spaCy/spacy/tests/regression/test_issue4042.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

80 lines
2.3 KiB
Python

import spacy
from spacy.pipeline import EntityRecognizer, EntityRuler
from spacy.lang.en import English
from spacy.tokens import Span
from spacy.util import ensure_path
from spacy.ml.models.defaults import default_ner
from ..util import make_tempdir
def test_issue4042():
"""Test that serialization of an EntityRuler before NER works fine."""
nlp = English()
# add ner pipe
ner = nlp.create_pipe("ner")
ner.add_label("SOME_LABEL")
nlp.add_pipe(ner)
nlp.begin_training()
# Add entity ruler
ruler = EntityRuler(nlp)
patterns = [
{"label": "MY_ORG", "pattern": "Apple"},
{"label": "MY_GPE", "pattern": [{"lower": "san"}, {"lower": "francisco"}]},
]
ruler.add_patterns(patterns)
nlp.add_pipe(ruler, before="ner") # works fine with "after"
doc1 = nlp("What do you think about Apple ?")
assert doc1.ents[0].label_ == "MY_ORG"
with make_tempdir() as d:
output_dir = ensure_path(d)
if not output_dir.exists():
output_dir.mkdir()
nlp.to_disk(output_dir)
nlp2 = spacy.load(output_dir)
doc2 = nlp2("What do you think about Apple ?")
assert doc2.ents[0].label_ == "MY_ORG"
def test_issue4042_bug2():
"""
Test that serialization of an NER works fine when new labels were added.
This is the second bug of two bugs underlying the issue 4042.
"""
nlp1 = English()
vocab = nlp1.vocab
# add ner pipe
ner1 = nlp1.create_pipe("ner")
ner1.add_label("SOME_LABEL")
nlp1.add_pipe(ner1)
nlp1.begin_training()
# add a new label to the doc
doc1 = nlp1("What do you think about Apple ?")
assert len(ner1.labels) == 1
assert "SOME_LABEL" in ner1.labels
apple_ent = Span(doc1, 5, 6, label="MY_ORG")
doc1.ents = list(doc1.ents) + [apple_ent]
# reapply the NER - at this point it should resize itself
ner1(doc1)
assert len(ner1.labels) == 2
assert "SOME_LABEL" in ner1.labels
assert "MY_ORG" in ner1.labels
with make_tempdir() as d:
# assert IO goes fine
output_dir = ensure_path(d)
if not output_dir.exists():
output_dir.mkdir()
ner1.to_disk(output_dir)
ner2 = EntityRecognizer(vocab, default_ner())
ner2.from_disk(output_dir)
assert len(ner2.labels) == 2