spaCy/spacy/tests/parser/test_preset_sbd.py
Sofie Van Landeghem 06f0a8daa0
Default settings to configurations (#4995)
* 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
2020-02-27 18:42:27 +01:00

74 lines
2.0 KiB
Python

import pytest
from thinc.api import Adam
from spacy.attrs import NORM
from spacy.gold import GoldParse
from spacy.vocab import Vocab
from spacy.ml.models.defaults import default_parser
from spacy.tokens import Doc
from spacy.pipeline import DependencyParser
@pytest.fixture
def vocab():
return Vocab(lex_attr_getters={NORM: lambda s: s})
@pytest.fixture
def parser(vocab):
parser = DependencyParser(vocab, default_parser())
parser.cfg["token_vector_width"] = 4
parser.cfg["hidden_width"] = 32
# parser.add_label('right')
parser.add_label("left")
parser.begin_training([], **parser.cfg)
sgd = Adam(0.001)
for i in range(10):
losses = {}
doc = Doc(vocab, words=["a", "b", "c", "d"])
gold = GoldParse(doc, heads=[1, 1, 3, 3], deps=["left", "ROOT", "left", "ROOT"])
parser.update((doc, gold), sgd=sgd, losses=losses)
return parser
def test_no_sentences(parser):
doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
doc = parser(doc)
assert len(list(doc.sents)) >= 1
def test_sents_1(parser):
doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
doc[2].sent_start = True
doc = parser(doc)
assert len(list(doc.sents)) >= 2
doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
doc[1].sent_start = False
doc[2].sent_start = True
doc[3].sent_start = False
doc = parser(doc)
assert len(list(doc.sents)) == 2
def test_sents_1_2(parser):
doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
doc[1].sent_start = True
doc[2].sent_start = True
doc = parser(doc)
assert len(list(doc.sents)) >= 3
def test_sents_1_3(parser):
doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
doc[1].sent_start = True
doc[3].sent_start = True
doc = parser(doc)
assert len(list(doc.sents)) >= 3
doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
doc[1].sent_start = True
doc[2].sent_start = False
doc[3].sent_start = True
doc = parser(doc)
assert len(list(doc.sents)) == 3