def main():
me=Classifier()
feature_counter=Counter()
feature_set=pickle.load(open('validation_set.pkl', 'rb'))
feature_set_labels=[]
for tweet, rating in feature_set:
print rating
try:
float(rating)
except:
continue
if float(rating)>0:
label='positive'
elif float(rating)<0:
label='negative'
else:
label='neutral'
feature_set_labels.append((tweet, label))
feature_list=chain.from_iterable([word_tokenize(process_tweet(tweet)) for tweet, sentiment in feature_set_labels])
for feat in feature_list:
feature_counter[feat]+=1
me.feature_list=[feat for feat, count in feature_counter.most_common(1000)]
ts=[(me.extract_features(tweet), label) for tweet, label in feature_set]
print 'training Maxent'
me.classifier=MaxentClassifier.train(ts)
return me
def main():
me=Classifier()
feature_counter=Counter()
feature_set=pickle.load(open('undersampled_emoticon.pkl', 'rb'))
feature_list=chain.from_iterable([word_tokenize(process_tweet(tweet)) for tweet, sentiment in feature_set])
for feat in feature_list:
feature_counter[feat]+=1
me.feature_list=[feat for feat, count in feature_counter.most_common(1000)]
ts=[(me.extract_features(tweet), label) for tweet, label in feature_set]
print 'training Maxent, algorithm CG'
me.classifier=MaxentClassifier.train(ts)
return me