spaCy/spacy/tests/parser/test_add_label.py
Ines Montani 43b960c01b
Refactor pipeline components, config and language data (#5759)
* 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>
2020-07-22 13:42:59 +02:00

109 lines
3.5 KiB
Python

import pytest
from thinc.api import Adam, fix_random_seed
from spacy import registry
from spacy.attrs import NORM
from spacy.vocab import Vocab
from spacy.gold import Example
from spacy.tokens import Doc
from spacy.pipeline import DependencyParser, EntityRecognizer
from spacy.pipeline.ner import DEFAULT_NER_MODEL
from spacy.pipeline.dep_parser import DEFAULT_PARSER_MODEL
@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)
return parser
def test_init_parser(parser):
pass
def _train_parser(parser):
fix_random_seed(1)
parser.add_label("left")
parser.begin_training([], **parser.cfg)
sgd = Adam(0.001)
for i in range(5):
losses = {}
doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
gold = {"heads": [1, 1, 3, 3], "deps": ["left", "ROOT", "left", "ROOT"]}
example = Example.from_dict(doc, gold)
parser.update([example], sgd=sgd, losses=losses)
return parser
def test_add_label(parser):
parser = _train_parser(parser)
parser.add_label("right")
sgd = Adam(0.001)
for i in range(100):
losses = {}
doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
gold = {"heads": [1, 1, 3, 3], "deps": ["right", "ROOT", "left", "ROOT"]}
example = Example.from_dict(doc, gold)
parser.update([example], sgd=sgd, losses=losses)
doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
doc = parser(doc)
assert doc[0].dep_ == "right"
assert doc[2].dep_ == "left"
def test_add_label_deserializes_correctly():
config = {
"learn_tokens": False,
"min_action_freq": 30,
"update_with_oracle_cut_size": 100,
}
model = registry.make_from_config({"model": DEFAULT_NER_MODEL}, validate=True)["model"]
ner1 = EntityRecognizer(Vocab(), model, **config)
ner1.add_label("C")
ner1.add_label("B")
ner1.add_label("A")
ner1.begin_training([])
ner2 = EntityRecognizer(Vocab(), model, **config)
# the second model needs to be resized before we can call from_bytes
ner2.model.attrs["resize_output"](ner2.model, ner1.moves.n_moves)
ner2.from_bytes(ner1.to_bytes())
assert ner1.moves.n_moves == ner2.moves.n_moves
for i in range(ner1.moves.n_moves):
assert ner1.moves.get_class_name(i) == ner2.moves.get_class_name(i)
@pytest.mark.parametrize(
"pipe_cls,n_moves,model_config",
[(DependencyParser, 5, DEFAULT_PARSER_MODEL), (EntityRecognizer, 4, DEFAULT_NER_MODEL)],
)
def test_add_label_get_label(pipe_cls, n_moves, model_config):
"""Test that added labels are returned correctly. This test was added to
test for a bug in DependencyParser.labels that'd cause it to fail when
splitting the move names.
"""
labels = ["A", "B", "C"]
model = registry.make_from_config({"model": model_config}, validate=True)["model"]
config = {
"learn_tokens": False,
"min_action_freq": 30,
"update_with_oracle_cut_size": 100,
}
pipe = pipe_cls(Vocab(), model, **config)
for label in labels:
pipe.add_label(label)
assert len(pipe.move_names) == len(labels) * n_moves
pipe_labels = sorted(list(pipe.labels))
assert pipe_labels == labels