CI: Upgrade mypy to 1.17.1 and pyright to 1.1.404

.pre-commit-config.yaml

@@ -121,7 +121,7 @@ repos:
         types: [python]
         stages: [manual]
         additional_dependencies: &pyright_dependencies
-        - [email protected].383
+        - [email protected].404
     -   id: pyright
         # note: assumes python env is setup and activated
         name: pyright reportGeneralTypeIssues

environment.yml

@@ -77,7 +77,7 @@ dependencies:
 
   # code checks
   - flake8=7.1.0  # run in subprocess over docstring examples
-  - mypy=1.13.0  # pre-commit uses locally installed mypy
+  - mypy=1.17.1  # pre-commit uses locally installed mypy
   - tokenize-rt  # scripts/check_for_inconsistent_pandas_namespace.py
   - pre-commit>=4.2.0
 

pandas/_libs/tslibs/dtypes.pyi

@@ -28,33 +28,35 @@ class PeriodDtypeBase:
     def _td64_unit(self) -> str: ...
 
 class FreqGroup(Enum):
-    FR_ANN: int
-    FR_QTR: int
-    FR_MTH: int
-    FR_WK: int
-    FR_BUS: int
-    FR_DAY: int
-    FR_HR: int
-    FR_MIN: int
-    FR_SEC: int
-    FR_MS: int
-    FR_US: int
-    FR_NS: int
-    FR_UND: int
+    _value_: int
+    FR_ANN = ...
+    FR_QTR = ...
+    FR_MTH = ...
+    FR_WK = ...
+    FR_BUS = ...
+    FR_DAY = ...
+    FR_HR = ...
+    FR_MIN = ...
+    FR_SEC = ...
+    FR_MS = ...
+    FR_US = ...
+    FR_NS = ...
+    FR_UND = ...
     @staticmethod
     def from_period_dtype_code(code: int) -> FreqGroup: ...
 
 class Resolution(Enum):
-    RESO_NS: int
-    RESO_US: int
-    RESO_MS: int
-    RESO_SEC: int
-    RESO_MIN: int
-    RESO_HR: int
-    RESO_DAY: int
-    RESO_MTH: int
-    RESO_QTR: int
-    RESO_YR: int
+    _value_: int
+    RESO_NS = ...
+    RESO_US = ...
+    RESO_MS = ...
+    RESO_SEC = ...
+    RESO_MIN = ...
+    RESO_HR = ...
+    RESO_DAY = ...
+    RESO_MTH = ...
+    RESO_QTR = ...
+    RESO_YR = ...
     def __lt__(self, other: Resolution) -> bool: ...
     def __ge__(self, other: Resolution) -> bool: ...
     @property
@@ -67,17 +69,18 @@ class Resolution(Enum):
     def attr_abbrev(self) -> str: ...
 
 class NpyDatetimeUnit(Enum):
-    NPY_FR_Y: int
-    NPY_FR_M: int
-    NPY_FR_W: int
-    NPY_FR_D: int
-    NPY_FR_h: int
-    NPY_FR_m: int
-    NPY_FR_s: int
-    NPY_FR_ms: int
-    NPY_FR_us: int
-    NPY_FR_ns: int
-    NPY_FR_ps: int
-    NPY_FR_fs: int
-    NPY_FR_as: int
-    NPY_FR_GENERIC: int
+    _value_: int
+    NPY_FR_Y = ...
+    NPY_FR_M = ...
+    NPY_FR_W = ...
+    NPY_FR_D = ...
+    NPY_FR_h = ...
+    NPY_FR_m = ...
+    NPY_FR_s = ...
+    NPY_FR_ms = ...
+    NPY_FR_us = ...
+    NPY_FR_ns = ...
+    NPY_FR_ps = ...
+    NPY_FR_fs = ...
+    NPY_FR_as = ...
+    NPY_FR_GENERIC = ...

