BUG: Fixed DataFrame.combine with non-unique columns

doc/source/whatsnew/v3.0.0.rst

@@ -1261,6 +1261,7 @@ Other
 - Bug in printing a :class:`DataFrame` with a :class:`DataFrame` stored in :attr:`DataFrame.attrs` raised a ``ValueError`` (:issue:`60455`)
 - Bug in printing a :class:`Series` with a :class:`DataFrame` stored in :attr:`Series.attrs` raised a ``ValueError`` (:issue:`60568`)
 - Deprecated the keyword ``check_datetimelike_compat`` in :meth:`testing.assert_frame_equal` and :meth:`testing.assert_series_equal` (:issue:`55638`)
+- Fixed bug in :meth:`DataFrame.combine` with non-unique columns (:issue:`51340`)
 - Fixed bug in :meth:`Series.replace` and :meth:`DataFrame.replace` when trying to replace :class:`NA` values in a :class:`Float64Dtype` object with ``np.nan``; this now works with ``pd.set_option("mode.nan_is_na", False)`` and is irrelevant otherwise (:issue:`55127`)
 - Fixed bug in :meth:`Series.replace` and :meth:`DataFrame.replace` when trying to replace :class:`np.nan` values in a :class:`Int64Dtype` object with :class:`NA`; this is now a no-op with ``pd.set_option("mode.nan_is_na", False)`` and is irrelevant otherwise (:issue:`51237`)
 - Fixed bug in the :meth:`Series.rank` with object dtype and extremely small float values (:issue:`62036`)

pandas/core/frame.py

@@ -194,7 +194,10 @@
     nargsort,
 )
 
-from pandas.io.common import get_handle
+from pandas.io.common import (
+    dedup_names,
+    get_handle,
+)
 from pandas.io.formats import (
     console,
     format as fmt,
@@ -9093,7 +9096,7 @@ def combine(
         2  NaN  3.0 1.0
         """
         other_idxlen = len(other.index)  # save for compare
-        other_columns = other.columns
+        self_columns, other_columns = self.columns, other.columns
 
         this, other = self.align(other)
         new_index = this.index
@@ -9104,11 +9107,26 @@ def combine(
         if self.empty and len(other) == other_idxlen:
             return other.copy()
 
+        new_columns_out = self.columns.union(other_columns, sort=False)
+        # Deduplicate column names if necessary
+        self_columns = Index(
+            dedup_names(list(self_columns), False), dtype=self_columns.dtype
+        )
+        other_columns = Index(
+            dedup_names(list(other_columns), False), dtype=other_columns.dtype
+        )
+        this.columns = Index(
+            dedup_names(list(this.columns), False), dtype=this.columns.dtype
+        )
+        other.columns = Index(
+            dedup_names(list(other.columns), False), dtype=other.columns.dtype
+        )
+
         # preserve column order
-        new_columns = self.columns.union(other_columns, sort=False)
+        new_columns_unique = self_columns.union(other_columns, sort=False)
         do_fill = fill_value is not None
         result = {}
-        for col in new_columns:
+        for col in new_columns_unique:
             series = this[col]
             other_series = other[col]
 
@@ -9158,7 +9176,9 @@ def combine(
             result[col] = arr
 
         # convert_objects just in case
-        frame_result = self._constructor(result, index=new_index, columns=new_columns)
+        frame_result = self._constructor(
+            result, index=new_index, columns=new_columns_out
+        )
         return frame_result.__finalize__(self, method="combine")
 
     def combine_first(self, other: DataFrame) -> DataFrame:

pandas/tests/frame/methods/test_combine.py

@@ -45,3 +45,17 @@ def test_combine_generic(self, float_frame):
         )
         tm.assert_frame_equal(chunk, exp)
         tm.assert_frame_equal(chunk2, exp)
+
+    def test_combine_non_unique_columns(self):
+        # GH#51340
+        df = pd.DataFrame({"A": range(5), "B": range(5)})
+        df.columns = ["A", "A"]
+
+        other = df.copy()
+        df.iloc[1, :] = 11
+
+        def combiner(a, b):
+            return b
+
+        result = df.combine(other, combiner)
+        tm.assert_frame_equal(result, other)