f1 = codecs.open('output.txt', 'r+', encoding='utf8') lines1 = f1.readlines() Myobject = TwitterHybridClassifier(trainset) #count = {'RB':0, 'LB':0, 'ML':0 } observed = list() answer = list() for line in lines: x = line.split('\t') prediction = Myobject.classify(x[5]) if (len(prediction) == 1): result = prediction[0][0] elif (len(prediction) == 2): result = prediction[1][0] else: result = prediction[2][0] #count[method] += 1 observed.append(result) #print(prediction) for line in lines1: line = line.strip()
semeval = SemevalTwitter(train_path,dev_path,test_path) trainset = semeval.trainset devset = semeval.devset testset = semeval.testset # Training the supervised model print "Training..." classifier = TwitterHybridClassifier(trainset + devset) # Apply the classifier for all tweets in the testset output_file = 'task2-TEAM-B-twitter-constrained.output' fp = open(output_file,'w') for num,tweet in enumerate(testset): print "Processing...",num tweet_class = classifier.classify(tweet['MESSAGE']) line = tweet['SID'] + '\t' + tweet['UID'] + '\t' + tweet_class + '\t' + tweet['MESSAGE'] fp.write(line) fp.close() # Apply the classifier for all sms data in the testset train_path='Data/tweeti-b.dist.data' dev_path='Data/twitter-dev-gold-B.tsv' test_path='Data/sms-test-input-B.tsv' semeval = SemevalTwitter(train_path,dev_path,test_path) testset = semeval.testset output_file = 'task2-TEAM-B-sms-constrained.output' fp = open(output_file,'w')
semeval = SemevalTwitter(train_path, dev_path, test_path) trainset = semeval.trainset devset = semeval.devset testset = semeval.testset # Training the supervised model print "Training..." classifier = TwitterHybridClassifier(trainset + devset) # Apply the classifier for all tweets in the testset output_file = 'task2-TEAM-B-twitter-constrained.output' fp = open(output_file, 'w') for num, tweet in enumerate(testset): print "Processing...", num tweet_class = classifier.classify(tweet['MESSAGE']) line = tweet['SID'] + '\t' + tweet[ 'UID'] + '\t' + tweet_class + '\t' + tweet['MESSAGE'] fp.write(line) fp.close() # Apply the classifier for all sms data in the testset train_path = 'Data/tweeti-b.dist.data' dev_path = 'Data/twitter-dev-gold-B.tsv' test_path = 'Data/sms-test-input-B.tsv' semeval = SemevalTwitter(train_path, dev_path, test_path) testset = semeval.testset output_file = 'task2-TEAM-B-sms-constrained.output' fp = open(output_file, 'w')