pandas/_testing/__init__.py

@@ -348,8 +348,9 @@ class SubclassedDataFrame(DataFrame):
     def _constructor(self):
         return lambda *args, **kwargs: SubclassedDataFrame(*args, **kwargs)
 
+    # error: Cannot override writeable attribute with read-only property
     @property
-    def _constructor_sliced(self):
+    def _constructor_sliced(self):  # type: ignore[override]
         return lambda *args, **kwargs: SubclassedSeries(*args, **kwargs)
 
 

pandas/_testing/_io.py

@@ -81,12 +81,12 @@ def round_trip_pathlib(writer, reader, path: str | None = None):
     if path is None:
         path = "___pathlib___"
     with ensure_clean(path) as path:
-        writer(Path(path))  # type: ignore[arg-type]
-        obj = reader(Path(path))  # type: ignore[arg-type]
+        writer(Path(path))
+        obj = reader(Path(path))
     return obj
 
 
-def write_to_compressed(compression, path, data, dest: str = "test") -> None:
+def write_to_compressed(compression, path: str, data, dest: str = "test") -> None:
     """
     Write data to a compressed file.
 
@@ -138,5 +138,9 @@ def write_to_compressed(compression, path, data, dest: str = "test") -> None:
     else:
         raise ValueError(f"Unrecognized compression type: {compression}")
 
-    with compress_method(path, mode=mode) as f:
+    # error: No overload variant of "ZipFile" matches argument types "str", "str"
+    # error: No overload variant of "BZ2File" matches argument types "str", "str"
+    # error: Argument "mode" to "TarFile" has incompatible type "str";
+    #  expected "Literal['r', 'a', 'w', 'x']
+    with compress_method(path, mode=mode) as f:  # type: ignore[call-overload, arg-type]
         getattr(f, method)(*args)

pandas/core/_numba/executor.py

@@ -87,7 +87,11 @@ def column_looper(
     else:
 
         @numba.jit(nopython=nopython, nogil=nogil, parallel=parallel)
-        def column_looper(
+        # error: Incompatible redefinition (redefinition with type
+        # "Callable[[ndarray[Any, Any], ndarray[Any, Any], ndarray[Any, Any],
+        # int, VarArg(Any)], Any]", original type "Callable[[ndarray[Any, Any],
+        # ndarray[Any, Any], int, int, VarArg(Any)], Any]")
+        def column_looper(  # type: ignore[misc]
             values: np.ndarray,
             start: np.ndarray,
             end: np.ndarray,

pandas/core/algorithms.py

@@ -216,7 +216,7 @@ def _reconstruct_data(
         values = cls._from_sequence(values, dtype=dtype)  # type: ignore[assignment]
 
     else:
-        values = values.astype(dtype, copy=False)  # type: ignore[assignment]
+        values = values.astype(dtype, copy=False)
 
     return values
 
@@ -904,7 +904,10 @@ def value_counts_internal(
                 .size()
             )
             result.index.names = values.names
-            counts = result._values
+            # error: Incompatible types in assignment (expression has type
+            # "ndarray[Any, Any] | DatetimeArray | TimedeltaArray | PeriodArray | Any",
+            # variable has type "ndarray[tuple[int, ...], dtype[Any]]")
+            counts = result._values  # type: ignore[assignment]
 
         else:
             values = _ensure_arraylike(values, func_name="value_counts")
@@ -1311,7 +1314,7 @@ def searchsorted(
 _diff_special = {"float64", "float32", "int64", "int32", "int16", "int8"}
 
 
-def diff(arr, n: int, axis: AxisInt = 0):
+def diff(arr, n: int | float | np.integer, axis: AxisInt = 0):
     """
     difference of n between self,
     analogous to s-s.shift(n)
@@ -1400,7 +1403,7 @@ def diff(arr, n: int, axis: AxisInt = 0):
     if arr.dtype.name in _diff_special:
         # TODO: can diff_2d dtype specialization troubles be fixed by defining
         #  out_arr inside diff_2d?
-        algos.diff_2d(arr, out_arr, n, axis, datetimelike=is_timedelta)
+        algos.diff_2d(arr, out_arr, int(n), axis, datetimelike=is_timedelta)
     else:
         # To keep mypy happy, _res_indexer is a list while res_indexer is
         #  a tuple, ditto for lag_indexer.

