spaCy/spacy/tests/parser/test_preset_sbd.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

75 lines
2.1 KiB
Python

import pytest
from thinc.api import Adam
from spacy.attrs import NORM
from spacy.gold import GoldParse
from spacy.vocab import Vocab
from spacy.pipeline.defaults import default_parser
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, "beam_width": 1, "beam_update_prob": 1.0}
parser = DependencyParser(vocab, default_parser(), **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"])
gold = GoldParse(doc, heads=[1, 1, 3, 3], deps=["left", "ROOT", "left", "ROOT"])
parser.update((doc, gold), 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