mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-04 01:48:04 +03:00
8e7557656f
* version bump to 3.0.0a16 * rename "gold" folder to "training" * rename 'annotation_setter' to 'set_extra_annotations' * formatting
89 lines
2.5 KiB
Python
89 lines
2.5 KiB
Python
import pytest
|
|
from thinc.api import Adam
|
|
from spacy.attrs import NORM
|
|
from spacy.vocab import Vocab
|
|
from spacy import registry
|
|
from spacy.training import Example
|
|
from spacy.pipeline.dep_parser import DEFAULT_PARSER_MODEL
|
|
from spacy.tokens import Doc
|
|
from spacy.pipeline import DependencyParser
|
|
|
|
|
|
@pytest.fixture
|
|
def vocab():
|
|
return Vocab(lex_attr_getters={NORM: lambda s: s})
|
|
|
|
|
|
def _parser_example(parser):
|
|
doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
|
|
gold = {"heads": [1, 1, 3, 3], "deps": ["right", "ROOT", "left", "ROOT"]}
|
|
return Example.from_dict(doc, gold)
|
|
|
|
|
|
@pytest.fixture
|
|
def parser(vocab):
|
|
config = {
|
|
"learn_tokens": False,
|
|
"min_action_freq": 30,
|
|
"update_with_oracle_cut_size": 100,
|
|
}
|
|
cfg = {"model": DEFAULT_PARSER_MODEL}
|
|
model = registry.make_from_config(cfg, validate=True)["model"]
|
|
parser = DependencyParser(vocab, model, **config)
|
|
parser.cfg["token_vector_width"] = 4
|
|
parser.cfg["hidden_width"] = 32
|
|
# parser.add_label('right')
|
|
parser.add_label("left")
|
|
parser.begin_training(lambda: [_parser_example(parser)], **parser.cfg)
|
|
sgd = Adam(0.001)
|
|
|
|
for i in range(10):
|
|
losses = {}
|
|
doc = Doc(vocab, words=["a", "b", "c", "d"])
|
|
example = Example.from_dict(
|
|
doc, {"heads": [1, 1, 3, 3], "deps": ["left", "ROOT", "left", "ROOT"]}
|
|
)
|
|
parser.update([example], 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
|