Fixing fetching of categorical sparse data (#823)

* Replacing numpy conversion with pandas categorical encoding

* Adding more unit tests check

* Changing unit test data fetch parameter

Author: Neeratyoy

openml/datasets/dataset.py

@@ -258,6 +258,7 @@ def _get_arff(self, format: str) -> Dict:
             when converted to lower case.
 
 
+
         Returns
         -------
         dict
@@ -332,13 +333,15 @@ def _parse_data_from_arff(
         attribute_names = []
         categories_names = {}
         categorical = []
-        for name, type_ in data['attributes']:
+        for i, (name, type_) in enumerate(data['attributes']):
             # if the feature is nominal and the a sparse matrix is
             # requested, the categories need to be numeric
             if (isinstance(type_, list)
                     and self.format.lower() == 'sparse_arff'):
                 try:
-                    np.array(type_, dtype=np.float32)
+                    # checks if the strings which should be the class labels
+                    # can be encoded into integers
+                    pd.factorize(type_)[0]
                 except ValueError:
                     raise ValueError(
                         "Categorical data needs to be numeric when "

tests/test_datasets/test_dataset.py

@@ -9,6 +9,7 @@
 import openml
 from openml.testing import TestBase
 from openml.exceptions import PyOpenMLError
+from openml.datasets import OpenMLDataset, OpenMLDataFeature
 
 
 class OpenMLDatasetTest(TestBase):
@@ -341,6 +342,16 @@ def test_get_sparse_dataset_rowid_and_ignore_and_target(self):
         self.assertListEqual(categorical, [False] * 19998)
         self.assertEqual(y.shape, (600, ))
 
+    def test_get_sparse_categorical_data_id_395(self):
+        dataset = openml.datasets.get_dataset(395, download_data=True)
+        feature = dataset.features[3758]
+        self.assertTrue(isinstance(dataset, OpenMLDataset))
+        self.assertTrue(isinstance(feature, OpenMLDataFeature))
+        self.assertEqual(dataset.name, 're1.wc')
+        self.assertEqual(feature.name, 'CLASS_LABEL')
+        self.assertEqual(feature.data_type, 'nominal')
+        self.assertEqual(len(feature.nominal_values), 25)
+
 
 class OpenMLDatasetQualityTest(TestBase):
     def test__check_qualities(self):