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.
Python artificial-intelligencedagdata-sciencedata-visualizationdataflowdeveloper-toolsmachine-learningnotebookspipelinepythonreactivesqlweb-app
improvement: support pandas 3.0 str col (#8146)
Myles Scolnickb5272cb3f576
diff --git a/marimo/_plugins/ui/_impl/tables/pandas_table.py b/marimo/_plugins/ui/_impl/tables/pandas_table.pyindex 816e5f65ed..0513b0ad2f 100644--- a/marimo/_plugins/ui/_impl/tables/pandas_table.py+++ b/marimo/_plugins/ui/_impl/tables/pandas_table.py@@ -413,7 +413,7 @@ class PandasTableManagerFactory(TableManagerFactory):return ("string", dtype)if lower_dtype == "category":return ("string", dtype)- if lower_dtype == "string":+ if lower_dtype == "string" or lower_dtype == "str":return ("string", dtype)if lower_dtype.startswith("complex"):return ("unknown", dtype)diff --git a/tests/_plugins/ui/_impl/tables/test_pandas_table.py b/tests/_plugins/ui/_impl/tables/test_pandas_table.pyindex f649c00b3d..2b072b11d1 100644--- a/tests/_plugins/ui/_impl/tables/test_pandas_table.py+++ b/tests/_plugins/ui/_impl/tables/test_pandas_table.py@@ -679,6 +679,46 @@ class TestPandasTableManager(unittest.TestCase):("B", ("string", "string")),]+ def test_get_field_types_str_dtype(self) -> None:+ # Test for pandas 3.0's new "str" dtype (issue #8093)+ # In pandas 3.0, dtype="str" is the new default for string columns+ # This test ensures we correctly identify "str" dtype as "string" field type+ data = pd.DataFrame(+ {+ "A": pd.array(["a", "b", "c"], dtype="str"),+ "B": pd.array(+ ["x", "y", "z"], dtype="string"+ ), # older StringDtype+ }+ )++ manager = self.factory.create()(data)+ field_types = manager.get_field_types()++ # Both "str" and "string" dtypes should map to "string" field type+ assert field_types[0][0] == "A"+ assert (+ field_types[0][1][0] == "string"+ ) # field type should be "string"+ assert field_types[1][0] == "B"+ assert (+ field_types[1][1][0] == "string"+ ) # field type should be "string"++ def test_get_unique_column_values_str_dtype(self) -> None:+ # Test that unique values work correctly with pandas 3.0's "str" dtype+ data = pd.DataFrame(+ {+ "A": pd.array(["a", "b", "c", "a"], dtype="str"),+ }+ )+ manager = self.factory.create()(data)+ unique_values = manager.get_unique_column_values("A")++ # Should return Python strings, not pandas StringArray elements+ assert set(unique_values) == {"a", "b", "c"}+ assert all(isinstance(v, str) for v in unique_values)+@pytest.mark.xfail(reason="Narwhals (wrapped pandas) doesn't support duplicate columns",)