CLN: assorted (pandas-dev#53932)

Author: jbrockmendel

pandas/_libs/lib.pyi

@@ -36,7 +36,7 @@ NoDefault = Literal[_NoDefault.no_default]
 i8max: int
 u8max: int
 
-def is_np_dtype(dtype: object, kinds: str | None = ...) -> bool: ...
+def is_np_dtype(dtype: object, kinds: str | None = ...) -> TypeGuard[np.dtype]: ...
 def item_from_zerodim(val: object) -> object: ...
 def infer_dtype(value: object, skipna: bool = ...) -> str: ...
 def is_iterator(obj: object) -> bool: ...

pandas/core/array_algos/take.py

@@ -95,7 +95,7 @@ def take_nd(
     """
     if fill_value is lib.no_default:
         fill_value = na_value_for_dtype(arr.dtype, compat=False)
-    elif isinstance(arr.dtype, np.dtype) and arr.dtype.kind in "mM":
+    elif lib.is_np_dtype(arr.dtype, "mM"):
         dtype, fill_value = maybe_promote(arr.dtype, fill_value)
         if arr.dtype != dtype:
             # EA.take is strict about returning a new object of the same type

pandas/core/arrays/timedeltas.py

@@ -217,7 +217,7 @@ def _simple_new(  # type: ignore[override]
         dtype: np.dtype[np.timedelta64] = TD64NS_DTYPE,
     ) -> Self:
         # Require td64 dtype, not unit-less, matching values.dtype
-        assert isinstance(dtype, np.dtype) and dtype.kind == "m"
+        assert lib.is_np_dtype(dtype, "m")
         assert not tslibs.is_unitless(dtype)
         assert isinstance(values, np.ndarray), type(values)
         assert dtype == values.dtype
@@ -363,7 +363,7 @@ def astype(self, dtype, copy: bool = True):
         # DatetimeLikeArrayMixin super call handles other cases
         dtype = pandas_dtype(dtype)
 
-        if isinstance(dtype, np.dtype) and dtype.kind == "m":
+        if lib.is_np_dtype(dtype, "m"):
             if dtype == self.dtype:
                 if copy:
                     return self.copy()

pandas/core/construction.py

@@ -364,19 +364,9 @@ def array(
     #   1. datetime64[ns,us,ms,s]
     #   2. timedelta64[ns,us,ms,s]
     # so that a DatetimeArray is returned.
-    if (
-        lib.is_np_dtype(dtype, "M")
-        # error: Argument 1 to "py_get_unit_from_dtype" has incompatible type
-        # "Optional[dtype[Any]]"; expected "dtype[Any]"
-        and is_supported_unit(get_unit_from_dtype(dtype))  # type: ignore[arg-type]
-    ):
+    if lib.is_np_dtype(dtype, "M") and is_supported_unit(get_unit_from_dtype(dtype)):
         return DatetimeArray._from_sequence(data, dtype=dtype, copy=copy)
-    if (
-        lib.is_np_dtype(dtype, "m")
-        # error: Argument 1 to "py_get_unit_from_dtype" has incompatible type
-        # "Optional[dtype[Any]]"; expected "dtype[Any]"
-        and is_supported_unit(get_unit_from_dtype(dtype))  # type: ignore[arg-type]
-    ):
+    if lib.is_np_dtype(dtype, "m") and is_supported_unit(get_unit_from_dtype(dtype)):
         return TimedeltaArray._from_sequence(data, dtype=dtype, copy=copy)
 
     return PandasArray._from_sequence(data, dtype=dtype, copy=copy)

pandas/core/dtypes/cast.py

@@ -1325,7 +1325,7 @@ def common_dtype_categorical_compat(
     # GH#38240
 
     # TODO: more generally, could do `not can_hold_na(dtype)`
-    if isinstance(dtype, np.dtype) and dtype.kind in "iu":
+    if lib.is_np_dtype(dtype, "iu"):
         for obj in objs:
             # We don't want to accientally allow e.g. "categorical" str here
             obj_dtype = getattr(obj, "dtype", None)
@@ -1502,7 +1502,7 @@ def construct_1d_arraylike_from_scalar(
         if length and dtype.kind in "iu" and isna(value):
             # coerce if we have nan for an integer dtype
             dtype = np.dtype("float64")
-        elif isinstance(dtype, np.dtype) and dtype.kind in "US":
+        elif lib.is_np_dtype(dtype, "US"):
             # we need to coerce to object dtype to avoid
             # to allow numpy to take our string as a scalar value
             dtype = np.dtype("object")

