TYP: Add ignores for numpy 2.2 updates (#61265)

* TYP: Add ignores for numpy 2.2 updates

* fix tests and plotting

* ignore pyright error

Author: mroeschke

pandas/core/algorithms.py

@@ -215,7 +215,7 @@ def _reconstruct_data(
         values = cls._from_sequence(values, dtype=dtype)  # type: ignore[assignment]
 
     else:
-        values = values.astype(dtype, copy=False)
+        values = values.astype(dtype, copy=False)  # type: ignore[assignment]
 
     return values
 

pandas/core/array_algos/quantile.py

@@ -102,7 +102,7 @@ def quantile_with_mask(
             interpolation=interpolation,
         )
 
-        result = np.asarray(result)
+        result = np.asarray(result)  # type: ignore[assignment]
         result = result.T
 
     return result
@@ -196,7 +196,7 @@ def _nanquantile(
         # Caller is responsible for ensuring mask shape match
         assert mask.shape == values.shape
         result = [
-            _nanquantile_1d(val, m, qs, na_value, interpolation=interpolation)
+            _nanquantile_1d(val, m, qs, na_value, interpolation=interpolation)  # type: ignore[arg-type]
             for (val, m) in zip(list(values), list(mask))
         ]
         if values.dtype.kind == "f":

pandas/core/arrays/_mixins.py

@@ -142,18 +142,12 @@ def view(self, dtype: Dtype | None = None) -> ArrayLike:
 
             dt64_values = arr.view(dtype)
             return DatetimeArray._simple_new(dt64_values, dtype=dtype)
-
         elif lib.is_np_dtype(dtype, "m") and is_supported_dtype(dtype):
             from pandas.core.arrays import TimedeltaArray
 
             td64_values = arr.view(dtype)
             return TimedeltaArray._simple_new(td64_values, dtype=dtype)
-
-        # error: Argument "dtype" to "view" of "_ArrayOrScalarCommon" has incompatible
-        # type "Union[ExtensionDtype, dtype[Any]]"; expected "Union[dtype[Any], None,
-        # type, _SupportsDType, str, Union[Tuple[Any, int], Tuple[Any, Union[int,
-        # Sequence[int]]], List[Any], _DTypeDict, Tuple[Any, Any]]]"
-        return arr.view(dtype=dtype)  # type: ignore[arg-type]
+        return arr.view(dtype=dtype)
 
     def take(
         self,

pandas/core/arrays/arrow/_arrow_utils.py

@@ -44,7 +44,7 @@ def pyarrow_array_to_numpy_and_mask(
         mask = pyarrow.BooleanArray.from_buffers(
             pyarrow.bool_(), len(arr), [None, bitmask], offset=arr.offset
         )
-        mask = np.asarray(mask)
+        mask = np.asarray(mask)  # type: ignore[assignment]
     else:
         mask = np.ones(len(arr), dtype=bool)
     return data, mask

pandas/core/arrays/arrow/array.py

@@ -2540,7 +2540,7 @@ def _str_get_dummies(self, sep: str = "|", dtype: NpDtype | None = None):
             dummies_dtype = np.bool_
         dummies = np.zeros(n_rows * n_cols, dtype=dummies_dtype)
         dummies[indices] = True
-        dummies = dummies.reshape((n_rows, n_cols))
+        dummies = dummies.reshape((n_rows, n_cols))  # type: ignore[assignment]
         result = type(self)(pa.array(list(dummies)))
         return result, uniques_sorted.to_pylist()
 

pandas/core/arrays/base.py

@@ -596,7 +596,7 @@ def to_numpy(
         if copy or na_value is not lib.no_default:
             result = result.copy()
         if na_value is not lib.no_default:
-            result[self.isna()] = na_value
+            result[self.isna()] = na_value  # type: ignore[index]
         return result
 
     # ------------------------------------------------------------------------

pandas/core/arrays/categorical.py

@@ -1853,7 +1853,7 @@ def value_counts(self, dropna: bool = True) -> Series:
             count = np.bincount(obs, minlength=ncat or 0)
         else:
             count = np.bincount(np.where(mask, code, ncat))
-            ix = np.append(ix, -1)
+            ix = np.append(ix, -1)  # type: ignore[assignment]
 
         ix = coerce_indexer_dtype(ix, self.dtype.categories)
         ix_categorical = self._from_backing_data(ix)

pandas/core/arrays/datetimelike.py

@@ -2394,7 +2394,7 @@ def take(
         )
 
