explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-21 03:19:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'develop' of https://github.com/explosion/spaCy into develop

Browse Source
This commit is contained in:
Matthew Honnibal 2018-05-21 17:42:55 +02:00
commit d5af38f80c
12 changed files with 117 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
spacy/compat.py
View File

@ -88,11 +88,11 @@ def symlink_to(orig, dest):
def is_config(python2=None, python3=None, windows=None, linux=None, osx=None):
return ((python2 is None or python2 == is_python2) and
(python3 is None or python3 == is_python3) and
(windows is None or windows == is_windows) and
(linux is None or linux == is_linux) and
(osx is None or osx == is_osx))
return (python2 in (None, is_python2) and
python3 in (None, is_python3) and
windows in (None, is_windows) and
linux in (None, is_linux) and
osx in (None, is_osx))
def normalize_string_keys(old):

18
spacy/errors.py
View File

@ -38,6 +38,14 @@ class Warnings(object):
"surprising to you, make sure the Doc was processed using a model "
"that supports named entity recognition, and check the `doc.ents` "
"property manually if necessary.")
W007 = ("The model you're using has no word vectors loaded, so the result "
"of the {obj}.similarity method will be based on the tagger, "
"parser and NER, which may not give useful similarity judgements. "
"This may happen if you're using one of the small models, e.g. "
"`en_core_web_sm`, which don't ship with word vectors and only "
"use context-sensitive tensors. You can always add your own word "
"vectors, or use one of the larger models instead if available.")
W008 = ("Evaluating {obj}.similarity based on empty vectors.")
@add_codes
@ -286,8 +294,15 @@ def _get_warn_types(arg):
if w_type.strip() in WARNINGS]
def _get_warn_excl(arg):
if not arg:
return []
return [w_id.strip() for w_id in arg.split(',')]
SPACY_WARNING_FILTER = os.environ.get('SPACY_WARNING_FILTER', 'always')
SPACY_WARNING_TYPES = _get_warn_types(os.environ.get('SPACY_WARNING_TYPES'))
SPACY_WARNING_IGNORE = _get_warn_excl(os.environ.get('SPACY_WARNING_IGNORE'))
def user_warning(message):
@ -307,7 +322,8 @@ def _warn(message, warn_type='user'):
message (unicode): The message to display.
category (Warning): The Warning to show.
"""
if warn_type in SPACY_WARNING_TYPES:
w_id = message.split('[', 1)[1].split(']', 1)[0] # get ID from string
if warn_type in SPACY_WARNING_TYPES and w_id not in SPACY_WARNING_IGNORE:
category = WARNINGS[warn_type]
stack = inspect.stack()[-1]
with warnings.catch_warnings():

3
spacy/lexeme.pyx
View File

@ -15,7 +15,7 @@ from .attrs cimport IS_TITLE, IS_UPPER, LIKE_URL, LIKE_NUM, LIKE_EMAIL, IS_STOP
from .attrs cimport IS_BRACKET, IS_QUOTE, IS_LEFT_PUNCT, IS_RIGHT_PUNCT, IS_CURRENCY, IS_OOV
from .attrs cimport PROB
from .attrs import intify_attrs
from .errors import Errors
from .errors import Errors, Warnings, user_warning
memset(&EMPTY_LEXEME, 0, sizeof(LexemeC))
@ -122,6 +122,7 @@ cdef class Lexeme:
if self.c.orth == other[0].orth:
return 1.0
if self.vector_norm == 0 or other.vector_norm == 0:
user_warning(Warnings.W008.format(obj='Lexeme'))
return 0.0
return (numpy.dot(self.vector, other.vector) /
(self.vector_norm * other.vector_norm))

