mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-22 20:09:18 +03:00
f9b541f9ef
* add unit test for setting entities with duplicate identifiers * count the number of actual unique identifiers and throw duplicate warning
35 lines
981 B
Python
35 lines
981 B
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
from spacy.kb import KnowledgeBase
|
|
from spacy.util import ensure_path
|
|
|
|
from spacy.lang.en import English
|
|
from spacy.tests.util import make_tempdir
|
|
|
|
|
|
def test_issue4674():
|
|
"""Test that setting entities with overlapping identifiers does not mess up IO"""
|
|
nlp = English()
|
|
kb = KnowledgeBase(nlp.vocab, entity_vector_length=3)
|
|
|
|
vector1 = [0.9, 1.1, 1.01]
|
|
vector2 = [1.8, 2.25, 2.01]
|
|
kb.set_entities(entity_list=["Q1", "Q1"], freq_list=[32, 111], vector_list=[vector1, vector2])
|
|
|
|
assert kb.get_size_entities() == 1
|
|
|
|
# dumping to file & loading back in
|
|
with make_tempdir() as d:
|
|
dir_path = ensure_path(d)
|
|
if not dir_path.exists():
|
|
dir_path.mkdir()
|
|
file_path = dir_path / "kb"
|
|
kb.dump(str(file_path))
|
|
|
|
kb2 = KnowledgeBase(vocab=nlp.vocab, entity_vector_length=3)
|
|
kb2.load_bulk(str(file_path))
|
|
|
|
assert kb2.get_size_entities() == 1
|
|
|