Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Rename modified textcat scorer to v2 (#11971) 

As a follow-up to #11696, rename the modified scorer to v2 and move the
v1 scorer to `spacy-legacy`.
This commit is contained in:
Adriane Boyd 2022-12-29 14:01:08 +01:00 committed by GitHub
parent 933b54ac79
commit ef9e504eac
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 21 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
requirements.txt
View File

@ -1,5 +1,5 @@
# Our libraries # Our libraries
spacy-legacy>=3.0.10,<3.1.0 spacy-legacy>=3.0.11,<3.1.0
spacy-loggers>=1.0.0,<2.0.0 spacy-loggers>=1.0.0,<2.0.0
cymem>=2.0.2,<2.1.0 cymem>=2.0.2,<2.1.0
preshed>=3.0.2,<3.1.0 preshed>=3.0.2,<3.1.0

2
setup.cfg
View File

@ -42,7 +42,7 @@ setup_requires =
thinc>=8.1.0,<8.2.0 thinc>=8.1.0,<8.2.0
install_requires = install_requires =
# Our libraries # Our libraries
spacy-legacy>=3.0.10,<3.1.0 spacy-legacy>=3.0.11,<3.1.0
spacy-loggers>=1.0.0,<2.0.0 spacy-loggers>=1.0.0,<2.0.0
murmurhash>=0.28.0,<1.1.0 murmurhash>=0.28.0,<1.1.0
cymem>=2.0.2,<2.1.0 cymem>=2.0.2,<2.1.0

4
spacy/pipeline/textcat.py
View File

@ -74,7 +74,7 @@ subword_features = true
default_config={ default_config={
"threshold": 0.0, "threshold": 0.0,
"model": DEFAULT_SINGLE_TEXTCAT_MODEL, "model": DEFAULT_SINGLE_TEXTCAT_MODEL,
"scorer": {"@scorers": "spacy.textcat_scorer.v1"}, "scorer": {"@scorers": "spacy.textcat_scorer.v2"},
}, },
default_score_weights={ default_score_weights={
"cats_score": 1.0, "cats_score": 1.0,
@ -117,7 +117,7 @@ def textcat_score(examples: Iterable[Example], **kwargs) -> Dict[str, Any]:
) )
@registry.scorers("spacy.textcat_scorer.v1") @registry.scorers("spacy.textcat_scorer.v2")
def make_textcat_scorer(): def make_textcat_scorer():
return textcat_score return textcat_score

17
spacy/tests/pipeline/test_textcat.py
View File

@ -895,3 +895,20 @@ def test_textcat_multi_threshold():
scores = nlp.evaluate(train_examples, scorer_cfg={"threshold": 0}) scores = nlp.evaluate(train_examples, scorer_cfg={"threshold": 0})
assert scores["cats_f_per_type"]["POSITIVE"]["r"] == 1.0 assert scores["cats_f_per_type"]["POSITIVE"]["r"] == 1.0
@pytest.mark.parametrize("component_name,scorer", [("textcat", "spacy.textcat_scorer.v1")])
def test_textcat_legacy_scorers(component_name, scorer):
"""Check that legacy scorers are registered and produce the expected score
keys."""
nlp = English()
nlp.add_pipe(component_name, config={"scorer": {"@scorers": scorer}})
train_examples = []
for text, annotations in TRAIN_DATA_SINGLE_LABEL:
train_examples.append(Example.from_dict(nlp.make_doc(text), annotations))
nlp.initialize(get_examples=lambda: train_examples)
# score the model (it's not actually trained but that doesn't matter)
scores = nlp.evaluate(train_examples)
assert 0 <= scores["cats_score"] <= 1