mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 10:26:35 +03:00
06f0a8daa0
* fix grad_clip naming * cleaning up pretrained_vectors out of cfg * further refactoring Model init's * move Model building out of pipes * further refactor to require a model config when creating a pipe * small fixes * making cfg in nn_parser more consistent * fixing nr_class for parser * fixing nn_parser's nO * fix printing of loss * architectures in own file per type, consistent naming * convenience methods default_tagger_config and default_tok2vec_config * let create_pipe access default config if available for that component * default_parser_config * move defaults to separate folder * allow reading nlp from package or dir with argument 'name' * architecture spacy.VocabVectors.v1 to read static vectors from file * cleanup * default configs for nel, textcat, morphologizer, tensorizer * fix imports * fixing unit tests * fixes and clean up * fixing defaults, nO, fix unit tests * restore parser IO * fix IO * 'fix' serialization test * add *.cfg to manifest * fix example configs with additional arguments * replace Morpohologizer with Tagger * add IO bit when testing overfitting of tagger (currently failing) * fix IO - don't initialize when reading from disk * expand overfitting tests to also check IO goes OK * remove dropout from HashEmbed to fix Tagger performance * add defaults for sentrec * update thinc * always pass a Model instance to a Pipe * fix piped_added statement * remove obsolete W029 * remove obsolete errors * restore byte checking tests (work again) * clean up test * further test cleanup * convert from config to Model in create_pipe * bring back error when component is not initialized * cleanup * remove calls for nlp2.begin_training * use thinc.api in imports * allow setting charembed's nM and nC * fix for hardcoded nM/nC + unit test * formatting fixes * trigger build
102 lines
2.1 KiB
Python
102 lines
2.1 KiB
Python
import pytest
|
|
import numpy
|
|
from spacy.vocab import Vocab
|
|
from spacy.language import Language
|
|
from spacy.ml.models.defaults import default_parser
|
|
from spacy.pipeline import DependencyParser
|
|
from spacy.syntax.arc_eager import ArcEager
|
|
from spacy.tokens import Doc
|
|
from spacy.syntax._beam_utils import ParserBeam
|
|
from spacy.syntax.stateclass import StateClass
|
|
from spacy.gold import GoldParse
|
|
|
|
|
|
@pytest.fixture
|
|
def vocab():
|
|
return Vocab()
|
|
|
|
|
|
@pytest.fixture
|
|
def moves(vocab):
|
|
aeager = ArcEager(vocab.strings, {})
|
|
aeager.add_action(2, "nsubj")
|
|
aeager.add_action(3, "dobj")
|
|
aeager.add_action(2, "aux")
|
|
return aeager
|
|
|
|
|
|
@pytest.fixture
|
|
def docs(vocab):
|
|
return [Doc(vocab, words=["Rats", "bite", "things"])]
|
|
|
|
|
|
@pytest.fixture
|
|
def states(docs):
|
|
return [StateClass(doc) for doc in docs]
|
|
|
|
|
|
@pytest.fixture
|
|
def tokvecs(docs, vector_size):
|
|
output = []
|
|
for doc in docs:
|
|
vec = numpy.random.uniform(-0.1, 0.1, (len(doc), vector_size))
|
|
output.append(numpy.asarray(vec))
|
|
return output
|
|
|
|
|
|
@pytest.fixture
|
|
def golds(docs):
|
|
return [GoldParse(doc) for doc in docs]
|
|
|
|
|
|
@pytest.fixture
|
|
def batch_size(docs):
|
|
return len(docs)
|
|
|
|
|
|
@pytest.fixture
|
|
def beam_width():
|
|
return 4
|
|
|
|
|
|
@pytest.fixture
|
|
def vector_size():
|
|
return 6
|
|
|
|
|
|
@pytest.fixture
|
|
def beam(moves, states, golds, beam_width):
|
|
return ParserBeam(moves, states, golds, width=beam_width, density=0.0)
|
|
|
|
|
|
@pytest.fixture
|
|
def scores(moves, batch_size, beam_width):
|
|
return [
|
|
numpy.asarray(
|
|
numpy.random.uniform(-0.1, 0.1, (batch_size, moves.n_moves)), dtype="f"
|
|
)
|
|
for _ in range(batch_size)
|
|
]
|
|
|
|
|
|
def test_create_beam(beam):
|
|
pass
|
|
|
|
|
|
def test_beam_advance(beam, scores):
|
|
beam.advance(scores)
|
|
|
|
|
|
def test_beam_advance_too_few_scores(beam, scores):
|
|
with pytest.raises(IndexError):
|
|
beam.advance(scores[:-1])
|
|
|
|
|
|
def test_beam_parse():
|
|
nlp = Language()
|
|
nlp.add_pipe(DependencyParser(nlp.vocab, default_parser()), name="parser")
|
|
nlp.parser.add_label("nsubj")
|
|
nlp.parser.begin_training([], token_vector_width=8, hidden_width=8)
|
|
doc = nlp.make_doc("Australia is a country")
|
|
nlp.parser(doc, beam_width=2)
|