mirror of
https://github.com/explosion/spaCy.git
synced 2025-10-31 07:57:35 +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
69 lines
2.1 KiB
Python
69 lines
2.1 KiB
Python
import pytest
|
|
import re
|
|
|
|
from spacy.language import Language
|
|
from spacy.tokenizer import Tokenizer
|
|
|
|
from ..util import make_tempdir
|
|
|
|
|
|
@pytest.fixture
|
|
def meta_data():
|
|
return {
|
|
"name": "name-in-fixture",
|
|
"version": "version-in-fixture",
|
|
"description": "description-in-fixture",
|
|
"author": "author-in-fixture",
|
|
"email": "email-in-fixture",
|
|
"url": "url-in-fixture",
|
|
"license": "license-in-fixture",
|
|
"vectors": {"width": 0, "vectors": 0, "keys": 0, "name": None},
|
|
}
|
|
|
|
|
|
def test_serialize_language_meta_disk(meta_data):
|
|
language = Language(meta=meta_data)
|
|
with make_tempdir() as d:
|
|
language.to_disk(d)
|
|
new_language = Language().from_disk(d)
|
|
assert new_language.meta == language.meta
|
|
|
|
|
|
def test_serialize_with_custom_tokenizer():
|
|
"""Test that serialization with custom tokenizer works without token_match.
|
|
See: https://support.prodi.gy/t/how-to-save-a-custom-tokenizer/661/2
|
|
"""
|
|
prefix_re = re.compile(r"""1/|2/|:[0-9][0-9][A-K]:|:[0-9][0-9]:""")
|
|
suffix_re = re.compile(r"""""")
|
|
infix_re = re.compile(r"""[~]""")
|
|
|
|
def custom_tokenizer(nlp):
|
|
return Tokenizer(
|
|
nlp.vocab,
|
|
{},
|
|
prefix_search=prefix_re.search,
|
|
suffix_search=suffix_re.search,
|
|
infix_finditer=infix_re.finditer,
|
|
)
|
|
|
|
nlp = Language()
|
|
nlp.tokenizer = custom_tokenizer(nlp)
|
|
with make_tempdir() as d:
|
|
nlp.to_disk(d)
|
|
|
|
|
|
def test_serialize_language_exclude(meta_data):
|
|
name = "name-in-fixture"
|
|
nlp = Language(meta=meta_data)
|
|
assert nlp.meta["name"] == name
|
|
new_nlp = Language().from_bytes(nlp.to_bytes())
|
|
assert new_nlp.meta["name"] == name
|
|
new_nlp = Language().from_bytes(nlp.to_bytes(), exclude=["meta"])
|
|
assert not new_nlp.meta["name"] == name
|
|
new_nlp = Language().from_bytes(nlp.to_bytes(exclude=["meta"]))
|
|
assert not new_nlp.meta["name"] == name
|
|
with pytest.raises(ValueError):
|
|
nlp.to_bytes(meta=False)
|
|
with pytest.raises(ValueError):
|
|
Language().from_bytes(nlp.to_bytes(), meta=False)
|