ENH: Allow Iterable[Hashable] in drop_duplicates

doc/source/whatsnew/v3.0.0.rst

@@ -51,7 +51,7 @@ Other enhancements
 - :meth:`Series.cummin` and :meth:`Series.cummax` now supports :class:`CategoricalDtype` (:issue:`52335`)
 - :meth:`Series.plot` now correctly handle the ``ylabel`` parameter for pie charts, allowing for explicit control over the y-axis label (:issue:`58239`)
 - Restore support for reading Stata 104-format and enable reading 103-format dta files (:issue:`58554`)
-- Support passing a :class:`Set` input to :meth:`DataFrame.drop_duplicates` (:issue:`59237`)
+- Support passing a :class:`Set` and :class:`Iterable[Hashable]` input to :meth:`DataFrame.drop_duplicates` (:issue:`59237`)
 - Support reading Stata 102-format (Stata 1) dta files (:issue:`58978`)
 - Support reading Stata 110-format (Stata 7) dta files (:issue:`47176`)
 

pandas/core/frame.py

@@ -20,7 +20,6 @@
     Iterator,
     Mapping,
     Sequence,
-    Set as AbstractSet,
 )
 import functools
 from io import StringIO
@@ -6405,7 +6404,7 @@ def dropna(
 
         thresh : int, optional
             Require that many non-NA values. Cannot be combined with how.
-        subset : column label or sequence of labels, optional
+        subset : column label or iterable of labels, optional
             Labels along other axis to consider, e.g. if you are dropping rows
             these would be a list of columns to include.
         inplace : bool, default False
@@ -6535,7 +6534,7 @@ def dropna(
     @overload
     def drop_duplicates(
         self,
-        subset: Hashable | Sequence[Hashable] | AbstractSet | None = ...,
+        subset: Hashable | Iterable[Hashable] | set | None = ...,
         *,
         keep: DropKeep = ...,
         inplace: Literal[True],
@@ -6545,7 +6544,7 @@ def drop_duplicates(
     @overload
     def drop_duplicates(
         self,
-        subset: Hashable | Sequence[Hashable] | AbstractSet | None = ...,
+        subset: Hashable | Iterable[Hashable] | set | None = ...,
         *,
         keep: DropKeep = ...,
         inplace: Literal[False] = ...,
@@ -6555,7 +6554,7 @@ def drop_duplicates(
     @overload
     def drop_duplicates(
         self,
-        subset: Hashable | Sequence[Hashable] | AbstractSet | None = ...,
+        subset: Hashable | Iterable[Hashable] | set | None = ...,
         *,
         keep: DropKeep = ...,
         inplace: bool = ...,
@@ -6564,7 +6563,7 @@ def drop_duplicates(
 
     def drop_duplicates(
         self,
-        subset: Hashable | Sequence[Hashable] | AbstractSet | None = None,
+        subset: Hashable | Iterable[Hashable] | set | None = None,
         *,
         keep: DropKeep = "first",
         inplace: bool = False,
@@ -6578,7 +6577,7 @@ def drop_duplicates(
 
         Parameters
         ----------
-        subset : column label or sequence of labels, optional
+        subset : column label or iterable of labels, optional
             Only consider certain columns for identifying duplicates, by
             default use all of the columns.
         keep : {'first', 'last', ``False``}, default 'first'
@@ -6668,7 +6667,7 @@ def drop_duplicates(
 
     def duplicated(
         self,
-        subset: Hashable | Sequence[Hashable] | AbstractSet | None = None,
+        subset: Hashable | Iterable[Hashable] | set | None = None,
         keep: DropKeep = "first",
     ) -> Series:
         """
@@ -6678,7 +6677,7 @@ def duplicated(
 
         Parameters
         ----------
-        subset : column label or sequence of labels, optional
+        subset : column label or iterable of labels, optional
             Only consider certain columns for identifying duplicates, by
             default use all of the columns.
         keep : {'first', 'last', False}, default 'first'
@@ -6793,13 +6792,8 @@ def f(vals) -> tuple[np.ndarray, int]:
             raise KeyError(Index(diff))
 
         if len(subset) == 1 and self.columns.is_unique:
-            # GH#59237 adding support for single element sets
-            if isinstance(subset, set):
-                elem = subset.pop()
-            else:
-                elem = subset[0]
             # GH#45236 This is faster than get_group_index below
-            result = self[elem].duplicated(keep)
+            result = self[next(iter(subset))].duplicated(keep)
             result.name = None
         else:
             vals = (col.values for name, col in self.items() if name in subset)