def test_dump_load(model):
loc = '/tmp/test_model'
model.end_training()
model.dump(loc)
string = open(loc, 'rb').read()
assert string
new_model = AveragedPerceptron([(1,), (2,), (3,), (4,)])
nr_class = 5
assert get_scores(nr_class, model, {1: 1, 3: 1, 4: 1}) != \
get_scores(nr_class, new_model, {1:1, 3:1, 4:1})
assert get_scores(nr_class, model, {2:1, 5:1}) != \
get_scores(nr_class, new_model, {2:1, 5:1})
assert get_scores(nr_class, model, {2:1, 3:1, 4:1}) != \
get_scores(nr_class, new_model, {2:1, 3:1, 4:1})
new_model.load(loc)
assert get_scores(nr_class, model, {1:1, 3:1, 4:1}) == \
get_scores(nr_class, new_model, {1:1, 3:1, 4:1})
assert get_scores(nr_class, model, {2:1, 5:1}) == \
get_scores(nr_class, new_model, {2:1, 5:1})
assert get_scores(nr_class, model, {2:1, 3:1, 4:1}) == \
get_scores(nr_class, new_model, {2:1, 3:1, 4:1})
def test_dump_load(model):
loc = tempfile.mkstemp()[1]
model.end_training()
model.dump(loc)
string = open(loc, 'rb').read()
assert string
new_model = AveragedPerceptron([(1, ), (2, ), (3, ), (4, )])
nr_class = 5
assert get_scores(nr_class, model, {1: 1, 3: 1, 4: 1}) != \
get_scores(nr_class, new_model, {1:1, 3:1, 4:1})
assert get_scores(nr_class, model, {2:1, 5:1}) != \
get_scores(nr_class, new_model, {2:1, 5:1})
assert get_scores(nr_class, model, {2:1, 3:1, 4:1}) != \
get_scores(nr_class, new_model, {2:1, 3:1, 4:1})
new_model.load(loc)
assert get_scores(nr_class, model, {1:1, 3:1, 4:1}) == \
get_scores(nr_class, new_model, {1:1, 3:1, 4:1})
assert get_scores(nr_class, model, {2:1, 5:1}) == \
get_scores(nr_class, new_model, {2:1, 5:1})
assert get_scores(nr_class, model, {2:1, 3:1, 4:1}) == \
get_scores(nr_class, new_model, {2:1, 3:1, 4:1})
class ThincModel(object):
def __init__(self, nlp, nr_class):
self.nlp = nlp
self.nr_class = nr_class
self._eg = Example(nr_class=nr_class)
self._model = AveragedPerceptron([])
def Eg(self, text, opt=None, label=None):
eg = self._eg
eg.reset()
doc = self.nlp(text)
features = []
word_types = set()
i = 0
for token in doc[:-1]:
next_token = doc[i + 1]
strings = (token.lower_, next_token.lower_)
key = hash_string('%s_%s' % strings)
feat_slot = 0
feat_value = 1
features.append((0, token.lower, 1))
features.append((feat_slot, key, feat_value))
i += 1
eg.features = features
if opt is not None:
eg.is_valid = [(clas in opt) for clas in range(self.nr_class)]
if label is not None:
eg.costs = [clas != label for clas in range(self.nr_class)]
return eg
def predict(self, text, opt):
return self._model.predict_example(self.Eg(text, opt))
def train(self, examples, n_iter=5):
for i in range(n_iter):
loss = 0
random.shuffle(examples)
negation_count = 0
for text, opt, label in examples:
eg = self.Eg(text, opt, label)
self._model.train_example(eg)
loss += eg.guess != label
print(loss)
self._model.end_training()
def evaluate(self, examples):
total = 0
correct = 0
for i, (text, opt, label) in enumerate(examples):
eg = self.predict(text, opt)
correct += eg.guess == label
total += 1
return correct / total
def dump(self, loc):
self._model.dump(loc)
def load(self, loc):
self._model.load(loc)
