mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 09:56:28 +03:00
f99d6d5e39
* 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>
33 lines
1.1 KiB
Python
33 lines
1.1 KiB
Python
from typing import Optional, Callable
|
|
|
|
from thinc.api import Model
|
|
|
|
from ..ru.lemmatizer import RussianLemmatizer
|
|
from ...pipeline.lemmatizer import lemmatizer_score
|
|
from ...vocab import Vocab
|
|
|
|
|
|
class UkrainianLemmatizer(RussianLemmatizer):
|
|
def __init__(
|
|
self,
|
|
vocab: Vocab,
|
|
model: Optional[Model],
|
|
name: str = "lemmatizer",
|
|
*,
|
|
mode: str = "pymorphy2",
|
|
overwrite: bool = False,
|
|
scorer: Optional[Callable] = lemmatizer_score,
|
|
) -> None:
|
|
if mode == "pymorphy2":
|
|
try:
|
|
from pymorphy2 import MorphAnalyzer
|
|
except ImportError:
|
|
raise ImportError(
|
|
"The Ukrainian lemmatizer mode 'pymorphy2' requires the "
|
|
"pymorphy2 library and dictionaries. Install them with: "
|
|
"pip install pymorphy2 pymorphy2-dicts-uk"
|
|
) from None
|
|
if getattr(self, "_morph", None) is None:
|
|
self._morph = MorphAnalyzer(lang="uk")
|
|
super().__init__(vocab, model, name, mode=mode, overwrite=overwrite, scorer=scorer)
|