fe.py 文件源码

def get_text_len(DB, tr, te):
    if tr is None:
        if te=='stage1':
            Data = [DB.data['training_text'],DB.data['test_text_filter']]
        else:
            Data = [pd.concat([DB.data['training_text'],DB.data['test_text_filter']],axis=0),DB.data['stage2_test_text']]
    else:
        Data = [DB.data['training_text']]
    for data in Data:
        data['tl'] = data['Text'].apply(lambda x:len(x))
        data['tl2'] = data['Text'].apply(lambda x:len(x.split()))
    if tr is None:
        X,Xt = Data
        return X[['tl','tl2']].values, Xt[['tl','tl2']].values
    else:
        X = Data[0][['tl','tl2']].values
        return X[tr],X[te]