TYP: Update mypy and pyright (pandas-dev#56493)

* changes for mypy

* changes for pyright

* 1.1.400 would require too many difficult changes

Author: twoertwein

.pre-commit-config.yaml

@@ -132,11 +132,11 @@ repos:
         types: [python]
         stages: [manual]
         additional_dependencies: &pyright_dependencies
-        - [email protected].318
+        - [email protected].339
     -   id: pyright
         # note: assumes python env is setup and activated
         name: pyright reportGeneralTypeIssues
-        entry: pyright --skipunannotated -p pyright_reportGeneralTypeIssues.json --level warning
+        entry: pyright -p pyright_reportGeneralTypeIssues.json --level warning
         language: node
         pass_filenames: false
         types: [python]

doc/source/whatsnew/v2.2.0.rst

@@ -346,6 +346,8 @@ Optional libraries below the lowest tested version may still work, but are not c
 +-----------------+-----------------+---------+
 | Package         | Minimum Version | Changed |
 +=================+=================+=========+
+| mypy (dev)      | 1.7.1           |    X    |
++-----------------+-----------------+---------+
 |                 |                 |    X    |
 +-----------------+-----------------+---------+
 

environment.yml

@@ -76,7 +76,7 @@ dependencies:
 
   # code checks
   - flake8=6.1.0  # run in subprocess over docstring examples
-  - mypy=1.4.1  # pre-commit uses locally installed mypy
+  - mypy=1.7.1  # pre-commit uses locally installed mypy
   - tokenize-rt  # scripts/check_for_inconsistent_pandas_namespace.py
   - pre-commit>=3.6.0
 

pandas/_config/config.py

@@ -220,6 +220,8 @@ def get_default_val(pat: str):
 class DictWrapper:
     """provide attribute-style access to a nested dict"""
 
+    d: dict[str, Any]
+
     def __init__(self, d: dict[str, Any], prefix: str = "") -> None:
         object.__setattr__(self, "d", d)
         object.__setattr__(self, "prefix", prefix)
@@ -250,7 +252,7 @@ def __getattr__(self, key: str):
         else:
             return _get_option(prefix)
 
-    def __dir__(self) -> Iterable[str]:
+    def __dir__(self) -> list[str]:
         return list(self.d.keys())
 
 

pandas/_libs/tslibs/nattype.pyi

@@ -8,6 +8,7 @@ import typing
 import numpy as np
 
 from pandas._libs.tslibs.period import Period
+from pandas._typing import Self
 
 NaT: NaTType
 iNaT: int
@@ -132,4 +133,9 @@ class NaTType:
     __le__: _NatComparison
     __gt__: _NatComparison
     __ge__: _NatComparison
+    def __sub__(self, other: Self | timedelta | datetime) -> Self: ...
+    def __rsub__(self, other: Self | timedelta | datetime) -> Self: ...
+    def __add__(self, other: Self | timedelta | datetime) -> Self: ...
+    def __radd__(self, other: Self | timedelta | datetime) -> Self: ...
+    def __hash__(self) -> int: ...
     def as_unit(self, unit: str, round_ok: bool = ...) -> NaTType: ...

pandas/_libs/tslibs/timestamps.pyi

@@ -10,7 +10,6 @@ from typing import (
     ClassVar,
     Literal,
     TypeAlias,
-    TypeVar,
     overload,
 )
 
@@ -28,7 +27,6 @@ from pandas._typing import (
     TimestampNonexistent,
 )
 
-_DatetimeT = TypeVar("_DatetimeT", bound=datetime)
 _TimeZones: TypeAlias = str | _tzinfo | None | int
 
 def integer_op_not_supported(obj: object) -> TypeError: ...
@@ -42,7 +40,7 @@ class Timestamp(datetime):
     _value: int  # np.int64
     # error: "__new__" must return a class instance (got "Union[Timestamp, NaTType]")
     def __new__(  # type: ignore[misc]
-        cls: type[_DatetimeT],
+        cls: type[Self],
         ts_input: np.integer | float | str | _date | datetime | np.datetime64 = ...,
         year: int | None = ...,
         month: int | None = ...,
@@ -57,7 +55,7 @@ class Timestamp(datetime):
         tz: _TimeZones = ...,
         unit: str | int | None = ...,
         fold: int | None = ...,
-    ) -> _DatetimeT | NaTType: ...
+    ) -> Self | NaTType: ...
     @classmethod
     def _from_value_and_reso(
         cls, value: int, reso: int, tz: _TimeZones

pandas/_testing/_hypothesis.py

@@ -54,8 +54,12 @@
     DATETIME_NO_TZ = st.datetimes()
 
 DATETIME_JAN_1_1900_OPTIONAL_TZ = st.datetimes(
-    min_value=pd.Timestamp(1900, 1, 1).to_pydatetime(),
-    max_value=pd.Timestamp(1900, 1, 1).to_pydatetime(),
+    min_value=pd.Timestamp(
+        1900, 1, 1
+    ).to_pydatetime(),  # pyright: ignore[reportGeneralTypeIssues]
+    max_value=pd.Timestamp(
+        1900, 1, 1
+    ).to_pydatetime(),  # pyright: ignore[reportGeneralTypeIssues]
     timezones=st.one_of(st.none(), dateutil_timezones(), pytz_timezones()),
 )
 

pandas/_typing.py

@@ -234,7 +234,9 @@ def __reversed__(self) -> Iterator[_T_co]:
 
 # types of `func` kwarg for DataFrame.aggregate and Series.aggregate
 AggFuncTypeBase = Union[Callable, str]
-AggFuncTypeDict = dict[Hashable, Union[AggFuncTypeBase, list[AggFuncTypeBase]]]
+AggFuncTypeDict = MutableMapping[
+    Hashable, Union[AggFuncTypeBase, list[AggFuncTypeBase]]
+]
 AggFuncType = Union[
     AggFuncTypeBase,
     list[AggFuncTypeBase],

pandas/conftest.py

@@ -1353,7 +1353,7 @@ def fixed_now_ts() -> Timestamp:
     """
     Fixture emits fixed Timestamp.now()
     """
-    return Timestamp(
+    return Timestamp(  # pyright: ignore[reportGeneralTypeIssues]
         year=2021, month=1, day=1, hour=12, minute=4, second=13, microsecond=22
     )
 

pandas/core/_numba/kernels/var_.py

@@ -116,7 +116,7 @@ def sliding_var(
                     ssqdm_x,
                     compensation_add,
                     num_consecutive_same_value,
-                    prev_value,  # pyright: ignore[reportGeneralTypeIssues]
+                    prev_value,
                 )
         else:
             for j in range(start[i - 1], s):
@@ -141,7 +141,7 @@ def sliding_var(
                     ssqdm_x,
                     compensation_add,
                     num_consecutive_same_value,
-                    prev_value,  # pyright: ignore[reportGeneralTypeIssues]
+                    prev_value,
                 )
 
         if nobs >= min_periods and nobs > ddof: