DEPR: scalar index for length-1-list level groupby

doc/source/whatsnew/v2.0.0.rst

@@ -816,6 +816,7 @@ Deprecations
 - Deprecated :meth:`DataFrame.pad` in favor of :meth:`DataFrame.ffill` (:issue:`33396`)
 - Deprecated :meth:`DataFrame.backfill` in favor of :meth:`DataFrame.bfill` (:issue:`33396`)
 - Deprecated :meth:`~pandas.io.stata.StataReader.close`. Use :class:`~pandas.io.stata.StataReader` as a context manager instead (:issue:`49228`)
+- Deprecated producing a single element when iterating over a :class:`DataFrameGroupBy` or a :class:`SeriesGroupBy` that has been grouped by a ``level`` parameter that is a list of length 1; A tuple of length one will be returned instead (:issue:`51583`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_200.prior_deprecations:

pandas/core/groupby/groupby.py

@@ -626,6 +626,7 @@ class BaseGroupBy(PandasObject, SelectionMixin[NDFrameT], GroupByIndexingMixin):
     axis: AxisInt
     grouper: ops.BaseGrouper
     keys: _KeysArgType | None = None
+    level: IndexLabel | None = None
     group_keys: bool | lib.NoDefault
 
     @final
@@ -810,9 +811,16 @@ def __iter__(self) -> Iterator[tuple[Hashable, NDFrameT]]:
         for each group
         """
         keys = self.keys
+        level = self.level
         result = self.grouper.get_iterator(self._selected_obj, axis=self.axis)
-        if isinstance(keys, list) and len(keys) == 1:
+        if (
+            isinstance(keys, list)
+            and len(keys) == 1
+            or isinstance(level, list)
+            and len(level) == 1
+        ):
             # GH#42795 - when keys is a list, return tuples even when length is 1
+            # GH#51583 - when level is a list, return tuples even when length is 1
             result = (((key,), group) for key, group in result)
         return result
 

pandas/tests/groupby/test_groupby.py

@@ -2709,6 +2709,22 @@ def test_single_element_list_grouping():
     assert result == expected
 
 
+def test_single_element_list_level_grouping():
+    # GH 51583
+    df = DataFrame({"a": [1, 2], "b": [3, 4], "c": [5, 6]}, index=["x", "y"])
+    result = [key for key, _ in df.groupby(level=[0])]
+    expected = [("x",), ("y",)]
+    assert result == expected
+
+
+def test_single_element_list_multiindex_level_grouping():
+    # GH 51583
+    df = MultiIndex.from_product([[1, 2], [3, 4]], names=["x", "y"]).to_frame()
+    result = [key for key, _ in df.groupby(level=[0])]
+    expected = [(1,), (2,)]
+    assert result == expected
+
+
 @pytest.mark.parametrize("func", ["sum", "cumsum", "cumprod", "prod"])
 def test_groupby_avoid_casting_to_float(func):
     # GH#37493