LDA 算法

import jieba
import jieba.analyse as analyse
import gensim
from gensim import corpora, models, similarities


# 停用词表加载方法
def get_stopword_list():
    # 停用词表存储路径，每一行为一个词，按行读取进行加载
    # 进行编码转换确保匹配准确率
    stop_word_path = './stopword.txt'
    stopword_list = [sw.replace('\n', '') for sw in open(stop_word_path, encoding='utf-8').readlines()]
    return stopword_list

import jieba
import jieba.analyse as analyse
import gensim
from gensim import corpora, models, similarities


# 停用词表加载方法
def get_stopword_list():
    # 停用词表存储路径，每一行为一个词，按行读取进行加载
    # 进行编码转换确保匹配准确率
    stop_word_path = './stopword.txt'
    stopword_list = [sw.replace('\n', '') for sw in open(stop_word_path, encoding='utf-8').readlines()]
    return stopword_list


# 停用词
stop_word = get_stopword_list()
text = input()

# 分词
sentences = []
segs = jieba.lcut(text)
segs = list(filter(lambda x: x not in stop_word, segs))
sentences.append(segs)

# 构建词袋模型
dictionary = corpora.Dictionary(sentences)
corpus = [dictionary.doc2bow(sentence) for sentence in sentences]
result = ""
# 任务：使用gensim模块中的函数构造LDA模型，得出最佳主题词的分析结果保存到result变量中。
# ********** Begin *********#
lda = gensim.models.ldamodel.LdaModel(corpus=corpus,id2word=dictionary, num_topics=8)
result=lda.print_topic(1, topn=1)



# ********** End **********#
print(result.split('*')[1],end="")

一定要评测两遍