def test_add_listener(self):
adaptor = Adaptor(1)
room = Room()
adaptor.add_listener(room)
self.assertEqual(len(adaptor.get_listeners()), 1)
kernel_type = config.get('kernel_type', '')
cost = config.get('cost', 1)
degree = config.get('degree', 3)
coef0 = config.get('coef0', 0)
sparse_matrix = config.get('sparse_matrix', False)
threshold = config.get('threshold', 50)
y_train, x_train = svm_read_problem(train_data_path)
y_test, x_test = svm_read_problem(test_data_path)
data_size_train = len(y_train)
data_size_test = len(y_test)
features_num = extract_features_from_data(x_train, x_test)
gamma = config.get('gamma', 1 / features_num)
adaptor_train = Adaptor(y=y_train,
x=x_train,
data_size=data_size_train,
features_num=features_num)
adaptor_test = Adaptor(y=y_test,
x=x_test,
data_size=data_size_test,
features_num=features_num)
npx_train = adaptor_train.adapt_x()
npy_train = adaptor_train.adapt_y()
npx_test = adaptor_test.adapt_x()
npy_test = adaptor_test.adapt_y()
lower_boundary = np.zeros((npy_train.shape[0], npy_train.shape[1]))
upper_boundary = np.ones((npy_train.shape[0], npy_train.shape[1])) * cost
q = np.ones((npy_train.shape[0], npy_train.shape[1]))
check_generation_memory(data_size_train, features_num, sparse_matrix)
def test_start_reading(self):
adaptor = Adaptor(1)
adaptor.start_reading()
