def google_lexicon_lookup(): """ Fetches the tweets and performs lexicon translatino and lookup. """ tweets = utils.get_pickles(0) words_with_values = lexicon.perform_google_sentiment_lexicon_lookup(tweets) print "Storing..." utils.store_sentimentvalues(words_with_values, "models/google_sentimentvalues_random_dataset") tweets = utils.get_pickles(1) words_with_values = lexicon.perform_google_sentiment_lexicon_lookup(tweets) print "Storing..." utils.store_sentimentvalues(words_with_values, "models/google_sentimentvalues_rosenborg_dataset") tweets = utils.get_pickles(2) words_with_values = lexicon.perform_google_sentiment_lexicon_lookup(tweets) print "Storing..." utils.store_sentimentvalues(words_with_values, "models/google_sentimentvalues_erna_dataset")
def preprocess_temporal_dataset(): tweetlines = utils.get_dataset(utils.complete_datasets[3]) tweets = [] for line in tweetlines: if len(line) > 1: tweets.append(tweet.to_tweet(line)) tweets = preprocessing.preprocess_tweets(tweets) sentiments = lexicon.perform_google_sentiment_lexicon_lookup(tweets) pickle.dump(sentiments, open("temporal_sentiments", "wb")) pickle.dump(tweets, open("temporal_tweets2", "wb"))