def test_prepare_data(self):
""" Test _prepare_data method on numpy array data """
dc = DatasetClient(self.project.hid)
samples = 100
columns = 10
X = np.random.rand(samples, columns)
y = np.random.choice([0, 1], samples, replace=True)
data, data_hash = dc._prepare_data(X, y)
self.assertTrue(data is not None)
self.assertTrue(data_hash is not None)
self.assertTrue(isinstance(data_hash, str))
self.assertEqual(11, len(data.columns))
self.assertTrue('target' in data.columns)
self.assertTrue('attribute_1' in data.columns)
self.assertTrue('attribute_10' in data.columns)
def test_prepare_data_two_sources_numpy(self):
dc = DatasetClient(self.project.hid)
data_1, data_hash_1 = dc._prepare_data(np.array(self.X),
np.array(self.y))
data_2, data_hash_2 = dc._prepare_data(np.array(self.X), None)
self.assertNotEqual(data_hash_1, data_hash_2)
def test_prepare_data_two_sources(self):
dc = DatasetClient(self.project.hid)
data_1, data_hash_1 = dc._prepare_data(self.X, self.y)
data_2, data_hash_2 = dc._prepare_data(self.X, None)
self.assertNotEqual(data_hash_1, data_hash_2)