TYP: enable reportGeneralTypeIssues for more files (#54423)

* TYP: enable reportGeneralTypeIssues for more files * fixes * Added some time-related annotations based on the tests from pandas-stubs * remove python version from second pyright config file

Author: twoertwein

.pre-commit-config.yaml

@@ -138,7 +138,7 @@ repos:
  types: [python]
  stages: [manual]
  additional_dependencies: &pyright_dependencies
- - pyright@1.1.305
+ - pyright@1.1.318
  - id: pyright
  # note: assumes python env is setup and activated
  name: pyright reportGeneralTypeIssues

pandas/_libs/tslibs/offsets.pyi

@@ -1,5 +1,6 @@
 from datetime import (
  datetime,
+ time,
  timedelta,
 )
 from typing import (
@@ -14,6 +15,7 @@ import numpy as np
 
 from pandas._libs.tslibs.nattype import NaTType
 from pandas._typing import (
+ OffsetCalendar,
  Self,
  npt,
 )
@@ -141,8 +143,8 @@ class BusinessHour(BusinessMixin):
  self,
  n: int = ...,
  normalize: bool = ...,
- start: str | Collection[str] = ...,
- end: str | Collection[str] = ...,
+ start: str | time | Collection[str | time] = ...,
+ end: str | time | Collection[str | time] = ...,
  offset: timedelta = ...,
  ) -> None: ...
 
@@ -228,7 +230,7 @@ class _CustomBusinessMonth(BusinessMixin):
  normalize: bool = ...,
  weekmask: str = ...,
  holidays: list | None = ...,
- calendar: np.busdaycalendar | None = ...,
+ calendar: OffsetCalendar | None = ...,
  offset: timedelta = ...,
  ) -> None: ...
 
@@ -239,7 +241,7 @@ class CustomBusinessDay(BusinessDay):
  normalize: bool = ...,
  weekmask: str = ...,
  holidays: list | None = ...,
- calendar: np.busdaycalendar | None = ...,
+ calendar: OffsetCalendar | None = ...,
  offset: timedelta = ...,
  ) -> None: ...
 
@@ -250,9 +252,9 @@ class CustomBusinessHour(BusinessHour):
  normalize: bool = ...,
  weekmask: str = ...,
  holidays: list | None = ...,
- calendar: np.busdaycalendar | None = ...,
- start: str = ...,
- end: str = ...,
+ calendar: OffsetCalendar | None = ...,
+ start: str | time | Collection[str | time] = ...,
+ end: str | time | Collection[str | time] = ...,
  offset: timedelta = ...,
  ) -> None: ...
 

pandas/_libs/tslibs/timestamps.pyi

@@ -21,7 +21,10 @@ from pandas._libs.tslibs import (
  Tick,
  Timedelta,
 )
-from pandas._typing import Self
+from pandas._typing import (
+ Self,
+ TimestampNonexistent,
+)
 
 _DatetimeT = TypeVar("_DatetimeT", bound=datetime)
 
@@ -187,18 +190,27 @@ class Timestamp(datetime):
  self,
  tz: _tzinfo | str | None,
  ambiguous: str = ...,
- nonexistent: str = ...,
+ nonexistent: TimestampNonexistent = ...,
  ) -> Self: ...
  def normalize(self) -> Self: ...
  # TODO: round/floor/ceil could return NaT?
  def round(
- self, freq: str, ambiguous: bool | str = ..., nonexistent: str = ...
+ self,
+ freq: str,
+ ambiguous: bool | str = ...,
+ nonexistent: TimestampNonexistent = ...,
  ) -> Self: ...
  def floor(
- self, freq: str, ambiguous: bool | str = ..., nonexistent: str = ...
+ self,
+ freq: str,
+ ambiguous: bool | str = ...,
+ nonexistent: TimestampNonexistent = ...,
  ) -> Self: ...
  def ceil(
- self, freq: str, ambiguous: bool | str = ..., nonexistent: str = ...
+ self,
+ freq: str,
+ ambiguous: bool | str = ...,
+ nonexistent: TimestampNonexistent = ...,
  ) -> Self: ...
  def day_name(self, locale: str | None = ...) -> str: ...
  def month_name(self, locale: str | None = ...) -> str: ...

pandas/_typing.py

@@ -7,6 +7,7 @@
  Sequence,
 )
 from datetime import (
+ date,
  datetime,
  timedelta,
  tzinfo,
@@ -68,6 +69,7 @@
  from pandas.core.window.rolling import BaseWindow
 
  from pandas.io.formats.format import EngFormatter
+ from pandas.tseries.holiday import AbstractHolidayCalendar
 
  ScalarLike_co = Union[
  int,
@@ -89,7 +91,7 @@
  from typing_extensions import TypeGuard # pyright: ignore[reportUnusedImport]
 
  if sys.version_info >= (3, 11):
- from typing import Self
+ from typing import Self # pyright: ignore[reportUnusedImport]
  else:
  from typing_extensions import Self # pyright: ignore[reportUnusedImport]
 else:
@@ -117,14 +119,17 @@
 PythonScalar = Union[str, float, bool]
 DatetimeLikeScalar = Union["Period", "Timestamp", "Timedelta"]
 PandasScalar = Union["Period", "Timestamp", "Timedelta", "Interval"]
-Scalar = Union[PythonScalar, PandasScalar, np.datetime64, np.timedelta64, datetime]
+Scalar = Union[PythonScalar, PandasScalar, np.datetime64, np.timedelta64, date]
 IntStrT = TypeVar("IntStrT", int, str)
 
