mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +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.
100 lines
3.5 KiB
Python
100 lines
3.5 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from pathlib import Path
|
|
from spacy import util
|
|
from spacy import displacy
|
|
from spacy.tokens import Span
|
|
from spacy._ml import PrecomputableAffine
|
|
|
|
from .util import get_doc
|
|
|
|
|
|
@pytest.mark.parametrize('text', ['hello/world', 'hello world'])
|
|
def test_util_ensure_path_succeeds(text):
|
|
path = util.ensure_path(text)
|
|
assert isinstance(path, Path)
|
|
|
|
|
|
@pytest.mark.parametrize('package', ['numpy'])
|
|
def test_util_is_package(package):
|
|
"""Test that an installed package via pip is recognised by util.is_package."""
|
|
assert util.is_package(package)
|
|
|
|
|
|
@pytest.mark.parametrize('package', ['thinc'])
|
|
def test_util_get_package_path(package):
|
|
"""Test that a Path object is returned for a package name."""
|
|
path = util.get_package_path(package)
|
|
assert isinstance(path, Path)
|
|
|
|
|
|
def test_displacy_parse_ents(en_vocab):
|
|
"""Test that named entities on a Doc are converted into displaCy's format."""
|
|
doc = get_doc(en_vocab, words=["But", "Google", "is", "starting", "from", "behind"])
|
|
doc.ents = [Span(doc, 1, 2, label=doc.vocab.strings['ORG'])]
|
|
ents = displacy.parse_ents(doc)
|
|
assert isinstance(ents, dict)
|
|
assert ents['text'] == 'But Google is starting from behind '
|
|
assert ents['ents'] == [{'start': 4, 'end': 10, 'label': 'ORG'}]
|
|
|
|
|
|
def test_displacy_parse_deps(en_vocab):
|
|
"""Test that deps and tags on a Doc are converted into displaCy's format."""
|
|
words = ["This", "is", "a", "sentence"]
|
|
heads = [1, 0, 1, -2]
|
|
pos = ['DET', 'VERB', 'DET', 'NOUN']
|
|
tags = ['DT', 'VBZ', 'DT', 'NN']
|
|
deps = ['nsubj', 'ROOT', 'det', 'attr']
|
|
doc = get_doc(en_vocab, words=words, heads=heads, pos=pos, tags=tags,
|
|
deps=deps)
|
|
deps = displacy.parse_deps(doc)
|
|
assert isinstance(deps, dict)
|
|
assert deps['words'] == [{'text': 'This', 'tag': 'DET'},
|
|
{'text': 'is', 'tag': 'VERB'},
|
|
{'text': 'a', 'tag': 'DET'},
|
|
{'text': 'sentence', 'tag': 'NOUN'}]
|
|
assert deps['arcs'] == [{'start': 0, 'end': 1, 'label': 'nsubj', 'dir': 'left'},
|
|
{'start': 2, 'end': 3, 'label': 'det', 'dir': 'left'},
|
|
{'start': 1, 'end': 3, 'label': 'attr', 'dir': 'right'}]
|
|
|
|
|
|
def test_displacy_spans(en_vocab):
|
|
"""Test that displaCy can render Spans."""
|
|
doc = get_doc(en_vocab, words=["But", "Google", "is", "starting", "from", "behind"])
|
|
doc.ents = [Span(doc, 1, 2, label=doc.vocab.strings['ORG'])]
|
|
html = displacy.render(doc[1:4], style='ent')
|
|
assert html.startswith('<div')
|
|
|
|
|
|
def test_displacy_raises_for_wrong_type(en_vocab):
|
|
with pytest.raises(ValueError):
|
|
html = displacy.render('hello world')
|
|
|
|
|
|
def test_PrecomputableAffine(nO=4, nI=5, nF=3, nP=2):
|
|
model = PrecomputableAffine(nO=nO, nI=nI, nF=nF, nP=nP)
|
|
assert model.W.shape == (nF, nO, nP, nI)
|
|
tensor = model.ops.allocate((10, nI))
|
|
Y, get_dX = model.begin_update(tensor)
|
|
assert Y.shape == (tensor.shape[0]+1, nF, nO, nP)
|
|
assert model.d_pad.shape == (1, nF, nO, nP)
|
|
dY = model.ops.allocate((15, nO, nP))
|
|
ids = model.ops.allocate((15, nF))
|
|
ids[1,2] = -1
|
|
dY[1] = 1
|
|
assert model.d_pad[0, 2, 0, 0] == 0.
|
|
model._backprop_padding(dY, ids)
|
|
assert model.d_pad[0, 2, 0, 0] == 1.
|
|
model.d_pad.fill(0.)
|
|
ids.fill(0.)
|
|
dY.fill(0.)
|
|
ids[1,2] = -1
|
|
ids[1,1] = -1
|
|
ids[1,0] = -1
|
|
dY[1] = 1
|
|
assert model.d_pad[0, 2, 0, 0] == 0.
|
|
model._backprop_padding(dY, ids)
|
|
assert model.d_pad[0, 2, 0, 0] == 3.
|