fixed factorize bug

Author: satvshr

openml/datasets/dataset.py

@@ -488,7 +488,7 @@ def _parse_data_from_arff(  # noqa: C901, PLR0912, PLR0915
                 try:
                     # checks if the strings which should be the class labels
                     # can be encoded into integers
-                    pd.factorize(type_)[0]
+                    pd.factorize(np.array(type_))[0]
                 except ValueError as e:
                     raise ValueError(
                         "Categorical data needs to be numeric when using sparse ARFF."

tests/test_datasets/test_dataset.py

@@ -357,7 +357,7 @@ def setUp(self):
     def test_get_sparse_dataset_dataframe_with_target(self):
         X, y, _, attribute_names = self.sparse_dataset.get_data(target="class")
         assert isinstance(X, pd.DataFrame)
-        assert isinstance(X.dtypes[0], pd.SparseDtype)
+        assert isinstance(X.dtypes.iloc[0], pd.SparseDtype)
         assert X.shape == (600, 20000)
 
         assert isinstance(y, pd.Series)