def evaluate(self, dataset_uri):
dataset = dataset_utils.load_dataset_of_corpus(dataset_uri)
(sents_tokens, sents_tags) = zip(*[zip(*sent) for sent in dataset])
(sents_pred_tags) = self._tag_sents(self._num_tags, sents_tokens,
self._trans_probs,
self._emiss_probs)
acc = self._compute_accuracy(sents_tags, sents_pred_tags)
return acc
def train(self, dataset_uri):
dataset = dataset_utils.load_dataset_of_corpus(dataset_uri)
(sents_tokens, sents_tags) = zip(*[zip(*sent) for sent in dataset])
self._num_tags = dataset.tag_num_classes[0]
(self._trans_probs,
self._emiss_probs) = self._compute_probs(self._num_tags, sents_tokens,
sents_tags)
logger.log('No. of tags: {}'.format(self._num_tags))
def train(self, dataset_uri):
dataset = dataset_utils.load_dataset_of_corpus(dataset_uri)
self._word_dict = self._extract_word_dict(dataset)
self._tag_count = dataset.tag_num_classes[0]
logger.log('No. of unique words: {}'.format(len(self._word_dict)))
logger.log('No. of tags: {}'.format(self._tag_count))
(self._net, self._optimizer) = self._train(dataset)
sents_tags = self._predict(dataset)
acc = self._compute_accuracy(dataset, sents_tags)
logger.log('Train accuracy: {}'.format(acc))
def evaluate(self, dataset_uri):
dataset = dataset_utils.load_dataset_of_corpus(dataset_uri)
sents_tags = self._predict(dataset)
acc = self._compute_accuracy(dataset, sents_tags)
return acc