def similar_tweeters(user1, user2):
u1tweets = usertweets.UserTweets(user1)
u2tweets = usertweets.UserTweets(user2)
u1text = [t.text for t in u1tweets]
u2text = [t.text for t in u2tweets]
u1tokens = [tokenize_tweets(t) for t in u1text]
u2tokens = [tokenize_tweets(t) for t in u2text]
u1filtered = remove_stop(u1tokens)
u2filtered = remove_stop(u2tokens)
return cos_sim(u1filtered, u2filtered)
def similar_tweeters(user1, user2):
u1tweets = usertweets.UserTweets(user1)
u2tweets = usertweets.UserTweets(user2)
u1text = [t.text for t in u1tweets]
u2text = [t.text for t in u2tweets]
u1tokens = [tokenize_tweets(t) for t in u1text]
u2tokens = [tokenize_tweets(t) for t in u2text]
u1filtered = remove_stop(u1tokens)
u2filtered = remove_stop(u2tokens)
stemmer = PorterStemmer()
stem1 = stem_words(u1filtered, stemmer)
stem2 = stem_words(u2filtered, stemmer)
return cos_sim(stem1, stem2)
def similar_tweeters(user1, user2):
# Load the list of stop words
STOP_WORDS = _load_stop_words()
# Fetch User Tweets
user1_tweets = usertweets.UserTweets(user1)
user2_tweets = usertweets.UserTweets(user2)
# Tokenize Tweets
user1_tweets = list(_tokenize((t.text for t in user1_tweets), STOP_WORDS))
user2_tweets = list(_tokenize((t.text for t in user2_tweets), STOP_WORDS))
# Return words that are in both lists
return (word_1 for word_1 in user1_tweets if word_1 in user2_tweets)
def similar_tweeters(user1, user2):
"""Output similarity value for two different users based on 200 tweets."""
u1 = usertweets.UserTweets(user1)
u2 = usertweets.UserTweets(user2)
tt_u1 = " ".join(
_word_set(_remove_solo_words(_get_important_tweet_words(u1))))
tt_u2 = " ".join(
_word_set(_remove_solo_words(_get_important_tweet_words(u2))))
doc1 = nlp(tt_u1)
doc2 = nlp(tt_u2)
sim = doc1.similarity(doc2)
print(sim)
def similar_tweeters(user1, user2):
user1_tweets = nlp(' '.join(
tokenize_user_tweets(usertweets.UserTweets(user1))))
user2_tweets = nlp(' '.join(
tokenize_user_tweets(usertweets.UserTweets(user2))))
return user1_tweets.similarity(user2_tweets)