# df_data_1_test = raw_values[upper_train - 1:upper_test]
df_data_1_test = diff_values[upper_train:upper_test]
test_set = df_data_1_test.values
# reshaping
test_set = numpy.reshape(test_set, (test_set.shape[0], 1))
# scaling
test_set = sc.fit_transform(numpy.float64(test_set))
x_test, y_test = data_misc.test_data_to_timesteps(
test=test_set, testset_length=testset_length, timesteps=timesteps)
rmse, predictions = compare(y_test, y_test)
predicted_bcg_values_test_mae = regressor_mae.predict(x_test,
batch_size=batch_size)
regressor_mae.reset_states()
print(predicted_bcg_values_test_mae.shape)
# reshaping
predicted_bcg_values_test_mae = numpy.reshape(
predicted_bcg_values_test_mae, (predicted_bcg_values_test_mae.shape[0],
predicted_bcg_values_test_mae.shape[1]))
y_test = numpy.reshape(y_test, (y_test.shape[0], y_test.shape[1]))
print(predicted_bcg_values_test_mae.shape)
# inverse transform
predicted_bcg_values_test_mae = sc.inverse_transform(
