文本中高频词云图制作

python代码，jieba分词，中文文本。

其中font_path去电脑系统设置的字体中“字体文件”找。

 

import jieba
from collections import Counter
from wordcloud import WordCloud
import matplotlib.pyplot as plt


# 读取文本文件
with open('text.txt', 'r', encoding='utf-8') as file:
    text = file.read()

# 分词
seg_list = jieba.cut(text)
tokens = [token for token in seg_list if len(token) > 1]

# 统计词频
word_counts = Counter(tokens)

# 生成词云
wordcloud = WordCloud(font_path='C:\WINDOWS\FONTS\MSYHL.TTC',
                      width=800,
                      height=400,
                      background_color='white',
                      max_words=100).generate_from_frequencies(word_counts)

# 保存词云图为图片
wordcloud.to_file('wordcloud.png')