embedding_dim=embedding_dim,
scale_model=scale_model)
dt_val = dataset_manager.encode_data_with_label_all_data_act_res_embedding(
val,
embedding_type=embedding_type,
embedding_dim=embedding_dim,
scale_model=scale_model)
if "bpic2017" in dataset_name:
max_len = min(20, dataset_manager.get_pos_case_length_quantile(data, 0.95))
else:
max_len = min(40, dataset_manager.get_pos_case_length_quantile(data, 0.95))
data_dim = dt_train.shape[1] - 3
X, _, _, y_o = dataset_manager.generate_3d_data_with_label_all_data(
dt_train, max_len)
X_val, _, _, y_o_val = dataset_manager.generate_3d_data_with_label_all_data(
dt_val, max_len)
print(X.shape, y_o.shape, X_val.shape, y_o_val.shape)
print("Done: %s" % (time.time() - start))
print('Optimizing parameters...')
space = {
'dropout':
hp.uniform('dropout', 0, 0.3),
'lstmsize':
hp.choice('lstmsize', [str(val) for val in range(10, 151)]),
'batch_size':
hp.choice('batch_size', ["8", "16", "32", "64"]),
dataset_manager.calculate_divisors(dt_train)
elif normalize_over == "all":
dt_all = dataset_manager.extract_timestamp_features(data)
dt_all = dataset_manager.extract_duration_features(dt_all)
dataset_manager.calculate_divisors(dt_all)
else:
print("unknown normalization mode")
dt_train = dataset_manager.normalize_data(dt_train)
max_len = dataset_manager.get_max_case_length(dt_train)
activity_cols = [col for col in dt_train.columns if col.startswith("act")]
n_activities = len(activity_cols)
data_dim = dt_train.shape[1] - 3
X, y_a, y_t, y_o = dataset_manager.generate_3d_data_with_label_all_data(
dt_train, max_len)
print(X.shape, y_a.shape, y_t.shape, y_o.shape)
sys.stdout.flush()
print("Done: %s" % (time.time() - start))
# compile a model with same parameters that was trained, and load the weights of the trained model
print('Training model...')
start = time.time()
main_input = Input(shape=(max_len, data_dim), name='main_input')
# train a 2-layer LSTM with one shared layer
l1 = LSTM(lstmsize,
input_shape=(max_len, data_dim),
consume_less='gpu',
init='glorot_uniform',
