Python DatasetManager.encode_data_with_label_all_data示例

示例#1

文件： evaluate_singletask_outcome_all_data.py 项目： irhete/lstm-predictive-monitoring

results_file = os.path.join(
    output_dir, "evaluation_results/results_%s_%s_%s.csv" %
    (cls_method, dataset_name, params))

##### MAIN PART ######

print('Preparing data...')
start = time.time()

dataset_manager = DatasetManager(dataset_name)
data = dataset_manager.read_dataset()
train, test = dataset_manager.split_data(
    data, train_ratio, split=data_split_type
)  # to reproduce results of Tax et al., use 'ordered' instead of 'temporal'

dt_train = dataset_manager.encode_data_with_label_all_data(train)
dt_test = dataset_manager.encode_data_with_label_all_data(test)

if normalize_over == "train":
    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_test = dataset_manager.normalize_data(dt_test)

print("Done: %s" % (time.time() - start))

示例#2

文件： validate.py 项目： irhete/business-process-embeddings

train_ratio = 0.8
val_ratio = 0.2
activation = "sigmoid"
optimizer = "adam"
nb_epoch = 50

dataset_manager = DatasetManager(dataset_name)
data = dataset_manager.read_dataset()
train, _ = dataset_manager.split_data_strict(data,
                                             train_ratio,
                                             split="temporal")
train, val = dataset_manager.split_val(train, val_ratio, split="random")

if embedding_type == "none":
    dt_train = dataset_manager.encode_data_with_label_all_data(train)
    dt_val = dataset_manager.encode_data_with_label_all_data(val)
else:
    dt_train = dataset_manager.encode_data_with_label_all_data_act_res_embedding(
        train,
        embedding_type=embedding_type,
        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))