Add support for serializing numpy data types. (#635)

* Add support for serializing numpy data types.

* Added tests on numpy-types in sklearn_to_flow.

Author: PGijsbers

openml/flows/sklearn_converter.py

@@ -37,7 +37,10 @@
 
 def sklearn_to_flow(o, parent_model=None):
     # TODO: assert that only on first recursion lvl `parent_model` can be None
-
+    simple_numpy_types = [nptype for type_cat, nptypes in np.sctypes.items()
+                          for nptype in nptypes
+                          if type_cat != 'others']
+    simple_types = tuple([bool, int, float, str] + simple_numpy_types)
     if _is_estimator(o):
         # is the main model or a submodel
         rval = _serialize_model(o)
@@ -46,7 +49,9 @@ def sklearn_to_flow(o, parent_model=None):
         rval = [sklearn_to_flow(element, parent_model) for element in o]
         if isinstance(o, tuple):
             rval = tuple(rval)
-    elif isinstance(o, (bool, int, float, str)) or o is None:
+    elif isinstance(o, simple_types) or o is None:
+        if isinstance(o, tuple(simple_numpy_types)):
+            o = o.item()
         # base parameter values
         rval = o
     elif isinstance(o, dict):

tests/test_flows/test_sklearn.py

@@ -1180,3 +1180,18 @@ def test_obtain_parameter_values(self):
             if parameter['oml:name'] == 'n_estimators':
                 self.assertEqual(parameter['oml:value'], '5')
                 self.assertEqual(parameter['oml:component'], 2)
+
+    def test_numpy_type_allowed_in_flow(self):
+        """ Simple numpy types should be serializable. """
+        dt = sklearn.tree.DecisionTreeClassifier(
+            max_depth=np.float64(3.0),
+            min_samples_leaf=np.int32(5)
+        )
+        sklearn_to_flow(dt)
+
+    def test_numpy_array_not_allowed_in_flow(self):
+        """ Simple numpy arrays should not be serializable. """
+        bin = sklearn.preprocessing.MultiLabelBinarizer(
+            classes=np.asarray([1, 2, 3])
+        )
+        self.assertRaises(TypeError, sklearn_to_flow, bin)