agreed on all other points

Author: janvanrijn

openml/flows/sklearn_converter.py

@@ -533,7 +533,7 @@ def _serialize_cross_validator(o):
     for key in args:
         # We need deprecation warnings to always be on in order to
         # catch deprecated param values.
-        # This is set in utils/__init__.py.py.py but it gets overwritten
+        # This is set in utils/__init__.py but it gets overwritten
         # when running under python3 somehow.
         warnings.simplefilter("always", DeprecationWarning)
         try:

openml/setups/functions.py

@@ -74,7 +74,7 @@ def get_setup(setup_id):
     return _create_setup_from_xml(result_dict)
 
 
-def setup_list(flow=None, tag=None, offset=None, size=None):
+def list_setups(flow=None, tag=None, offset=None, size=None):
     """List all setups matching all of the given filters.
 
         Perform API call `/setup/list/{filters}
@@ -120,11 +120,11 @@ def _list_setups(api_call):
                          % str(setups_dict))
     elif '@xmlns:oml' not in setups_dict['oml:setups']:
         raise ValueError('Error in return XML, does not contain '
-                         '"oml:runs"/@xmlns:oml: %s'
+                         '"oml:setups"/@xmlns:oml: %s'
                          % str(setups_dict))
     elif setups_dict['oml:setups']['@xmlns:oml'] != 'http://openml.org/openml':
         raise ValueError('Error in return XML, value of  '
-                         '"oml:runs"/@xmlns:oml is not '
+                         '"oml:seyups"/@xmlns:oml is not '
                          '"http://openml.org/openml": %s'
                          % str(setups_dict))
 

tests/test_flows/test_flow.py

@@ -239,17 +239,26 @@ def get_sentinel():
     def test_existing_flow_exists(self):
         # create a flow
         nb = sklearn.naive_bayes.GaussianNB()
-        flow = openml.flows.sklearn_to_flow(nb)
-        flow, _ = self._add_sentinel_to_flow_name(flow, None)
-        #publish the flow
-        flow = flow.publish()
-        #redownload the flow
-        flow = openml.flows.get_flow(flow.flow_id)
-
-        # check if flow exists can find it
-        flow = openml.flows.get_flow(flow.flow_id)
-        downloaded_flow_id = openml.flows.flow_exists(flow.name, flow.external_version)
-        self.assertEquals(downloaded_flow_id, flow.flow_id)
+
+        steps = [('imputation', sklearn.preprocessing.Imputer(strategy='median')),
+                 ('hotencoding', sklearn.preprocessing.OneHotEncoder(sparse=False,
+                                                                     handle_unknown='ignore')),
+                 ('variencethreshold', sklearn.feature_selection.VarianceThreshold()),
+                 ('classifier', sklearn.tree.DecisionTreeClassifier())]
+        complicated = sklearn.pipeline.Pipeline(steps=steps)
+
+        for classifier in [nb, complicated]:
+            flow = openml.flows.sklearn_to_flow(classifier)
+            flow, _ = self._add_sentinel_to_flow_name(flow, None)
+            #publish the flow
+            flow = flow.publish()
+            #redownload the flow
+            flow = openml.flows.get_flow(flow.flow_id)
+
+            # check if flow exists can find it
+            flow = openml.flows.get_flow(flow.flow_id)
+            downloaded_flow_id = openml.flows.flow_exists(flow.name, flow.external_version)
+            self.assertEquals(downloaded_flow_id, flow.flow_id)
 
     def test_sklearn_to_upload_to_flow(self):
         iris = sklearn.datasets.load_iris()