mirror of
https://github.com/explosion/spaCy.git
synced 2025-10-29 15:07:54 +03:00
1c4df8fd09
* Replace pytokenizations with internal alignment Replace pytokenizations with internal alignment algorithm that is restricted to only allow differences in whitespace and capitalization. * Rename `spacy.training.align` to `spacy.training.alignment` to contain the `Alignment` dataclass * Implement `get_alignments` in `spacy.training.align` * Refactor trailing whitespace handling * Remove unnecessary exception for empty docs Allow a non-empty whitespace-only doc to be aligned with an empty doc * Remove empty docs exceptions completely
11 lines
676 B
Python
11 lines
676 B
Python
from .corpus import Corpus # noqa: F401
|
|
from .example import Example, validate_examples, validate_get_examples # noqa: F401
|
|
from .alignment import Alignment # noqa: F401
|
|
from .augment import dont_augment, orth_variants_augmenter # noqa: F401
|
|
from .iob_utils import iob_to_biluo, biluo_to_iob # noqa: F401
|
|
from .iob_utils import offsets_to_biluo_tags, biluo_tags_to_offsets # noqa: F401
|
|
from .iob_utils import biluo_tags_to_spans, tags_to_entities # noqa: F401
|
|
from .gold_io import docs_to_json, read_json_file # noqa: F401
|
|
from .batchers import minibatch_by_padded_size, minibatch_by_words # noqa: F401
|
|
from .loggers import console_logger, wandb_logger # noqa: F401
|