DataSets can now be created directly from numpy arrays.

pml/data/model.py

@@ -50,8 +50,9 @@ def __init__(self, data, labels=None):
           data: 
             Data of unknown type.  The supported types are:
                 1) pandas DataFrame
-                2) Python lists or pandas DataFrame
-                3) an existing DataSet object 
+                2) Python lists
+                3) numpy array
+                4) an existing DataSet object
           labels: pandas Series, Python list or Python dictionary
             The classification labels for the samples in data.  If they are 
             not known (i.e. it is an unlabelled data set) the value None 
@@ -67,6 +68,8 @@ def __init__(self, data, labels=None):
             self._dataframe = data
         elif isinstance(data, list):
             self._dataframe = pd.DataFrame(data)
+        elif isinstance(data, np.ndarray):
+            self._dataframe = pd.DataFrame(data)
         elif isinstance(data, DataSet):
             self._dataframe = data._dataframe.copy()
         else:

test/test_pml/test_data/test_model.py

@@ -40,6 +40,12 @@
 from test.matchers.pandas_matchers import equals_series, equals_dataframe
 
 class DataSetTest(base_tests.BaseDataSetTest, base_tests.BaseFileLoadingTest):
+    def test_create_dataset_from_numpy_array(self):
+        as_list = [[0, 1], [2, 3]]
+        np_array = np.array(as_list)
+        dataset = DataSet(np_array)
+
+        assert_that(dataset, equals_dataset(as_list))
 
     def test_reduce_rows(self):
         dataset = DataSet([[1, 2, 3], [4, 5, 6], [7, 8, 9]])