mirror of
https://github.com/explosion/spaCy.git
synced 2025-01-26 17:24:41 +03:00
Modernise vector tests, use add_vecs_to_vocab and don't depend on models
This commit is contained in:
Ines Montani
parent
96f0caa28a
commit
138deb80a1
|
|
@ -1,7 +1,7 @@
|
||||||
# coding: utf-8
|
# coding: utf-8
|
||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
from ..util import get_doc, get_cosine
|
from ..util import get_doc, get_cosine, add_vecs_to_vocab
|
||||||
|
|
||||||
import numpy
|
import numpy
|
||||||
import pytest
|
import pytest
|
||||||
|
|
@ -9,22 +9,16 @@ import pytest
|
||||||
|
|
||||||
@pytest.fixture
|
@pytest.fixture
|
||||||
def vectors():
|
def vectors():
|
||||||
return ("apple", [1, 2, 3], "orange", [-1, -2, -3])
|
return [("apple", [1, 2, 3]), ("orange", [-1, -2, -3])]
|
||||||
|
|
||||||
|
|
||||||
@pytest.fixture()
|
@pytest.fixture()
|
||||||
def vocab(en_vocab, vectors):
|
def vocab(en_vocab, vectors):
|
||||||
word1, vec1, word2, vec2 = vectors
|
return add_vecs_to_vocab(en_vocab, vectors)
|
||||||
en_vocab.resize_vectors(3)
|
|
||||||
lex1 = en_vocab[word1]
|
|
||||||
lex2 = en_vocab[word2]
|
|
||||||
lex1.vector = vec1
|
|
||||||
lex2.vector = vec2
|
|
||||||
return en_vocab
|
|
||||||
|
|
||||||
|
|
||||||
def test_vectors_similarity_LL(vocab, vectors):
|
def test_vectors_similarity_LL(vocab, vectors):
|
||||||
word1, vec1, word2, vec2 = vectors
|
[(word1, vec1), (word2, vec2)] = vectors
|
||||||
lex1 = vocab[word1]
|
lex1 = vocab[word1]
|
||||||
lex2 = vocab[word2]
|
lex2 = vocab[word2]
|
||||||
assert lex1.has_vector
|
assert lex1.has_vector
|
||||||
|
|
@ -37,7 +31,7 @@ def test_vectors_similarity_LL(vocab, vectors):
|
||||||
|
|
||||||
|
|
||||||
def test_vectors_similarity_TT(vocab, vectors):
|
def test_vectors_similarity_TT(vocab, vectors):
|
||||||
word1, vec1, word2, vec2 = vectors
|
[(word1, vec1), (word2, vec2)] = vectors
|
||||||
doc = get_doc(vocab, words=[word1, word2])
|
doc = get_doc(vocab, words=[word1, word2])
|
||||||
assert doc[0].has_vector
|
assert doc[0].has_vector
|
||||||
assert doc[1].has_vector
|
assert doc[1].has_vector
|
||||||
|
|
@ -49,18 +43,18 @@ def test_vectors_similarity_TT(vocab, vectors):
|
||||||
|
|
||||||
|
|
||||||
def test_vectors_similarity_TD(vocab, vectors):
|
def test_vectors_similarity_TD(vocab, vectors):
|
||||||
word1, vec1, word2, vec2 = vectors
|
[(word1, vec1), (word2, vec2)] = vectors
|
||||||
doc = get_doc(vocab, words=[word1, word2])
|
doc = get_doc(vocab, words=[word1, word2])
|
||||||
assert doc.similarity(doc[0]) == doc[0].similarity(doc)
|
assert doc.similarity(doc[0]) == doc[0].similarity(doc)
|
||||||
|
|
||||||
|
|
||||||
def test_vectors_similarity_DS(vocab, vectors):
|
def test_vectors_similarity_DS(vocab, vectors):
|
||||||
word1, vec1, word2, vec2 = vectors
|
[(word1, vec1), (word2, vec2)] = vectors
|
||||||
doc = get_doc(vocab, words=[word1, word2])
|
doc = get_doc(vocab, words=[word1, word2])
|
||||||
assert doc.similarity(doc[:2]) == doc[:2].similarity(doc)
|
assert doc.similarity(doc[:2]) == doc[:2].similarity(doc)
|
||||||
|
|
||||||
|
|
||||||
def test_vectors_similarity_TS(vocab, vectors):
|
def test_vectors_similarity_TS(vocab, vectors):
|
||||||
word1, vec1, word2, vec2 = vectors
|
[(word1, vec1), (word2, vec2)] = vectors
|
||||||
doc = get_doc(vocab, words=[word1, word2])
|
doc = get_doc(vocab, words=[word1, word2])
|
||||||
assert doc[:2].similarity(doc[0]) == doc[0].similarity(doc[:2])
|
assert doc[:2].similarity(doc[0]) == doc[0].similarity(doc[:2])
|
||||||
|
|
|
||||||
|
|
@ -1,109 +1,126 @@
|
||||||
|
# coding: utf-8
|
||||||
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
|
from ...tokenizer import Tokenizer
|
||||||
|
from ..util import get_doc, add_vecs_to_vocab
