mirror of
https://github.com/explosion/spaCy.git
synced 2025-02-03 21:24:11 +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.
59 lines
1.9 KiB
Python
59 lines
1.9 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
import random
|
|
import numpy.random
|
|
from spacy.language import Language
|
|
from spacy.pipeline import TextCategorizer
|
|
from spacy.tokens import Doc
|
|
from spacy.gold import GoldParse
|
|
|
|
|
|
def test_simple_train():
|
|
nlp = Language()
|
|
nlp.add_pipe(nlp.create_pipe('textcat'))
|
|
nlp.get_pipe('textcat').add_label('answer')
|
|
nlp.begin_training()
|
|
for i in range(5):
|
|
for text, answer in [('aaaa', 1.), ('bbbb', 0), ('aa', 1.),
|
|
('bbbbbbbbb', 0.), ('aaaaaa', 1)]:
|
|
nlp.update([text], [{'cats': {'answer': answer}}])
|
|
doc = nlp('aaa')
|
|
assert 'answer' in doc.cats
|
|
assert doc.cats['answer'] >= 0.5
|
|
|
|
|
|
@pytest.mark.skip(reason="Test is flakey when run with others")
|
|
def test_textcat_learns_multilabel():
|
|
random.seed(5)
|
|
numpy.random.seed(5)
|
|
docs = []
|
|
nlp = Language()
|
|
letters = ['a', 'b', 'c']
|
|
for w1 in letters:
|
|
for w2 in letters:
|
|
cats = {letter: float(w2==letter) for letter in letters}
|
|
docs.append((Doc(nlp.vocab, words=['d']*3 + [w1, w2] + ['d']*3), cats))
|
|
random.shuffle(docs)
|
|
model = TextCategorizer(nlp.vocab, width=8)
|
|
for letter in letters:
|
|
model.add_label(letter)
|
|
optimizer = model.begin_training()
|
|
for i in range(30):
|
|
losses = {}
|
|
Ys = [GoldParse(doc, cats=cats) for doc, cats in docs]
|
|
Xs = [doc for doc, cats in docs]
|
|
model.update(Xs, Ys, sgd=optimizer, losses=losses)
|
|
random.shuffle(docs)
|
|
for w1 in letters:
|
|
for w2 in letters:
|
|
doc = Doc(nlp.vocab, words=['d']*3 + [w1, w2] + ['d']*3)
|
|
truth = {letter: w2==letter for letter in letters}
|
|
model(doc)
|
|
for cat, score in doc.cats.items():
|
|
if not truth[cat]:
|
|
assert score < 0.5
|
|
else:
|
|
assert score > 0.5
|