subdataset = "machine-1-1"
n_bins = 10
n_random_cuts = 100
point_adjustment = True
iterate_threshold = True
if __name__ == "__main__":
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s P%(process)d %(levelname)s %(message)s",
)
# load dataset
data_dict = load_dataset(
dataset,
subdataset,
"all",
)
x_train = data_dict["train"]
x_test = data_dict["test"]
x_test_labels = data_dict["test_labels"]
# data preprocessing for MSCRED
od = LODA(n_bins=n_bins, n_random_cuts=n_random_cuts)
od.fit(x_train)
# get outlier scores
anomaly_score = od.decision_function(x_test)
anomaly_label = x_test_labels
if __name__ == "__main__":
config = ExpConfig()
config.x_dim = get_data_dim(dataset)
# print_with_title("Configurations", pformat(config.to_dict()), after="\n")
# open the result object and prepare for result directories if specified
results = MLResults(config.result_dir)
results.save_config(config) # save experiment settings for review
results.make_dirs(config.save_dir, exist_ok=True)
logging.basicConfig(
level="INFO",
format="%(asctime)s [%(levelname)s] %(name)s: %(message)s")
data_dict = load_dataset(dataset, subdataset)
# preprocessing
pp = preprocessor()
data_dict = pp.normalize(data_dict)
# generate sliding windows
window_dict = generate_windows(data_dict,
window_size=config.window_length,
stride=5)
# batch data
x_train = DataGenerator(window_dict["train_windows"])
x_test = DataGenerator(window_dict["test_windows"])
test_labels = DataGenerator(window_dict["test_labels"])
