TYP: a few mismatches found by stubtest (#47764)

* TYP: a few mismatches found by stubtest

* a few more

* flake8

Author: twoertwein

pandas/_libs/algos.pyi

@@ -42,7 +42,7 @@ def groupsort_indexer(
     np.ndarray,  # ndarray[int64_t, ndim=1]
 ]: ...
 def kth_smallest(
-    a: np.ndarray,  # numeric[:]
+    arr: np.ndarray,  # numeric[:]
     k: int,
 ) -> Any: ...  # numeric
 

pandas/_libs/groupby.pyi

@@ -105,26 +105,28 @@ def group_last(
     values: np.ndarray,  # ndarray[rank_t, ndim=2]
     labels: np.ndarray,  # const int64_t[:]
     mask: npt.NDArray[np.bool_] | None,
-    result_mask: npt.NDArray[np.bool_] | None,
+    result_mask: npt.NDArray[np.bool_] | None = ...,
     min_count: int = ...,  # Py_ssize_t
+    is_datetimelike: bool = ...,
 ) -> None: ...
 def group_nth(
     out: np.ndarray,  # rank_t[:, ::1]
     counts: np.ndarray,  # int64_t[::1]
     values: np.ndarray,  # ndarray[rank_t, ndim=2]
     labels: np.ndarray,  # const int64_t[:]
     mask: npt.NDArray[np.bool_] | None,
-    result_mask: npt.NDArray[np.bool_] | None,
+    result_mask: npt.NDArray[np.bool_] | None = ...,
     min_count: int = ...,  # int64_t
     rank: int = ...,  # int64_t
+    is_datetimelike: bool = ...,
 ) -> None: ...
 def group_rank(
     out: np.ndarray,  # float64_t[:, ::1]
     values: np.ndarray,  # ndarray[rank_t, ndim=2]
     labels: np.ndarray,  # const int64_t[:]
     ngroups: int,
     is_datetimelike: bool,
-    ties_method: Literal["aveage", "min", "max", "first", "dense"] = ...,
+    ties_method: Literal["average", "min", "max", "first", "dense"] = ...,
     ascending: bool = ...,
     pct: bool = ...,
     na_option: Literal["keep", "top", "bottom"] = ...,
@@ -136,6 +138,7 @@ def group_max(
     values: np.ndarray,  # ndarray[groupby_t, ndim=2]
     labels: np.ndarray,  # const int64_t[:]
     min_count: int = ...,
+    is_datetimelike: bool = ...,
     mask: np.ndarray | None = ...,
     result_mask: np.ndarray | None = ...,
 ) -> None: ...
@@ -145,6 +148,7 @@ def group_min(
     values: np.ndarray,  # ndarray[groupby_t, ndim=2]
     labels: np.ndarray,  # const int64_t[:]
     min_count: int = ...,
+    is_datetimelike: bool = ...,
     mask: np.ndarray | None = ...,
     result_mask: np.ndarray | None = ...,
 ) -> None: ...
@@ -154,11 +158,17 @@ def group_cummin(
     labels: np.ndarray,  # const int64_t[:]
     ngroups: int,
     is_datetimelike: bool,
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+    skipna: bool = ...,
 ) -> None: ...
 def group_cummax(
     out: np.ndarray,  # groupby_t[:, ::1]
     values: np.ndarray,  # ndarray[groupby_t, ndim=2]
     labels: np.ndarray,  # const int64_t[:]
     ngroups: int,
     is_datetimelike: bool,
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+    skipna: bool = ...,
 ) -> None: ...

pandas/_libs/internals.pyi

@@ -32,7 +32,7 @@ def update_blklocs_and_blknos(
     loc: int,
     nblocks: int,
 ) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
-
+@final
 class BlockPlacement:
     def __init__(self, val: int | slice | np.ndarray): ...
     @property

