mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 18:36:36 +03:00
75f3234404
## Description Related issues: #2379 (should be fixed by separating model tests) * **total execution time down from > 300 seconds to under 60 seconds** 🎉 * removed all model-specific tests that could only really be run manually anyway – those will now live in a separate test suite in the [`spacy-models`](https://github.com/explosion/spacy-models) repository and are already integrated into our new model training infrastructure * changed all relative imports to absolute imports to prepare for moving the test suite from `/spacy/tests` to `/tests` (it'll now always test against the installed version) * merged old regression tests into collections, e.g. `test_issue1001-1500.py` (about 90% of the regression tests are very short anyways) * tidied up and rewrote existing tests wherever possible ### Todo - [ ] move tests to `/tests` and adjust CI commands accordingly - [x] move model test suite from internal repo to `spacy-models` - [x] ~~investigate why `pipeline/test_textcat.py` is flakey~~ - [x] review old regression tests (leftover files) and see if they can be merged, simplified or deleted - [ ] update documentation on how to run tests ### Types of change enhancement, tests ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
77 lines
2.1 KiB
Python
77 lines
2.1 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from thinc.neural.optimizers import Adam
|
|
from thinc.neural.ops import NumpyOps
|
|
from spacy.attrs import NORM
|
|
from spacy.gold import GoldParse
|
|
from spacy.vocab import Vocab
|
|
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):
|
|
parser = DependencyParser(vocab)
|
|
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(NumpyOps(), 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
|