def test_min_padding_length(self):
sentence = "AllenNLP is awesome ."
tokens = [Token(token) for token in sentence.split(" ")]
vocab = Vocabulary()
vocab.add_token_to_namespace("A", namespace="characters") # 2
vocab.add_token_to_namespace("l", namespace="characters") # 3
vocab.add_token_to_namespace("e", namespace="characters") # 4
vocab.add_token_to_namespace("n", namespace="characters") # 5
vocab.add_token_to_namespace("N", namespace="characters") # 6
vocab.add_token_to_namespace("L", namespace="characters") # 7
vocab.add_token_to_namespace("P", namespace="characters") # 8
vocab.add_token_to_namespace("i", namespace="characters") # 9
vocab.add_token_to_namespace("s", namespace="characters") # 10
vocab.add_token_to_namespace("a", namespace="characters") # 11
vocab.add_token_to_namespace("w", namespace="characters") # 12
vocab.add_token_to_namespace("o", namespace="characters") # 13
vocab.add_token_to_namespace("m", namespace="characters") # 14
vocab.add_token_to_namespace(".", namespace="characters") # 15
indexer = TokenCharactersIndexer("characters", min_padding_length=10)
indices = indexer.tokens_to_indices(tokens, vocab, "char")
key_padding_lengths = "num_token_characters"
value_padding_lengths = 0
for token in indices["char"]:
item = indexer.get_padding_lengths(token)
value = item.values()
value_padding_lengths = max(value_padding_lengths, max(value))
padded = indexer.pad_token_sequence(indices,
{"char": len(indices["char"])},
{key_padding_lengths: value_padding_lengths})
assert padded == {"char": [[2, 3, 3, 4, 5, 6, 7, 8, 0, 0],
[9, 10, 0, 0, 0, 0, 0, 0, 0, 0],
[11, 12, 4, 10, 13, 14, 4, 0, 0, 0],
[15, 0, 0, 0, 0, 0, 0, 0, 0, 0]]}
def test_as_array_produces_token_sequence(self):
indexer = TokenCharactersIndexer("characters")
padded_tokens = indexer.pad_token_sequence([[1, 2, 3, 4, 5], [1, 2, 3], [1]],
desired_num_tokens=4,
padding_lengths={"num_token_characters": 10})
assert padded_tokens == [[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_as_array_produces_token_sequence(self):
indexer = TokenCharactersIndexer("characters")
padded_tokens = indexer.pad_token_sequence([[1, 2, 3, 4, 5], [1, 2, 3], [1]],
desired_num_tokens=4,
padding_lengths={"num_token_characters": 10})
assert padded_tokens == [[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_min_padding_length(self):
sentence = "AllenNLP is awesome ."
tokens = [Token(token) for token in sentence.split(" ")]
vocab = Vocabulary()
vocab.add_token_to_namespace("A", namespace="characters") # 2
vocab.add_token_to_namespace("l", namespace="characters") # 3
vocab.add_token_to_namespace("e", namespace="characters") # 4
vocab.add_token_to_namespace("n", namespace="characters") # 5
vocab.add_token_to_namespace("N", namespace="characters") # 6
vocab.add_token_to_namespace("L", namespace="characters") # 7
vocab.add_token_to_namespace("P", namespace="characters") # 8
vocab.add_token_to_namespace("i", namespace="characters") # 9
vocab.add_token_to_namespace("s", namespace="characters") # 10
vocab.add_token_to_namespace("a", namespace="characters") # 11
vocab.add_token_to_namespace("w", namespace="characters") # 12
vocab.add_token_to_namespace("o", namespace="characters") # 13
vocab.add_token_to_namespace("m", namespace="characters") # 14
vocab.add_token_to_namespace(".", namespace="characters") # 15
indexer = TokenCharactersIndexer("characters", min_padding_length=10)
indices = indexer.tokens_to_indices(tokens, vocab, "char")
key_padding_lengths = "num_token_characters"
value_padding_lengths = 0
for token in indices["char"]:
item = indexer.get_padding_lengths(token)
value = item.values()
value_padding_lengths = max(value_padding_lengths, max(value))
padded = indexer.pad_token_sequence(
indices, {"char": len(indices["char"])},
{key_padding_lengths: value_padding_lengths})
assert padded == {
"char": [[2, 3, 3, 4, 5, 6, 7, 8, 0, 0],
[9, 10, 0, 0, 0, 0, 0, 0, 0, 0],
[11, 12, 4, 10, 13, 14, 4, 0, 0, 0],
[15, 0, 0, 0, 0, 0, 0, 0, 0, 0]]
}