Merge branch 'master' of https://github.com/openml/python

Author: joaquinvanschoren

README.md

@@ -5,3 +5,6 @@
 
 A python interface for [OpenML](http://openml.org). The documentation is
 hosted at [readthedocs.org](https://readthedocs.org/projects/openml/).
+
+Please commit to the right branches following the gitflow pattern:
+http://nvie.com/posts/a-successful-git-branching-model/

openml/entities/dataset.py

@@ -134,7 +134,7 @@ def get_dataset(self, target=None, include_row_id=False,
             raise ValueError("Cannot find a ndarray file for dataset %s at"
                              "location %s " % (self.name, path))
         else:
-            with open(path) as fh:
+            with open(path, "rb") as fh:
                 data, categorical, attribute_names = pickle.load(fh)
 
         to_exclude = []

openml/entities/split.py

@@ -43,10 +43,11 @@ def __eq__(self, other):
                     return False
                 else:
                     for fold in self.split[repetition]:
-                        if all(self.split[repetition][fold][0] != \
-                                other.split[repetition][fold][0]) and \
-                                all(self.split[repetition][fold][1] != \
-                                other.split[repetition][fold][1]):
+                        if np.all(self.split[repetition][fold].test != \
+                                other.split[repetition][fold].test)\
+                                and \
+                                np.all(self.split[repetition][fold].train
+                                != other.split[repetition][fold].train):
                             return False
         return True
 

tests/entities/test_split.py

@@ -43,7 +43,7 @@ def test_eq(self):
         self.assertNotEqual(split, split2)
 
         split2 = OpenMLSplit.from_arff_file(self.arff_filename)
-        split2.split[0][0] = (np.zeros((80)), np.zeros((9)))
+        split2.split[0][0] = Split(np.zeros((80)), np.zeros((9)))
         self.assertNotEqual(split, split2)
 
     def test_from_arff_file(self):

tests/entities/tmp.pkl

@@ -234,9 +234,6 @@ def check_run(run):
             self.assertEqual(len(run), 6)
 
         runs = self.connector.get_runs_list(task_id=1)
-        # 1759 as the number of supervised classification tasks retrieved
-        # openml.org from this call; don't trust the number on openml.org as
-        # it also counts private datasets
         self.assertGreaterEqual(len(runs), 800)
         for run in runs:
             check_run(run)
@@ -247,7 +244,7 @@ def check_run(run):
             check_run(run)
 
         runs = self.connector.get_runs_list(setup_id=1)
-        self.assertGreaterEqual(len(runs), 261)
+        self.assertGreaterEqual(len(runs), 260)
         for run in runs:
             check_run(run)