使用Gensim库对txt文件进行LDA主题模型分析

以下是基于Python的Gensim库实现的LDA主题模型代码：

1. 加载文本数据

import os
from gensim import corpora

# 加载文本数据
def load_data(path):
    file_list = os.listdir(path)
    data = []
    for file_name in file_list:
        with open(os.path.join(path, file_name), 'r', encoding='utf-8') as f:
            data.append(f.read())
    return data

# 构建语料库
def build_corpus(data):
    texts = [[word for word in document.lower().split()] for document in data]
    dictionary = corpora.Dictionary(texts)
    corpus = [dictionary.doc2bow(text) for text in texts]
    return corpus, dictionary

2. 训练LDA主题模型

from gensim.models.ldamodel import LdaModel

# 训练LDA主题模型
def train_lda_model(corpus, dictionary, num_topics=10, passes=10):
    lda_model = LdaModel(corpus=corpus, id2word=dictionary, num_topics=num_topics, passes=passes)
    return lda_model

3. 可视化主题分布

import pyLDAvis.gensim
import warnings

warnings.filterwarnings('ignore')

# 可视化主题分布
def visualize_topics(lda_model, corpus, dictionary):
    vis_data = pyLDAvis.gensim.prepare(lda_model, corpus, dictionary)
    pyLDAvis.display(vis_data)

4. 主程序

if __name__ == '__main__':
    data = load_data('./data')
    corpus, dictionary = build_corpus(data)
    lda_model = train_lda_model(corpus, dictionary)
    visualize_topics(lda_model, corpus, dictionary)

以上是基于Gensim库的LDA主题模型代码，可以通过调整模型参数来优化主题分布效果。