FIX serialize list of integers which are argument to sklearn model

Author: mfeurer

openml/flows/sklearn_converter.py

@@ -73,7 +73,7 @@ def serialize_object(self, o):
         elif self._is_cross_validator(o):
             rval = self.serialize_cross_validator(o)
         else:
-            raise TypeError(o)
+            raise TypeError(o, type(o))
 
         assert o is None or rval is not None
 
@@ -201,7 +201,9 @@ def _serialize_model(self, model):
             if k not in model_parameters.parameters:
                 continue
 
-            if isinstance(rval, (list, tuple)):
+            if isinstance(rval, (list, tuple)) and \
+                    isinstance(rval[0], (list, tuple)) and \
+                    [type(rval[0]) == type(rval[i]) for i in range(len(rval))]:
 
                 # Steps in a pipeline or feature union
                 parameter_value = list()

tests/flows/test_sklearn.py

@@ -198,12 +198,12 @@ def test_serialize_feature_union(self):
         new_model.fit(self.X, self.y)
 
     def test_serialize_complex_flow(self):
+        ohe = sklearn.preprocessing.OneHotEncoder(categorical_features=[0])
         scaler = sklearn.preprocessing.StandardScaler(with_mean=False)
-
         boosting = sklearn.ensemble.AdaBoostClassifier(
             base_estimator=sklearn.tree.DecisionTreeClassifier())
         model = sklearn.pipeline.Pipeline(steps=(
-            ('scaler', scaler), ('boosting', boosting)))
+            ('ohe', ohe), ('scaler', scaler), ('boosting', boosting)))
         parameter_grid = {'n_estimators': [1, 5, 10, 100],
                           'learning_rate': scipy.stats.uniform(0.01, 0.99),
                           'base_estimator__max_depth': scipy.stats.randint(1,
@@ -216,6 +216,7 @@ def test_serialize_complex_flow(self):
         fixture_name = 'sklearn.model_selection._search.RandomizedSearchCV(' \
                        'sklearn.model_selection._split.StratifiedKFold,' \
                        'sklearn.pipeline.Pipeline(' \
+                       'sklearn.preprocessing.data.OneHotEncoder,' \
                        'sklearn.preprocessing.data.StandardScaler,' \
                        'sklearn.ensemble.weight_boosting.AdaBoostClassifier(' \
                        'sklearn.tree.tree.DecisionTreeClassifier)))'