10
spacy/tests/doc/test_doc_api.py
View File

@ -253,11 +253,13 @@ def test_doc_api_has_vector():
def test_doc_api_similarity_match():
doc = Doc(Vocab(), words=['a'])
assert doc.similarity(doc[0]) == 1.0
assert doc.similarity(doc.vocab['a']) == 1.0
with pytest.warns(None):
assert doc.similarity(doc[0]) == 1.0
assert doc.similarity(doc.vocab['a']) == 1.0
doc2 = Doc(doc.vocab, words=['a', 'b', 'c'])
assert doc.similarity(doc2[:1]) == 1.0
assert doc.similarity(doc2) == 0.0
with pytest.warns(None):
assert doc.similarity(doc2[:1]) == 1.0
assert doc.similarity(doc2) == 0.0
def test_lowest_common_ancestor(en_tokenizer):

7
spacy/tests/doc/test_span.py
View File

@ -88,9 +88,10 @@ def test_span_similarity_match():
doc = Doc(Vocab(), words=['a', 'b', 'a', 'b'])
span1 = doc[:2]
span2 = doc[2:]
assert span1.similarity(span2) == 1.0
assert span1.similarity(doc) == 0.0
assert span1[:1].similarity(doc.vocab['a']) == 1.0
with pytest.warns(None):
assert span1.similarity(span2) == 1.0
assert span1.similarity(doc) == 0.0
assert span1[:1].similarity(doc.vocab['a']) == 1.0
def test_spans_default_sentiment(en_tokenizer):

6
spacy/tests/vectors/test_similarity.py
View File

@ -45,7 +45,8 @@ def test_vectors_similarity_TT(vocab, vectors):
def test_vectors_similarity_TD(vocab, vectors):
[(word1, vec1), (word2, vec2)] = vectors
doc = get_doc(vocab, words=[word1, word2])
assert doc.similarity(doc[0]) == doc[0].similarity(doc)
with pytest.warns(None):
assert doc.similarity(doc[0]) == doc[0].similarity(doc)
def test_vectors_similarity_DS(vocab, vectors):
@ -57,4 +58,5 @@ def test_vectors_similarity_DS(vocab, vectors):
def test_vectors_similarity_TS(vocab, vectors):
[(word1, vec1), (word2, vec2)] = vectors
doc = get_doc(vocab, words=[word1, word2])
assert doc[:2].similarity(doc[0]) == doc[0].similarity(doc[:2])
with pytest.warns(None):
assert doc[:2].similarity(doc[0]) == doc[0].similarity(doc[:2])

34
spacy/tests/vectors/test_vectors.py
View File

@ -23,6 +23,18 @@ def vectors():
('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():
@ -105,6 +117,18 @@ def test_vectors_token_vector(tokenizer_v, vectors, text):
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]
@ -182,15 +206,17 @@ def test_vectors_lexeme_doc_similarity(vocab, text):
@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 -1. < doc[0:2].similarity(doc[1:3]) < 1.0
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 = get_doc(vocab, text)
assert doc[0:2].similarity(doc) == doc.similarity(doc[0:2])
assert -1. < doc[0:2].similarity(doc) < 1.0
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', [

7
spacy/tokens/doc.pyx
View File

@ -31,7 +31,8 @@ from ..attrs cimport ENT_TYPE, SENT_START
from ..parts_of_speech cimport CCONJ, PUNCT, NOUN, univ_pos_t
from ..util import normalize_slice
from ..compat import is_config, copy_reg, pickle, basestring_
from ..errors import Errors, Warnings, deprecation_warning
from ..errors import deprecation_warning, models_warning, user_warning
from ..errors import Errors, Warnings
from .. import util
from .underscore import Underscore, get_ext_args
from ._retokenize import Retokenizer
@ -318,8 +319,10 @@ cdef class Doc:
break
else:
return 1.0
if self.vocab.vectors.n_keys == 0:
models_warning(Warnings.W007.format(obj='Doc'))
if self.vector_norm == 0 or other.vector_norm == 0:
user_warning(Warnings.W008.format(obj='Doc'))
return 0.0
return numpy.dot(self.vector, other.vector) / (self.vector_norm * other.vector_norm)

