knock78.py 文件源码

def make_kfold(target, feature):
    preds = []
    kf = KFold(len(target), n_folds=folds,shuffle=True)
    test_numbers = []
    for trains, tests in kf:
        test_numbers.append(tests)
        pred_list = []
        feature_list = word_vec.fit_transform([dict(Counter(feature[train])) for train in trains])
        target_list = [target[train] for train in trains]
        logreg.fit(feature_list, target_list)
        for test in tests:
            feature_dict = defaultdict(int)
            for f in word_vec.get_feature_names():
                feature_dict[f] = 0
            for key, value in dict(Counter(feature[test])).items():
                if key in feature_dict:
                    feature_dict[key] = value
            pred_list.append(feature_dict)
        preds.append(logreg.predict(word_vec.fit_transform(pred_list)))
    return preds, test_numbers