mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-28 02:46:35 +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
91 lines
2.0 KiB
Python
91 lines
2.0 KiB
Python
import pytest
|
|
from spacy.ml.models.defaults import default_parser, default_tok2vec
|
|
from spacy.vocab import Vocab
|
|
from spacy.syntax.arc_eager import ArcEager
|
|
from spacy.syntax.nn_parser import Parser
|
|
from spacy.syntax._parser_model import ParserModel
|
|
from spacy.tokens.doc import Doc
|
|
from spacy.gold import GoldParse
|
|
|
|
|
|
@pytest.fixture
|
|
def vocab():
|
|
return Vocab()
|
|
|
|
|
|
@pytest.fixture
|
|
def arc_eager(vocab):
|
|
actions = ArcEager.get_actions(left_labels=["L"], right_labels=["R"])
|
|
return ArcEager(vocab.strings, actions)
|
|
|
|
|
|
@pytest.fixture
|
|
def tok2vec():
|
|
tok2vec = default_tok2vec()
|
|
tok2vec.initialize()
|
|
return tok2vec
|
|
|
|
|
|
@pytest.fixture
|
|
def parser(vocab, arc_eager):
|
|
return Parser(vocab, model=default_parser(), moves=arc_eager)
|
|
|
|
|
|
@pytest.fixture
|
|
def model(arc_eager, tok2vec, vocab):
|
|
model = default_parser()
|
|
model.resize_output(arc_eager.n_moves)
|
|
model.initialize()
|
|
return model
|
|
|
|
|
|
@pytest.fixture
|
|
def doc(vocab):
|
|
return Doc(vocab, words=["a", "b", "c"])
|
|
|
|
|
|
@pytest.fixture
|
|
def gold(doc):
|
|
return GoldParse(doc, heads=[1, 1, 1], deps=["L", "ROOT", "R"])
|
|
|
|
|
|
def test_can_init_nn_parser(parser):
|
|
assert isinstance(parser.model, ParserModel)
|
|
|
|
|
|
def test_build_model(parser, vocab):
|
|
parser.model = Parser(vocab, model=default_parser(), moves=parser.moves).model
|
|
assert parser.model is not None
|
|
|
|
|
|
def test_predict_doc(parser, tok2vec, model, doc):
|
|
doc.tensor = tok2vec.predict([doc])[0]
|
|
parser.model = model
|
|
parser(doc)
|
|
|
|
|
|
def test_update_doc(parser, model, doc, gold):
|
|
parser.model = model
|
|
|
|
def optimize(key, weights, gradient):
|
|
weights -= 0.001 * gradient
|
|
return weights, gradient
|
|
|
|
parser.update((doc, gold), sgd=optimize)
|
|
|
|
|
|
@pytest.mark.xfail
|
|
def test_predict_doc_beam(parser, model, doc):
|
|
parser.model = model
|
|
parser(doc, beam_width=32, beam_density=0.001)
|
|
|
|
|
|
@pytest.mark.xfail
|
|
def test_update_doc_beam(parser, model, doc, gold):
|
|
parser.model = model
|
|
|
|
def optimize(weights, gradient, key=None):
|
|
weights -= 0.001 * gradient
|
|
|
|
parser.update_beam((doc, gold), sgd=optimize)
|