add duplicate column name validation

rapidsai · Jan 25, 2022 · b1dfe93 · b1dfe93
1 parent a552afb
commit b1dfe93
Show file tree

Hide file tree

Showing 2 changed files with 18 additions and 5 deletions.
diff --git a/python/cudf/cudf/core/column_accessor.py b/python/cudf/cudf/core/column_accessor.py
@@ -1,4 +1,4 @@
-# Copyright (c) 2021, NVIDIA CORPORATION.
+# Copyright (c) 2021-2022, NVIDIA CORPORATION.
 
 from __future__ import annotations
 
@@ -523,14 +523,19 @@ def rename_column(x):
                 raise IndexError(
                     f"Too many levels: Index has only 1 level, not {level+1}"
                 )
+
             if isinstance(mapper, Mapping):
-                new_names = (
+                new_col_names = [
                     mapper.get(col_name, col_name) for col_name in self.keys()
-                )
+                ]
             else:
-                new_names = (mapper(col_name) for col_name in self.keys())
+                new_col_names = [mapper(col_name) for col_name in self.keys()]
+
+            if len(new_col_names) != len(set(new_col_names)):
+                raise ValueError("Duplicate column names are not allowed")
+
             ca = ColumnAccessor(
-                dict(zip(new_names, self.values())),
+                dict(zip(new_col_names, self.values())),
                 level_names=self.level_names,
                 multiindex=self.multiindex,
             )

diff --git a/python/cudf/cudf/tests/test_dataframe.py b/python/cudf/cudf/tests/test_dataframe.py
@@ -9083,3 +9083,11 @@ def test_dataframe_assign_cp_np_array():
     gdf[[f"f_{i}" for i in range(n)]] = cp_ndarray
 
     assert_eq(pdf, gdf)
+
+
+def test_dataframe_rename_duplicate_column():
+    gdf = cudf.DataFrame({"a": [1, 2, 3], "b": [3, 4, 5]})
+    with pytest.raises(
+        ValueError, match="Duplicate column names are not allowed"
+    ):
+        gdf.rename(columns={"a": "b"}, inplace=True)