def build_and_save_lsi_model(): print('Connecting to the database...') sentences = SentencesIterator(tokens_generator) dct = Dictionary(sentences) # Corpus as dictionary ids lists, in memory # Can be transformed in an iterable as done with the others if needed print('Calculating the LSI model...') bow_corpus = [dct.doc2bow(s) for s in sentences] model = LsiModel(bow_corpus, id2word=dct) model.print_debug() model.save(LSI_MODEL_FILE) for t in range(model.get_topics().shape[0]): print(t) print(model.print_topic(t))