mirror of
https://github.com/explosion/spaCy.git
synced 2025-10-31 16:07:41 +03:00
c003aac29a
* span finder integrated into spacy from experimental * black * isort * black * default spankey constant * black * Update spacy/pipeline/spancat.py Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * rename * rename * max_length and min_length as Optional[int] and strict checking * black * mypy fix for integer type infinity * revert line order * implement all comparison operators for inf int * avoid two for loops over all docs by not precomputing * interleave thresholding with span creation * black * revert to not interleaving (relized its faster) * black * Update spacy/errors.py Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * update dosctring * enforce that the gold and predicted documents have the same text * new error for ensuring reference and predicted texts are the same * remove todo * adjust test * black * handle misaligned tokenization * return correct variable * failing overfit test * only use a single spans_key like in spancat * black * remove debug lines * typo * remove comment * remove near duplicate reduntant method * use the 'spans_key' variable name everywhere * Update spacy/pipeline/span_finder.py Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * flaky test fix suggestion, hand set bias terms * only test suggester and test result exhaustively * make it clear that the span_finder_suggester is more general (not specific to span_finder) * Update spacy/tests/pipeline/test_span_finder.py Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Apply suggestions from code review * remove question comment * move preset_spans_suggester test to spancat tests * Add docs and unify default configs for spancat and span finder * Add `allow_overlap=True` to span finder scorer * Fix offset bug in set_annotations * Ignore labels in span finder scorer * Format * Add span_finder to quickstart template * Move settings to self.cfg, store min/max unset as None * Remove debugging * Update docstrings and docs * Update spacy/pipeline/span_finder.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix imports --------- Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
45 lines
1.2 KiB
Python
45 lines
1.2 KiB
Python
from .attributeruler import AttributeRuler
|
|
from .dep_parser import DependencyParser
|
|
from .edit_tree_lemmatizer import EditTreeLemmatizer
|
|
from .entity_linker import EntityLinker
|
|
from .entityruler import EntityRuler
|
|
from .functions import merge_entities, merge_noun_chunks, merge_subtokens
|
|
from .lemmatizer import Lemmatizer
|
|
from .morphologizer import Morphologizer
|
|
from .ner import EntityRecognizer
|
|
from .pipe import Pipe
|
|
from .sentencizer import Sentencizer
|
|
from .senter import SentenceRecognizer
|
|
from .span_finder import SpanFinder
|
|
from .span_ruler import SpanRuler
|
|
from .spancat import SpanCategorizer
|
|
from .tagger import Tagger
|
|
from .textcat import TextCategorizer
|
|
from .textcat_multilabel import MultiLabel_TextCategorizer
|
|
from .tok2vec import Tok2Vec
|
|
from .trainable_pipe import TrainablePipe
|
|
|
|
__all__ = [
|
|
"AttributeRuler",
|
|
"DependencyParser",
|
|
"EntityLinker",
|
|
"EntityRecognizer",
|
|
"EntityRuler",
|
|
"Morphologizer",
|
|
"Lemmatizer",
|
|
"MultiLabel_TextCategorizer",
|
|
"Pipe",
|
|
"SentenceRecognizer",
|
|
"Sentencizer",
|
|
"SpanCategorizer",
|
|
"SpanFinder",
|
|
"SpanRuler",
|
|
"Tagger",
|
|
"TextCategorizer",
|
|
"Tok2Vec",
|
|
"TrainablePipe",
|
|
"merge_entities",
|
|
"merge_noun_chunks",
|
|
"merge_subtokens",
|
|
]
|