def test_kb_to_bytes():
# Test that the KB's to_bytes method works correctly
nlp = English()
kb_1 = KnowledgeBase(nlp.vocab, entity_vector_length=3)
kb_1.add_entity(entity="Q2146908", freq=12, entity_vector=[6, -4, 3])
kb_1.add_entity(entity="Q66", freq=9, entity_vector=[1, 2, 3])
kb_1.add_alias(alias="Russ Cochran",
entities=["Q2146908"],
probabilities=[0.8])
kb_1.add_alias(alias="Boeing", entities=["Q66"], probabilities=[0.5])
kb_1.add_alias(alias="Randomness",
entities=["Q66", "Q2146908"],
probabilities=[0.1, 0.2])
assert kb_1.contains_alias("Russ Cochran")
kb_bytes = kb_1.to_bytes()
kb_2 = KnowledgeBase(nlp.vocab, entity_vector_length=3)
assert not kb_2.contains_alias("Russ Cochran")
kb_2 = kb_2.from_bytes(kb_bytes)
# check that both KBs are exactly the same
assert kb_1.get_size_entities() == kb_2.get_size_entities()
assert kb_1.entity_vector_length == kb_2.entity_vector_length
assert kb_1.get_entity_strings() == kb_2.get_entity_strings()
assert kb_1.get_vector("Q2146908") == kb_2.get_vector("Q2146908")
assert kb_1.get_vector("Q66") == kb_2.get_vector("Q66")
assert kb_2.contains_alias("Russ Cochran")
assert kb_1.get_size_aliases() == kb_2.get_size_aliases()
assert kb_1.get_alias_strings() == kb_2.get_alias_strings()
assert len(kb_1.get_alias_candidates("Russ Cochran")) == len(
kb_2.get_alias_candidates("Russ Cochran"))
assert len(kb_1.get_alias_candidates("Randomness")) == len(
kb_2.get_alias_candidates("Randomness"))
def test_kb_pickle():
# Test that the KB can be pickled
nlp = English()
kb_1 = KnowledgeBase(nlp.vocab, entity_vector_length=3)
kb_1.add_entity(entity="Q2146908", freq=12, entity_vector=[6, -4, 3])
assert not kb_1.contains_alias("Russ Cochran")
kb_1.add_alias(alias="Russ Cochran",
entities=["Q2146908"],
probabilities=[0.8])
assert kb_1.contains_alias("Russ Cochran")
data = pickle.dumps(kb_1)
kb_2 = pickle.loads(data)
assert kb_2.contains_alias("Russ Cochran")
def test_issue6730(en_vocab):
"""Ensure that the KB does not accept empty strings, but otherwise IO works fine."""
from spacy.kb import KnowledgeBase
kb = KnowledgeBase(en_vocab, entity_vector_length=3)
kb.add_entity(entity="1", freq=148, entity_vector=[1, 2, 3])
with pytest.raises(ValueError):
kb.add_alias(alias="", entities=["1"], probabilities=[0.4])
assert kb.contains_alias("") is False
kb.add_alias(alias="x", entities=["1"], probabilities=[0.2])
kb.add_alias(alias="y", entities=["1"], probabilities=[0.1])
with make_tempdir() as tmp_dir:
kb.to_disk(tmp_dir)
kb.from_disk(tmp_dir)
assert kb.get_size_aliases() == 2
assert set(kb.get_alias_strings()) == {"x", "y"}