pandas/core/apply.py

@@ -1645,7 +1645,7 @@ def agg_or_apply_dict_like(
         assert op_name in ["agg", "apply"]
 
         obj = self.obj
-        kwargs = {}
+        kwargs: dict[str, Any] = {}
         if op_name == "apply":
             by_row = "_compat" if self.by_row else False
             kwargs.update({"by_row": by_row})
@@ -2012,7 +2012,8 @@ def _managle_lambda_list(aggfuncs: Sequence[Any]) -> Sequence[Any]:
     for aggfunc in aggfuncs:
         if com.get_callable_name(aggfunc) == "<lambda>":
             aggfunc = partial(aggfunc)
-            aggfunc.__name__ = f"<lambda_{i}>"
+            # error: "partial[Any]" has no attribute "__name__"; maybe "__new__"?
+            aggfunc.__name__ = f"<lambda_{i}>"  # type: ignore[attr-defined]
             i += 1
         mangled_aggfuncs.append(aggfunc)
 

pandas/core/array_algos/quantile.py

@@ -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)  # type: ignore[arg-type]
+            _nanquantile_1d(val, m, qs, na_value, interpolation=interpolation)
             for (val, m) in zip(list(values), list(mask))
         ]
         if values.dtype.kind == "f":

pandas/core/arrays/_mixins.py

@@ -88,9 +88,7 @@ def method(self, *args, **kwargs):
     return cast(F, method)
 
 
-# error: Definition of "delete/ravel/T/repeat/copy" in base class "NDArrayBacked"
-# is incompatible with definition in base class "ExtensionArray"
-class NDArrayBackedExtensionArray(NDArrayBacked, ExtensionArray):  # type: ignore[misc]
+class NDArrayBackedExtensionArray(NDArrayBacked, ExtensionArray):
     """
     ExtensionArray that is backed by a single NumPy ndarray.
     """

pandas/core/arrays/boolean.py

@@ -368,7 +368,7 @@ def _coerce_to_array(
             assert dtype == "boolean"
         return coerce_to_array(value, copy=copy)
 
-    def _logical_method(self, other, op):  # type: ignore[override]
+    def _logical_method(self, other, op):
         assert op.__name__ in {"or_", "ror_", "and_", "rand_", "xor", "rxor"}
         other_is_scalar = lib.is_scalar(other)
         mask = None

pandas/core/arrays/categorical.py

@@ -241,9 +241,7 @@ def contains(cat, key, container) -> bool:
         return any(loc_ in container for loc_ in loc)
 
 
-# error: Definition of "delete/ravel/T/repeat/copy" in base class "NDArrayBacked"
-# is incompatible with definition in base class "ExtensionArray"
-class Categorical(NDArrayBackedExtensionArray, PandasObject, ObjectStringArrayMixin):  # type: ignore[misc]
+class Categorical(NDArrayBackedExtensionArray, PandasObject, ObjectStringArrayMixin):
     """
     Represent a categorical variable in classic R / S-plus fashion.
 
@@ -2942,9 +2940,7 @@ def _validate(data) -> None:
     def _delegate_property_get(self, name: str):
         return getattr(self._parent, name)
 
-    # error: Signature of "_delegate_property_set" incompatible with supertype
-    # "PandasDelegate"
-    def _delegate_property_set(self, name: str, new_values) -> None:  # type: ignore[override]
+    def _delegate_property_set(self, name: str, new_values) -> None:
         setattr(self._parent, name, new_values)
 
     @property

pandas/core/arrays/datetimelike.py

@@ -197,11 +197,7 @@ def new_meth(self, *args, **kwargs):
     return cast(F, new_meth)
 
