TYP: assorted annotations (#39798)

Author: jbrockmendel

pandas/_libs/reduction.pyx

@@ -109,9 +109,8 @@ cdef class SeriesBinGrouper(_BaseGrouper):
         ndarray arr, index, dummy_arr, dummy_index
         object values, f, bins, typ, ityp, name
 
-    def __init__(self, object series, object f, object bins, object dummy):
+    def __init__(self, object series, object f, object bins):
 
-        assert dummy is not None  # always obj[:0]
         assert len(bins) > 0  # otherwise we get IndexError in get_result
 
         self.bins = bins
@@ -127,6 +126,7 @@ cdef class SeriesBinGrouper(_BaseGrouper):
         self.index = series.index.values
         self.name = series.name
 
+        dummy = series.iloc[:0]
         self.dummy_arr, self.dummy_index = self._check_dummy(dummy)
 
         # kludge for #1688
@@ -203,10 +203,7 @@ cdef class SeriesGrouper(_BaseGrouper):
         object f, labels, values, typ, ityp, name
 
     def __init__(self, object series, object f, object labels,
-                 Py_ssize_t ngroups, object dummy):
-
-        # in practice we always pass obj.iloc[:0] or equivalent
-        assert dummy is not None
+                 Py_ssize_t ngroups):
 
         if len(series) == 0:
             # get_result would never assign `result`
@@ -225,6 +222,7 @@ cdef class SeriesGrouper(_BaseGrouper):
         self.index = series.index.values
         self.name = series.name
 
+        dummy = series.iloc[:0]
         self.dummy_arr, self.dummy_index = self._check_dummy(dummy)
         self.ngroups = ngroups
 

pandas/core/algorithms.py

@@ -263,7 +263,7 @@ def _reconstruct_data(
     return values
 
 
-def _ensure_arraylike(values):
+def _ensure_arraylike(values) -> ArrayLike:
     """
     ensure that we are arraylike if not already
     """
@@ -323,7 +323,7 @@ def get_data_algo(values: ArrayLike):
     return htable, values
 
 
-def _check_object_for_strings(values) -> str:
+def _check_object_for_strings(values: np.ndarray) -> str:
     """
     Check if we can use string hashtable instead of object hashtable.
 
@@ -527,7 +527,11 @@ def f(c, v):
 
 
 def factorize_array(
-    values: np.ndarray, na_sentinel: int = -1, size_hint=None, na_value=None, mask=None
+    values: np.ndarray,
+    na_sentinel: int = -1,
+    size_hint: Optional[int] = None,
+    na_value=None,
+    mask: Optional[np.ndarray] = None,
 ) -> Tuple[np.ndarray, np.ndarray]:
     """
     Factorize an array-like to codes and uniques.
@@ -982,13 +986,13 @@ def mode(values, dropna: bool = True) -> Series:
 
 
 def rank(
-    values,
+    values: ArrayLike,
     axis: int = 0,
     method: str = "average",
     na_option: str = "keep",
     ascending: bool = True,
     pct: bool = False,
-):
+) -> np.ndarray:
     """
     Rank the values along a given axis.
 
@@ -1038,7 +1042,12 @@ def rank(
     return ranks
 
 
-def checked_add_with_arr(arr, b, arr_mask=None, b_mask=None):
+def checked_add_with_arr(
+    arr: np.ndarray,
+    b,
+    arr_mask: Optional[np.ndarray] = None,
+    b_mask: Optional[np.ndarray] = None,
+) -> np.ndarray:
     """
     Perform array addition that checks for underflow and overflow.
 
@@ -1051,9 +1060,9 @@ def checked_add_with_arr(arr, b, arr_mask=None, b_mask=None):
     ----------
     arr : array addend.
     b : array or scalar addend.
-    arr_mask : boolean array or None
+    arr_mask : np.ndarray[bool] or None, default None
         array indicating which elements to exclude from checking
-    b_mask : boolean array or boolean or None
+    b_mask : np.ndarray[bool] or None, default None
         array or scalar indicating which element(s) to exclude from checking
 
     Returns
@@ -1406,7 +1415,9 @@ def get_indexer(current_indexer, other_indexer):
 
 
 def _view_wrapper(f, arr_dtype=None, out_dtype=None, fill_wrap=None):
-    def wrapper(arr, indexer, out, fill_value=np.nan):
+    def wrapper(
+        arr: np.ndarray, indexer: np.ndarray, out: np.ndarray, fill_value=np.nan
+    ):
         if arr_dtype is not None:
             arr = arr.view(arr_dtype)
         if out_dtype is not None:
@@ -1419,7 +1430,9 @@ def wrapper(arr, indexer, out, fill_value=np.nan):
 
 
 def _convert_wrapper(f, conv_dtype):
-    def wrapper(arr, indexer, out, fill_value=np.nan):
+    def wrapper(
+        arr: np.ndarray, indexer: np.ndarray, out: np.ndarray, fill_value=np.nan
+    ):
         if conv_dtype == object:
             # GH#39755 avoid casting dt64/td64 to integers
             arr = ensure_wrapped_if_datetimelike(arr)
@@ -1429,7 +1442,9 @@ def wrapper(arr, indexer, out, fill_value=np.nan):
     return wrapper
 
 
-def _take_2d_multi_object(arr, indexer, out, fill_value, mask_info):
+def _take_2d_multi_object(
+    arr: np.ndarray, indexer: np.ndarray, out: np.ndarray, fill_value, mask_info
+) -> None:
     # this is not ideal, performance-wise, but it's better than raising
     # an exception (best to optimize in Cython to avoid getting here)
     row_idx, col_idx = indexer
@@ -1452,7 +1467,14 @@ def _take_2d_multi_object(arr, indexer, out, fill_value, mask_info):
             out[i, j] = arr[u_, v]
 
 
-def _take_nd_object(arr, indexer, out, axis: int, fill_value, mask_info):
+def _take_nd_object(
+    arr: np.ndarray,
+    indexer: np.ndarray,
+    out: np.ndarray,
+    axis: int,
+    fill_value,
+    mask_info,
+):
     if mask_info is not None:
         mask, needs_masking = mask_info
     else:
@@ -1570,7 +1592,7 @@ def _take_nd_object(arr, indexer, out, axis: int, fill_value, mask_info):
 
 
 def _get_take_nd_function(
-    ndim: int, arr_dtype, out_dtype, axis: int = 0, mask_info=None
+    ndim: int, arr_dtype: np.dtype, out_dtype: np.dtype, axis: int = 0, mask_info=None
 ):
     if ndim <= 2:
         tup = (arr_dtype.name, out_dtype.name)
@@ -1605,7 +1627,9 @@ def func2(arr, indexer, out, fill_value=np.nan):
     return func2
 
 
-def take(arr, indices, axis: int = 0, allow_fill: bool = False, fill_value=None):
+def take(
+    arr, indices: np.ndarray, axis: int = 0, allow_fill: bool = False, fill_value=None
+):
     """
     Take elements from an array.
 
@@ -1739,7 +1763,7 @@ def take_nd(
     arr,
     indexer,
     axis: int = 0,
-    out=None,
+    out: Optional[np.ndarray] = None,
     fill_value=lib.no_default,
     allow_fill: bool = True,
 ):