def main(top_pct,pct_tweets,iterations): print top_pct, pct_tweets, iterations p_pd, n_pd = sentParser.createSimpDict('sentmtListsm.txt',2) #pd = sentParser.createParseDict() #p_pd, n_pd = sentParser.createSimpDict('testsent.txt',2) tweets = tweetCleaner.cleanTweets('/scratch/nschult1/prunedTweets.txt') gs_test_tweets = tweets[1:50] train_tweets = tweets[50:] for i in range(iterations): p_twd , p_num_tweets = tweetParser(train_tweets,p_pd) n_twd , n_num_tweets = tweetParser(train_tweets,n_pd) thresh = top_pct thresh2 = pct_tweets p_pd = improvePD(p_twd,p_pd,p_num_tweets,thresh,thresh2,False) n_pd = improvePD(n_twd,n_pd,n_num_tweets,thresh,thresh2,True) pd = combine(p_pd, n_pd) f = open('newparser.txt','w') for key in pd: f.write('%s %f\n' %(key,pd[key])) f.close() total_score = tweetScorer.scorer(gs_test_tweets,pd,sentParser.createEDict(), True, True)
def main(): txt='newparser.txt' txt2='sentmtListsm.txt' total_score=scorer('/scratch/nschult1/prunedTweets.txt', sentParser.createSimpDict(txt,1), sentParser.createEDict(), True, True) print "Total Score: ", total_score