Backport PR #48850 on branch 1.5.x (TYP: Fix typing errors caused by new numpy) (#48859)

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

@@ -540,7 +540,9 @@ 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/accessor.py

@@ -369,7 +369,8 @@ def density(self) -> float:
         Ratio of non-sparse points to total (dense) data points.
         """
         tmp = np.mean([column.array.density for _, column in self._parent.items()])
-        return tmp
+        # error: Expression of type "floating" cannot be assigned to return type "float"
+        return tmp  # pyright: ignore[reportGeneralTypeIssues]
 
     @staticmethod
     def _prep_index(data, index, columns):

pandas/core/arrays/sparse/array.py

@@ -1424,8 +1424,7 @@ 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

@@ -80,6 +80,7 @@
     from pandas._typing import (
         NumpySorter,
         NumpyValueArrayLike,
+        ScalarLike_co,
     )
 
     from pandas import (
@@ -1267,7 +1268,7 @@ 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

@@ -707,7 +707,9 @@ 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

@@ -691,7 +691,12 @@ 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

@@ -1886,7 +1886,9 @@ 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/util.py

@@ -55,7 +55,15 @@ def cartesian_product(X) -> list[np.ndarray]:
         # if any factor is empty, the cartesian product is empty
         b = np.zeros_like(cumprodX)
 
-    return [tile_compat(np.repeat(x, b[i]), np.product(a[i])) for i, x in enumerate(X)]
+    # error: Argument of type "int_" cannot be assigned to parameter "num" of
+    # type "int" in function "tile_compat"
+    return [
+        tile_compat(
+            np.repeat(x, b[i]),
+            np.product(a[i]),  # pyright: ignore[reportGeneralTypeIssues]
+        )
+        for i, x in enumerate(X)
+    ]
 
 
 def tile_compat(arr: NumpyIndexT, num: int) -> NumpyIndexT: