def test_standard_scaler_sparse_boston_data(self):
X_train, Y_train, X_test, Y_test = get_dataset('boston',
make_sparse=True)
num_data_points = len(X_train.data)
scaler = StandardScaler()
scaler.fit(X_train, Y_train)
tr = scaler.transform(X_train)
# Test this for every single dimension!
means = np.array([tr.data[tr.indptr[i]:tr.indptr[i + 1]].mean()
for i in range(13)])
vars = np.array([tr.data[tr.indptr[i]:tr.indptr[i + 1]].var()
for i in range(13)])
for i in chain(range(1, 3), range(4, 13)):
self.assertAlmostEqual(means[i], 0, 2)
self.assertAlmostEqual(vars[i], 1, 2)
self.assertAlmostEqual(means[3], 1)
self.assertAlmostEqual(vars[3], 0)
# Test that the matrix is still sparse
self.assertTrue(scipy.sparse.issparse(tr))
self.assertEqual(num_data_points, len(tr.data))
