two_fold_validation.py 文件源码

def score(train_labels, train_features, test_labels, test_features, save_file, use_tree=False):
    if use_tree:
        train_clf = Classifier(tree.DecisionTreeClassifier())
    else:
        train_clf = Classifier()

    print train_clf.clf
    print ''

    t_start = time.clock()
    train_clf.learn(train_features, train_labels)
    t_end = time.clock()
    if save_file:
        train_clf.save_to_file(open(save_file, 'w'))

    p_start = time.clock()
    predicted = train_clf.clf.predict(test_features)
    p_end = time.clock()

    test_labels_t = train_clf.labels.transform(test_labels)
    print classification_report(test_labels_t, predicted, target_names=train_clf.labels.classes_)
    print 'Training time: %fs' % (t_end - t_start)
    print 'Predicting time: %fs' % (p_end - p_start)
    print 'Mean squared error: %f' % mean_squared_error(test_labels_t, predicted)
    return train_clf.score(test_features, test_labels)