Skip to content

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

fix: resolve duplicate column keys when index name conflicts with column name (#8999)

Shahmir Varqhaa83e8d8af986
diff --git a/marimo/_plugins/ui/_impl/tables/pandas_table.py b/marimo/_plugins/ui/_impl/tables/pandas_table.py
index fc0449b4cc..340741667b 100644
--- a/marimo/_plugins/ui/_impl/tables/pandas_table.py
+++ b/marimo/_plugins/ui/_impl/tables/pandas_table.py
@@ -42,6 +42,11 @@ def _trivial_range_index(index: pd.Index) -> bool:
return isinstance(index, pd.RangeIndex) and index.name is None
+def _resolve_index_name(name: object, columns: set[str]) -> str:
+ """Return a non-conflicting index name by appending '_index' if needed."""
+ return f"{name}_index" if name in columns else str(name)
+
+
def _resolve_index_column_conflicts(df: pd.DataFrame) -> pd.DataFrame:
"""Rename index names that conflict with column names by appending '_index'.
@@ -55,12 +60,8 @@ def _resolve_index_column_conflicts(df: pd.DataFrame) -> pd.DataFrame:
if not conflicting_names:
return df
- new_names: list[str] = []
- for name in index_names:
- if name in conflicting_names:
- new_names.append(f"{name}_index")
- else:
- new_names.append(str(name))
+ columns = set(df.columns)
+ new_names = [_resolve_index_name(name, columns) for name in index_names]
if isinstance(df.index, pd.MultiIndex):
df.index = df.index.set_names(new_names)
@@ -329,9 +330,16 @@ class PandasTableManagerFactory(TableManagerFactory):
# We override the default implementation to use pandas
# headers
def get_row_headers(self) -> FieldTypes:
- return self._get_row_headers_for_index(
+ headers = self._get_row_headers_for_index(
self._original_data.index
)
+ # Rename headers that collide with column names so the
+ # frontend receives names consistent with to_json_str().
+ columns = set(self._original_data.columns)
+ return [
+ (_resolve_index_name(name, columns), ft)
+ for name, ft in headers
+ ]
def _has_non_trivial_index(self) -> bool:
"""Check if the DataFrame has a non-trivial index that should be searched."""
diff --git a/tests/_plugins/ui/_impl/tables/test_pandas_table.py b/tests/_plugins/ui/_impl/tables/test_pandas_table.py
index e08626aae2..00311a9008 100644
--- a/tests/_plugins/ui/_impl/tables/test_pandas_table.py
+++ b/tests/_plugins/ui/_impl/tables/test_pandas_table.py
@@ -652,6 +652,40 @@ class TestPandasTableManager(unittest.TestCase):
[("X", ("string", "str")), ("Y", ("integer", "int64"))],
]
+ def test_get_row_headers_index_column_name_conflict(self) -> None:
+ data = pd.DataFrame(
+ {"ID_SOMETHING": [1, 2], "ID_DATE": [3, 4]},
+ index=pd.Index(["2026-04-01", "2026-04-02"], name="ID_DATE"),
+ )
+ manager = self.factory.create()(data)
+ headers = manager.get_row_headers()
+ # Index renamed to avoid collision with column of the same name
+ header_names = [h[0] for h in headers]
+ assert header_names == ["ID_DATE_index"]
+
+ def test_get_row_headers_multi_index_partial_conflict(self) -> None:
+ data = pd.DataFrame(
+ {"x": [1, 2, 3], "y": [4, 5, 6]},
+ index=pd.MultiIndex.from_tuples(
+ [(1, 4), (2, 5), (3, 6)], names=["x", "z"]
+ ),
+ )
+ manager = self.factory.create()(data)
+ headers = manager.get_row_headers()
+ # Only the conflicting level is renamed
+ header_names = [h[0] for h in headers]
+ assert header_names == ["x_index", "z"]
+
+ def test_get_row_headers_no_conflict(self) -> None:
+ data = pd.DataFrame(
+ {"A": [1, 2, 3]},
+ index=pd.Index(["a", "b", "c"], name="idx"),
+ )
+ manager = self.factory.create()(data)
+ headers = manager.get_row_headers()
+ header_names = [h[0] for h in headers]
+ assert header_names == ["idx"]
+
def test_is_type(self) -> None:
assert self.manager.is_type(self.data)
assert not self.manager.is_type("not a dataframe")