pandas/_libs/join.pyi

@@ -56,6 +56,7 @@ def asof_join_backward_on_X_by_Y(
     right_by_values: np.ndarray,  # by_t[:]
     allow_exact_matches: bool = ...,
     tolerance: np.number | int | float | None = ...,
+    use_hashtable: bool = ...,
 ) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
 def asof_join_forward_on_X_by_Y(
     left_values: np.ndarray,  # asof_t[:]
@@ -64,6 +65,7 @@ def asof_join_forward_on_X_by_Y(
     right_by_values: np.ndarray,  # by_t[:]
     allow_exact_matches: bool = ...,
     tolerance: np.number | int | float | None = ...,
+    use_hashtable: bool = ...,
 ) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
 def asof_join_nearest_on_X_by_Y(
     left_values: np.ndarray,  # asof_t[:]
@@ -72,22 +74,5 @@ def asof_join_nearest_on_X_by_Y(
     right_by_values: np.ndarray,  # by_t[:]
     allow_exact_matches: bool = ...,
     tolerance: np.number | int | float | None = ...,
-) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
-def asof_join_backward(
-    left_values: np.ndarray,  # asof_t[:]
-    right_values: np.ndarray,  # asof_t[:]
-    allow_exact_matches: bool = ...,
-    tolerance: np.number | int | float | None = ...,
-) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
-def asof_join_forward(
-    left_values: np.ndarray,  # asof_t[:]
-    right_values: np.ndarray,  # asof_t[:]
-    allow_exact_matches: bool = ...,
-    tolerance: np.number | int | float | None = ...,
-) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
-def asof_join_nearest(
-    left_values: np.ndarray,  # asof_t[:]
-    right_values: np.ndarray,  # asof_t[:]
-    allow_exact_matches: bool = ...,
-    tolerance: np.number | int | float | None = ...,
+    use_hashtable: bool = ...,
 ) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...

pandas/_libs/missing.pyi

@@ -1,7 +1,8 @@
 import numpy as np
 from numpy import typing as npt
 
-class NAType: ...
+class NAType:
+    def __new__(cls, *args, **kwargs): ...
 
 NA: NAType
 

pandas/_libs/parsers.pyi

@@ -63,7 +63,6 @@ class TextReader:
         skip_blank_lines: bool = ...,
         encoding_errors: bytes | str = ...,
     ): ...
-    def set_error_bad_lines(self, status: int) -> None: ...
     def set_noconvert(self, i: int) -> None: ...
     def remove_noconvert(self, i: int) -> None: ...
     def close(self) -> None: ...

pandas/_libs/tslibs/ccalendar.pyi

@@ -8,7 +8,5 @@ def get_firstbday(year: int, month: int) -> int: ...
 def get_lastbday(year: int, month: int) -> int: ...
 def get_day_of_year(year: int, month: int, day: int) -> int: ...
 def get_iso_calendar(year: int, month: int, day: int) -> tuple[int, int, int]: ...
-def is_leapyear(year: int) -> bool: ...
 def get_week_of_year(year: int, month: int, day: int) -> int: ...
 def get_days_in_month(year: int, month: int) -> int: ...
-def dayofweek(y: int, m: int, d: int) -> int: ...

pandas/_libs/tslibs/dtypes.pyi

@@ -14,10 +14,12 @@ class PeriodDtypeBase:
 
     # actually __cinit__
     def __new__(cls, code: int): ...
+    @property
     def _freq_group_code(self) -> int: ...
     @property
     def _resolution_obj(self) -> Resolution: ...
     def _get_to_timestamp_base(self) -> int: ...
+    @property
     def _freqstr(self) -> str: ...
 
 class FreqGroup(Enum):

pandas/_libs/tslibs/nattype.pyi

@@ -12,15 +12,14 @@ NaT: NaTType
 iNaT: int
 nat_strings: set[str]
 
-def is_null_datetimelike(val: object, inat_is_null: bool = ...) -> bool: ...
-
 _NaTComparisonTypes = datetime | timedelta | Period | np.datetime64 | np.timedelta64
 
 class _NatComparison:
     def __call__(self, other: _NaTComparisonTypes) -> bool: ...
 
 class NaTType:
     value: np.int64
+    @property
     def asm8(self) -> np.datetime64: ...
     def to_datetime64(self) -> np.datetime64: ...
     def to_numpy(

pandas/_libs/tslibs/offsets.pyi

@@ -80,6 +80,7 @@ class BaseOffset:
     def name(self) -> str: ...
     @property
     def rule_code(self) -> str: ...
+    @property
     def freqstr(self) -> str: ...
     def apply_index(self, dtindex: DatetimeIndex) -> DatetimeIndex: ...
     def _apply_array(self, dtarr) -> None: ...

pandas/_libs/tslibs/timezones.pyi

@@ -6,8 +6,6 @@ from typing import Callable
 
 import numpy as np
 
-from pandas._typing import npt
-
 # imported from dateutil.tz
 dateutil_gettz: Callable[[str], tzinfo]
 
@@ -17,9 +15,6 @@ def infer_tzinfo(
     start: datetime | None,
     end: datetime | None,
 ) -> tzinfo | None: ...
-def get_dst_info(
-    tz: tzinfo,
-) -> tuple[npt.NDArray[np.int64], npt.NDArray[np.int64], str]: ...
 def maybe_get_tz(tz: str | int | np.int64 | tzinfo | None) -> tzinfo | None: ...
 def get_timezone(tz: tzinfo) -> tzinfo | str: ...
 def is_utc(tz: tzinfo | None) -> bool: ...