mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +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>
60 lines
2.4 KiB
Python
60 lines
2.4 KiB
Python
import pytest
|
|
from spacy.tokens import Doc
|
|
from spacy.language import Language
|
|
from spacy.lookups import Lookups
|
|
from spacy.lemmatizer import Lemmatizer
|
|
|
|
|
|
def test_lemmatizer_reflects_lookups_changes():
|
|
"""Test for an issue that'd cause lookups available in a model loaded from
|
|
disk to not be reflected in the lemmatizer."""
|
|
nlp = Language()
|
|
assert Doc(nlp.vocab, words=["foo"])[0].lemma_ == "foo"
|
|
table = nlp.vocab.lookups.add_table("lemma_lookup")
|
|
table["foo"] = "bar"
|
|
assert Doc(nlp.vocab, words=["foo"])[0].lemma_ == "bar"
|
|
table = nlp.vocab.lookups.get_table("lemma_lookup")
|
|
table["hello"] = "world"
|
|
# The update to the table should be reflected in the lemmatizer
|
|
assert Doc(nlp.vocab, words=["hello"])[0].lemma_ == "world"
|
|
new_nlp = Language()
|
|
table = new_nlp.vocab.lookups.add_table("lemma_lookup")
|
|
table["hello"] = "hi"
|
|
assert Doc(new_nlp.vocab, words=["hello"])[0].lemma_ == "hi"
|
|
nlp_bytes = nlp.to_bytes()
|
|
new_nlp.from_bytes(nlp_bytes)
|
|
# Make sure we have the previously saved lookup table
|
|
assert "lemma_lookup" in new_nlp.vocab.lookups
|
|
assert len(new_nlp.vocab.lookups.get_table("lemma_lookup")) == 2
|
|
assert new_nlp.vocab.lookups.get_table("lemma_lookup")["hello"] == "world"
|
|
assert Doc(new_nlp.vocab, words=["foo"])[0].lemma_ == "bar"
|
|
assert Doc(new_nlp.vocab, words=["hello"])[0].lemma_ == "world"
|
|
|
|
|
|
def test_tagger_warns_no_lookups():
|
|
nlp = Language()
|
|
nlp.vocab.lookups = Lookups()
|
|
assert not len(nlp.vocab.lookups)
|
|
tagger = nlp.add_pipe("tagger")
|
|
with pytest.warns(UserWarning):
|
|
tagger.begin_training()
|
|
with pytest.warns(UserWarning):
|
|
nlp.begin_training()
|
|
nlp.vocab.lookups.add_table("lemma_lookup")
|
|
nlp.vocab.lookups.add_table("lexeme_norm")
|
|
nlp.vocab.lookups.get_table("lexeme_norm")["a"] = "A"
|
|
with pytest.warns(None) as record:
|
|
nlp.begin_training()
|
|
assert not record.list
|
|
|
|
|
|
def test_lemmatizer_without_is_base_form_implementation():
|
|
# Norwegian example from #5658
|
|
lookups = Lookups()
|
|
lookups.add_table("lemma_rules", {"noun": []})
|
|
lookups.add_table("lemma_index", {"noun": {}})
|
|
lookups.add_table("lemma_exc", {"noun": {"formuesskatten": ["formuesskatt"]}})
|
|
|
|
lemmatizer = Lemmatizer(lookups, is_base_form=None)
|
|
assert lemmatizer("Formuesskatten", "noun", {'Definite': 'def', 'Gender': 'masc', 'Number': 'sing'}) == ["formuesskatt"]
|