pandas/core/dtypes/common.py

@@ -890,9 +890,7 @@ def is_datetime64_any_dtype(arr_or_dtype) -> bool:
         tipo = _get_dtype(arr_or_dtype)
     except TypeError:
         return False
-    return (isinstance(tipo, np.dtype) and tipo.kind == "M") or isinstance(
-        tipo, DatetimeTZDtype
-    )
+    return lib.is_np_dtype(tipo, "M") or isinstance(tipo, DatetimeTZDtype)
 
 
 def is_datetime64_ns_dtype(arr_or_dtype) -> bool:
@@ -1329,9 +1327,7 @@ def is_ea_or_datetimelike_dtype(dtype: DtypeObj | None) -> bool:
     -----
     Checks only for dtype objects, not dtype-castable strings or types.
     """
-    return isinstance(dtype, ExtensionDtype) or (
-        isinstance(dtype, np.dtype) and dtype.kind in "mM"
-    )
+    return isinstance(dtype, ExtensionDtype) or (lib.is_np_dtype(dtype, "mM"))
 
 
 def is_complex_dtype(arr_or_dtype) -> bool:

pandas/core/dtypes/missing.py

@@ -749,10 +749,10 @@ def isna_all(arr: ArrayLike) -> bool:
     chunk_len = max(total_len // 40, 1000)
 
     dtype = arr.dtype
-    if dtype.kind == "f" and isinstance(dtype, np.dtype):
+    if lib.is_np_dtype(dtype, "f"):
         checker = nan_checker
 
-    elif (isinstance(dtype, np.dtype) and dtype.kind in "mM") or isinstance(
+    elif (lib.is_np_dtype(dtype, "mM")) or isinstance(
         dtype, (DatetimeTZDtype, PeriodDtype)
     ):
         # error: Incompatible types in assignment (expression has type

pandas/core/interchange/utils.py

@@ -135,7 +135,7 @@ def dtype_to_arrow_c_fmt(dtype: DtypeObj) -> str:
     if lib.is_np_dtype(dtype, "M"):
         # Selecting the first char of resolution string:
         # dtype.str -> '<M8[ns]'
-        resolution = re.findall(r"\[(.*)\]", typing.cast(np.dtype, dtype).str)[0][:1]
+        resolution = re.findall(r"\[(.*)\]", dtype.str)[0][:1]
         return ArrowCTypes.TIMESTAMP.format(resolution=resolution, tz="")
 
     raise NotImplementedError(

pandas/core/internals/array_manager.py

@@ -220,7 +220,7 @@ def apply(
         assert "filter" not in kwargs
 
         align_keys = align_keys or []
-        result_arrays: list[np.ndarray] = []
+        result_arrays: list[ArrayLike] = []
         # fillna: Series/DataFrame is responsible for making sure value is aligned
 
         aligned_args = {k: kwargs[k] for k in align_keys}
@@ -247,16 +247,10 @@ def apply(
             else:
                 applied = getattr(arr, f)(**kwargs)
 
-            # if not isinstance(applied, ExtensionArray):
-            #     # TODO not all EA operations return new EAs (eg astype)
-            #     applied = array(applied)
             result_arrays.append(applied)
 
         new_axes = self._axes
-
-        # error: Argument 1 to "ArrayManager" has incompatible type "List[ndarray]";
-        # expected "List[Union[ndarray, ExtensionArray]]"
-        return type(self)(result_arrays, new_axes)  # type: ignore[arg-type]
+        return type(self)(result_arrays, new_axes)
 
     def apply_with_block(self, f, align_keys=None, **kwargs) -> Self:
         # switch axis to follow BlockManager logic
@@ -1319,7 +1313,7 @@ def concat_arrays(to_concat: list) -> ArrayLike:
 
     if single_dtype:
         target_dtype = to_concat_no_proxy[0].dtype
-    elif all(x.kind in "iub" and isinstance(x, np.dtype) for x in dtypes):
+    elif all(lib.is_np_dtype(x, "iub") for x in dtypes):
         # GH#42092
         target_dtype = np_find_common_type(*dtypes)
     else:

pandas/core/internals/blocks.py

@@ -463,6 +463,7 @@ def _downcast_2d(self, dtype, using_cow: bool = False) -> list[Block]:
         refs = self.refs if using_cow and new_values is self.values else None
         return [self.make_block(new_values, refs=refs)]
 
+    @final
     def convert(
         self,
         *,
@@ -951,6 +952,7 @@ def set_inplace(self, locs, values: ArrayLike, copy: bool = False) -> None:
             self.values = self.values.copy()
         self.values[locs] = values
 
