python_homework4:用Python统计政府工作报告热词频率并生成词云

将政府工作报告保存为report.txt，准备中文字体文件，中文停用词表stopwords.txt

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

# 1. 读取文本文件（假设文件名为report.txt）
with open('report.txt', 'r', encoding='utf-8') as f:
    text = f.read()

# 2. 中文分词
words = jieba.lcut(text)

# 3. 加载停用词表（需提前准备或下载中文停用词表）
stopwords = set()
with open('stopwords.txt', 'r', encoding='utf-8') as f:
    for line in f:
        stopwords.add(line.strip())

# 4. 过滤停用词和非中文字符
filtered_words = [
    word for word in words 
    if len(word) > 1 
    and word not in stopwords 
    and '\u4e00' <= word <= '\u9fff'
]

# 5. 统计词频
word_counts = Counter(filtered_words)
top_words = word_counts.most_common(50)

# 打印前20个高频词
print("高频词汇Top20:")
for word, count in top_words[:20]:
    print(f"{word}: {count}")

# 6. 生成词云
font_path = 'msyh.ttc'  # 需要中文字体文件
wc = WordCloud(
    font_path=font_path,
    background_color='white',
    max_words=200,
    width=800,
    height=600
)

wc.generate_from_frequencies(word_counts)

# 显示词云
plt.imshow(wc, interpolation='bilinear')
plt.axis('off')
plt.show()

# 保存词云图片
wc.to_file('wordcloud.png')