explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-14 18:22:27 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'v4' into refactor/el-candidates

Browse Source 
# Conflicts:
#	spacy/errors.py
This commit is contained in:
Raphael Mitsch 2023-03-07 14:00:01 +01:00
commit 0c63940407
3 changed files with 5 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/errors.py
View File

@ -960,8 +960,10 @@ class Errors(metaclass=ErrorsWithCodes):
E4003 = ("Training examples for distillation must have the exact same tokens in the " E4003 = ("Training examples for distillation must have the exact same tokens in the "
"reference and predicted docs.") "reference and predicted docs.")
E4004 = ("Backprop is not supported when is_train is not set.") E4004 = ("Backprop is not supported when is_train is not set.")
E4005 = ("EntityLinker_v1 is not supported in spaCy v4. Update your configuration.")
E4006 = ("Expected `entity_id` to be of type {exp_type}, but is of type {found_type}.") E4006 = ("Expected `entity_id` to be of type {exp_type}, but is of type {found_type}.")
RENAMED_LANGUAGE_CODES = {"xx": "mul", "is": "isl"} RENAMED_LANGUAGE_CODES = {"xx": "mul", "is": "isl"}
# fmt: on # fmt: on

23
spacy/pipeline/entity_linker.py
View File

@ -117,28 +117,9 @@ def make_entity_linker(
prediction is discarded. If None, predictions are not filtered by any threshold. prediction is discarded. If None, predictions are not filtered by any threshold.
save_activations (bool): save model activations in Doc when annotating. save_activations (bool): save model activations in Doc when annotating.
""" """
if not model.attrs.get("include_span_maker", False): if not model.attrs.get("include_span_maker", False):
try: raise ValueError(Errors.E4005)
from spacy_legacy.components.entity_linker import EntityLinker_v1
except:
raise ImportError(
"In order to use v1 of the EntityLinker, you must use spacy-legacy>=3.0.12."
)
# The only difference in arguments here is that use_gold_ents and threshold aren't available.
return EntityLinker_v1(
nlp.vocab,
model,
name,
labels_discard=labels_discard,
n_sents=n_sents,
incl_prior=incl_prior,
incl_context=incl_context,
entity_vector_length=entity_vector_length,
get_candidates=get_candidates,
overwrite=overwrite,
scorer=scorer,
)
return EntityLinker( return EntityLinker(
nlp.vocab, nlp.vocab,
model, model,

7
spacy/tests/pipeline/test_entity_linker.py
View File

@ -991,13 +991,11 @@ def test_scorer_links():
@pytest.mark.parametrize( @pytest.mark.parametrize(
"name,config", "name,config",
[ [
("entity_linker", {"@architectures": "spacy.EntityLinker.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL}),
("entity_linker", {"@architectures": "spacy.EntityLinker.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL}), ("entity_linker", {"@architectures": "spacy.EntityLinker.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL}),
], ],
) )
# fmt: on # fmt: on
def test_legacy_architectures(name, config): def test_legacy_architectures(name, config):
from spacy_legacy.components.entity_linker import EntityLinker_v1
# Ensure that the legacy architectures still work # Ensure that the legacy architectures still work
vector_length = 3 vector_length = 3
@ -1020,10 +1018,7 @@ def test_legacy_architectures(name, config):
return mykb return mykb
entity_linker = nlp.add_pipe(name, config={"model": config}) entity_linker = nlp.add_pipe(name, config={"model": config})
if config["@architectures"] == "spacy.EntityLinker.v1": assert isinstance(entity_linker, EntityLinker)
assert isinstance(entity_linker, EntityLinker_v1)
else:
assert isinstance(entity_linker, EntityLinker)
entity_linker.set_kb(create_kb) entity_linker.set_kb(create_kb)
optimizer = nlp.initialize(get_examples=lambda: train_examples) optimizer = nlp.initialize(get_examples=lambda: train_examples)