def test_instance(self):
sentence = ['This', 'is', 'is', 'a', 'a', 'test', 'sentence']
counter = {'my_word': Counter(), 'my_char': Counter()}
vocab = Vocabulary()
glove = ['This', 'is', 'glove', 'sentence', 'vocabulary']
vocab.extend_from_pretrained_vocab({'glove': glove})
single_id = SingleIdTokenIndexer(['my_word', 'glove'])
char = CharTokenIndexer(['my_char'])
sent = TextField('sentence', sentence, [single_id, char])
data = Instance([sent])
# Test count_vocab_items()
data.count_vocab_items(counter)
assert counter['my_word']['This'] == 1
assert counter['my_word']['is'] == 2
assert counter['my_word']['That'] == 0
assert counter['my_char']['s'] == 5
assert counter['my_char']['T'] == 1
assert counter['my_char']['t'] == 3
assert counter['my_char']['A'] == 0
vocab.extend_from_counter(counter)
# Test index()
result = data.index_fields(vocab)
assert result['sentence']['glove'] == [2, 3, 3, 0, 0, 0, 5]
assert result['sentence']['my_word'] == [2, 3, 3, 4, 4, 5, 6]
assert result['sentence']['my_char'][0] == [2, 3, 4, 5] # 'This'
assert result['sentence']['my_char'][1] == result['sentence'][
'my_char'][2]
assert result['sentence']['my_char'][3] == result['sentence'][
'my_char'][4]
def main():
# Configuration file processing
...
# DyNet setting
...
# Build the dataset of the training process
## Build data reader
data_reader = PTBReader(
field_list=['word', 'tag', 'head', 'rel'],
root='0\t**root**\t_\t**rpos**\t_\t_\t0\t**rrel**\t_\t_',
spacer=r'[\t]',)
## Build vocabulary with pretrained glove
vocabulary = Vocabulary()
g_word, _ = glove_reader(cfg.GLOVE)
pretrained_vocabs = {'glove': g_word}
vocabulary.extend_from_pretrained_vocab(pretrained_vocabs)
## Setup datasets
datasets_settings = {
'train': DatasetSetting(cfg.TRAIN, True),
'dev': DatasetSetting(cfg.DEV, True),
'test': DatasetSetting(cfg.TEST, True),}
datasets = SingleTaskDataset(vocabulary, datasets_settings, data_reader)
counters = {'word': Counter(), 'tag': Counter(), 'rel': Counter()}
datasets.build_dataset(
counters, no_pad_namespace={'rel'}, no_unk_namespace={'rel'})
# Build model
...
# Train model
train_batch = datasets.get_batches('train', cfg.TRAIN_BATCH_SIZE, True, cmp, True)
valid_batch = datasets.get_batches('dev', cfg.TEST_BATCH_SIZE, True, cmp, False)
test_batch = datasets.get_batches('test', cfg.TEST_BATCH_SIZE, True, cmp, False)
def test_single_id_token_indexer(self):
sentence = ['This', 'is', 'is', 'a', 'a', 'test', 'sentence']
counter = {'my_word': Counter()}
vocab = Vocabulary()
glove = ['This', 'is', 'glove', 'sentence', 'vocabulary']
vocab.extend_from_pretrained_vocab({'glove': glove})
indexer = SingleIdTokenIndexer(['my_word', 'glove'])
sent = TextField('sentence', sentence, [indexer])
# Test count_vocab_items()
sent.count_vocab_items(counter)
assert counter['my_word']['This'] == 1
assert counter['my_word']['is'] == 2
assert counter['my_word']['That'] == 0
vocab.extend_from_counter(counter)
# Test index()
sent.index(vocab)
assert sent.indexes['glove'] == [2, 3, 3, 0, 0, 0, 5]
assert sent.indexes['my_word'] == [2, 3, 3, 4, 4, 5, 6]
def test_char_token_indexer(self):
sentence = ['This', 'is', 'is', 'a', 'a', 'test', 'sentence']
counter = {'my_char': Counter()}
vocab = Vocabulary()
glove = ['a', 'b', 'c', 'd', 'e']
vocab.extend_from_pretrained_vocab({'glove': glove})
indexer = CharTokenIndexer(['my_char', 'glove'])
sent = TextField('sentence', sentence, [indexer])
# Test count_vocab_items()
sent.count_vocab_items(counter)
assert counter['my_char']['s'] == 5
assert counter['my_char']['T'] == 1
assert counter['my_char']['t'] == 3
assert counter['my_char']['A'] == 0
vocab.extend_from_counter(counter)
# Test index()
sent.index(vocab)
assert sent.indexes['glove'][0] == [0, 0, 0, 0] # 'This'
assert sent.indexes['glove'][3] == [2] # 'a'
assert sent.indexes['my_char'][0] == [2, 3, 4, 5] # 'This'
def test_extend_from_pretrained_vocab(self):
vocab = Vocabulary()
# Test extend a vocabulary from a simple pretained vocab
pretrained_vocabs = {'glove': ['a', 'b', 'c']}
vocab.extend_from_pretrained_vocab(pretrained_vocabs)
assert vocab.get_token_index('a', 'glove') == 2
assert vocab.get_token_index('c', 'glove') == 4
assert vocab.get_token_index('d', 'glove') == 0
# Test extend a vocabulary from a pretained vocabulary,
# and intersect with another vocabulary.
pretrained_vocabs = {'w2v': ['b', 'c', 'd']}
vocab.extend_from_pretrained_vocab(pretrained_vocabs, {'w2v': 'glove'})
assert vocab.get_token_index('b', 'w2v') == 2
assert vocab.get_token_index('d', 'w2v') == 0
assert vocab.get_token_from_index(2, 'w2v') == 'b'
with pytest.raises(RuntimeError) as excinfo:
vocab.get_token_from_index(4, 'w2v')
assert excinfo.type == RuntimeError
# Test extend a vocabulary from a no oov pretained vocabulary
pretrained_vocabs = {'glove_nounk': ['a', 'b', 'c']}
vocab.extend_from_pretrained_vocab(pretrained_vocabs,
no_unk_namespace={
'glove_nounk',
})
assert vocab.get_token_index('a', 'glove_nounk') == 1
assert vocab.get_token_index('c', 'glove_nounk') == 3
with pytest.raises(RuntimeError) as excinfo:
vocab.get_token_index('d', 'glove_nounk')
assert excinfo.type == RuntimeError
# Test extend a vocabulary from a no oov and pad pretained vocabulary
pretrained_vocabs = {'glove_nounk_nopad': ['a', 'b', 'c']}
vocab.extend_from_pretrained_vocab(
pretrained_vocabs,
no_unk_namespace={
'glove_nounk_nopad',
},
no_pad_namespace={"glove_nounk_nopad"})
assert vocab.get_token_index('a', 'glove_nounk_nopad') == 0
assert vocab.get_token_index('c', 'glove_nounk_nopad') == 2
with pytest.raises(RuntimeError) as excinfo:
vocab.get_token_index('d', 'glove_nounk_nopad')
assert excinfo.type == RuntimeError