mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-01 00:17:44 +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.
82 lines
1.8 KiB
Python
82 lines
1.8 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from spacy._ml import 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
|
|
|
|
|
|
@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():
|
|
return Tok2Vec(8, 100)
|
|
|
|
|
|
@pytest.fixture
|
|
def parser(vocab, arc_eager):
|
|
return Parser(vocab, moves=arc_eager, model=None)
|
|
|
|
@pytest.fixture
|
|
def model(arc_eager, tok2vec):
|
|
return Parser.Model(arc_eager.n_moves, token_vector_width=tok2vec.nO)[0]
|
|
|
|
|
|
@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 parser.model is None
|
|
|
|
|
|
def test_build_model(parser):
|
|
parser.model = Parser.Model(parser.moves.n_moves, hist_size=0)[0]
|
|
assert parser.model is not None
|
|
|
|
|
|
def test_predict_doc(parser, tok2vec, model, doc):
|
|
doc.tensor = tok2vec([doc])[0]
|
|
parser.model = model
|
|
parser(doc)
|
|
|
|
|
|
def test_update_doc(parser, model, doc, gold):
|
|
parser.model = model
|
|
def optimize(weights, gradient, key=None):
|
|
weights -= 0.001 * 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)
|