         indices = np.asarray(indices, dtype=np.intp)
-        maybe_slice = lib.maybe_indices_to_slice(indices, len(self))
+        maybe_slice = lib.maybe_indices_to_slice(indices, len(self))  # type: ignore[arg-type]
 
         if isinstance(maybe_slice, slice):
             freq = self._get_getitem_freq(maybe_slice)

pandas/core/arrays/datetimes.py

@@ -331,7 +331,7 @@ def _simple_new(  # type: ignore[override]
         else:
             # DatetimeTZDtype. If we have e.g. DatetimeTZDtype[us, UTC],
             #  then values.dtype should be M8[us].
-            assert dtype._creso == get_unit_from_dtype(values.dtype)
+            assert dtype._creso == get_unit_from_dtype(values.dtype)  # type: ignore[union-attr]
 
         result = super()._simple_new(values, dtype)
         result._freq = freq
@@ -542,7 +542,7 @@ def _unbox_scalar(self, value) -> np.datetime64:
             raise ValueError("'value' should be a Timestamp.")
         self._check_compatible_with(value)
         if value is NaT:
-            return np.datetime64(value._value, self.unit)
+            return np.datetime64(value._value, self.unit)  # type: ignore[call-overload]
         else:
             return value.as_unit(self.unit, round_ok=False).asm8
 
@@ -813,10 +813,7 @@ def _add_offset(self, offset: BaseOffset) -> Self:
         try:
             res_values = offset._apply_array(values._ndarray)
             if res_values.dtype.kind == "i":
-                # error: Argument 1 to "view" of "ndarray" has incompatible type
-                # "dtype[datetime64] | DatetimeTZDtype"; expected
-                # "dtype[Any] | type[Any] | _SupportsDType[dtype[Any]]"
-                res_values = res_values.view(values.dtype)  # type: ignore[arg-type]
+                res_values = res_values.view(values.dtype)
         except NotImplementedError:
             if get_option("performance_warnings"):
                 warnings.warn(

pandas/core/arrays/masked.py

@@ -515,7 +515,7 @@ def tolist(self) -> list:
         if self.ndim > 1:
             return [x.tolist() for x in self]
         dtype = None if self._hasna else self._data.dtype
-        return self.to_numpy(dtype=dtype, na_value=libmissing.NA).tolist()
+        return self.to_numpy(dtype=dtype, na_value=libmissing.NA).tolist()  # type: ignore[return-value]
 
     @overload
     def astype(self, dtype: npt.DTypeLike, copy: bool = ...) -> np.ndarray: ...
@@ -1497,10 +1497,10 @@ def all(
         result = values.all(axis=axis)
 
         if skipna:
-            return result
+            return result  # type: ignore[return-value]
         else:
             if not result or len(self) == 0 or not self._mask.any():
-                return result
+                return result  # type: ignore[return-value]
             else:
                 return self.dtype.na_value
 

pandas/core/arrays/sparse/scipy_sparse.py

@@ -79,7 +79,7 @@ def _levels_to_axis(
         ax_coords = codes[valid_ilocs]
 
     ax_labels = ax_labels.tolist()
-    return ax_coords, ax_labels
+    return ax_coords, ax_labels  # pyright: ignore[reportReturnType]
 
 
 def _to_ijv(

pandas/core/arrays/timedeltas.py

@@ -325,7 +325,7 @@ def _unbox_scalar(self, value) -> np.timedelta64:
             raise ValueError("'value' should be a Timedelta.")
         self._check_compatible_with(value)
         if value is NaT:
-            return np.timedelta64(value._value, self.unit)
+            return np.timedelta64(value._value, self.unit)  # type: ignore[call-overload]
         else:
             return value.as_unit(self.unit, round_ok=False).asm8
 

pandas/core/base.py

@@ -875,7 +875,7 @@ def tolist(self) -> list:
         >>> idx.to_list()
         [1, 2, 3]
         """
-        return self._values.tolist()
+        return self._values.tolist()  # type: ignore[return-value]
 
     to_list = tolist
 

pandas/core/groupby/generic.py

@@ -2142,7 +2142,7 @@ def _wrap_applied_output_series(
 
         if stacked_values.dtype == object:
             # We'll have the DataFrame constructor do inference
-            stacked_values = stacked_values.tolist()
+            stacked_values = stacked_values.tolist()  # type: ignore[assignment]
         result = self.obj._constructor(stacked_values, index=index, columns=columns)
 
         if not self.as_index:

pandas/core/groupby/groupby.py

@@ -1878,7 +1878,7 @@ def _apply_filter(self, indices, dropna):
             mask.fill(False)
             mask[indices.astype(int)] = True
             # mask fails to broadcast when passed to where; broadcast manually.
-            mask = np.tile(mask, list(self._selected_obj.shape[1:]) + [1]).T
+            mask = np.tile(mask, list(self._selected_obj.shape[1:]) + [1]).T  # type: ignore[assignment]
             filtered = self._selected_obj.where(mask)  # Fill with NaNs.
         return filtered
 
