spaCy/spacy/lang/mk/__init__.py
Adriane Boyd f99d6d5e39
Refactor scoring methods to use registered functions (#8766)
* Add scorer option to components

Add an optional `scorer` parameter to all pipeline components. If a
scoring function is provided, it overrides the default scoring method
for that component.

* Add registered scorers for all components

* Add `scorers` registry
* Move all scoring methods outside of components as independent
  functions and register
* Use the registered scoring methods as defaults in configs and inits

Additional:

* The scoring methods no longer have access to the full component, so
  use settings from `cfg` as default scorer options to handle settings
  such as `labels`, `threshold`, and `positive_label`
* The `attribute_ruler` scoring method no longer has access to the
  patterns, so all scoring methods are called
* Bug fix: `spancat` scoring method is updated to set `allow_overlap` to
  score overlapping spans correctly

* Update Russian lemmatizer to use direct score method

* Check type of cfg in Pipe.score

* Fix check

* Update spacy/pipeline/sentencizer.pyx

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Remove validate_examples from scoring functions

* Use Pipe.labels instead of Pipe.cfg["labels"]

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
2021-08-10 15:13:39 +02:00

63 lines
1.6 KiB
Python

from typing import Optional, Callable
from thinc.api import Model
from .lemmatizer import MacedonianLemmatizer
from .stop_words import STOP_WORDS
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .lex_attrs import LEX_ATTRS
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...language import Language
from ...attrs import LANG
from ...util import update_exc
from ...lookups import Lookups
class MacedonianDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: "mk"
# Optional: replace flags with custom functions, e.g. like_num()
lex_attr_getters.update(LEX_ATTRS)
# Merge base exceptions and custom tokenizer exceptions
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = STOP_WORDS
@classmethod
def create_lemmatizer(cls, nlp=None, lookups=None):
if lookups is None:
lookups = Lookups()
return MacedonianLemmatizer(lookups)
class Macedonian(Language):
lang = "mk"
Defaults = MacedonianDefaults
@Macedonian.factory(
"lemmatizer",
assigns=["token.lemma"],
default_config={
"model": None,
"mode": "rule",
"overwrite": False,
"scorer": {"@scorers": "spacy.lemmatizer_scorer.v1"},
},
default_score_weights={"lemma_acc": 1.0},
)
def make_lemmatizer(
nlp: Language,
model: Optional[Model],
name: str,
mode: str,
overwrite: bool,
scorer: Optional[Callable],
):
return MacedonianLemmatizer(
nlp.vocab, model, name, mode=mode, overwrite=overwrite, scorer=scorer
)
__all__ = ["Macedonian"]