CLN: collected cleanups (pandas-dev#42827)

Author: jbrockmendel

pandas/core/base.py

@@ -1221,7 +1221,7 @@ def factorize(self, sort: bool = False, na_sentinel: int | None = -1):
         """
 
     @doc(_shared_docs["searchsorted"], klass="Index")
-    def searchsorted(self, value, side="left", sorter=None) -> np.ndarray:
+    def searchsorted(self, value, side="left", sorter=None) -> npt.NDArray[np.intp]:
         return algorithms.searchsorted(self._values, value, side=side, sorter=sorter)
 
     def drop_duplicates(self, keep="first"):
@@ -1232,5 +1232,5 @@ def drop_duplicates(self, keep="first"):
     @final
     def _duplicated(
         self, keep: Literal["first", "last", False] = "first"
-    ) -> np.ndarray:
+    ) -> npt.NDArray[np.bool_]:
         return duplicated(self._values, keep=keep)

pandas/core/construction.py

@@ -402,7 +402,7 @@ def extract_array(
     >>> extract_array([1, 2, 3])
     [1, 2, 3]
 
-    For an ndarray-backed Series / Index a PandasArray is returned.
+    For an ndarray-backed Series / Index the ndarray is returned.
 
     >>> extract_array(pd.Series([1, 2, 3]))
     array([1, 2, 3])

pandas/core/indexes/datetimelike.py

@@ -238,10 +238,11 @@ def _format_attrs(self):
         """
         attrs = super()._format_attrs()
         for attrib in self._attributes:
+            # iterating over _attributes prevents us from doing this for PeriodIndex
             if attrib == "freq":
                 freq = self.freqstr
                 if freq is not None:
-                    freq = repr(freq)
+                    freq = repr(freq)  # e.g. D -> 'D'
                 # Argument 1 to "append" of "list" has incompatible type
                 # "Tuple[str, Optional[str]]"; expected "Tuple[str, Union[str, int]]"
                 attrs.append(("freq", freq))  # type: ignore[arg-type]

pandas/core/indexing.py

@@ -642,7 +642,7 @@ def _get_setitem_indexer(self, key):
             self._ensure_listlike_indexer(key)
 
         if self.axis is not None:
-            return self._convert_tuple(key, is_setter=True)
+            return self._convert_tuple(key)
 
         ax = self.obj._get_axis(0)
 
@@ -653,12 +653,12 @@ def _get_setitem_indexer(self, key):
 
         if isinstance(key, tuple):
             with suppress(IndexingError):
-                return self._convert_tuple(key, is_setter=True)
+                return self._convert_tuple(key)
 
         if isinstance(key, range):
             return list(key)
 
-        return self._convert_to_indexer(key, axis=0, is_setter=True)
+        return self._convert_to_indexer(key, axis=0)
 
     def _ensure_listlike_indexer(self, key, axis=None, value=None):
         """
@@ -755,21 +755,19 @@ def _is_nested_tuple_indexer(self, tup: tuple) -> bool:
             return any(is_nested_tuple(tup, ax) for ax in self.obj.axes)
         return False
 
-    def _convert_tuple(self, key, is_setter: bool = False):
+    def _convert_tuple(self, key):
         keyidx = []
         if self.axis is not None:
             axis = self.obj._get_axis_number(self.axis)
             for i in range(self.ndim):
                 if i == axis:
-                    keyidx.append(
-                        self._convert_to_indexer(key, axis=axis, is_setter=is_setter)
-                    )
+                    keyidx.append(self._convert_to_indexer(key, axis=axis))
                 else:
                     keyidx.append(slice(None))
         else:
             self._validate_key_length(key)
             for i, k in enumerate(key):
-                idx = self._convert_to_indexer(k, axis=i, is_setter=is_setter)
+                idx = self._convert_to_indexer(k, axis=i)
                 keyidx.append(idx)
 
         return tuple(keyidx)
@@ -867,8 +865,8 @@ def _getitem_nested_tuple(self, tup: tuple):
         # a tuple passed to a series with a multi-index
         if len(tup) > self.ndim:
             if self.name != "loc":
-                # This should never be reached, but lets be explicit about it
-                raise ValueError("Too many indices")
+                # This should never be reached, but let's be explicit about it
+                raise ValueError("Too many indices")  # pragma: no cover
             if all(is_hashable(x) or com.is_null_slice(x) for x in tup):
                 # GH#10521 Series should reduce MultiIndex dimensions instead of
                 #  DataFrame, IndexingError is not raised when slice(None,None,None)
@@ -911,7 +909,7 @@ def _getitem_nested_tuple(self, tup: tuple):
 
         return obj
 
-    def _convert_to_indexer(self, key, axis: int, is_setter: bool = False):
+    def _convert_to_indexer(self, key, axis: int):
         raise AbstractMethodError(self)
 
     def __getitem__(self, key):
@@ -1176,7 +1174,7 @@ def _get_slice_axis(self, slice_obj: slice, axis: int):
             #  return a DatetimeIndex instead of a slice object.
             return self.obj.take(indexer, axis=axis)
 
-    def _convert_to_indexer(self, key, axis: int, is_setter: bool = False):
+    def _convert_to_indexer(self, key, axis: int):
         """
         Convert indexing key into something we can use to do actual fancy
         indexing on a ndarray.
@@ -1486,7 +1484,7 @@ def _get_slice_axis(self, slice_obj: slice, axis: int):
         labels._validate_positional_slice(slice_obj)
         return self.obj._slice(slice_obj, axis=axis)
 
-    def _convert_to_indexer(self, key, axis: int, is_setter: bool = False):
+    def _convert_to_indexer(self, key, axis: int):
         """
         Much simpler as we only have to deal with our valid types.
         """

pandas/core/internals/concat.py

@@ -672,6 +672,7 @@ def _combine_concat_plans(plans, concat_axis: int):
                 offset += last_plc.as_slice.stop
 
     else:
+        # singleton list so we can modify it as a side-effect within _next_or_none
         num_ended = [0]
 
         def _next_or_none(seq):

pandas/core/series.py

@@ -4385,7 +4385,7 @@ def _reduce(
                 return op(delegate, skipna=skipna, **kwds)
 
     def _reindex_indexer(
-        self, new_index: Index | None, indexer: np.ndarray | None, copy: bool
+        self, new_index: Index | None, indexer: npt.NDArray[np.intp] | None, copy: bool
     ) -> Series:
         # Note: new_index is None iff indexer is None
         # if not None, indexer is np.intp