explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-11 04:08:09 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add tests for entity->biluo transformation

Browse Source
This commit is contained in:
Matthew Honnibal 2016-10-15 21:50:43 +02:00
parent a557a24189
commit 2163fd238f
1 changed files with 48 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
spacy/tests/gold/test_biluo.py Normal file
View File

@ -0,0 +1,48 @@
from __future__ import unicode_literals
from ...gold import biluo_tags_from_offsets
from ...vocab import Vocab
from ...tokens.doc import Doc
import pytest
@pytest.fixture
def vocab():
return Vocab()
def test_U(vocab):
orths_and_spaces = [('I', True), ('flew', True), ('to', True), ('London', False),
('.', True)]
doc = Doc(vocab, orths_and_spaces=orths_and_spaces)
entities = [(len("I flew to "), len("I flew to London"), 'LOC')]
tags = biluo_tags_from_offsets(doc, entities)
assert tags == ['O', 'O', 'O', 'U-LOC', 'O']
def test_BL(vocab):
orths_and_spaces = [('I', True), ('flew', True), ('to', True), ('San', True),
('Francisco', False), ('.', True)]
doc = Doc(vocab, orths_and_spaces=orths_and_spaces)
entities = [(len("I flew to "), len("I flew to San Francisco"), 'LOC')]
tags = biluo_tags_from_offsets(doc, entities)
assert tags == ['O', 'O', 'O', 'B-LOC', 'L-LOC', 'O']
def test_BIL(vocab):
orths_and_spaces = [('I', True), ('flew', True), ('to', True), ('San', True),
('Francisco', True), ('Valley', False), ('.', True)]
doc = Doc(vocab, orths_and_spaces=orths_and_spaces)
entities = [(len("I flew to "), len("I flew to San Francisco Valley"), 'LOC')]
tags = biluo_tags_from_offsets(doc, entities)
assert tags == ['O', 'O', 'O', 'B-LOC', 'I-LOC', 'L-LOC', 'O']
def test_misalign(vocab):
orths_and_spaces = [('I', True), ('flew', True), ('to', True), ('San', True),
('Francisco', True), ('Valley.', False)]
doc = Doc(vocab, orths_and_spaces=orths_and_spaces)
entities = [(len("I flew to "), len("I flew to San Francisco Valley"), 'LOC')]
tags = biluo_tags_from_offsets(doc, entities)
assert tags == ['O', 'O', 'O', '', '', '']