5
spacy/tokens/span.pyx
View File

@ -16,7 +16,7 @@ from ..util import normalize_slice
from ..attrs cimport IS_PUNCT, IS_SPACE
from ..lexeme cimport Lexeme
from ..compat import is_config
from ..errors import Errors, TempErrors
from ..errors import Errors, TempErrors, Warnings, user_warning, models_warning
from .underscore import Underscore, get_ext_args
@ -200,7 +200,10 @@ cdef class Span:
break
else:
return 1.0
if self.vocab.vectors.n_keys == 0:
models_warning(Warnings.W007.format(obj='Span'))
if self.vector_norm == 0.0 or other.vector_norm == 0.0:
user_warning(Warnings.W008.format(obj='Span'))
return 0.0
return numpy.dot(self.vector, other.vector) / (self.vector_norm * other.vector_norm)

5
spacy/tokens/token.pyx
View File

@ -19,7 +19,7 @@ from ..attrs cimport IS_OOV, IS_TITLE, IS_UPPER, IS_CURRENCY, LIKE_URL, LIKE_NUM
from ..attrs cimport IS_STOP, ID, ORTH, NORM, LOWER, SHAPE, PREFIX, SUFFIX
from ..attrs cimport LENGTH, CLUSTER, LEMMA, POS, TAG, DEP
from ..compat import is_config
from ..errors import Errors
from ..errors import Errors, Warnings, user_warning, models_warning
from .. import util
from .underscore import Underscore, get_ext_args
@ -161,7 +161,10 @@ cdef class Token:
elif hasattr(other, 'orth'):
if self.c.lex.orth == other.orth:
return 1.0
if self.vocab.vectors.n_keys == 0:
models_warning(Warnings.W007.format(obj='Token'))
if self.vector_norm == 0 or other.vector_norm == 0:
user_warning(Warnings.W008.format(obj='Token'))
return 0.0
return (numpy.dot(self.vector, other.vector) /
(self.vector_norm * other.vector_norm))

38
spacy/vocab.pyx
View File

@ -309,7 +309,7 @@ cdef class Vocab:
link_vectors_to_models(self)
return remap
def get_vector(self, orth):
def get_vector(self, orth, minn=None, maxn=None):
"""Retrieve a vector for a word in the vocabulary. Words can be looked
up by string or int ID. If no vectors data is loaded, ValueError is
raised.
@ -320,10 +320,42 @@ cdef class Vocab:
"""
if isinstance(orth, basestring_):
orth = self.strings.add(orth)
word = self[orth].orth_
if orth in self.vectors.key2row:
return self.vectors[orth]
else:
return numpy.zeros((self.vectors_length,), dtype='f')
# Assign default ngram limits to minn and maxn which is the length of the word.
if minn is None:
minn = len(word)
if maxn is None:
maxn = len(word)
vectors = numpy.zeros((self.vectors_length,), dtype='f')
# Fasttext's ngram computation taken from https://github.com/facebookresearch/fastText
ngrams_size = 0;
for i in range(len(word)):
ngram = ""
if (word[i] and 0xC0) == 0x80:
continue
n = 1
j = i
while (j < len(word) and n <= maxn):
if n > maxn:
break
ngram += word[j]
j = j + 1
while (j < len(word) and (word[j] and 0xC0) == 0x80):
ngram += word[j]
j = j + 1
if (n >= minn and not (n == 1 and (i == 0 or j == len(word)))):
if self.strings[ngram] in self.vectors.key2row:
vectors = numpy.add(self.vectors[self.strings[ngram]],vectors)
ngrams_size += 1
n = n + 1
if ngrams_size > 0:
vectors = vectors * (1.0/ngrams_size)
return vectors
def set_vector(self, orth, vector):
"""Set a vector for a word in the vocabulary. Words can be referenced

1
website/api/cli.jade
View File

@ -47,6 +47,7 @@ p
+row
+cell other
+tag-new(2.1)
+cell -
+cell
| Additional installation options to be passed to