def test_as_tensor_handles_words(self):
field = TextField([Token(t) for t in ["This", "is", "a", "sentence", "."]],
token_indexers={"words": SingleIdTokenIndexer("words")})
field.index(self.vocab)
padding_lengths = field.get_padding_lengths()
tensor_dict = field.as_tensor(padding_lengths)
numpy.testing.assert_array_almost_equal(tensor_dict["words"].detach().cpu().numpy(),
numpy.array([1, 1, 1, 2, 1]))
def test_as_tensor_handles_characters(self):
field = TextField([Token(t) for t in ["This", "is", "a", "sentence", "."]],
token_indexers={"characters": TokenCharactersIndexer("characters")})
field.index(self.vocab)
padding_lengths = field.get_padding_lengths()
tensor_dict = field.as_tensor(padding_lengths)
expected_character_array = numpy.array([[1, 1, 1, 3, 0, 0, 0, 0],
[1, 3, 0, 0, 0, 0, 0, 0],
[1, 0, 0, 0, 0, 0, 0, 0],
[3, 4, 5, 6, 4, 5, 7, 4],
[1, 0, 0, 0, 0, 0, 0, 0]])
numpy.testing.assert_array_almost_equal(tensor_dict["characters"].detach().cpu().numpy(),
expected_character_array)
def test_as_tensor_handles_words_and_characters_with_longer_lengths(self):
field = TextField([Token(t) for t in ["a", "sentence", "."]],
token_indexers={"words": SingleIdTokenIndexer("words"),
"characters": TokenCharactersIndexer("characters")})
field.index(self.vocab)
padding_lengths = field.get_padding_lengths()
padding_lengths["num_tokens"] = 5
padding_lengths["num_token_characters"] = 10
tensor_dict = field.as_tensor(padding_lengths)
numpy.testing.assert_array_almost_equal(tensor_dict["words"].detach().cpu().numpy(),
numpy.array([1, 2, 1, 0, 0]))
numpy.testing.assert_array_almost_equal(tensor_dict["characters"].detach().cpu().numpy(),
numpy.array([[1, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[3, 4, 5, 6, 4, 5, 7, 4, 0, 0],
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]]))
def test_saving_and_loading_works_with_byte_encoding(self):
# We're going to set a vocabulary from a TextField using byte encoding, index it, save the
# vocab, load the vocab, then index the text field again, and make sure we get the same
# result.
tokenizer = CharacterTokenizer(byte_encoding='utf-8')
token_indexer = TokenCharactersIndexer(character_tokenizer=tokenizer)
tokens = [Token(t) for t in ["Øyvind", "für", "汉字"]]
text_field = TextField(tokens, {"characters": token_indexer})
dataset = Batch([Instance({"sentence": text_field})])
vocab = Vocabulary.from_instances(dataset)
text_field.index(vocab)
indexed_tokens = deepcopy(text_field._indexed_tokens) # pylint: disable=protected-access
vocab_dir = self.TEST_DIR / 'vocab_save'
vocab.save_to_files(vocab_dir)
vocab2 = Vocabulary.from_files(vocab_dir)
text_field2 = TextField(tokens, {"characters": token_indexer})
text_field2.index(vocab2)
indexed_tokens2 = deepcopy(text_field2._indexed_tokens) # pylint: disable=protected-access
assert indexed_tokens == indexed_tokens2
def test_index_converts_field_correctly(self):
vocab = Vocabulary()
sentence_index = vocab.add_token_to_namespace("sentence", namespace='words')
capital_a_index = vocab.add_token_to_namespace("A", namespace='words')
capital_a_char_index = vocab.add_token_to_namespace("A", namespace='characters')
s_index = vocab.add_token_to_namespace("s", namespace='characters')
e_index = vocab.add_token_to_namespace("e", namespace='characters')
n_index = vocab.add_token_to_namespace("n", namespace='characters')
t_index = vocab.add_token_to_namespace("t", namespace='characters')
c_index = vocab.add_token_to_namespace("c", namespace='characters')
field = TextField([Token(t) for t in ["A", "sentence"]],
{"words": SingleIdTokenIndexer(namespace="words")})
field.index(vocab)
# pylint: disable=protected-access
assert field._indexed_tokens["words"] == [capital_a_index, sentence_index]
field1 = TextField([Token(t) for t in ["A", "sentence"]],
{"characters": TokenCharactersIndexer(namespace="characters")})
field1.index(vocab)
assert field1._indexed_tokens["characters"] == [[capital_a_char_index],
[s_index, e_index, n_index, t_index,
e_index, n_index, c_index, e_index]]
field2 = TextField([Token(t) for t in ["A", "sentence"]],
token_indexers={"words": SingleIdTokenIndexer(namespace="words"),
"characters": TokenCharactersIndexer(namespace="characters")})
field2.index(vocab)
assert field2._indexed_tokens["words"] == [capital_a_index, sentence_index]
assert field2._indexed_tokens["characters"] == [[capital_a_char_index],
[s_index, e_index, n_index, t_index,
e_index, n_index, c_index, e_index]]
def test_token_embedder_returns_dict(self):
field = TextField([Token(t) for t in ["A", "sentence"]],
token_indexers={"field_with_dict": DictReturningTokenIndexer(),
"words": SingleIdTokenIndexer("words"),
"characters": TokenCharactersIndexer("characters")})
field.index(self.vocab)
padding_lengths = field.get_padding_lengths()
assert padding_lengths == {
'token_ids': 5,
'additional_key': 2,
'words': 2,
'characters': 2,
'num_token_characters': 8
}
padding_lengths['token_ids'] = 7
padding_lengths['additional_key'] = 3
padding_lengths['words'] = 4
padding_lengths['characters'] = 4
tensors = field.as_tensor(padding_lengths)
assert list(tensors['token_ids'].shape) == [7]
assert list(tensors['additional_key'].shape) == [3]
assert list(tensors['words'].shape) == [4]
assert list(tensors['characters'].shape) == [4, 8]
def test_padding_lengths_are_computed_correctly(self):
field = TextField([Token(t) for t in ["This", "is", "a", "sentence", "."]],
token_indexers={"words": SingleIdTokenIndexer("words")})
field.index(self.vocab)
padding_lengths = field.get_padding_lengths()
assert padding_lengths == {"num_tokens": 5}
field = TextField([Token(t) for t in ["This", "is", "a", "sentence", "."]],
token_indexers={"characters": TokenCharactersIndexer("characters")})
field.index(self.vocab)
padding_lengths = field.get_padding_lengths()
assert padding_lengths == {"num_tokens": 5, "num_token_characters": 8}
field = TextField([Token(t) for t in ["This", "is", "a", "sentence", "."]],
token_indexers={"characters": TokenCharactersIndexer("characters"),
"words": SingleIdTokenIndexer("words")})
field.index(self.vocab)
padding_lengths = field.get_padding_lengths()
assert padding_lengths == {"num_tokens": 5, "num_token_characters": 8}
