evaluate_features.py 文件源码

def evaluate(X, args):
    enum = ShuffleSplit(len(X), n_iter=args.n_iterations, test_size=args.test_size)
    train_scores = []
    test_scores = []
    for train_index, test_index in enum:
        X_train = [X[idx] for idx in train_index]
        X_test = [X[idx] for idx in test_index]
        X_train, X_test = preprocess_datasets(X_train, X_test, args)
        model = GaussianHMM(n_states=args.n_states, n_training_iterations=args.n_training_iterations,
                            topology=args.topology)
        model.fit(X_train)
        train_scores.extend([model.loglikelihood(X_curr) for X_curr in X_train])
        test_scores.extend([model.loglikelihood(X_curr) for X_curr in X_test])

    train_scores_array = np.array(train_scores)
    train_mean = float(np.mean(train_scores_array))
    train_std = float(np.std(train_scores_array))
    test_scores_array = np.array(test_scores)
    test_mean = float(np.mean(test_scores_array))
    test_std = float(np.std(test_scores_array))
    return train_mean, train_std, test_mean, test_std