Python jieba分词添加自定义词和去除不需要长尾词的操作方法

            # 找到高频词汇 tmp_content = self.getContent(tmp_path) keyword_list = tmp_content.split('\n') word_count = dict() for keyword in keyword_list: for word,flag in jp.cut(keyword): if word in word_count: word_count[word] = word_count[word] +1 else: word_count[word] =1 for word, count in word_count.items(): print('%s\t%s' % (word,count))

import jieba import jieba.posseg as jp jieba.load_userdict(r'jieba_dict.txt')

import jieba import jieba.posseg as jp jieba.del_word('创建活动')