gensim_lsi.py

from gensim import corpora, models, similarities

documents = ["Human machine interface for lab abc computer applications",
              "A survey of user opinion of computer system response time",
              "The EPS user interface management system",
              "System and human system engineering testing of EPS",
              "Relation of user perceived response time to error measurement",
              "The generation of random binary unordered trees",
              "The intersection graph of paths in trees",
              "Graph minors IV Widths of trees and well quasi ordering",
              "Graph minors A survey"]

stoplist = set('for a of the and to in'.split())
texts = [[word for word in document.lower().split() if word not in stoplist] for document in documents]

all_tokens = sum(texts, [])
tokens_once = set(word for word in set(all_tokens) if all_tokens.count(word) == 1)
texts = [[word for word in text if word not in tokens_once] for text in texts]

print texts

dictionary = corpora.Dictionary(texts)

print(dictionary.token2id)

corpus = [dictionary.doc2bow(text) for text in texts]

print(corpus)

tfidf = models.TfidfModel(corpus)

print tfidf

corpus_tfidf = tfidf[corpus]

for doc in corpus_tfidf:
	print(doc)

lsi = models.LsiModel(corpus_tfidf, id2word=dictionary, num_topics=2) # initialize an LSI transformation
corpus_lsi = lsi[corpus_tfidf] # create a double wrapper over the original corpus: bow->tfidf->fold-in-lsi
lsi.print_topics(2)

for doc in corpus_lsi: # both bow->tfidf and tfidf->lsi transformations are actually executed here, on the fly
	print(doc)