def GetTfidf(self, dictionary, corpus):
tfidf = models.TfidfModel(corpus)
vec_lsi = tfidf[corpus[0]]
index = Similarity('t_index', corpus, len(dictionary))
#tsims = index[vec_lsi]
cnt = 0
for similarities in index:
if cnt == 1:
return list(enumerate(similarities))
cnt += 1
#return list(enumerate(tsims))
def GetSimilarities(self, dictionary, corpus):
self.GetWord2Vec(dictionary, corpus)
#print("lsims")
lsims = self.GetLsm(dictionary, corpus)
#print("tsims")
tsims = self.GetTfidf(dictionary, corpus)
return (
tsims,
lsims,
)
if __name__ == '__main__':
reader = Reader(r"C:\Users\CCrowe\Documents\Kaggle\Quora\train.csv",
r"C:\Users\CCrowe\Documents\Kaggle\Quora\test.csv")
documents = reader.GetDocuments()
print("documents retrieved")
similar = Similar(documents, texts)
