Python作业4

编写程序，统计两会政府工作报告热词频率，并生成词云。

点击查看代码

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

# 读取文本文件
with open("2025政府工作报告.txt", "r", encoding="utf-8") as f:
    t = f.read()

# 使用jieba进行中文分词
ls = jieba.lcut(t)

# 过滤掉单字词
filtered_words = [word for word in ls if len(word) > 1]

# 统计词频
word_counts = Counter(filtered_words)

# 创建WordCloud对象，设置词云的基本参数
w = WordCloud( \
    width = 1000, height = 700,\
    background_color = "white",
    font_path = "msyh.ttc"
    )

# 根据词频生成词云
w.generate_from_frequencies(word_counts)

# 显示词云图
plt.figure(figsize=(10, 7))
plt.imshow(w, interpolation='bilinear')
plt.axis('off')  # 不显示坐标轴
plt.show()

# 将生成的词云图保存到文件
w.to_file("grwordcloude_filtered.png")