@@ -4441,11 +4441,11 @@ def blk_func(values: ArrayLike) -> ArrayLike:
                     )
 
             if vals.ndim == 1:
-                out = out.ravel("K")
+                out = out.ravel("K")  # type: ignore[assignment]
                 if result_mask is not None:
-                    result_mask = result_mask.ravel("K")
+                    result_mask = result_mask.ravel("K")  # type: ignore[assignment]
             else:
-                out = out.reshape(ncols, ngroups * nqs)
+                out = out.reshape(ncols, ngroups * nqs)  # type: ignore[assignment]
 
             return post_processor(out, inference, result_mask, orig_vals)
 

pandas/core/groupby/ops.py

@@ -1131,7 +1131,7 @@ def get_iterator(self, data: NDFrame):
         """
         slicer = lambda start, edge: data.iloc[start:edge]
 
-        start = 0
+        start: np.int64 | int = 0
         for edge, label in zip(self.bins, self.binlabels):
             if label is not NaT:
                 yield label, slicer(start, edge)
@@ -1144,7 +1144,7 @@ def get_iterator(self, data: NDFrame):
     def indices(self):
         indices = collections.defaultdict(list)
 
-        i = 0
+        i: np.int64 | int = 0
         for label, bin in zip(self.binlabels, self.bins):
             if i < bin:
                 if label is not NaT:

pandas/core/indexers/objects.py

@@ -131,8 +131,8 @@ def get_window_bounds(
         if closed in ["left", "neither"]:
             end -= 1
 
-        end = np.clip(end, 0, num_values)
-        start = np.clip(start, 0, num_values)
+        end = np.clip(end, 0, num_values)  # type: ignore[assignment]
+        start = np.clip(start, 0, num_values)  # type: ignore[assignment]
 
         return start, end
 
@@ -402,7 +402,7 @@ def get_window_bounds(
         start = np.arange(0, num_values, step, dtype="int64")
         end = start + self.window_size
         if self.window_size:
-            end = np.clip(end, 0, num_values)
+            end = np.clip(end, 0, num_values)  # type: ignore[assignment]
 
         return start, end
 
@@ -488,7 +488,7 @@ def get_window_bounds(
             )
             window_indices_start += len(indices)
             # Extend as we'll be slicing window like [start, end)
-            window_indices = np.append(window_indices, [window_indices[-1] + 1]).astype(
+            window_indices = np.append(window_indices, [window_indices[-1] + 1]).astype(  # type: ignore[assignment]
                 np.int64, copy=False
             )
             start_arrays.append(window_indices.take(ensure_platform_int(start)))

pandas/core/indexes/interval.py

@@ -1279,14 +1279,7 @@ def interval_range(
             breaks = np.linspace(start, end, periods)
         if all(is_integer(x) for x in com.not_none(start, end, freq)):
             # np.linspace always produces float output
-
-            # 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]
-                dtype,
-            )
+            breaks = maybe_downcast_numeric(breaks, dtype)
     else:
         # delegate to the appropriate range function
         if isinstance(endpoint, Timestamp):

pandas/core/internals/blocks.py

@@ -2094,7 +2094,7 @@ def _unstack(
                 self.values.take(
                     indices, allow_fill=needs_masking[i], fill_value=fill_value
                 ),
-                BlockPlacement(place),
+                BlockPlacement(place),  # type: ignore[arg-type]
                 ndim=2,
             )
             for i, (indices, place) in enumerate(zip(new_values, new_placement))

pandas/core/internals/construction.py

@@ -634,7 +634,7 @@ def reorder_arrays(
                     arr = np.empty(length, dtype=object)
                     arr.fill(np.nan)
                 else:
-                    arr = arrays[k]
+                    arr = arrays[k]  # type: ignore[assignment]
                 new_arrays.append(arr)
 
             arrays = new_arrays

pandas/core/missing.py

@@ -241,7 +241,8 @@ def find_valid_index(how: str, is_valid: npt.NDArray[np.bool_]) -> int | None:
         return None
 
     if is_valid.ndim == 2:
-        is_valid = is_valid.any(axis=1)  # reduce axis 1
+        # reduce axis 1
+        is_valid = is_valid.any(axis=1)  # type: ignore[assignment]
 
     if how == "first":
         idxpos = is_valid[::].argmax()
@@ -404,10 +405,7 @@ def func(yvalues: np.ndarray) -> None:
             **kwargs,
         )
 