+    @final
     def take_nd(
         self,
         indexer: npt.NDArray[np.intp],
@@ -1632,6 +1634,7 @@ class EABackedBlock(Block):
 
     values: ExtensionArray
 
+    @final
     def shift(self, periods: int, fill_value: Any = None) -> list[Block]:
         """
         Shift the block by `periods`.
@@ -1644,6 +1647,7 @@ def shift(self, periods: int, fill_value: Any = None) -> list[Block]:
         new_values = self.values.T.shift(periods=periods, fill_value=fill_value).T
         return [self.make_block_same_class(new_values)]
 
+    @final
     def setitem(self, indexer, value, using_cow: bool = False):
         """
         Attempt self.values[indexer] = value, possibly creating a new array.
@@ -1702,6 +1706,7 @@ def setitem(self, indexer, value, using_cow: bool = False):
         else:
             return self
 
+    @final
     def where(
         self, other, cond, _downcast: str | bool = "infer", using_cow: bool = False
     ) -> list[Block]:
@@ -1772,6 +1777,7 @@ def where(
         nb = self.make_block_same_class(res_values)
         return [nb]
 
+    @final
     def putmask(self, mask, new, using_cow: bool = False) -> list[Block]:
         """
         See Block.putmask.__doc__
@@ -1839,6 +1845,7 @@ def putmask(self, mask, new, using_cow: bool = False) -> list[Block]:
 
         return [self]
 
+    @final
     def delete(self, loc) -> list[Block]:
         # This will be unnecessary if/when __array_function__ is implemented
         if self.ndim == 1:
@@ -1850,10 +1857,12 @@ def delete(self, loc) -> list[Block]:
             return []
         return super().delete(loc)
 
+    @final
     @cache_readonly
     def array_values(self) -> ExtensionArray:
         return self.values
 
+    @final
     def get_values(self, dtype: DtypeObj | None = None) -> np.ndarray:
         """
         return object dtype as boxed values, such as Timestamps/Timedelta

pandas/core/internals/managers.py

@@ -1607,11 +1607,7 @@ def as_array(
             if na_value is not lib.no_default:
                 # We want to copy when na_value is provided to avoid
                 # mutating the original object
-                if (
-                    isinstance(blk.dtype, np.dtype)
-                    and blk.dtype.kind == "f"
-                    and passed_nan
-                ):
+                if lib.is_np_dtype(blk.dtype, "f") and passed_nan:
                     # We are already numpy-float and na_value=np.nan
                     pass
                 else:

pandas/core/tools/datetimes.py

@@ -404,7 +404,6 @@ def _convert_listlike_datetimes(
         return arg
 
     elif lib.is_np_dtype(arg_dtype, "M"):
-        arg_dtype = cast(np.dtype, arg_dtype)
         if not is_supported_unit(get_unit_from_dtype(arg_dtype)):
             # We go to closest supported reso, i.e. "s"
             arg = astype_overflowsafe(

pandas/tests/indexes/test_setops.py

@@ -8,6 +8,8 @@
 import numpy as np
 import pytest
 
+from pandas._libs import lib
+
 from pandas.core.dtypes.cast import find_common_type
 
 from pandas import (
@@ -67,18 +69,8 @@ def test_union_different_types(index_flat, index_flat2, request):
     warn = None
     if not len(idx1) or not len(idx2):
         pass
-    elif (
-        idx1.dtype.kind == "c"
-        and (
-            idx2.dtype.kind not in ["i", "u", "f", "c"]
-            or not isinstance(idx2.dtype, np.dtype)
-        )
-    ) or (
-        idx2.dtype.kind == "c"
-        and (
-            idx1.dtype.kind not in ["i", "u", "f", "c"]
-            or not isinstance(idx1.dtype, np.dtype)
-        )
+    elif (idx1.dtype.kind == "c" and (not lib.is_np_dtype(idx2.dtype, "iufc"))) or (
+        idx2.dtype.kind == "c" and (not lib.is_np_dtype(idx1.dtype, "iufc"))
     ):
         # complex objects non-sortable
         warn = RuntimeWarning

pandas/tests/reshape/merge/test_merge_asof.py

@@ -1518,7 +1518,7 @@ def test_merge_asof_index_behavior(kwargs):
     tm.assert_frame_equal(result, expected)
 
 
-def test_merge_asof_numeri_column_in_index():
+def test_merge_asof_numeric_column_in_index():
     # GH#34488
     left = pd.DataFrame({"b": [10, 11, 12]}, index=Index([1, 2, 3], name="a"))
     right = pd.DataFrame({"c": [20, 21, 22]}, index=Index([0, 2, 3], name="a"))
@@ -1528,7 +1528,7 @@ def test_merge_asof_numeri_column_in_index():
     tm.assert_frame_equal(result, expected)
 
 
-def test_merge_asof_numeri_column_in_multiindex():
+def test_merge_asof_numeric_column_in_multiindex():
     # GH#34488
     left = pd.DataFrame(
         {"b": [10, 11, 12]},