mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 01:46:28 +03:00
85778dfcf4
* Add edit tree lemmatizer Co-authored-by: Daniël de Kok <me@danieldk.eu> * Hide edit tree lemmatizer labels * Use relative imports * Switch to single quotes in error message * Type annotation fixes Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Reformat edit_tree_lemmatizer with black * EditTreeLemmatizer.predict: take Iterable Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Validate edit trees during deserialization This change also changes the serialized representation. Rather than mirroring the deep C structure, we use a simple flat union of the match and substitution node types. * Move edit_trees to _edit_tree_internals * Fix invalid edit tree format error message * edit_tree_lemmatizer: remove outdated TODO comment * Rename factory name to trainable_lemmatizer * Ignore type instead of casting truths to List[Union[Ints1d, Floats2d, List[int], List[str]]] for thinc v8.0.14 * Switch to Tagger.v2 * Add documentation for EditTreeLemmatizer * docs: Fix 3.2 -> 3.3 somewhere * trainable_lemmatizer documentation fixes * docs: EditTreeLemmatizer is in edit_tree_lemmatizer.py Co-authored-by: Daniël de Kok <me@danieldk.eu> Co-authored-by: Daniël de Kok <me@github.danieldk.eu> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
41 lines
1.1 KiB
Python
41 lines
1.1 KiB
Python
from .attributeruler import AttributeRuler
|
|
from .dep_parser import DependencyParser
|
|
from .edit_tree_lemmatizer import EditTreeLemmatizer
|
|
from .entity_linker import EntityLinker
|
|
from .ner import EntityRecognizer
|
|
from .entityruler import EntityRuler
|
|
from .lemmatizer import Lemmatizer
|
|
from .morphologizer import Morphologizer
|
|
from .pipe import Pipe
|
|
from .trainable_pipe import TrainablePipe
|
|
from .senter import SentenceRecognizer
|
|
from .sentencizer import Sentencizer
|
|
from .tagger import Tagger
|
|
from .textcat import TextCategorizer
|
|
from .spancat import SpanCategorizer
|
|
from .textcat_multilabel import MultiLabel_TextCategorizer
|
|
from .tok2vec import Tok2Vec
|
|
from .functions import merge_entities, merge_noun_chunks, merge_subtokens
|
|
|
|
__all__ = [
|
|
"AttributeRuler",
|
|
"DependencyParser",
|
|
"EntityLinker",
|
|
"EntityRecognizer",
|
|
"EntityRuler",
|
|
"Morphologizer",
|
|
"Lemmatizer",
|
|
"MultiLabel_TextCategorizer",
|
|
"Pipe",
|
|
"SentenceRecognizer",
|
|
"Sentencizer",
|
|
"SpanCategorizer",
|
|
"Tagger",
|
|
"TextCategorizer",
|
|
"Tok2Vec",
|
|
"TrainablePipe",
|
|
"merge_entities",
|
|
"merge_noun_chunks",
|
|
"merge_subtokens",
|
|
]
|