mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 18:06:29 +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>
82 lines
2.3 KiB
Python
82 lines
2.3 KiB
Python
import pytest
|
|
from thinc.api import Adam
|
|
from spacy.attrs import NORM
|
|
from spacy.vocab import Vocab
|
|
from spacy import registry
|
|
from spacy.gold import Example
|
|
from spacy.pipeline.dep_parser import DEFAULT_PARSER_MODEL
|
|
from spacy.tokens import Doc
|
|
from spacy.pipeline import DependencyParser
|
|
|
|
|
|
@pytest.fixture
|
|
def vocab():
|
|
return Vocab(lex_attr_getters={NORM: lambda s: s})
|
|
|
|
|
|
@pytest.fixture
|
|
def parser(vocab):
|
|
config = {
|
|
"learn_tokens": False,
|
|
"min_action_freq": 30,
|
|
"update_with_oracle_cut_size": 100,
|
|
}
|
|
model = registry.make_from_config({"model": DEFAULT_PARSER_MODEL}, validate=True)["model"]
|
|
parser = DependencyParser(vocab, model, **config)
|
|
parser.cfg["token_vector_width"] = 4
|
|
parser.cfg["hidden_width"] = 32
|
|
# parser.add_label('right')
|
|
parser.add_label("left")
|
|
parser.begin_training([], **parser.cfg)
|
|
sgd = Adam(0.001)
|
|
|
|
for i in range(10):
|
|
losses = {}
|
|
doc = Doc(vocab, words=["a", "b", "c", "d"])
|
|
example = Example.from_dict(
|
|
doc, {"heads": [1, 1, 3, 3], "deps": ["left", "ROOT", "left", "ROOT"]}
|
|
)
|
|
parser.update([example], sgd=sgd, losses=losses)
|
|
return parser
|
|
|
|
|
|
def test_no_sentences(parser):
|
|
doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
|
|
doc = parser(doc)
|
|
assert len(list(doc.sents)) >= 1
|
|
|
|
|
|
def test_sents_1(parser):
|
|
doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
|
|
doc[2].sent_start = True
|
|
doc = parser(doc)
|
|
assert len(list(doc.sents)) >= 2
|
|
doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
|
|
doc[1].sent_start = False
|
|
doc[2].sent_start = True
|
|
doc[3].sent_start = False
|
|
doc = parser(doc)
|
|
assert len(list(doc.sents)) == 2
|
|
|
|
|
|
def test_sents_1_2(parser):
|
|
doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
|
|
doc[1].sent_start = True
|
|
doc[2].sent_start = True
|
|
doc = parser(doc)
|
|
assert len(list(doc.sents)) >= 3
|
|
|
|
|
|
def test_sents_1_3(parser):
|
|
doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
|
|
doc[1].sent_start = True
|
|
doc[3].sent_start = True
|
|
doc = parser(doc)
|
|
assert len(list(doc.sents)) >= 3
|
|
doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
|
|
doc[1].sent_start = True
|
|
doc[2].sent_start = False
|
|
doc[3].sent_start = True
|
|
doc = parser(doc)
|
|
assert len(list(doc.sents)) == 3
|