explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 09:26:27 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Fix formatting on serializer tests

Browse Source
This commit is contained in:
Matthew Honnibal 2016-05-02 16:07:21 +02:00
parent 6e1f1c4b9e
commit c1c11a8ae0
1 changed files with 38 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

78
spacy/tests/serialize/test_serialization.py
View File

@ -4,85 +4,83 @@ import pytest
from spacy.tokens import Doc from spacy.tokens import Doc
def equal(doc1, doc2): def equal(doc1, doc2):
# tokens # tokens
assert [ t.orth for t in doc1 ] == [ t.orth for t in doc2 ] assert [ t.orth for t in doc1 ] == [ t.orth for t in doc2 ]
# tags # tags
assert [ t.pos for t in doc1 ] == [ t.pos for t in doc2 ] assert [ t.pos for t in doc1 ] == [ t.pos for t in doc2 ]
assert [ t.tag for t in doc1 ] == [ t.tag for t in doc2 ] assert [ t.tag for t in doc1 ] == [ t.tag for t in doc2 ]
# parse # parse
assert [ t.head.i for t in doc1 ] == [ t.head.i for t in doc2 ] assert [ t.head.i for t in doc1 ] == [ t.head.i for t in doc2 ]
assert [ t.dep for t in doc1 ] == [ t.dep for t in doc2 ] assert [ t.dep for t in doc1 ] == [ t.dep for t in doc2 ]
if doc1.is_parsed and doc2.is_parsed:
if doc1.is_parsed and doc2.is_parsed: assert [ s for s in doc1.sents ] == [ s for s in doc2.sents ]
assert [ s for s in doc1.sents ] == [ s for s in doc2.sents ]
# entities # entities
assert [ t.ent_type for t in doc1 ] == [ t.ent_type for t in doc2 ] assert [ t.ent_type for t in doc1 ] == [ t.ent_type for t in doc2 ]
assert [ t.ent_iob for t in doc1 ] == [ t.ent_iob for t in doc2 ] assert [ t.ent_iob for t in doc1 ] == [ t.ent_iob for t in doc2 ]
assert [ ent for ent in doc1.ents ] == [ ent for ent in doc2.ents ] assert [ ent for ent in doc1.ents ] == [ ent for ent in doc2.ents ]
@pytest.mark.models @pytest.mark.models
def test_serialize_tokens(EN): def test_serialize_tokens(EN):
doc1 = EN(u'This is a test sentence.',tag=False,parse=False,entity=False) doc1 = EN(u'This is a test sentence.',tag=False, parse=False, entity=False)
doc2 = Doc(EN.vocab).from_bytes(doc1.to_bytes()) doc2 = Doc(EN.vocab).from_bytes(doc1.to_bytes())
equal(doc1,doc2) equal(doc1, doc2)
@pytest.mark.models @pytest.mark.models
def test_serialize_tokens_tags(EN): def test_serialize_tokens_tags(EN):
doc1 = EN(u'This is a test sentence.',tag=True,parse=False,entity=False) doc1 = EN(u'This is a test sentence.',tag=True, parse=False, entity=False)
doc2 = Doc(EN.vocab).from_bytes(doc1.to_bytes())
doc2 = Doc(EN.vocab).from_bytes(doc1.to_bytes()) equal(doc1, doc2)
equal(doc1,doc2)
@pytest.mark.models @pytest.mark.models
def test_serialize_tokens_parse(EN): def test_serialize_tokens_parse(EN):
doc1 = EN(u'This is a test sentence.',tag=False,parse=True,entity=False) doc1 = EN(u'This is a test sentence.',tag=False, parse=True, entity=False)
doc2 = Doc(EN.vocab).from_bytes(doc1.to_bytes()) doc2 = Doc(EN.vocab).from_bytes(doc1.to_bytes())
equal(doc1,doc2) equal(doc1, doc2)
@pytest.mark.models @pytest.mark.models
def test_serialize_tokens_ner(EN): def test_serialize_tokens_ner(EN):
doc1 = EN(u'This is a test sentence.',tag=False,parse=False,entity=True) doc1 = EN(u'This is a test sentence.', tag=False, parse=False, entity=True)
doc2 = Doc(EN.vocab).from_bytes(doc1.to_bytes()) doc2 = Doc(EN.vocab).from_bytes(doc1.to_bytes())
equal(doc1,doc2) equal(doc1, doc2)
@pytest.mark.models @pytest.mark.models
def test_serialize_tokens_tags_parse(EN): def test_serialize_tokens_tags_parse(EN):
doc1 = EN(u'This is a test sentence.',tag=True,parse=True,entity=True) doc1 = EN(u'This is a test sentence.', tag=True, parse=True, entity=False)
doc2 = Doc(EN.vocab).from_bytes(doc1.to_bytes()) doc2 = Doc(EN.vocab).from_bytes(doc1.to_bytes())
equal(doc1,doc2) equal(doc1, doc2)
@pytest.mark.models @pytest.mark.models
def test_serialize_tokens_tags_ner(EN): def test_serialize_tokens_tags_ner(EN):
doc1 = EN(u'This is a test sentence.',tag=True,parse=False,entity=True) doc1 = EN(u'This is a test sentence.', tag=True, parse=False, entity=True)
doc2 = Doc(EN.vocab).from_bytes(doc1.to_bytes()) doc2 = Doc(EN.vocab).from_bytes(doc1.to_bytes())
equal(doc1,doc2) equal(doc1, doc2)
@pytest.mark.models @pytest.mark.models
def test_serialize_tokens_ner_parse(EN): def test_serialize_tokens_ner_parse(EN):
doc1 = EN(u'This is a test sentence.',tag=False,parse=True,entity=True) doc1 = EN(u'This is a test sentence.', tag=False, parse=True, entity=True)
doc2 = Doc(EN.vocab).from_bytes(doc1.to_bytes()) doc2 = Doc(EN.vocab).from_bytes(doc1.to_bytes())
equal(doc1,doc2) equal(doc1, doc2)
@pytest.mark.models @pytest.mark.models
def test_serialize_tokens_tags_parse_ner(EN): def test_serialize_tokens_tags_parse_ner(EN):
doc1 = EN(u'This is a test sentence.',tag=True,parse=True,entity=True) doc1 = EN(u'This is a test sentence.', tag=True, parse=True, entity=True)
doc2 = Doc(EN.vocab).from_bytes(doc1.to_bytes()) doc2 = Doc(EN.vocab).from_bytes(doc1.to_bytes())
equal(doc1,doc2) equal(doc1, doc2)