def test_save_load(self):
"""Test saving and loading with blog classifier"""
train, test = self.split_blogs_corpus(BlogFeatures)
classifier = NaiveBayes()
classifier.train(train)
classifier.save("model")
class2 = NaiveBayes()
class2.load("model")
self.assertGreater(accuracy(class2, test), 0.55)
def test_save_load_blogs_bag(self):
train, test = self.split_blogs_corpus(BagOfWords)
classifier = NaiveBayes()
classifier.train(train)
classifier.save('trained_model.p')
c2 = NaiveBayes()
c2.load('trained_model.p')
self.assertEqual(classifier.model, c2.model)
self.assertEqual(classifier.priorCount, c2.priorCount)
self.assertEqual(classifier.countPerFeature, c2.countPerFeature)
tokens += nltk.regexp_tokenize(l,pattern="\w+")
data = util.del_dup(tokens)
if filepath[-4:-1] == 'neg':
ins = Instance(filename,'negative',data,tokens)
elif filepath[-4:-1] == 'pos':
ins = Instance(filename,'positive',data,tokens)
else:
raise Exception, "Wrong path!"
ins_list.append(ins)
f.close()
return ins_list
instance_list = load_instance('txt_sentoken/neg/')
instance_list += load_instance('txt_sentoken/pos/')
#random split train-test
p0 = random.random()
p1 = 1-p0
prop = [p0,p1]
#prop = [0.5,0.5]
accuracy = split_train_test(nb,instance_list,prop,ID,limits)
nb.save("movie_review_classifier.json")
nb1 = NaiveBayes.load("movie_review_classifier.json")
accuracy = split_train_test(nb,instance_list,prop,ID,limits)
f = open('results/results'+repr(ID)+'.txt','a+w')
f.write(repr(p0)+' '+repr(accuracy) + '\n')
f.close()