def create_sim_matrix(tfidf, corpus, dictionary, outputDir):
""""
Creates a Gensim simiariry matrix for document similarity comparison and saves it
tfidf (Gensim tfidf model): Gensim tfidf model
corpus (Gensim corpus object): Gensim corpus
dictionary (Gensim dictionary object): Gensim dictionary
outputDir (string): Location to save matrix
"""
indicesFile = outputDir + 'indices'
simFile = outputDir + 'Index'
sims = Similarity(indicesFile,
tfidf[corpus],
num_features=(len(dictionary)))
sims.close_shard()
sims.save(simFile)
print('Similarity matrix created and stored at: ' + simFile)
