spaCy/spacy/tests/parser/test_neural_parser.py
Sofie Van Landeghem c0f4a1e43b
train is from-config by default (#5575)
* verbose and tag_map options

* adding init_tok2vec option and only changing the tok2vec that is specified

* adding omit_extra_lookups and verifying textcat config

* wip

* pretrain bugfix

* add replace and resume options

* train_textcat fix

* raw text functionality

* improve UX when KeyError or when input data can't be parsed

* avoid unnecessary access to goldparse in TextCat pipe

* save performance information in nlp.meta

* add noise_level to config

* move nn_parser's defaults to config file

* multitask in config - doesn't work yet

* scorer offering both F and AUC options, need to be specified in config

* add textcat verification code from old train script

* small fixes to config files

* clean up

* set default config for ner/parser to allow create_pipe to work as before

* two more test fixes

* small fixes

* cleanup

* fix NER pickling + additional unit test

* create_pipe as before
2020-06-12 02:02:07 +02:00

92 lines
2.1 KiB
Python

import pytest
from spacy.pipeline.defaults import default_parser, default_tok2vec
from spacy.vocab import Vocab
from spacy.syntax.arc_eager import ArcEager
from spacy.syntax.nn_parser import Parser
from spacy.tokens.doc import Doc
from spacy.gold import GoldParse
from thinc.api import Model
@pytest.fixture
def vocab():
return Vocab()
@pytest.fixture
def arc_eager(vocab):
actions = ArcEager.get_actions(left_labels=["L"], right_labels=["R"])
return ArcEager(vocab.strings, actions)
@pytest.fixture
def tok2vec():
tok2vec = default_tok2vec()
tok2vec.initialize()
return tok2vec
@pytest.fixture
def parser(vocab, arc_eager):
config = {"learn_tokens": False, "min_action_freq": 30, "beam_width": 1, "beam_update_prob": 1.0}
return Parser(vocab, model=default_parser(), moves=arc_eager, **config)
@pytest.fixture
def model(arc_eager, tok2vec, vocab):
model = default_parser()
model.attrs["resize_output"](model, arc_eager.n_moves)
model.initialize()
return model
@pytest.fixture
def doc(vocab):
return Doc(vocab, words=["a", "b", "c"])
@pytest.fixture
def gold(doc):
return GoldParse(doc, heads=[1, 1, 1], deps=["L", "ROOT", "R"])
def test_can_init_nn_parser(parser):
assert isinstance(parser.model, Model)
def test_build_model(parser, vocab):
parser.model = Parser(vocab, model=default_parser(), moves=parser.moves).model
assert parser.model is not None
def test_predict_doc(parser, tok2vec, model, doc):
doc.tensor = tok2vec.predict([doc])[0]
parser.model = model
parser(doc)
def test_update_doc(parser, model, doc, gold):
parser.model = model
def optimize(key, weights, gradient):
weights -= 0.001 * gradient
return weights, gradient
parser.update((doc, gold), sgd=optimize)
@pytest.mark.xfail
def test_predict_doc_beam(parser, model, doc):
parser.model = model
parser(doc, beam_width=32, beam_density=0.001)
@pytest.mark.xfail
def test_update_doc_beam(parser, model, doc, gold):
parser.model = model
def optimize(weights, gradient, key=None):
weights -= 0.001 * gradient
parser.update_beam((doc, gold), sgd=optimize)