By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement . We’ll occasionally send you account related emails.

上图是我的数据前一部分，我的目的是对 titles 一列进行分词，分词的代码如下。现在遇到的问题是 AttributeError: 'int' object has no attribute 'decode' ，所以我认为是 titles 中有 int 所致，所以添加了一个判断条件，但是代码执行的结果依旧是报之前的错。请问这是什么原因？

def jiebait(text):
    seglist = jieba.cut(text, cut_all = True)
    fenci = []
    for word in seglist:
        if (not isinstance(word, int)) and (len(word) >= 2):
            fenci.append(word)
    # 如用搜索引擎模式：
    #seglist = jieba.cut_for_search(text)
    return ' '.join(fenci)

AttributeError Traceback (most recent call last)
in ()
2 result_line = ""
3 # segment
----> 4 seg_list = [str(w) for w in jieba.cut(line, cut_all = False)]
5 # remove special character
6 temp = re.sub("[\s+.!_,$%^ (+"')]+|[+——()?【】“”！，。？、~@#￥%……& （）]+", "",("/".join(seg_list)))

in (.0)
2 result_line = ""
3 # segment
----> 4 seg_list = [str(w) for w in jieba.cut(line, cut_all = False)]
5 # remove special character
6 temp = re.sub("[\s+.!_,$%^ (+"')]+|[+——()?【】“”！，。？、~@#￥%……& （）]+", "",("/".join(seg_list)))

D:\Anaconda\lib\site-packages\jieba_ init _.py in cut(self, sentence, cut_all, HMM)
280 - HMM: Whether to use the Hidden Markov Model.
281 '''
--> 282 sentence = strdecode(sentence)
284 if cut_all:

D:\Anaconda\lib\site-packages\jieba_compat.py in strdecode(sentence)
35 if not isinstance(sentence, text_type):
36 try:
---> 37 sentence = sentence.decode('utf-8')
38 except UnicodeDecodeError:
39 sentence = sentence.decode('gbk', 'ignore')

AttributeError: 'int' object has no attribute 'decode'