feat: better error message for duplicate column names in pandas (#1270)

Author: MarcoGorelli

narwhals/_pandas_like/dataframe.py

@@ -89,7 +89,14 @@ def _validate_columns(self, columns: pd.Index) -> None:
             raise ValueError(msg) from None
 
         if len(columns) != len_unique_columns:
-            msg = f"Expected unique column names, got: {columns}"
+            from collections import Counter
+
+            counter = Counter(columns)
+            msg = ""
+            for key, value in counter.items():
+                if value > 1:
+                    msg += f"\n- '{key}' {value} times"
+            msg = f"Expected unique column names, got:{msg}"
             raise ValueError(msg)
 
     def _from_native_frame(self, df: Any) -> Self:

tests/translate/from_native_test.py

@@ -151,7 +151,9 @@ def test_pandas_like_validate() -> None:
     df2 = pd.DataFrame({"b": [1, 2, 3]})
     df = pd.concat([df1, df2, df2], axis=1)
 
-    with pytest.raises(ValueError, match="Expected unique column names"):
+    with pytest.raises(
+        ValueError, match=r"Expected unique column names, got:\n- 'b' 2 times"
+    ):
         nw.from_native(df)