中文词频统计

作业要求：https://edu.cnblogs.com/campus/gzcc/GZCC-16SE2/homework/2773

1. 下载一长篇中文小说。

 来自红楼梦的一小章内容：

2. 从文件读取待分析文本。

text=open('123.txt','r',encoding='utf-8').read()

3. 安装并使用jieba进行中文分词。

pip install jieba

import jieba

jieba.lcut(text)

import jieba
wordsls=jieba.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

参考词库下载地址：https://pinyin.sogou.com/dict/

转换代码：scel_to_text

词库：

worddict1=[line.strip() for line in open('23.txt',encoding='utf-8').readlines()]
jieba.load_userdict(worddict1)

5. 生成词频统计

wcdict={}

for word in wordsls:
    if word not in worddict2:（7.排除语法型）
      if len(word)==1:
        continue
      else:
        wcdict[word]=wcdict.get(word,0)+1

6. 排序

wcls=list(wcdict.items())
wcls.sort(key=lambda  x:x[1],reverse=True)　

7. 排除语法型词汇，代词、冠词、连词等停用词。

文件：

 

stops

worddict2=[line.strip() for line in open('stops_chinese.txt',encoding='utf-8').readlines()]

8. 输出词频最大TOP20，把结果存放到文件里

import pandas as pd
pd.DataFrame(data=word).to_csv('E:/1234.csv',encoding='utf-8')

9. 生成词云。

wl_split=" ".join(wordsls) 

from wordcloud import WordCloud
import matplotlib.pyplot as plt

mywc = WordCloud().generate(wl_split)

plt.imshow(mywc)
plt.axis("off")
plt.show()

10.最总代码总和和截图：

import jieba
text=open('D://123.txt','r',encoding='utf-8').read()

worddict1=open('D://23.txt','r',encoding='utf-8').read()

worddict2=open('D://stops_chinese.txt','r',encoding='utf-8').read()

wordsls=jieba.lcut(text)

wcdict={}

for word in wordsls:
    if word not in worddict2:
      if len(word)==1:
        continue
      else:
        wcdict[word]=wcdict.get(word,0)+1

wcls=list(wcdict.items())
wcls.sort(key=lambda  x:x[1],reverse=True)

for i in range(25):
    print(wcls[i])

wl_split=" ".join(wordsls) 

from wordcloud import WordCloud
import matplotlib.pyplot as plt


mywc = WordCloud().generate(wl_split)

plt.imshow(mywc)
plt.axis("off")
plt.show()