spaCy/spacy/tests/regression/test_issue4674.py

40 lines
1.0 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
2019-12-21 23:14:52 +03:00
import pytest
from spacy.kb import KnowledgeBase
from spacy.util import ensure_path
from spacy.lang.en import English
2019-12-21 23:14:52 +03:00
2019-12-21 23:17:45 +03:00
from ..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]
2019-12-21 23:14:52 +03:00
with pytest.warns(UserWarning):
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