V1版本
# -*- coding: utf-8 -*-
"""
中文文本主题分析完整代码(自定义停用词版)
功能:Word文档读取 -> 中文分词 -> 停用词过滤 -> LDA主题建模 -> 可视化
依赖库:pip install python-docx jieba gensim pyLDAvis wordcloud matplotlib
"""
# ================ 导入库 ================
import re
import jieba
from docx import Document
from gensim import corpora, models
import pyLDAvis.gensim_models as gensimvis
import pyLDAvis
from wordcloud import WordCloud
import matplotlib.pyplot as plt
# ================ 自定义配置 ===============