BUG: can't concatenate DataFrame with Series with duplicate keys (pandas-dev#33805)

Author: MarcoGorelli

doc/source/whatsnew/v1.1.0.rst

@@ -724,6 +724,7 @@ Reshaping
 - Bug in :meth:`concat` where when passing a non-dict mapping as ``objs`` would raise a ``TypeError`` (:issue:`32863`)
 - :meth:`DataFrame.agg` now provides more descriptive ``SpecificationError`` message when attempting to aggregating non-existant column (:issue:`32755`)
 - Bug in :meth:`DataFrame.unstack` when MultiIndexed columns and MultiIndexed rows were used (:issue:`32624`, :issue:`24729` and :issue:`28306`)
+- Bug in :func:`concat` was not allowing for concatenation of ``DataFrame`` and ``Series`` with duplicate keys (:issue:`33654`)
 - Bug in :func:`cut` raised an error when non-unique labels (:issue:`33141`)
 
 

pandas/core/reshape/concat.py

@@ -619,10 +619,10 @@ def _make_concat_multiindex(indexes, keys, levels=None, names=None) -> MultiInde
         for hlevel, level in zip(zipped, levels):
             to_concat = []
             for key, index in zip(hlevel, indexes):
-                try:
-                    i = level.get_loc(key)
-                except KeyError as err:
-                    raise ValueError(f"Key {key} not in level {level}") from err
+                mask = level == key
+                if not mask.any():
+                    raise ValueError(f"Key {key} not in level {level}")
+                i = np.nonzero(level == key)[0][0]
 
                 to_concat.append(np.repeat(i, len(index)))
             codes_list.append(np.concatenate(to_concat))

pandas/tests/reshape/test_concat.py

@@ -2802,3 +2802,18 @@ def test_concat_multiindex_datetime_object_index():
     )
     result = concat([s, s2], axis=1)
     tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize("keys", [["e", "f", "f"], ["f", "e", "f"]])
+def test_duplicate_keys(keys):
+    # GH 33654
+    df = DataFrame({"a": [1, 2, 3], "b": [4, 5, 6]})
+    s1 = Series([7, 8, 9], name="c")
+    s2 = Series([10, 11, 12], name="d")
+    result = concat([df, s1, s2], axis=1, keys=keys)
+    expected_values = [[1, 4, 7, 10], [2, 5, 8, 11], [3, 6, 9, 12]]
+    expected_columns = pd.MultiIndex.from_tuples(
+        [(keys[0], "a"), (keys[0], "b"), (keys[1], "c"), (keys[2], "d")]
+    )
+    expected = DataFrame(expected_values, columns=expected_columns)
+    tm.assert_frame_equal(result, expected)