水浒传词频统计python123

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

# 读取《水浒传》文本
with open('shuihuzhuan.txt', 'r', encoding='utf-8') as file:
    text = file.read()

# 使用jieba分词
words = jieba.lcut(text)

# 读取停用词库
with open('stopwords.txt', 'r', encoding='utf-8') as file:
    stopwords = file.read().splitlines()

# 进行词频统计
word_count = Counter([word for word in words if word not in stopwords])

# 生成词云
wordcloud = WordCloud(font_path="simhei.ttf").generate_from_frequencies(word_count)

# 可视化词云
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis("off")
plt.show()