7 @@ def _ensure_simple_new_inputs(
         closed: IntervalClosedType | None = None,
         copy: bool = False,
         dtype: Dtype | None = None,
-    ) -> tuple[IntervalSide, IntervalSide, IntervalDtype]:
+    ) -> tuple[_IntervalSide, _IntervalSide, IntervalDtype]:
         """Ensure correctness of input parameters for cls._simple_new."""
         from pandas.core.indexes.base import ensure_index
 
@@ -704,12 +704,12 @@ def __len__(self) -> int:
         return len(self._left)
 
     @overload
-    def __getitem__(self, key: ScalarIndexer) -> IntervalOrNA: ...
+    def __getitem__(self, key: ScalarIndexer) -> _IntervalOrNA: ...
 
     @overload
     def __getitem__(self, key: SequenceIndexer) -> Self: ...
 
-    def __getitem__(self, key: PositionalIndexer) -> Self | IntervalOrNA:
+    def __getitem__(self, key: PositionalIndexer) -> Self | _IntervalOrNA:
         key = check_array_indexer(self, key)
         left = self._left[key]
         right = self._right[key]
@@ -858,7 +858,7 @@ def argsort(
             ascending=ascending, kind=kind, na_position=na_position, **kwargs
         )
 
-    def min(self, *, axis: AxisInt | None = None, skipna: bool = True) -> IntervalOrNA:
+    def min(self, *, axis: AxisInt | None = None, skipna: bool = True) -> _IntervalOrNA:
         nv.validate_minmax_axis(axis, self.ndim)
 
         if not len(self):
@@ -875,7 +875,7 @@ def min(self, *, axis: AxisInt | None = None, skipna: bool = True) -> IntervalOr
         indexer = obj.argsort()[0]
         return obj[indexer]
 
-    def max(self, *, axis: AxisInt | None = None, skipna: bool = True) -> IntervalOrNA:
+    def max(self, *, axis: AxisInt | None = None, skipna: bool = True) -> _IntervalOrNA:
         nv.validate_minmax_axis(axis, self.ndim)
 
         if not len(self):
@@ -1016,8 +1016,10 @@ def _concat_same_type(cls, to_concat: Sequence[IntervalArray]) -> Self:
             raise ValueError("Intervals must all be closed on the same side.")
         closed = closed_set.pop()
 
-        left: IntervalSide = np.concatenate([interval.left for interval in to_concat])
-        right: IntervalSide = np.concatenate([interval.right for interval in to_concat])
+        left: _IntervalSide = np.concatenate([interval.left for interval in to_concat])
+        right: _IntervalSide = np.concatenate(
+            [interval.right for interval in to_concat]
+        )
 
         left, right, dtype = cls._ensure_simple_new_inputs(left, right, closed=closed)
 
@@ -1952,7 +1954,7 @@ def isin(self, values: ArrayLike) -> npt.NDArray[np.bool_]:
         return isin(self.astype(object), values.astype(object))
 
     @property
-    def _combined(self) -> IntervalSide:
+    def _combined(self) -> _IntervalSide:
         # error: Item "ExtensionArray" of "ExtensionArray | ndarray[Any, Any]"
         # has no attribute "reshape"  [union-attr]
         left = self.left._values.reshape(-1, 1)  # type: ignore[union-attr]

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
@@ -141,7 +141,7 @@ class NamedAgg(NamedTuple):
     """
 
     column: Hashable
-    aggfunc: AggScalar
+    aggfunc: _AggScalar
 
 
 @set_module("pandas.api.typing")

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"