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

# 设置字体 MAC
matplotlib.rcParams['font.sans-serif'] = ['Arial Unicode MS']
# 设置字体 Windows
# matplotlib.rcParams['font.sans-serif'] = ['SimHei']
matplotlib.rcParams['axes.unicode_minus'] = False  # 正确显示负号


# 读取Excel文件
df = pd.read_excel('智慧社区文本.xlsx')

# 读取停用词表
with open('stopwords.txt', 'r', encoding='utf-8') as f:
    stop_words = set([line.strip() for line in f.readlines()])

# 合并所有文本内容到一个字符串
all_text = ' '.join(df['文本内容'].dropna())

# 使用jieba进行中文分词
words = jieba.cut(all_text)


# 过滤停用词并统计词频
filtered_words = [word for word in words if word not in stop_words and len(word) > 1]
word_counts = Counter(filtered_words)

# 可视化最常见的词
most_common_words = word_counts.most_common(20)
words, counts = zip(*most_common_words)

plt.figure(figsize=(10, 8))
plt.barh(words, counts)
plt.xlabel('词频')
plt.title('词频分析')
plt.gca().invert_yaxis()  # 反转y轴，使得最高的条形图在上方
plt.savefig('词频分析.png')
plt.show()

# 创建词云图
wordcloud = WordCloud(font_path='苹方-简.ttf',width=800, height=600,
                      background_color='white').generate_from_frequencies(word_counts)

plt.figure(figsize=(10, 8))
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis('off')  # 关闭坐标轴
plt.title('词云图')
plt.savefig('词云图.png')
plt.show()