mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 13:47:13 +03:00
43b960c01b
* Update with WIP * Update with WIP * Update with pipeline serialization * Update types and pipe factories * Add deep merge, tidy up and add tests * Fix pipe creation from config * Don't validate default configs on load * Update spacy/language.py Co-authored-by: Ines Montani <ines@ines.io> * Adjust factory/component meta error * Clean up factory args and remove defaults * Add test for failing empty dict defaults * Update pipeline handling and methods * provide KB as registry function instead of as object * small change in test to make functionality more clear * update example script for EL configuration * Fix typo * Simplify test * Simplify test * splitting pipes.pyx into separate files * moving default configs to each component file * fix batch_size type * removing default values from component constructors where possible (TODO: test 4725) * skip instead of xfail * Add test for config -> nlp with multiple instances * pipeline.pipes -> pipeline.pipe * Tidy up, document, remove kwargs * small cleanup/generalization for Tok2VecListener * use DEFAULT_UPSTREAM field * revert to avoid circular imports * Fix tests * Replace deprecated arg * Make model dirs require config * fix pickling of keyword-only arguments in constructor * WIP: clean up and integrate full config * Add helper to handle function args more reliably Now also includes keyword-only args * Fix config composition and serialization * Improve config debugging and add visual diff * Remove unused defaults and fix type * Remove pipeline and factories from meta * Update spacy/default_config.cfg Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/default_config.cfg * small UX edits * avoid printing stack trace for debug CLI commands * Add support for language-specific factories * specify the section of the config which holds the model to debug * WIP: add Language.from_config * Update with language data refactor WIP * Auto-format * Add backwards-compat handling for Language.factories * Update morphologizer.pyx * Fix morphologizer * Update and simplify lemmatizers * Fix Japanese tests * Port over tagger changes * Fix Chinese and tests * Update to latest Thinc * WIP: xfail first Russian lemmatizer test * Fix component-specific overrides * fix nO for output layers in debug_model * Fix default value * Fix tests and don't pass objects in config * Fix deep merging * Fix lemma lookup data registry Only load the lookups if an entry is available in the registry (and if spacy-lookups-data is installed) * Add types * Add Vocab.from_config * Fix typo * Fix tests * Make config copying more elegant * Fix pipe analysis * Fix lemmatizers and is_base_form * WIP: move language defaults to config * Fix morphology type * Fix vocab * Remove comment * Update to latest Thinc * Add morph rules to config * Tidy up * Remove set_morphology option from tagger factory * Hack use_gpu * Move [pipeline] to top-level block and make [nlp.pipeline] list Allows separating component blocks from component order – otherwise, ordering the config would mean a changed component order, which is bad. Also allows initial config to define more components and not use all of them * Fix use_gpu and resume in CLI * Auto-format * Remove resume from config * Fix formatting and error * [pipeline] -> [components] * Fix types * Fix tagger test: requires set_morphology? Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
70 lines
2.3 KiB
Python
70 lines
2.3 KiB
Python
import pytest
|
|
|
|
from ...util import get_doc
|
|
|
|
|
|
@pytest.mark.xfail(reason="TODO: investigate why lemmatizer fails here")
|
|
def test_ru_doc_lemmatization(ru_tokenizer):
|
|
words = ["мама", "мыла", "раму"]
|
|
tags = [
|
|
"NOUN__Animacy=Anim|Case=Nom|Gender=Fem|Number=Sing",
|
|
"VERB__Aspect=Imp|Gender=Fem|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Act",
|
|
"NOUN__Animacy=Anim|Case=Acc|Gender=Fem|Number=Sing",
|
|
]
|
|
doc = get_doc(ru_tokenizer.vocab, words=words, tags=tags)
|
|
lemmas = [token.lemma_ for token in doc]
|
|
assert lemmas == ["мама", "мыть", "рама"]
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,lemmas",
|
|
[
|
|
("гвоздики", ["гвоздик", "гвоздика"]),
|
|
("люди", ["человек"]),
|
|
("реки", ["река"]),
|
|
("кольцо", ["кольцо"]),
|
|
("пепперони", ["пепперони"]),
|
|
],
|
|
)
|
|
def test_ru_lemmatizer_noun_lemmas(ru_lemmatizer, text, lemmas):
|
|
assert sorted(ru_lemmatizer.noun(text)) == lemmas
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,pos,morphology,lemma",
|
|
[
|
|
("рой", "NOUN", None, "рой"),
|
|
("рой", "VERB", None, "рыть"),
|
|
("клей", "NOUN", None, "клей"),
|
|
("клей", "VERB", None, "клеить"),
|
|
("три", "NUM", None, "три"),
|
|
("кос", "NOUN", {"Number": "Sing"}, "кос"),
|
|
("кос", "NOUN", {"Number": "Plur"}, "коса"),
|
|
("кос", "ADJ", None, "косой"),
|
|
("потом", "NOUN", None, "пот"),
|
|
("потом", "ADV", None, "потом"),
|
|
],
|
|
)
|
|
def test_ru_lemmatizer_works_with_different_pos_homonyms(
|
|
ru_lemmatizer, text, pos, morphology, lemma
|
|
):
|
|
assert ru_lemmatizer(text, pos, morphology) == [lemma]
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,morphology,lemma",
|
|
[
|
|
("гвоздики", {"Gender": "Fem"}, "гвоздика"),
|
|
("гвоздики", {"Gender": "Masc"}, "гвоздик"),
|
|
("вина", {"Gender": "Fem"}, "вина"),
|
|
("вина", {"Gender": "Neut"}, "вино"),
|
|
],
|
|
)
|
|
def test_ru_lemmatizer_works_with_noun_homonyms(ru_lemmatizer, text, morphology, lemma):
|
|
assert ru_lemmatizer.noun(text, morphology) == [lemma]
|
|
|
|
|
|
def test_ru_lemmatizer_punct(ru_lemmatizer):
|
|
assert ru_lemmatizer.punct("«") == ['"']
|
|
assert ru_lemmatizer.punct("»") == ['"']
|