mirror of
https://github.com/explosion/spaCy.git
synced 2025-01-19 05:54:11 +03:00
de5a9ecdf3
* remove duplicate unit test * unit test (currently failing) for issue 4267 * bugfix: ensure doc.ents preserves kb_id annotations * fix in setting doc.ents with empty label * rename * test for presetting an entity to a certain type * allow overwriting Outside + blocking presets * fix actions when previous label needs to be kept * fix default ent_iob in set entities * cleaner solution with U- action * remove debugging print statements * unit tests with explicit transitions and is_valid testing * remove U- from move_names explicitly * remove unit tests with pre-trained models that don't work * remove (working) unit tests with pre-trained models * clean up unit tests * move unit tests * small fixes * remove two TODO's from doc.ents comments
47 lines
1.3 KiB
Python
47 lines
1.3 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...pipeline import EntityRecognizer
|
|
from ..util import get_doc
|
|
from ...tokens import Span
|
|
|
|
import pytest
|
|
|
|
|
|
def test_doc_add_entities_set_ents_iob(en_vocab):
|
|
text = ["This", "is", "a", "lion"]
|
|
doc = get_doc(en_vocab, text)
|
|
ner = EntityRecognizer(en_vocab)
|
|
ner.begin_training([])
|
|
ner(doc)
|
|
assert len(list(doc.ents)) == 0
|
|
assert [w.ent_iob_ for w in doc] == (["O"] * len(doc))
|
|
|
|
doc.ents = [(doc.vocab.strings["ANIMAL"], 3, 4)]
|
|
assert [w.ent_iob_ for w in doc] == ["O", "O", "O", "B"]
|
|
|
|
doc.ents = [(doc.vocab.strings["WORD"], 0, 2)]
|
|
assert [w.ent_iob_ for w in doc] == ["B", "I", "O", "O"]
|
|
|
|
|
|
def test_ents_reset(en_vocab):
|
|
text = ["This", "is", "a", "lion"]
|
|
doc = get_doc(en_vocab, text)
|
|
ner = EntityRecognizer(en_vocab)
|
|
ner.begin_training([])
|
|
ner(doc)
|
|
assert [t.ent_iob_ for t in doc] == (["O"] * len(doc))
|
|
doc.ents = list(doc.ents)
|
|
assert [t.ent_iob_ for t in doc] == (["O"] * len(doc))
|
|
|
|
|
|
def test_add_overlapping_entities(en_vocab):
|
|
text = ["Louisiana", "Office", "of", "Conservation"]
|
|
doc = get_doc(en_vocab, text)
|
|
entity = Span(doc, 0, 4, label=391)
|
|
doc.ents = [entity]
|
|
|
|
new_entity = Span(doc, 0, 1, label=392)
|
|
with pytest.raises(ValueError):
|
|
doc.ents = list(doc.ents) + [new_entity]
|