TYP: Fix typing errors caused by new numpy (#48850)

Author: phofl

pandas/_typing.py

@@ -65,9 +65,19 @@
 
     from pandas.io.formats.format import EngFormatter
 
+    ScalarLike_co = Union[
+        int,
+        float,
+        complex,
+        str,
+        bytes,
+        np.generic,
+    ]
+
     # numpy compatible types
-    NumpyValueArrayLike = Union[npt._ScalarLike_co, npt.ArrayLike]
-    NumpySorter = Optional[npt._ArrayLikeInt_co]
+    NumpyValueArrayLike = Union[ScalarLike_co, npt.ArrayLike]
+    # Name "npt._ArrayLikeInt_co" is not defined  [name-defined]
+    NumpySorter = Optional[npt._ArrayLikeInt_co]  # type: ignore[name-defined]
 
 else:
     npt: Any = None

pandas/core/arrays/base.py

@@ -542,7 +542,9 @@ def size(self) -> int:
         """
         The number of elements in the array.
         """
-        return np.prod(self.shape)
+        # error: Incompatible return value type (got "signedinteger[_64Bit]",
+        # expected "int")  [return-value]
+        return np.prod(self.shape)  # type: ignore[return-value]
 
     @property
     def ndim(self) -> int:

pandas/core/arrays/sparse/array.py

@@ -1426,8 +1426,7 @@ def __setstate__(self, state) -> None:
         if isinstance(state, tuple):
             # Compat for pandas < 0.24.0
             nd_state, (fill_value, sp_index) = state
-            # error: Need type annotation for "sparse_values"
-            sparse_values = np.array([])  # type: ignore[var-annotated]
+            sparse_values = np.array([])
             sparse_values.__setstate__(nd_state)
 
             self._sparse_values = sparse_values

pandas/core/base.py

@@ -84,6 +84,7 @@
         DropKeep,
         NumpySorter,
         NumpyValueArrayLike,
+        ScalarLike_co,
     )
 
     from pandas import (
@@ -1275,7 +1276,7 @@ def factorize(
     # return types  [misc]
     def searchsorted(  # type: ignore[misc]
         self,
-        value: npt._ScalarLike_co,
+        value: ScalarLike_co,
         side: Literal["left", "right"] = ...,
         sorter: NumpySorter = ...,
     ) -> np.intp:

pandas/core/dtypes/missing.py

@@ -775,10 +775,5 @@ def isna_all(arr: ArrayLike) -> bool:
         )
 
     return all(
-        # error: Argument 1 to "__call__" of "ufunc" has incompatible type
-        # "Union[ExtensionArray, Any]"; expected "Union[Union[int, float, complex, str,
-        # bytes, generic], Sequence[Union[int, float, complex, str, bytes, generic]],
-        # Sequence[Sequence[Any]], _SupportsArray]"
-        checker(arr[i : i + chunk_len]).all()  # type: ignore[arg-type]
-        for i in range(0, total_len, chunk_len)
+        checker(arr[i : i + chunk_len]).all() for i in range(0, total_len, chunk_len)
     )

pandas/core/generic.py

@@ -714,7 +714,9 @@ def size(self) -> int:
         >>> df.size
         4
         """
-        return np.prod(self.shape)
+        # error: Incompatible return value type (got "signedinteger[_64Bit]",
+        # expected "int")  [return-value]
+        return np.prod(self.shape)  # type: ignore[return-value]
 
     @overload
     def set_axis(

pandas/core/groupby/generic.py

@@ -687,7 +687,12 @@ def value_counts(
 
         # multi-index components
         codes = self.grouper.reconstructed_codes
-        codes = [rep(level_codes) for level_codes in codes] + [llab(lab, inc)]
+        # error: Incompatible types in assignment (expression has type
+        # "List[ndarray[Any, dtype[_SCT]]]",
+        # variable has type "List[ndarray[Any, dtype[signedinteger[Any]]]]")
+        codes = [  # type: ignore[assignment]
+            rep(level_codes) for level_codes in codes
+        ] + [llab(lab, inc)]
         # error: List item 0 has incompatible type "Union[ndarray[Any, Any], Index]";
         # expected "Index"
         levels = [ping.group_index for ping in self.grouper.groupings] + [

pandas/core/indexes/interval.py

@@ -1110,7 +1110,13 @@ def interval_range(
         if all(is_integer(x) for x in com.not_none(start, end, freq)):
             # np.linspace always produces float output
 
-            breaks = maybe_downcast_numeric(breaks, np.dtype("int64"))
+            # error: Argument 1 to "maybe_downcast_numeric" has incompatible type
+            # "Union[ndarray[Any, Any], TimedeltaIndex, DatetimeIndex]";
+            # expected "ndarray[Any, Any]"  [
+            breaks = maybe_downcast_numeric(
+                breaks,  # type: ignore[arg-type]
+                np.dtype("int64"),
+            )
     else:
         # delegate to the appropriate range function
         if isinstance(endpoint, Timestamp):

pandas/core/resample.py

@@ -1902,7 +1902,9 @@ def _get_period_bins(self, ax: PeriodIndex):
         # NaT handling as in pandas._lib.lib.generate_bins_dt64()
         nat_count = 0
         if memb.hasnans:
-            nat_count = np.sum(memb._isnan)
+            # error: Incompatible types in assignment (expression has type
+            # "bool_", variable has type "int")  [assignment]
+            nat_count = np.sum(memb._isnan)  # type: ignore[assignment]
             memb = memb[~memb._isnan]
 
         if not len(memb):

pandas/core/reshape/merge.py

@@ -1301,13 +1301,7 @@ def _maybe_coerce_merge_keys(self) -> None:
                         # "Union[dtype[Any], Type[Any], _SupportsDType[dtype[Any]]]"
                         casted = lk.astype(rk.dtype)  # type: ignore[arg-type]
 
-                        # Argument 1 to "__call__" of "_UFunc_Nin1_Nout1" has
-                        # incompatible type "Union[ExtensionArray, ndarray[Any, Any],
-                        # Index, Series]"; expected "Union[_SupportsArray[dtype[Any]],
-                        # _NestedSequence[_SupportsArray[dtype[Any]]], bool, int,
-                        # float, complex, str, bytes, _NestedSequence[Union[bool,
-                        # int, float, complex, str, bytes]]]"
-                        mask = ~np.isnan(lk)  # type: ignore[arg-type]
+                        mask = ~np.isnan(lk)
                         match = lk == casted
                         # error: Item "ExtensionArray" of "Union[ExtensionArray,
                         # ndarray[Any, Any], Any]" has no attribute "all"
@@ -1329,13 +1323,7 @@ def _maybe_coerce_merge_keys(self) -> None:
                         # "Union[dtype[Any], Type[Any], _SupportsDType[dtype[Any]]]"
                         casted = rk.astype(lk.dtype)  # type: ignore[arg-type]
 
-                        # Argument 1 to "__call__" of "_UFunc_Nin1_Nout1" has
-                        # incompatible type "Union[ExtensionArray, ndarray[Any, Any],
-                        # Index, Series]"; expected "Union[_SupportsArray[dtype[Any]],
-                        # _NestedSequence[_SupportsArray[dtype[Any]]], bool, int,
-                        # float, complex, str, bytes, _NestedSequence[Union[bool,
-                        # int, float, complex, str, bytes]]]"
-                        mask = ~np.isnan(rk)  # type: ignore[arg-type]
+                        mask = ~np.isnan(rk)
                         match = rk == casted
                         # error: Item "ExtensionArray" of "Union[ExtensionArray,
                         # ndarray[Any, Any], Any]" has no attribute "all"