中文词频统计

Posted 2021-02-13 lijiajie

 

!pip install -i https://pypi.tuna.tsinghua.edu.cn/simple jieba

 

 

 

 

import jieba
str="在神兽白泽的陪同下，游览大千世界，揭秘诸神奥妙。从凯尔特的神话世界出发，北欧、埃及、希腊、希伯来、印度、九州……无尽神话历史，无数神魔鬼怪，无穷世界隐秘，为您呈现……"
for v in jieba.cut(str):
    print(v)

 

 

中文词频统计

1.下载一长篇中文小说。

 

 

2.从文件读取待分析文本。

 

 

3. 安装并使用jieba进行中文分词。

pip install jieba

import jieba

ljieba.lcut(text)

 

4. 更新词库，加入所分析对象的专业词汇。

jieba.add_word(‘天罡北斗阵‘)  #逐个添加

jieba.load_userdict(word_dict)  #词库文本文件

 

 

5. 生成词频统计

import jieba

txt=open(r‘stops_chinese1.txt‘,‘r‘,encoding=‘utf-8‘).read()



wcdict1=[line.strip() for line in open(‘stops_chinese2.txt‘,encoding=‘utf-8‘).readlines()]

jieba.load_userdict(wcdict1)



# wcdict2=[line.strip() for line in open(‘stop_chinese2.txt‘,encoding=‘utf-8‘).readlines()]

# jieba.load_userdict(wcdict2)



wordsls = jieba.lcut(txt)



wcdict = {}



for word in wordsls:

   if word not in wcdict1:

        if len(word)==1:

            continue

        else:

            wcdict[word]=wcdict.get(word,0)+1



wails=list(wcdict.items())

wails.sort(key=lambda x:x[1], reverse=True)



for i in range(25):

       print(wails)

 

 

 

6. 排序

 

 

 

7. 排除语法型词汇，代词、冠词、连词

 

8. 输出词频最大TOP25，把结果存放到文件里

 

 

 

9. 生成词云。

 

 

 

 

 

 

from wordcloud import WordCloud

import matplotlib.pyplot as plt

import jieba

txt=open(r‘stops_chinese1.txt‘,‘r‘,encoding=‘utf-8‘).read()

 

wcdict1=[line.strip() for line in open(‘stops_chinese2.txt‘,encoding=‘utf-8‘).readlines()]

jieba.load_userdict(wcdict1)

 

# wcdict2=[line.strip() for line in open(‘stop_chinese2.txt‘,encoding=‘utf-8‘).readlines()]

# jieba.load_userdict(wcdict2)

 

wordsls = jieba.lcut(txt)

 

wcdict = {}

 

for word in wordsls:

   if word not in wcdict1:

        if len(word)==1:

            continue

        else:

            wcdict[word]=wcdict.get(word,0)+1

 

wails=list(wcdict.items())

wails.sort(key=lambda x:x[1], reverse=True)

 

cut_text = " ".join(wordsls)

‘print(cut_text)‘

mywc = WordCloud(font_path = ‘msyh.ttf‘).generate(cut_text)

plt.imshow(mywc)

plt.axis("off")

plt.show()

for i in range(25):

       print(wails[i])

  

附：

import matplotlib.pyplot as plt

from wordcloud import WordCloud

import jieba

 

text_from_file_with_apath = open(‘/Users/hecom/23tips.txt‘).read()

 

wordlist_after_jieba = jieba.cut(text_from_file_with_apath, cut_all = True)

wl_space_split = " ".join(wordlist_after_jieba)

 

my_wordcloud = WordCloud().generate(wl_space_split)

 

plt.imshow(my_wordcloud)

plt.axis("off")

plt.show()