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_as_array_produces_token_sequence(self):
indexer = TokenCharactersIndexer("characters")
padded_tokens = indexer.pad_token_sequence({'k': [[1, 2, 3, 4, 5], [1, 2, 3], [1]]},
desired_num_tokens={'k': 4},
padding_lengths={"num_token_characters": 10})
assert padded_tokens == {'k': [[1, 2, 3, 4, 5, 0, 0, 0, 0, 0],
[1, 2, 3, 0, 0, 0, 0, 0, 0, 0],
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]]}
def test_tokens_to_indices_produces_correct_characters(self):
vocab = Vocabulary()
vocab.add_token_to_namespace("A", namespace='characters')
vocab.add_token_to_namespace("s", namespace='characters')
vocab.add_token_to_namespace("e", namespace='characters')
vocab.add_token_to_namespace("n", namespace='characters')
vocab.add_token_to_namespace("t", namespace='characters')
vocab.add_token_to_namespace("c", namespace='characters')
indexer = TokenCharactersIndexer("characters")
indices = indexer.tokens_to_indices([Token("sentential")], vocab, "char")
assert indices == {"char": [[3, 4, 5, 6, 4, 5, 6, 1, 1, 1]]}
def test_field_counts_vocab_items_correctly(self):
field = TextField([Token(t) for t in ["This", "is", "a", "sentence", "."]],
token_indexers={"words": SingleIdTokenIndexer("words")})
namespace_token_counts = defaultdict(lambda: defaultdict(int))
field.count_vocab_items(namespace_token_counts)
assert namespace_token_counts["words"]["This"] == 1
assert namespace_token_counts["words"]["is"] == 1
assert namespace_token_counts["words"]["a"] == 1
assert namespace_token_counts["words"]["sentence"] == 1
assert namespace_token_counts["words"]["."] == 1
assert list(namespace_token_counts.keys()) == ["words"]
field = TextField([Token(t) for t in ["This", "is", "a", "sentence", "."]],
token_indexers={"characters": TokenCharactersIndexer("characters")})
namespace_token_counts = defaultdict(lambda: defaultdict(int))
field.count_vocab_items(namespace_token_counts)
assert namespace_token_counts["characters"]["T"] == 1
assert namespace_token_counts["characters"]["h"] == 1
assert namespace_token_counts["characters"]["i"] == 2
assert namespace_token_counts["characters"]["s"] == 3
assert namespace_token_counts["characters"]["a"] == 1
assert namespace_token_counts["characters"]["e"] == 3
assert namespace_token_counts["characters"]["n"] == 2
assert namespace_token_counts["characters"]["t"] == 1
assert namespace_token_counts["characters"]["c"] == 1
assert namespace_token_counts["characters"]["."] == 1
assert list(namespace_token_counts.keys()) == ["characters"]
field = TextField([Token(t) for t in ["This", "is", "a", "sentence", "."]],
token_indexers={"words": SingleIdTokenIndexer("words"),
"characters": TokenCharactersIndexer("characters")})
namespace_token_counts = defaultdict(lambda: defaultdict(int))
field.count_vocab_items(namespace_token_counts)
assert namespace_token_counts["characters"]["T"] == 1
assert namespace_token_counts["characters"]["h"] == 1
assert namespace_token_counts["characters"]["i"] == 2
assert namespace_token_counts["characters"]["s"] == 3
assert namespace_token_counts["characters"]["a"] == 1
assert namespace_token_counts["characters"]["e"] == 3
assert namespace_token_counts["characters"]["n"] == 2
assert namespace_token_counts["characters"]["t"] == 1
assert namespace_token_counts["characters"]["c"] == 1
assert namespace_token_counts["characters"]["."] == 1
assert namespace_token_counts["words"]["This"] == 1
assert namespace_token_counts["words"]["is"] == 1
assert namespace_token_counts["words"]["a"] == 1
assert namespace_token_counts["words"]["sentence"] == 1
assert namespace_token_counts["words"]["."] == 1
assert set(namespace_token_counts.keys()) == {"words", "characters"}
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}
def test_count_vocab_items_respects_casing(self):
indexer = TokenCharactersIndexer("characters")
counter = defaultdict(lambda: defaultdict(int))
indexer.count_vocab_items(Token("Hello"), counter)
indexer.count_vocab_items(Token("hello"), counter)
assert counter["characters"] == {"h": 1, "H": 1, "e": 2, "l": 4, "o": 2}
indexer = TokenCharactersIndexer("characters", CharacterTokenizer(lowercase_characters=True))
counter = defaultdict(lambda: defaultdict(int))
indexer.count_vocab_items(Token("Hello"), counter)
indexer.count_vocab_items(Token("hello"), counter)
assert counter["characters"] == {"h": 2, "e": 2, "l": 4, "o": 2}
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_max_vocab_size_partial_dict(self):
indexers = {"tokens": SingleIdTokenIndexer(), "token_characters": TokenCharactersIndexer()}
instance = Instance({
'text': TextField([Token(w) for w in 'Abc def ghi jkl mno pqr stu vwx yz'.split(' ')], indexers)
})
dataset = Batch([instance])
params = Params({
"max_vocab_size": {
"tokens": 1
}
})
vocab = Vocabulary.from_params(params=params, instances=dataset)
assert len(vocab.get_index_to_token_vocabulary("tokens").values()) == 3 # 1 + 2
assert len(vocab.get_index_to_token_vocabulary("token_characters").values()) == 28 # 26 + 2
def test_padding_lengths_are_computed_correctly(self):
# pylint: disable=protected-access
self.field.index(self.vocab)
assert self.field.get_padding_lengths() == {
'num_entities': 9,
'num_entity_tokens': 3,
'num_utterance_tokens': 4
}
self.field._token_indexers[
'token_characters'] = TokenCharactersIndexer()
self.field.index(self.vocab)
assert self.field.get_padding_lengths() == {
'num_entities': 9,
'num_entity_tokens': 3,
'num_utterance_tokens': 4,
'num_token_characters': 9
}
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 setUp(self):
self.vocab = Vocabulary()
self.vocab.add_token_to_namespace("this", "words")
self.vocab.add_token_to_namespace("is", "words")
self.vocab.add_token_to_namespace("a", "words")
self.vocab.add_token_to_namespace("sentence", 'words')
self.vocab.add_token_to_namespace("s", 'characters')
self.vocab.add_token_to_namespace("e", 'characters')
self.vocab.add_token_to_namespace("n", 'characters')
self.vocab.add_token_to_namespace("t", 'characters')
self.vocab.add_token_to_namespace("c", 'characters')
for label in ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k']:
self.vocab.add_token_to_namespace(label, 'labels')
self.word_indexer = {"words": SingleIdTokenIndexer("words")}
self.words_and_characters_indexers = {
"words": SingleIdTokenIndexer("words"),
"characters": TokenCharactersIndexer("characters")
}
self.field1 = TextField(
[Token(t) for t in ["this", "is", "a", "sentence"]],
self.word_indexer)
self.field2 = TextField(
[Token(t) for t in ["this", "is", "a", "different", "sentence"]],
self.word_indexer)
self.field3 = TextField(
[Token(t) for t in ["this", "is", "another", "sentence"]],
self.word_indexer)
self.empty_text_field = self.field1.empty_field()
self.index_field = IndexField(1, self.field1)
self.empty_index_field = self.index_field.empty_field()
self.sequence_label_field = SequenceLabelField([1, 1, 0, 1],
self.field1)
self.empty_sequence_label_field = self.sequence_label_field.empty_field(
)
super(TestListField, self).setUp()
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]