mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-13 13:17:06 +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.
278 lines
8.2 KiB
Python
278 lines
8.2 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
import numpy
|
|
from numpy.testing import assert_allclose
|
|
from spacy._ml import cosine
|
|
from spacy.vocab import Vocab
|
|
from spacy.vectors import Vectors
|
|
from spacy.tokenizer import Tokenizer
|
|
from spacy.strings import hash_string
|
|
from spacy.tokens import Doc
|
|
|
|
from ..util import add_vecs_to_vocab
|
|
|
|
|
|
@pytest.fixture
|
|
def strings():
|
|
return ["apple", "orange"]
|
|
|
|
|
|
@pytest.fixture
|
|
def vectors():
|
|
return [
|
|
("apple", [1, 2, 3]),
|
|
("orange", [-1, -2, -3]),
|
|
('and', [-1, -1, -1]),
|
|
('juice', [5, 5, 10]),
|
|
('pie', [7, 6.3, 8.9])]
|
|
|
|
|
|
@pytest.fixture
|
|
def ngrams_vectors():
|
|
return [
|
|
("apple", [1, 2, 3]),
|
|
("app", [-0.1, -0.2, -0.3]),
|
|
('ppl', [-0.2, -0.3, -0.4]),
|
|
('pl', [0.7, 0.8, 0.9])
|
|
]
|
|
|
|
|
|
@pytest.fixture()
|
|
def ngrams_vocab(en_vocab, ngrams_vectors):
|
|
add_vecs_to_vocab(en_vocab, ngrams_vectors)
|
|
return en_vocab
|
|
|
|
|
|
@pytest.fixture
|
|
def data():
|
|
return numpy.asarray([[0.0, 1.0, 2.0], [3.0, -2.0, 4.0]], dtype='f')
|
|
|
|
|
|
@pytest.fixture
|
|
def resize_data():
|
|
return numpy.asarray([[0.0, 1.0], [2.0, 3.0]], dtype='f')
|
|
|
|
|
|
@pytest.fixture()
|
|
def vocab(en_vocab, vectors):
|
|
add_vecs_to_vocab(en_vocab, vectors)
|
|
return en_vocab
|
|
|
|
|
|
@pytest.fixture()
|
|
def tokenizer_v(vocab):
|
|
return Tokenizer(vocab, {}, None, None, None)
|
|
|
|
|
|
def test_init_vectors_with_resize_shape(strings,resize_data):
|
|
v = Vectors(shape=(len(strings), 3))
|
|
v.resize(shape=resize_data.shape)
|
|
assert v.shape == resize_data.shape
|
|
assert v.shape != (len(strings), 3)
|
|
|
|
|
|
def test_init_vectors_with_resize_data(data,resize_data):
|
|
v = Vectors(data=data)
|
|
v.resize(shape=resize_data.shape)
|
|
assert v.shape == resize_data.shape
|
|
assert v.shape != data.shape
|
|
|
|
|
|
def test_get_vector_resize(strings, data,resize_data):
|
|
v = Vectors(data=data)
|
|
v.resize(shape=resize_data.shape)
|
|
strings = [hash_string(s) for s in strings]
|
|
for i, string in enumerate(strings):
|
|
v.add(string, row=i)
|
|
|
|
assert list(v[strings[0]]) == list(resize_data[0])
|
|
assert list(v[strings[0]]) != list(resize_data[1])
|
|
assert list(v[strings[1]]) != list(resize_data[0])
|
|
assert list(v[strings[1]]) == list(resize_data[1])
|
|
|
|
|
|
def test_init_vectors_with_data(strings, data):
|
|
v = Vectors(data=data)
|
|
assert v.shape == data.shape
|
|
|
|
|
|
def test_init_vectors_with_shape(strings):
|
|
v = Vectors(shape=(len(strings), 3))
|
|
assert v.shape == (len(strings), 3)
|
|
|
|
|
|
def test_get_vector(strings, data):
|
|
v = Vectors(data=data)
|
|
strings = [hash_string(s) for s in strings]
|
|
for i, string in enumerate(strings):
|
|
v.add(string, row=i)
|
|
