gensim的主题模型LSI

<span style="font-size:24px;">将上问的输入文档归为两个主题</span>

from gensim import corpora,models,similarities
dictionary=corpora.Dictionary.load('/tmp/deerwester.dict')
corpus=corpora.MmCorpus('/tmp/deerwester.mm')
print(corpus)

tfidf=models.TfidfModel(corpus)

doc_bow=[(0,1),(1,1)] 
print(tfidf[doc_bow])  #计算最相关的文档

corpus_tfidf=tfidf[corpus]

#initialize an LSI transformation
lsi=models.LsiModel(corpus_tfidf,id2word=dictionary,num_topics=3)
#transformed tf-idf corpus via lsi into a laten 2-D space
corpus_lsi=lsi[corpus_tfidf]
lsi.print_topics(3)
for doc in corpus_lsi:
	print(doc)

lsi.save('/tmp/model.lsi')#same for tfidf,lda