 
 # timestamp and timedelta convertible types
 
 TimestampConvertibleTypes = Union[
- "Timestamp", datetime, np.datetime64, np.int64, float, str
+ "Timestamp", date, np.datetime64, np.int64, float, str
+]
+TimestampNonexistent = Union[
+ Literal["shift_forward", "shift_backward", "NaT", "raise"], timedelta
 ]
 TimedeltaConvertibleTypes = Union[
  "Timedelta", timedelta, np.timedelta64, np.int64, float, str
@@ -466,3 +471,6 @@ def closed(self) -> bool:
 
 # ExcelWriter
 ExcelWriterIfSheetExists = Literal["error", "new", "replace", "overlay"]
+
+# Offsets
+OffsetCalendar = Union[np.busdaycalendar, "AbstractHolidayCalendar"]

pandas/core/arrays/period.py

@@ -990,7 +990,7 @@ def raise_on_incompatible(left, right):
 
 def period_array(
  data: Sequence[Period | str | None] | AnyArrayLike,
- freq: str | Tick | None = None,
+ freq: str | Tick | BaseOffset | None = None,
  copy: bool = False,
 ) -> PeriodArray:
  """

pandas/core/indexes/datetimes.py

@@ -1024,7 +1024,7 @@ def bdate_range(
  start=None,
  end=None,
  periods: int | None = None,
- freq: Frequency = "B",
+ freq: Frequency | dt.timedelta = "B",
  tz=None,
  normalize: bool = True,
  name: Hashable | None = None,

pandas/core/reshape/concat.py

@@ -497,24 +497,22 @@ def _clean_keys_and_objs(
  if isinstance(objs, abc.Mapping):
  if keys is None:
  keys = list(objs.keys())
- objs = [objs[k] for k in keys]
+ objs_list = [objs[k] for k in keys]
  else:
- objs = list(objs)
+ objs_list = list(objs)
 
- if len(objs) == 0:
+ if len(objs_list) == 0:
  raise ValueError("No objects to concatenate")
 
  if keys is None:
- objs = list(com.not_none(*objs))
+ objs_list = list(com.not_none(*objs_list))
  else:
  # GH#1649
  clean_keys = []
  clean_objs = []
  if is_iterator(keys):
  keys = list(keys)
- if is_iterator(objs):
- objs = list(objs)
- if len(keys) != len(objs):
+ if len(keys) != len(objs_list):
  # GH#43485
  warnings.warn(
  "The behavior of pd.concat with len(keys) != len(objs) is "
@@ -523,12 +521,12 @@ def _clean_keys_and_objs(
  FutureWarning,
  stacklevel=find_stack_level(),
  )
- for k, v in zip(keys, objs):
+ for k, v in zip(keys, objs_list):
  if v is None:
  continue
  clean_keys.append(k)
  clean_objs.append(v)
- objs = clean_objs
+ objs_list = clean_objs
 
  if isinstance(keys, MultiIndex):
  # TODO: retain levels?
@@ -537,10 +535,10 @@ def _clean_keys_and_objs(
  name = getattr(keys, "name", None)
  keys = Index(clean_keys, name=name, dtype=getattr(keys, "dtype", None))
 
- if len(objs) == 0:
+ if len(objs_list) == 0:
  raise ValueError("All objects passed were None")
 
- return objs, keys
+ return objs_list, keys
 
  def _get_sample_object(
  self,

pandas/core/tools/datetimes.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from collections import abc
-from datetime import datetime
+from datetime import date
 from functools import partial
 from itertools import islice
 from typing import (
@@ -98,7 +98,7 @@
 
 ArrayConvertible = Union[list, tuple, AnyArrayLike]
 Scalar = Union[float, str]
-DatetimeScalar = Union[Scalar, datetime]
+DatetimeScalar = Union[Scalar, date, np.datetime64]
 
 DatetimeScalarOrArrayConvertible = Union[DatetimeScalar, ArrayConvertible]
 

pandas/core/tools/times.py

@@ -22,7 +22,7 @@
 
 def to_time(
  arg,
- format=None,
+ format: str | None = None,
  infer_time_format: bool = False,
  errors: DateTimeErrorChoices = "raise",
 ):

pandas/io/common.py

@@ -1023,10 +1023,12 @@ def __init__(
  self.archive_name = archive_name
 
  kwargs.setdefault("compression", zipfile.ZIP_DEFLATED)
- # error: Argument 1 to "ZipFile" has incompatible type "Union[
- # Union[str, PathLike[str]], ReadBuffer[bytes], WriteBuffer[bytes]]";
- # expected "Union[Union[str, PathLike[str]], IO[bytes]]"
- self.buffer = zipfile.ZipFile(file, mode, **kwargs) # type: ignore[arg-type]
+ # error: No overload variant of "ZipFile" matches argument types "str |
+ # PathLike[str] | ReadBuffer[bytes] | WriteBuffer[bytes]", "str", "dict[str,
+ # Any]"
+ self.buffer = zipfile.ZipFile( # type: ignore[call-overload]
+ file, mode, **kwargs
+ )
 
  def infer_filename(self) -> str | None:
  """