assert list(v[strings[0]]) == list(data[0])
|
|
assert list(v[strings[0]]) != list(data[1])
|
|
assert list(v[strings[1]]) != list(data[0])
|
|
|
|
|
|
def test_set_vector(strings, data):
|
|
orig = data.copy()
|
|
v = Vectors(data=data)
|
|
strings = [hash_string(s) for s in strings]
|
|
for i, string in enumerate(strings):
|
|
v.add(string, row=i)
|
|
assert list(v[strings[0]]) == list(orig[0])
|
|
assert list(v[strings[0]]) != list(orig[1])
|
|
v[strings[0]] = data[1]
|
|
assert list(v[strings[0]]) == list(orig[1])
|
|
assert list(v[strings[0]]) != list(orig[0])
|
|
|
|
|
|
@pytest.mark.parametrize('text', ["apple and orange"])
|
|
def test_vectors_token_vector(tokenizer_v, vectors, text):
|
|
doc = tokenizer_v(text)
|
|
assert vectors[0] == (doc[0].text, list(doc[0].vector))
|
|
assert vectors[1] == (doc[2].text, list(doc[2].vector))
|
|
|
|
|
|
@pytest.mark.parametrize('text', ["apple"])
|
|
def test_vectors__ngrams_word(ngrams_vocab, text):
|
|
assert list(ngrams_vocab.get_vector(text)) == list(ngrams_vectors()[0][1])
|
|
|
|
@pytest.mark.parametrize('text', ["applpie"])
|
|
def test_vectors__ngrams_subword(ngrams_vocab, text):
|
|
truth = list(ngrams_vocab.get_vector(text,1,6))
|
|
test = list([(ngrams_vectors()[1][1][i] + ngrams_vectors()[2][1][i] + ngrams_vectors()[3][1][i])/3 for i in range(len(ngrams_vectors()[1][1]))])
|
|
eps = [abs(truth[i] - test[i]) for i in range(len(truth))]
|
|
for i in eps:
|
|
assert i<1e-6
|
|
|
|
@pytest.mark.parametrize('text', ["apple", "orange"])
|
|
def test_vectors_lexeme_vector(vocab, text):
|
|
lex = vocab[text]
|
|
assert list(lex.vector)
|
|
assert lex.vector_norm
|
|
|
|
|
|
@pytest.mark.parametrize('text', [["apple", "and", "orange"]])
|
|
def test_vectors_doc_vector(vocab, text):
|
|
doc = Doc(vocab, words=text)
|
|
assert list(doc.vector)
|
|
assert doc.vector_norm
|
|
|
|
|
|
@pytest.mark.parametrize('text', [["apple", "and", "orange"]])
|
|
def test_vectors_span_vector(vocab, text):
|
|
span = Doc(vocab, words=text)[0:2]
|
|
assert list(span.vector)
|
|
assert span.vector_norm
|
|
|
|
|
|
@pytest.mark.parametrize('text', ["apple orange"])
|
|
def test_vectors_token_token_similarity(tokenizer_v, text):
|
|
doc = tokenizer_v(text)
|
|
assert doc[0].similarity(doc[1]) == doc[1].similarity(doc[0])
|
|
assert -1. < doc[0].similarity(doc[1]) < 1.0
|
|
|
|
|
|
@pytest.mark.parametrize('text1,text2', [("apple", "orange")])
|
|
def test_vectors_token_lexeme_similarity(tokenizer_v, vocab, text1, text2):
|
|
token = tokenizer_v(text1)
|
|
lex = vocab[text2]
|
|
assert token.similarity(lex) == lex.similarity(token)
|
|
assert -1. < token.similarity(lex) < 1.0
|
|
|
|
|
|
@pytest.mark.parametrize('text', [["apple", "orange", "juice"]])
|
|
def test_vectors_token_span_similarity(vocab, text):
|
|
doc = Doc(vocab, words=text)
|
|
assert doc[0].similarity(doc[1:3]) == doc[1:3].similarity(doc[0])
|
|
assert -1. < doc[0].similarity(doc[1:3]) < 1.0
|
|
|
|
|
|
@pytest.mark.parametrize('text', [["apple", "orange", "juice"]])
