Python实现LDA模型

# -*- coding: utf-8 -*-
# @Time : 2022/4/11 11:35
# @Author : MinChess
# @File : lda.py
# @Software: PyCharm 
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer

# 读取数据(已分词)
corpus = []

# 读取预料 一行预料为一个文档
for line in open('fenci.txt', 'r',encoding='utf-8').readlines():
    corpus.append(line.strip())

# 计算TF-IDF值
# 设置特征数
n_features = 2000

tf_vectorizer = TfidfVectorizer(strip_accents='unicode',
                                max_features=n_features,
                                stop_words=['的'],
                                max_df=0.99,
                                min_df=0.002)  # 去除文档内出现几率过大或过小的词汇

tf = tf_vectorizer.fit_transform(corpus)

print(tf.shape)
print(tf)

# LDA分析
from sklearn.decomposition import LatentDirichletAllocation

# 设置主题数
n_topics = 2

lda = LatentDirichletAllocation(n_components=n_topics,
                                max_iter=100,
                                learning_method='online',
                                learning_offset=50,
                                random_state=0)
lda.fit(tf)

# 显示主题数 model.topic_word_
print(lda.components_)
# 几个主题就是几行 多少个关键词就是几列
print(lda.components_.shape)

# 计算困惑度
print(u'困惑度：')
print(lda.perplexity(tf, sub_sampling=False))

# 主题-关键词分布
def print_top_words(model, tf_feature_names, n_top_words):
    for topic_idx, topic in enumerate(model.components_):
        print('Topic #%d:' % topic_idx)
        print(' '.join([tf_feature_names[i] for i in topic.argsort()[:-n_top_words - 1:-1]]))
        print("")

# 定义好函数之后 暂定每个主题输出前20个关键词
n_top_words = 20
tf_feature_names = tf_vectorizer.get_feature_names()
# 调用函数
print_top_words(lda, tf_feature_names, n_top_words)

# 可视化分析
import pyLDAvis
import pyLDAvis.sklearn

# pyLDAvis.enable_notebook()

data = pyLDAvis.sklearn.prepare(lda, tf, tf_vectorizer)
print(data)

# 显示图形
# pyLDAvis.show(data)
# pyLDAvis.save_json(data,' fileobj.html')