TYP: assorted annotations (pandas-dev#41250)

Author: jbrockmendel

pandas/_libs/hashtable.pyx

@@ -163,7 +163,7 @@ cdef class Int64Factorizer:
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def unique_label_indices(const int64_t[:] labels):
+def unique_label_indices(const int64_t[:] labels) -> ndarray:
     """
     Indices of the first occurrences of the unique labels
     *excluding* -1. equivalent to:

pandas/_libs/indexing.pyx

@@ -3,9 +3,10 @@ cdef class NDFrameIndexerBase:
     A base class for _NDFrameIndexer for fast instantiation and attribute access.
     """
     cdef public:
-        object obj, name, _ndim
+        str name
+        object obj, _ndim
 
-    def __init__(self, name, obj):
+    def __init__(self, name: str, obj):
         self.obj = obj
         self.name = name
         self._ndim = None

pandas/_libs/internals.pyx

@@ -372,7 +372,9 @@ cdef slice indexer_as_slice(intp_t[:] vals):
 
 @cython.boundscheck(False)
 @cython.wraparound(False)
-def get_blkno_indexers(int64_t[:] blknos, bint group=True):
+def get_blkno_indexers(
+    int64_t[:] blknos, bint group=True
+) -> list[tuple[int, slice | np.ndarray]]:
     """
     Enumerate contiguous runs of integers in ndarray.
 

pandas/core/frame.py

@@ -6219,7 +6219,6 @@ def sort_values(  # type: ignore[override]
             indexer = lexsort_indexer(
                 keys, orders=ascending, na_position=na_position, key=key
             )
-            indexer = ensure_platform_int(indexer)
         elif len(by):
 
             by = by[0]

pandas/core/indexes/base.py

@@ -3414,7 +3414,7 @@ def get_indexer(
         limit: int | None = None,
         tolerance=None,
     ) -> np.ndarray:
-
+        # returned ndarray is np.intp
         method = missing.clean_reindex_fill_method(method)
         target = ensure_index(target)
 
@@ -4099,7 +4099,10 @@ def _join_multi(self, other: Index, how: str_t):
         return result
 
     @final
-    def _join_non_unique(self, other, how="left"):
+    def _join_non_unique(
+        self, other: Index, how: str_t = "left"
+    ) -> tuple[Index, np.ndarray, np.ndarray]:
+        # returned ndarrays are np.intp
         from pandas.core.reshape.merge import get_join_indexers
 
         # We only get here if dtypes match
@@ -4125,7 +4128,10 @@ def _join_non_unique(self, other, how="left"):
         return join_index, left_idx, right_idx
 
     @final
-    def _join_level(self, other, level, how="left", keep_order=True):
+    def _join_level(
+        self, other: Index, level, how: str_t = "left", keep_order: bool = True
+    ) -> tuple[MultiIndex, np.ndarray | None, np.ndarray | None]:
+        # Any returned ndarrays are np.intp
         """
         The join method *only* affects the level of the resulting
         MultiIndex. Otherwise it just exactly aligns the Index data to the

pandas/core/internals/managers.py

@@ -1470,9 +1470,9 @@ def _interleave(
         if isinstance(dtype, SparseDtype):
             dtype = dtype.subtype
         elif isinstance(dtype, ExtensionDtype):
-            dtype = "object"
+            dtype = np.dtype("object")
         elif is_dtype_equal(dtype, str):
-            dtype = "object"
+            dtype = np.dtype("object")
 
         # error: Argument "dtype" to "empty" has incompatible type
         # "Union[ExtensionDtype, str, dtype[Any], Type[object], None]"; expected

pandas/core/reshape/reshape.py

@@ -131,7 +131,12 @@ def __init__(self, index: MultiIndex, level=-1, constructor=None):
         self._make_selectors()
 
     @cache_readonly
-    def _indexer_and_to_sort(self):
+    def _indexer_and_to_sort(
+        self,
+    ) -> tuple[
+        np.ndarray,  # np.ndarray[np.intp]
+        list[np.ndarray],  # each has _some_ signed integer dtype
+    ]:
         v = self.level
 
         codes = list(self.index.codes)
@@ -143,7 +148,6 @@ def _indexer_and_to_sort(self):
         ngroups = len(obs_ids)
 
         indexer = get_group_index_sorter(comp_index, ngroups)
-        indexer = ensure_platform_int(indexer)
         return indexer, to_sort
 
     @cache_readonly

pandas/core/series.py

@@ -113,15 +113,15 @@
 from pandas.core.indexes.accessors import CombinedDatetimelikeProperties
 from pandas.core.indexes.api import (
     CategoricalIndex,
+    DatetimeIndex,
     Float64Index,
     Index,
     MultiIndex,
+    PeriodIndex,
+    TimedeltaIndex,
     ensure_index,
 )
 import pandas.core.indexes.base as ibase
-from pandas.core.indexes.datetimes import DatetimeIndex
-from pandas.core.indexes.period import PeriodIndex
-from pandas.core.indexes.timedeltas import TimedeltaIndex
 from pandas.core.indexing import check_bool_indexer
 from pandas.core.internals import (
     SingleArrayManager,

pandas/core/window/rolling.py

@@ -381,10 +381,11 @@ def _apply_series(
         """
         obj = self._create_data(self._selected_obj)
 
-        try:
+        if name == "count":
             # GH 12541: Special case for count where we support date-like types
-            input = obj.values if name != "count" else notna(obj.values).astype(int)
-            values = self._prep_values(input)
+            obj = notna(obj).astype(int)
+        try:
+            values = self._prep_values(obj._values)
         except (TypeError, NotImplementedError) as err:
             raise DataError("No numeric types to aggregate") from err