|
|
def test_vectors_token_doc_similarity(vocab, text):
|
|
doc = Doc(vocab, words=text)
|
|
assert doc[0].similarity(doc) == doc.similarity(doc[0])
|
|
assert -1. < doc[0].similarity(doc) < 1.0
|
|
|
|
|
|
@pytest.mark.parametrize('text', [["apple", "orange", "juice"]])
|
|
def test_vectors_lexeme_span_similarity(vocab, text):
|
|
doc = Doc(vocab, words=text)
|
|
lex = vocab[text[0]]
|
|
assert lex.similarity(doc[1:3]) == doc[1:3].similarity(lex)
|
|
assert -1. < doc.similarity(doc[1:3]) < 1.0
|
|
|
|
|
|
@pytest.mark.parametrize('text1,text2', [("apple", "orange")])
|
|
def test_vectors_lexeme_lexeme_similarity(vocab, text1, text2):
|
|
lex1 = vocab[text1]
|
|
lex2 = vocab[text2]
|
|
assert lex1.similarity(lex2) == lex2.similarity(lex1)
|
|
assert -1. < lex1.similarity(lex2) < 1.0
|
|
|
|
|
|
@pytest.mark.parametrize('text', [["apple", "orange", "juice"]])
|
|
def test_vectors_lexeme_doc_similarity(vocab, text):
|
|
doc = Doc(vocab, words=text)
|
|
lex = vocab[text[0]]
|
|
assert lex.similarity(doc) == doc.similarity(lex)
|
|
assert -1. < lex.similarity(doc) < 1.0
|
|
|
|
|
|
@pytest.mark.parametrize('text', [["apple", "orange", "juice"]])
|
|
def test_vectors_span_span_similarity(vocab, text):
|
|
doc = Doc(vocab, words=text)
|
|
with pytest.warns(None):
|
|
assert doc[0:2].similarity(doc[1:3]) == doc[1:3].similarity(doc[0:2])
|
|
assert -1. < doc[0:2].similarity(doc[1:3]) < 1.0
|
|
|
|
|
|
@pytest.mark.parametrize('text', [["apple", "orange", "juice"]])
|
|
def test_vectors_span_doc_similarity(vocab, text):
|
|
doc = Doc(vocab, words=text)
|
|
with pytest.warns(None):
|
|
assert doc[0:2].similarity(doc) == doc.similarity(doc[0:2])
|
|
assert -1. < doc[0:2].similarity(doc) < 1.0
|
|
|
|
|
|
@pytest.mark.parametrize('text1,text2', [
|
|
(["apple", "and", "apple", "pie"], ["orange", "juice"])])
|
|
def test_vectors_doc_doc_similarity(vocab, text1, text2):
|
|
doc1 = Doc(vocab, words=text1)
|
|
doc2 = Doc(vocab, words=text2)
|
|
assert doc1.similarity(doc2) == doc2.similarity(doc1)
|
|
assert -1. < doc1.similarity(doc2) < 1.0
|
|
|
|
|
|
def test_vocab_add_vector():
|
|
vocab = Vocab()
|
|
data = numpy.ndarray((5,3), dtype='f')
|
|
data[0] = 1.
|
|
data[1] = 2.
|
|
vocab.set_vector('cat', data[0])
|
|
vocab.set_vector('dog', data[1])
|
|
cat = vocab['cat']
|
|
assert list(cat.vector) == [1., 1., 1.]
|
|
dog = vocab['dog']
|
|
assert list(dog.vector) == [2., 2., 2.]
|
|
|
|
|
|
def test_vocab_prune_vectors():
|
|
vocab = Vocab()
|
|
_ = vocab['cat']
|
|
_ = vocab['dog']
|
|
_ = vocab['kitten']
|
|
data = numpy.ndarray((5,3), dtype='f')
|
|
data[0] = 1.
|
|
data[1] = 2.
|
|
data[2] = 1.1
|
|
vocab.set_vector('cat', data[0])
|
|
vocab.set_vector('dog', data[1])
|
|
vocab.set_vector('kitten', data[2])
|
|
|
|
remap = vocab.prune_vectors(2)
|
|
assert list(remap.keys()) == ['kitten']
|
|
neighbour, similarity = list(remap.values())[0]
|
|
assert neighbour == 'cat', remap
|
|
assert_allclose(similarity, cosine(data[0], data[2]), atol=1e-6)
|