|
||||||
|
|
||||||
import pytest
|
import pytest
|
||||||
|
|
||||||
@pytest.mark.models
|
|
||||||
def test_token_vector(EN):
|
|
||||||
token = EN(u'Apples and oranges')[0]
|
|
||||||
token.vector
|
|
||||||
token.vector_norm
|
|
||||||
|
|
||||||
@pytest.mark.models
|
@pytest.fixture
|
||||||
def test_lexeme_vector(EN):
|
def vectors():
|
||||||
lexeme = EN.vocab[u'apples']
|
return [("apple", [0.0, 1.0, 2.0]), ("orange", [3.0, -2.0, 4.0])]
|
||||||
lexeme.vector
|
|
||||||
lexeme.vector_norm
|
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.models
|
@pytest.fixture()
|
||||||
def test_doc_vector(EN):
|
def vocab(en_vocab, vectors):
|
||||||
doc = EN(u'Apples and oranges')
|
return add_vecs_to_vocab(en_vocab, vectors)
|
||||||
doc.vector
|
|
||||||
doc.vector_norm
|
|
||||||
|
|
||||||
@pytest.mark.models
|
|
||||||
def test_span_vector(EN):
|
|
||||||
span = EN(u'Apples and oranges')[0:2]
|
|
||||||
span.vector
|
|
||||||
span.vector_norm
|
|
||||||
|
|
||||||
@pytest.mark.models
|
|
||||||
def test_token_token_similarity(EN):
|
|
||||||
apples, oranges = EN(u'apples oranges')
|
|
||||||
assert apples.similarity(oranges) == oranges.similarity(apples)
|
|
||||||
assert 0.0 < apples.similarity(oranges) < 1.0
|
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.models
|
|
||||||
def test_token_lexeme_similarity(EN):
|
|
||||||
apples = EN(u'apples')
|
|
||||||
oranges = EN.vocab[u'oranges']
|
|
||||||
assert apples.similarity(oranges) == oranges.similarity(apples)
|
|
||||||
assert 0.0 < apples.similarity(oranges) < 1.0
|
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.models
|
|
||||||
def test_token_span_similarity(EN):
|
|
||||||
doc = EN(u'apples orange juice')
|
|
||||||
apples = doc[0]
|
|
||||||
oranges = doc[1:3]
|
|
||||||
assert apples.similarity(oranges) == oranges.similarity(apples)
|
|
||||||
assert 0.0 < apples.similarity(oranges) < 1.0
|
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.models
|
|
||||||
def test_token_doc_similarity(EN):
|
|
||||||
doc = EN(u'apples orange juice')
|
|
||||||
apples = doc[0]
|
|
||||||
assert apples.similarity(doc) == doc.similarity(apples)
|
|
||||||
assert 0.0 < apples.similarity(doc) < 1.0
|
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.models
|
|
||||||
def test_lexeme_span_similarity(EN):
|
|
||||||
doc = EN(u'apples orange juice')
|
|
||||||
apples = EN.vocab[u'apples']
|
|
||||||
span = doc[1:3]
|
|
||||||
assert apples.similarity(span) == span.similarity(apples)
|
|
||||||
assert 0.0 < apples.similarity(span) < 1.0
|
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.models
|
@pytest.fixture()
|
||||||
def test_lexeme_lexeme_similarity(EN):
|
def tokenizer_v(vocab):
|
||||||
apples = EN.vocab[u'apples']
|
return Tokenizer(vocab, {}, None, None, None)
|
||||||
oranges = EN.vocab[u'oranges']
|
|
||||||
assert apples.similarity(oranges) == oranges.similarity(apples)
|
|
||||||
assert 0.0 < apples.similarity(oranges) < 1.0
|
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.models
|
|
||||||
def test_lexeme_doc_similarity(EN):
|
|
||||||
doc = EN(u'apples orange juice')
|
|
||||||
apples = EN.vocab[u'apples']
|
|
||||||
assert apples.similarity(doc) == doc.similarity(apples)
|
|
||||||
assert 0.0 < apples.similarity(doc) < 1.0
|
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.models
|
@pytest.mark.parametrize('text', ["apple and orange"])
|
||||||
def test_span_span_similarity(EN):
|
def test_vectors_token_vector(tokenizer_v, vectors, text):
|
||||||
doc = EN(u'apples orange juice')
|
doc = tokenizer_v(text)
|
||||||
apples = doc[0:2]
|
assert vectors[0] == (doc[0].text, list(doc[0].vector))
|
||||||
oj = doc[1:3]
|
assert vectors[1] == (doc[2].text, list(doc[2].vector))
|
||||||
