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: handle mixed-type column sorting in data table (#9102)

Kiran Gadhaveaf1e820c56ff
diff --git a/marimo/_plugins/ui/_impl/tables/pandas_table.py b/marimo/_plugins/ui/_impl/tables/pandas_table.py
index 17914cbdbf..47568a8e13 100644
--- a/marimo/_plugins/ui/_impl/tables/pandas_table.py
+++ b/marimo/_plugins/ui/_impl/tables/pandas_table.py
@@ -29,6 +29,8 @@ from marimo._plugins.ui._impl.tables.table_manager import (
if TYPE_CHECKING:
import pandas as pd
+ from marimo._plugins.ui._impl.table import SortArgs
+
LOGGER = _loggers.marimo_logger()
if TYPE_CHECKING:
@@ -107,6 +109,51 @@ class PandasTableManagerFactory(TableManagerFactory):
def schema(self) -> pd.Series[Any]:
return self._original_data.dtypes # type: ignore
+ def sort_values(self, by: list[SortArgs]) -> TableManager[Any]:
+ if not by:
+ return self
+
+ columns = [sort_arg.by for sort_arg in by]
+ descending = [sort_arg.descending for sort_arg in by]
+
+ # Object-dtype columns may contain mixed Python types
+ # (e.g. int + str) that can't be compared directly.
+ # Cast those to string via temp columns before sorting.
+ dtypes = self._original_data.dtypes
+ mixed_cols = [
+ col for col in columns if dtypes[col] == "object"
+ ]
+
+ if not mixed_cols:
+ return super().sort_values(by)
+
+ df = self.data
+ temp_cols: list[str] = []
+ sort_cols: list[str] = []
+ for col in columns:
+ if col in mixed_cols:
+ temp = f"__sort_{col}"
+ # Preserve nulls so nulls_last=True works.
+ # On pandas <3.0, cast(String) turns None
+ # into the string "None" instead of null.
+ df = df.with_columns(
+ nw.when(nw.col(col).is_null())
+ .then(None)
+ .otherwise(nw.col(col).cast(nw.String))
+ .alias(temp)
+ )
+ temp_cols.append(temp)
+ sort_cols.append(temp)
+ else:
+ sort_cols.append(col)
+
+ df = df.sort(
+ sort_cols,
+ descending=descending,
+ nulls_last=True,
+ ).drop(temp_cols)
+ return self.with_new_data(df)
+
# We override narwhals's to_csv_str to handle pandas
# headers
def to_csv_str(
diff --git a/tests/_plugins/ui/_impl/tables/test_pandas_table.py b/tests/_plugins/ui/_impl/tables/test_pandas_table.py
index 00311a9008..a11412b79e 100644
--- a/tests/_plugins/ui/_impl/tables/test_pandas_table.py
+++ b/tests/_plugins/ui/_impl/tables/test_pandas_table.py
@@ -1652,6 +1652,46 @@ class TestPandasTableManager(unittest.TestCase):
last = sorted_manager.data["A"][-1]
assert last is None or isnan(last)
+ def test_sort_values_with_mixed_types(self) -> None:
+ """Sorting a column with mixed types (int, str, float, bool, None)
+ should not raise, falling back to string comparison."""
+ df = pd.DataFrame(
+ {
+ "mixed": [42, "hello", 3.14, True, None, "world", 7],
+ "normal": [1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0],
+ }
+ )
+ manager = self.factory.create()(df)
+
+ # descending
+ sorted_manager = manager.sort_values(
+ [SortArgs(by="mixed", descending=True)]
+ )
+ assert sorted_manager.get_num_rows() == 7
+ values = sorted_manager.data["mixed"].to_list()
+ assert values[-1] is None or (
+ isinstance(values[-1], float) and isnan(values[-1])
+ )
+
+ # ascending
+ sorted_manager = manager.sort_values(
+ [SortArgs(by="mixed", descending=False)]
+ )
+ assert sorted_manager.get_num_rows() == 7
+ values = sorted_manager.data["mixed"].to_list()
+ assert values[-1] is None or (
+ isinstance(values[-1], float) and isnan(values[-1])
+ )
+
+ # multi-column sort with one mixed column
+ sorted_manager = manager.sort_values(
+ [
+ SortArgs(by="mixed", descending=False),
+ SortArgs(by="normal", descending=False),
+ ]
+ )
+ assert sorted_manager.get_num_rows() == 7
+
def test_dataframe_with_multiindex(self) -> None:
df = pd.DataFrame(
{"A": [1, 2, 3, 4], "B": [5, 6, 7, 8]},