def classify(text, sender=None, subject=None):
training_set = load_training_set()
classifier = NaiveBayesClassifier.train(training_set)
test_data = bag_of_words(extract_bigrams(text))
if sender is not None:
test_data[sender] = True
if subject is not None:
test_data[subject] = True
classified = classifier.prob_classify(test_data)
pprint({categories[sample]: classified.prob(sample) for sample in classified.samples()})
return categories[classified.max()]
def cross_validate():
training_set = load_training_set()
random.shuffle(training_set)
average = 0
cv = KFold(len(training_set), n_folds=10, indices=True, shuffle=False, random_state=None)
for traincv, evalcv in cv:
classifier = NaiveBayesClassifier.train(training_set[traincv[0]:traincv[len(traincv) - 1]])
acc = accuracy(classifier, training_set[evalcv[0]:evalcv[len(evalcv) - 1]])
print 'Range: ', evalcv[0], 'to', evalcv[len(evalcv) - 1]
print 'Accuracy: %4.2f' % acc
average += acc
print 'Average accuracy: %4.2f' % (average / 10)
def classify(text, sender=None, subject=None):
training_set = load_training_set()
classifier = NaiveBayesClassifier.train(training_set)
test_data = bag_of_words(extract_bigrams(text))
if sender is not None:
test_data[sender] = True
if subject is not None:
test_data[subject] = True
classified = classifier.prob_classify(test_data)
pprint({
categories[sample]: classified.prob(sample)
for sample in classified.samples()
})
return categories[classified.max()]
def cross_validate():
training_set = load_training_set()
random.shuffle(training_set)
average = 0
cv = KFold(len(training_set),
n_folds=10,
indices=True,
shuffle=False,
random_state=None)
for traincv, evalcv in cv:
classifier = NaiveBayesClassifier.train(
training_set[traincv[0]:traincv[len(traincv) - 1]])
acc = accuracy(classifier,
training_set[evalcv[0]:evalcv[len(evalcv) - 1]])
print 'Range: ', evalcv[0], 'to', evalcv[len(evalcv) - 1]
print 'Accuracy: %4.2f' % acc
average += acc
print 'Average accuracy: %4.2f' % (average / 10)
