def test_vader_save_load(self):
save_path = "test_vader_save_load"
if os.path.exists(save_path):
shutil.rmtree(save_path)
X_train, W_train, y_train = generate_x_w_y(7, 400)
# noinspection PyTypeChecker
vader = VADER(X_train=X_train,
W_train=W_train,
y_train=y_train,
save_path=save_path,
n_hidden=[12, 2],
k=4,
learning_rate=1e-3,
output_activation=None,
recurrent=True,
batch_size=16)
vader.pre_fit(n_epoch=10, verbose=True)
vader.fit(n_epoch=10, verbose=True)
clustering_before_loading = vader.cluster(X_train)
loaded_vader = VADER.load_model(save_path, X_train, W_train, y_train)
clustering_after_loading = loaded_vader.cluster(X_train)
if os.path.exists(save_path):
shutil.rmtree(save_path)
assert list(clustering_before_loading) == list(
clustering_after_loading)
data_reader_spec = importlib.util.spec_from_file_location(
"data_reader", args.data_reader_script)
data_reader_module = importlib.util.module_from_spec(data_reader_spec)
data_reader_spec.loader.exec_module(data_reader_module)
data_reader = data_reader_module.DataReader()
x_tensor = data_reader.read_data(args.input_data_file)
w_tensor = generate_wtensor_from_xtensor(x_tensor)
input_data = np.nan_to_num(x_tensor)
input_weights = w_tensor
features = data_reader.features
time_points = data_reader.time_points
x_label = data_reader.time_point_meaning
ids_list = data_reader.ids_list
vader = VADER.load_model(args.load_path, input_data, input_weights)
n_hidden = [str(layer_size) for layer_size in vader.n_hidden]
report_suffix = f"k{str(vader.K)}" \
f"_n_hidden{'_'.join(n_hidden)}" \
f"_learning_rate{str(vader.learning_rate)}" \
f"_batch_size{str(vader.batch_size)}" \
f"_n_epoch{str(vader.n_epoch)}" \
f"_seed{str(args.seed)}"
plot_file_path = os.path.join(
args.output_path, f"z_scores_trajectories_{report_suffix}.pdf")
clustering_file_path = os.path.join(args.output_path,
f"clustering_{report_suffix}.csv")
clustering = vader.cluster(input_data, input_weights)
pd.Series(list(clustering), index=ids_list, dtype=np.int64,
name='Cluster').to_csv(clustering_file_path)