else:
model.fit(x_train)
y_pred = model.predict(x_test)
y_pred = convert_predictions(y_pred)
metrics_report(y_test, y_pred)
scores.append(
create_experiment_report(get_metrics(y_test, y_pred),
model.get_params()))
return {'experiments': scores}
if __name__ == '__main__':
x_train = load_drain3(
'../../data/interim/HDFS1/train-data-Drain3-HDFS1-cv1-1.binlog')
y_train = load_labels(
'../../data/interim/HDFS1/train-labels-HDFS1-cv1-1.csv')
x_val = load_drain3(
'../../data/interim/HDFS1/val-data-Drain3-HDFS1-cv1-1.binlog')
y_val = load_labels('../../data/interim/HDFS1/val-labels-HDFS1-cv1-1.csv')
y_train = get_labels_from_csv(y_train, x_train.keys())
y_val = get_labels_from_csv(y_val, x_val.keys())
results = train_lof(x_train, x_val, y_train, y_val)
save_experiment(results,
'../../models/LOF-hyperparameters-Drain3-HDFS1.json')
results = train_iso_forest(x_train, x_val, y_train, y_val)
save_experiment(results,
'../../models/IF-hyperparameters-Drain3-HDFS1.json')
y_train = np.load(
'../../data/processed/HDFS1/y-train-HDFS1-cv1-1-block.npy')
y_val = np.load('../../data/processed/HDFS1/y-val-HDFS1-cv1-1-block.npy')
# results = train_window(X_train, X_val, y_train, y_val)
# save_experiment(results, '../../models/TCN-cropped-window-embeddings-HDFS1.json')
# results = train_tcnn(X_train, X_val, y_train, y_val)
# save_experiment(results, EXPERIMENT_PATH)
# results = train_cnn1d(X_train, X_val, y_train, y_val)
# save_experiment(results, EXPERIMENT_PATH)
# results = train_cnn2d(X_train, X_val, y_train, y_val)
# save_experiment(results, EXPERIMENT_PATH)
# results = train_tcnn_cnn1d(X_train, X_val, y_train, y_val)
# save_experiment(results, EXPERIMENT_PATH)
# results = train_aetcnn(X_train, X_val, y_train, y_val)
# save_experiment(results, EXPERIMENT_PATH)
# results = train_sa_cnn1d(X_train, X_val, y_train, y_val)
# save_experiment(results, EXPERIMENT_PATH)
# results = train_sa_cnn2d(X_train, X_val, y_train, y_val)
# save_experiment(results, EXPERIMENT_PATH)
results = train_aecnn1d(X_train, X_val, y_train, y_val)
save_experiment(results, EXPERIMENT_PATH)
print('AETCN + IF model:', json.dumps(results, indent=4, sort_keys=True))
results = evaluate_hybrid_model_ae(X_train, X_test, y_test)
experiment_reports['AETCN + AE model'] = results
print('AETCN + AE model:', json.dumps(results, indent=4, sort_keys=True))
############################### BASELINE METHODS ###################################################################
X_train = load_pickle_file(
'../../data/interim/HDFS1/train-data-Drain3-HDFS1-cv1-1.binlog')
y_train = load_labels(
'../../data/interim/HDFS1/train-labels-HDFS1-cv1-1.csv')
X_test = load_pickle_file(
'../../data/interim/HDFS1/test-data-Drain3-HDFS1.binlog')
y_test = load_labels('../../data/interim/HDFS1/test-labels-HDFS1.csv')
results = evaluate_autoencoder(X_train, X_test, y_test)
experiment_reports['AE model'] = results
print('AE model:', json.dumps(results, indent=4, sort_keys=True))
results = evaluate_iso_forest(X_train, X_test, y_test)
experiment_reports['IF model'] = results
print('IF model:', json.dumps(results, indent=4, sort_keys=True))
results = evaluate_lof(X_train, X_test, y_test)
experiment_reports['LOF model'] = results
print('LOF model:', json.dumps(results, indent=4, sort_keys=True))
print_report(experiment_reports)
save_experiment(experiment_reports, '../../reports/results/evalution.json')