def init_text_to_text_links(self): logging.info('Finding text to text links for {NAME}'.format(NAME=self.name())) lemmatizer = Lemmatizer() index = 0 for _news in self.news.get_documents(): _news.index = index index += 1 for tweet in self.tweets.get_documents(): tweet.words = lemmatizer.split_text_to_lemmas(tweet.text) tweet.index = index index += 1 #print len(tweets), len(news) similarity_matrix = get_similarity_matrix(self.get_documents(), self.get_documents(), self.corpus, self.tf_idf_matrix) #print 'preparation finished' self.text_to_text_links = get_text_to_text_relation(self.news.get_documents(), self.tweets.get_documents(), similarity_matrix)