assert apples.similarity(oj) == oj.similarity(apples)
|
|
||||||
assert 0.0 < apples.similarity(oj) < 1.0
|
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.models
|
|
||||||
def test_span_doc_similarity(EN):
|
|
||||||
doc = EN(u'apples orange juice')
|
|
||||||
apples = doc[0:2]
|
|
||||||
oj = doc[1:3]
|
|
||||||
assert apples.similarity(doc) == doc.similarity(apples)
|
|
||||||
assert 0.0 < apples.similarity(doc) < 1.0
|
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.models
|
@pytest.mark.parametrize('text', ["apple", "orange"])
|
||||||
def test_doc_doc_similarity(EN):
|
def test_vectors_lexeme_vector(vocab, text):
|
||||||
apples = EN(u'apples and apple pie')
|
lex = vocab[text]
|
||||||
oranges = EN(u'orange juice')
|
assert list(lex.vector)
|
||||||
assert apples.similarity(oranges) == apples.similarity(oranges)
|
assert lex.vector_norm
|
||||||
assert 0.0 < apples.similarity(oranges) < 1.0
|
|
||||||
|
|
||||||
|
@pytest.mark.parametrize('text', [["apple", "and", "orange"]])
|
||||||
|
def test_vectors_doc_vector(vocab, text):
|
||||||
|
doc = get_doc(vocab, text)
|
||||||
|
assert list(doc.vector)
|
||||||
|
assert doc.vector_norm
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.parametrize('text', [["apple", "and", "orange"]])
|
||||||
|
def test_vectors_span_vector(vocab, text):
|
||||||
|
span = get_doc(vocab, 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 0.0 < 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 0.0 < token.similarity(lex) < 1.0
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.parametrize('text', [["apple", "orange", "juice"]])
|
||||||
|
def test_vectors_token_span_similarity(vocab, text):
|
||||||
|
doc = get_doc(vocab, text)
|
||||||
|
assert doc[0].similarity(doc[1:3]) == doc[1:3].similarity(doc[0])
|
||||||
|
assert 0.0 < doc[0].similarity(doc[1:3]) < 1.0
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.parametrize('text', [["apple", "orange", "juice"]])
|
||||||
|
def test_vectors_token_doc_similarity(vocab, text):
|
||||||
|
doc = get_doc(vocab, text)
|
||||||
|
assert doc[0].similarity(doc) == doc.similarity(doc[0])
|
||||||
|
assert 0.0 < doc[0].similarity(doc) < 1.0
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.parametrize('text', [["apple", "orange", "juice"]])
|
||||||
|
def test_vectors_lexeme_span_similarity(vocab, text):
|
||||||
|
doc = get_doc(vocab, text)
|
||||||
|
lex = vocab[text[0]]
|
||||||
|
assert lex.similarity(doc[1:3]) == doc[1:3].similarity(lex)
|
||||||
|
assert 0.0 < 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 0.0 < lex1.similarity(lex2) < 1.0
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.parametrize('text', [["apple", "orange", "juice"]])
|
||||||
|
def test_vectors_lexeme_doc_similarity(vocab, text):
|
||||||
|
doc = get_doc(vocab, text)
|
||||||
|
lex = vocab[text[0]]
|
||||||
|
assert lex.similarity(doc) == doc.similarity(lex)
|
||||||
|
assert 0.0 < lex.similarity(doc) < 1.0
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.parametrize('text', [["apple", "orange", "juice"]])
|
||||||
|
def test_vectors_span_span_similarity(vocab, text):
|
||||||
|
doc = get_doc(vocab, text)
|
||||||
|
assert doc[0:2].similarity(doc[1:3]) == doc[1:3].similarity(doc[0:2])
|
||||||
|
assert 0.0 < 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 = get_doc(vocab, text)
|
||||||
|
assert doc[0:2].similarity(doc) == doc.similarity(doc[0:2])
|
||||||
|
assert 0.0 < 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 = get_doc(vocab, text1)
|
||||||
|
doc2 = get_doc(vocab, text2)
|
||||||
|
assert doc1.similarity(doc2) == doc2.similarity(doc1)
|
||||||
|
assert 0.0 < doc1.similarity(doc2) < 1.0
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue
Block a user