LDA主题关键词挖掘，关键词带权重版

import pandas as pd
from gensim import corpora
from gensim.models import LdaModel

# 读取文本数据
df = pd.read_excel('新闻情感分析结果.xlsx')
combined_texts = df['Combined Text'].tolist()

# 准备文档集合
documents = combined_texts

# 构建词袋模型
texts = [[word for word in document.split()] for document in documents]
dictionary = corpora.Dictionary(texts)
corpus = [dictionary.doc2bow(text) for text in texts]

# 创建LDA模型
num_topics = 8
lda_model = LdaModel(corpus, num_topics=num_topics, id2word=dictionary, passes=20, iterations=100)

# 显示带有权重的主题及其相关的词汇
topics = lda_model.print_topics(num_words=10)  # 每个主题显示前10个相关词汇
for topic in topics:
    print(topic)

# 退出代码为 0 表示正常结束
print("进程已结束，退出代码为 0")