def get_topic_similarity(self,user_data):
""" Returns cosine similarity between topic scores for two users"""
#=====[ Extracts tweet text from user data ]=====
tweets = [utils.get_tweets(data) for data in user_data]
tweets = [self.format_tweets(tweet_set) for tweet_set in tweets]
#=====[ Gets topics for list of tweets ]=====
all_tweet_topics = [self.get_topics(tweet_set) for tweet_set in tweets]
scores = []
#=====[ Rehydrates a vector in order to take cosine similarity
for topics in all_tweet_topics:
topic_scores = [0]*100
for score in topics:
topic_scores[score[0]] = score[1]
scores.append(topic_scores)
similarity = cosine_similarity(scores[0:1], scores)
similarity = int(float("%.3f" % similarity[0][1])*100)
return similarity
def distill_top_topics(self,user_data, topn):
#=====[ Extracts tweet text from user data ]=====
tweets = utils.get_tweets(user_data)
tweets = self.format_tweets(tweets)
#=====[ Gets topics for list of tweets ]=====
all_tweet_topics = self.get_topics(tweets)
topic_scores = {}
#=====[ Aggregates scores for each topic from each tweet ]=====
for topic in all_tweet_topics:
if topic[1] > 0.15:
topic_scores[topic[0]] = topic[1]
#=====[ Sorts topics and returns #topn of them ]=====
sorted_topics = sorted(topic_scores.items(), key=operator.itemgetter(1))
top_topics = []
for topic in sorted_topics:
topic_name = self.topic_names[topic[0]]
if topic_name not in top_topics:
top_topics.append(topic_name)
return top_topics
