def test_train():
mc = DocClassifier(picklefile)
doc = Doc(url='http://umsu.de/papers/variations.pdf')
doc.content = readfile(os.path.join(testdir, 'attitudes.txt'))
mc.train([doc], [True])
mc.save()
assert True
def test_classify():
mc = DocClassifier(picklefile)
ham = Doc(url='http://umsu.de/papers/variations.pdf')
ham.content = readfile(os.path.join(testdir, 'attitudes.txt'))
spam = Doc(url='http://umsu.de/papers/spam.pdf')
spam.content = """
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do
eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut
enim ad minim veniam, quis nostrud exercitation ullamco laboris
nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor
in reprehenderit in voluptate velit esse cillum dolore eu
fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
proident, sunt in culpa qui officia deserunt mollit anim id est
laborum.
"""
spam.content *= 50
mc.train([ham, spam], [True, False])
ham.content += 'foo bar'
prob = mc.classify(ham)
assert prob > 0.5
def test_setup():
mc = DocClassifier(picklefile)
mc.reset()
assert True
