def detect(systemName):
tuning_file = os.path.join(ROOT_DIR, 'experiments', 'tuning', 'results',
'incode', systemName + '.csv')
params = detection_utils.get_optimal_hyperparameters(tuning_file)
return detect_with_params(systemName, params['ATFD'], params['LAA'],
params['FDP'])
def predict(antipattern, systemName): tuning_file = os.path.join(ROOT_DIR, 'experiments', 'tuning', 'results', 'vote', antipattern, systemName + '.csv') params = detection_utils.get_optimal_hyperparameters(tuning_file) k = params['Policy'] toolsPredictions = asci_utils.get_tools_predictions(antipattern, systemName) return (np.sum(toolsPredictions, axis=0) >= k).astype(float)
def detect(systemName): tuning_file = os.path.join(ROOT_DIR, 'experiments', 'tuning', 'results', 'hist', 'feature_envy', systemName + '.csv') params = detection_utils.get_optimal_hyperparameters(tuning_file) core_metrics_map = cm.getFECoreMetrics(systemName) return [entityName for entityName, ratio in core_metrics_map.items() if ratio[0]>params['Alpha']]
def predict(antipattern, system):
tuning_file = os.path.join(ROOT_DIR, "experiments", "tuning", "results",
"smad", antipattern, system + ".csv")
params = detection_utils.get_optimal_hyperparameters(tuning_file)
X = detection_utils.getInstances(antipattern, system)
# New graph
tf.reset_default_graph()
# Create model
model = md.SMAD(shape=params["Dense sizes"], input_size=X.shape[-1])
return smad_utils.ensemble_prediction(
model=model,
save_paths=[
smad_utils.get_save_path(antipattern, system, i) for i in range(10)
],
input_x=X)
loss_train = session.run(model.loss, feed_dict={model.input_x:x_train, model.input_y:y_train, model.gamma: gamma})
loss_test = session.run(model.loss, feed_dict={model.input_x:x_test, model.input_y:y_test, model.gamma: gamma})
losses_train.append(loss_train)
losses_test.append(loss_test)
return losses_train, losses_test
if __name__ == "__main__":
args = parse_args()
# Use the "optimal" hyper-parameters found via tuning if unspecified
hyper_parameters = None
for key in ['learning_rate', 'beta', 'gamma', 'dense_sizes']:
if args.__dict__[key] == None:
if hyper_parameters == None:
tuning_file = os.path.join(ROOT_DIR, 'experiments', 'tuning', 'results', 'smad', args.antipattern, args.test_system + '.csv')
hyper_parameters = detection_utils.get_optimal_hyperparameters(tuning_file)
args.__dict__[key] = hyper_parameters[' '.join(key.split('_')).capitalize()]
# Remove the test system from the training set
systems = data_utils.getSystems()
systems.remove(args.test_system)
systems = list(systems)
# Get training data
x_train = reduce(lambda x1, x2: np.concatenate((x1, x2), axis=0), [detection_utils.getInstances(args.antipattern, s) for s in systems])
y_train = reduce(lambda x1, x2: np.concatenate((x1, x2), axis=0), [detection_utils.getLabels(args.antipattern, s) for s in systems])
# Get test data
x_test = detection_utils.getInstances(args.antipattern, args.test_system)
y_test = detection_utils.getLabels(args.antipattern, args.test_system)