 
-# error: Definition of "_concat_same_type" in base class "NDArrayBacked" is
-# incompatible with definition in base class "ExtensionArray"
-class DatetimeLikeArrayMixin(  # type: ignore[misc]
-    OpsMixin, NDArrayBackedExtensionArray
-):
+class DatetimeLikeArrayMixin(OpsMixin, NDArrayBackedExtensionArray):
     """
     Shared Base/Mixin class for DatetimeArray, TimedeltaArray, PeriodArray
 

pandas/core/arrays/datetimes.py

@@ -76,13 +76,15 @@
 
 if TYPE_CHECKING:
     from collections.abc import (
+        Callable,
         Generator,
         Iterator,
     )
 
     from pandas._typing import (
         ArrayLike,
         DateTimeErrorChoices,
+        DtypeObj,
         IntervalClosedType,
         TimeAmbiguous,
         TimeNonexistent,
@@ -168,9 +170,7 @@ def f(self):
     return property(f)
 
 
-# error: Definition of "_concat_same_type" in base class "NDArrayBacked" is
-# incompatible with definition in base class "ExtensionArray"
-class DatetimeArray(dtl.TimelikeOps, dtl.DatelikeOps):  # type: ignore[misc]
+class DatetimeArray(dtl.TimelikeOps, dtl.DatelikeOps):
     """
     Pandas ExtensionArray for tz-naive or tz-aware datetime data.
 
@@ -225,9 +225,9 @@ class DatetimeArray(dtl.TimelikeOps, dtl.DatelikeOps):  # type: ignore[misc]
     _typ = "datetimearray"
     _internal_fill_value = np.datetime64("NaT", "ns")
     _recognized_scalars = (datetime, np.datetime64)
-    _is_recognized_dtype = lambda x: lib.is_np_dtype(x, "M") or isinstance(
-        x, DatetimeTZDtype
-    )
+    _is_recognized_dtype: Callable[[DtypeObj], bool] = lambda x: lib.is_np_dtype(
+        x, "M"
+    ) or isinstance(x, DatetimeTZDtype)
     _infer_matches = ("datetime", "datetime64", "date")
 
     @property
@@ -322,7 +322,7 @@ 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)  # type: ignore[union-attr]
+            assert dtype._creso == get_unit_from_dtype(values.dtype)
 
         result = super()._simple_new(values, dtype)
         result._freq = freq

pandas/core/arrays/floating.py

@@ -1,6 +1,10 @@
 from __future__ import annotations
 
-from typing import ClassVar
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    ClassVar,
+)
 
 import numpy as np
 
@@ -12,6 +16,9 @@
     NumericDtype,
 )
 
+if TYPE_CHECKING:
+    from collections.abc import Callable
+
 
 class FloatingDtype(NumericDtype):
     """
@@ -26,7 +33,7 @@ class FloatingDtype(NumericDtype):
     # The value used to fill '_data' to avoid upcasting
     _internal_fill_value = np.nan
     _default_np_dtype = np.dtype(np.float64)
-    _checker = is_float_dtype
+    _checker: Callable[[Any], bool] = is_float_dtype
 
     def construct_array_type(self) -> type[FloatingArray]:
         """

pandas/core/arrays/integer.py

@@ -1,6 +1,10 @@
 from __future__ import annotations
 
-from typing import ClassVar
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    ClassVar,
+)
 
 import numpy as np
 
@@ -12,6 +16,9 @@
     NumericDtype,
 )
 
+if TYPE_CHECKING:
+    from collections.abc import Callable
+
 
 class IntegerDtype(NumericDtype):
     """
@@ -26,7 +33,7 @@ class IntegerDtype(NumericDtype):
     # The value used to fill '_data' to avoid upcasting
     _internal_fill_value = 1
     _default_np_dtype = np.dtype(np.int64)
-    _checker = is_integer_dtype
+    _checker: Callable[[Any], bool] = is_integer_dtype
 
     def construct_array_type(self) -> type[IntegerArray]:
         """