-    # error: No overload variant of "apply_along_axis" matches
-    # argument types "Callable[[ndarray[Any, Any]], None]",
-    # "int", "ndarray[Any, Any]"
-    np.apply_along_axis(func, axis, data)  # type: ignore[call-overload]
+    np.apply_along_axis(func, axis, data)
 
 
 def _index_to_interp_indices(index: Index, method: str) -> np.ndarray:

pandas/core/reshape/encoding.py

@@ -357,7 +357,7 @@ def get_empty_frame(data) -> DataFrame:
 
         if drop_first:
             # remove first GH12042
-            dummy_mat = dummy_mat[:, 1:]
+            dummy_mat = dummy_mat[:, 1:]  # type: ignore[assignment]
             dummy_cols = dummy_cols[1:]
         return DataFrame(dummy_mat, index=index, columns=dummy_cols, dtype=_dtype)
 

pandas/core/reshape/merge.py

@@ -2921,9 +2921,7 @@ def _convert_arrays_and_get_rizer_klass(
                 lk = lk.astype(dtype, copy=False)
                 rk = rk.astype(dtype, copy=False)
         if isinstance(lk, BaseMaskedArray):
-            #  Invalid index type "type" for "Dict[Type[object], Type[Factorizer]]";
-            #  expected type "Type[object]"
-            klass = _factorizers[lk.dtype.type]  # type: ignore[index]
+            klass = _factorizers[lk.dtype.type]
         elif isinstance(lk.dtype, ArrowDtype):
             klass = _factorizers[lk.dtype.numpy_dtype.type]
         else:

pandas/core/sorting.py

@@ -476,7 +476,7 @@ def nargminmax(values: ExtensionArray, method: str, axis: AxisInt = 0):
                 zipped = zip(arr_values, mask)
             else:
                 zipped = zip(arr_values.T, mask.T)
-            return np.array([_nanargminmax(v, m, func) for v, m in zipped])
+            return np.array([_nanargminmax(v, m, func) for v, m in zipped])  # type: ignore[arg-type]
         return func(arr_values, axis=axis)
 
     return _nanargminmax(arr_values, mask, func)

pandas/io/formats/format.py

@@ -1495,7 +1495,7 @@ def _format_strings(self) -> list[str]:
         fmt_values = values._format_native_types(
             na_rep=self.nat_rep, date_format=self.date_format
         )
-        return fmt_values.tolist()
+        return fmt_values.tolist()  # type: ignore[return-value]
 
 
 class _ExtensionArrayFormatter(_GenericArrayFormatter):

pandas/io/parsers/python_parser.py

@@ -1468,7 +1468,7 @@ def detect_colspecs(
         shifted[0] = 0
         edges = np.where((mask ^ shifted) == 1)[0]
         edge_pairs = list(zip(edges[::2], edges[1::2]))
-        return edge_pairs
+        return edge_pairs  # type: ignore[return-value]
 
     def __next__(self) -> list[str]:
         # Argument 1 to "next" has incompatible type "Union[IO[str],

pandas/plotting/_matplotlib/style.py

@@ -273,7 +273,7 @@ def _random_color(column: int) -> list[float]:
     """Get a random color represented as a list of length 3"""
     # GH17525 use common._random_state to avoid resetting the seed
     rs = com.random_state(column)
-    return rs.rand(3).tolist()
+    return rs.rand(3).tolist()  # type: ignore[return-value]
 
 
 def _is_single_string_color(color: Color) -> bool:

pandas/tests/dtypes/test_missing.py

@@ -769,8 +769,8 @@ def test_empty_like(self):
         np.datetime64("NaT"),
         np.timedelta64("NaT"),
     ]
-    + [np.datetime64("NaT", unit) for unit in m8_units]
-    + [np.timedelta64("NaT", unit) for unit in m8_units]
+    + [np.datetime64("NaT", unit) for unit in m8_units]  # type: ignore[call-overload]
+    + [np.timedelta64("NaT", unit) for unit in m8_units]  # type: ignore[call-overload]
 )
 
 inf_vals = [