jieba的基本操作

import jieba
import re
import jieba.analyse
import jieba.posseg as pseg
from collections import Counter
def token(file):
    f = open(r'E:\BaiduNetdiskDownload\cnews\stop_word.txt','r',encoding='utf8')
    lf = [re.sub('[\r\n]','',i) for i in f.readlines()]
    content = open(r'E:\BaiduNetdiskDownload\cnews\cnews.val.txt', 'rb').read() #rb 形式读取文件
    jieba.analyse.set_idf_path(r'E:\BaiduNetdiskDownload\cnews\idf.txt')
    jieba.analyse.set_stop_words(r'E:\BaiduNetdiskDownload\cnews\stop_word.txt') #去停用词
    key_word_tf_idf = jieba.analyse.extract_tags(content, topK=20, withWeight=True)  # 关键词提取，前20，返回权重，allowPOS不过滤词性
    key_word_text_rank = jieba.analyse.textrank(content, topK=20, withWeight=True) #利用text_rank进行关键词提取
    # print(key_word_text_rank)
    X_train= []
    count_list = []
    for i in train.readlines():
        i = re.sub('[\r\n]','',i)
        i = i.split('\t')
        result = jieba.lcut(i[1])
        pse = pseg.lcut(i[1],HMM=False) #词性标注切分
        for word,flage in pse:
            print(word,flage) #词性标注
        train_list = []
        for j in result:
            print(j)
            if j not in lf:
                train_list.append(j)
                count_list.append(j)
        X_train.append(train_list)
    count = Counter(count_list) #统计词频
    print(count)
train = open(r'E:\BaiduNetdiskDownload\cnews\cnews.val.txt','r',encoding='utf8')
token(train)
train.close()