def test_from_instances_exclusive_embeddings_file_inside_archive(self):
""" Just for ensuring there are no problems when reading pretrained tokens from an archive """
# Read embeddings file from archive
archive_path = str(self.TEST_DIR / "embeddings-archive.zip")
with zipfile.ZipFile(archive_path, 'w') as archive:
file_path = 'embedding.3d.vec'
with archive.open(file_path, 'w') as embeddings_file:
embeddings_file.write("a 1.0 2.3 -1.0\n".encode('utf-8'))
embeddings_file.write("b 0.1 0.4 -4.0\n".encode('utf-8'))
with archive.open('dummy.vec', 'w') as dummy_file:
dummy_file.write("c 1.0 2.3 -1.0 3.0\n".encode('utf-8'))
embeddings_file_uri = format_embeddings_file_uri(archive_path, file_path)
vocab = Vocabulary.from_instances(self.dataset,
min_count={'tokens': 4},
pretrained_files={'tokens': embeddings_file_uri},
only_include_pretrained_words=True)
words = set(vocab.get_index_to_token_vocabulary().values())
assert 'a' in words
assert 'b' not in words
assert 'c' not in words
vocab = Vocabulary.from_instances(self.dataset,
pretrained_files={'tokens': embeddings_file_uri},
only_include_pretrained_words=True)
words = set(vocab.get_index_to_token_vocabulary().values())
assert 'a' in words
assert 'b' in words
assert 'c' not in words
def test_from_dataset_respects_max_vocab_size_single_int(self):
max_vocab_size = 1
vocab = Vocabulary.from_instances(self.dataset, max_vocab_size=max_vocab_size)
words = vocab.get_index_to_token_vocabulary().values()
# Additional 2 tokens are '@@PADDING@@' and '@@UNKNOWN@@' by default
assert len(words) == max_vocab_size + 2
vocab = Vocabulary.from_instances(self.dataset, min_count=None)
words = vocab.get_index_to_token_vocabulary().values()
assert len(words) == 5
def test_from_dataset_respects_min_count(self):
vocab = Vocabulary.from_instances(self.dataset, min_count={'tokens': 4})
words = vocab.get_index_to_token_vocabulary().values()
assert 'a' in words
assert 'b' not in words
assert 'c' not in words
vocab = Vocabulary.from_instances(self.dataset, min_count=None)
words = vocab.get_index_to_token_vocabulary().values()
assert 'a' in words
assert 'b' in words
assert 'c' in words
def test_from_dataset_respects_inclusive_embedding_file(self):
embeddings_filename = str(self.TEST_DIR / "embeddings.gz")
with gzip.open(embeddings_filename, 'wb') as embeddings_file:
embeddings_file.write("a 1.0 2.3 -1.0\n".encode('utf-8'))
embeddings_file.write("b 0.1 0.4 -4.0\n".encode('utf-8'))
vocab = Vocabulary.from_instances(self.dataset,
min_count={'tokens': 4},
pretrained_files={'tokens': embeddings_filename},
only_include_pretrained_words=False)
words = vocab.get_index_to_token_vocabulary().values()
assert 'a' in words
assert 'b' in words
assert 'c' not in words
vocab = Vocabulary.from_instances(self.dataset,
pretrained_files={'tokens': embeddings_filename},
only_include_pretrained_words=False)
words = vocab.get_index_to_token_vocabulary().values()
assert 'a' in words
assert 'b' in words
assert 'c' in words
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
