中文词频统计

下载一长篇中文文章。

从文件读取待分析文本。

news = open('gzccnews.txt','r',encoding = 'utf-8')

安装与使用jieba进行中文分词。

pip install jieba

import jieba

list(jieba.lcut(news))

生成词频统计

排序

排除语法型词汇，代词、冠词、连词

输出词频最大TOP20

import jieba

fo = open('douluo.txt','r',encoding='utf-8').read()

wordsls = jieba.lcut(fo)
wcdict = {}
# for word in wordsls:
#   if len(word)==1:
#    continue
#   else:
#    wcdict[word]=wcdict.get(word,0)+1
for i in set(wordsls):
    wcdict[i]=wordsls.count(i)
    delete={'你','我','他','自己','都','已经','着','不','她','没有','和','他们','中','我们','下','什么','一个',
            '道','的','们','所','在','来','有','过','从','而','才','要','因','为','地','将','上','共','自','是',
            '令','但','被','就','也','说','语','呀','啊','呵','个','人','里','罢','内','该','与','会','对','去',
            '出','动','却','超','已','只','放','这','比','还','则','见','到','最','话','加','更','并','把',
            '儿','大','小','那',' ','了','-','\n','，','。','？','！','“','”','：','；','、','.','‘','’'}
for i in delete:
    if i in wcdict:
        del wcdict[i]
sort_word = sorted(wcdict.items(), key = lambda d:d[1], reverse = True)  # 排序
for i in range(20):  # 输出
    print(sort_word[i])

# fo = open("douluo1.txt", "r",encoding='utf-8')
# print ("文件名为: ", fo.name)
# for index in range(5):
#     line = next(fo)
#     print ("第 %d 行 - %s" % (index, line))
#
# # 关闭文件
# fo.close()