unicode strings

This commit is contained in:
svlandeg 2019-06-19 13:26:33 +02:00
parent 0b0959b363
commit b76a43bee4
1 changed files with 16 additions and 16 deletions

View File

@ -29,14 +29,14 @@ def test_serialize_kb_disk(en_vocab):
def _get_dummy_kb(vocab): def _get_dummy_kb(vocab):
kb = KnowledgeBase(vocab=vocab, entity_vector_length=3) kb = KnowledgeBase(vocab=vocab, entity_vector_length=3)
kb.add_entity(entity="Q53", prob=0.33, entity_vector=[0, 5, 3]) kb.add_entity(entity=u'Q53', prob=0.33, entity_vector=[0, 5, 3])
kb.add_entity(entity="Q17", prob=0.2, entity_vector=[7, 1, 0]) kb.add_entity(entity=u'Q17', prob=0.2, entity_vector=[7, 1, 0])
kb.add_entity(entity="Q007", prob=0.7, entity_vector=[0, 0, 7]) kb.add_entity(entity=u'Q007', prob=0.7, entity_vector=[0, 0, 7])
kb.add_entity(entity="Q44", prob=0.4, entity_vector=[4, 4, 4]) kb.add_entity(entity=u'Q44', prob=0.4, entity_vector=[4, 4, 4])
kb.add_alias(alias="double07", entities=["Q17", "Q007"], probabilities=[0.1, 0.9]) kb.add_alias(alias=u'double07', entities=[u'Q17', u'Q007'], probabilities=[0.1, 0.9])
kb.add_alias(alias="guy", entities=["Q53", "Q007", "Q17", "Q44"], probabilities=[0.3, 0.3, 0.2, 0.1]) kb.add_alias(alias=u'guy', entities=[u'Q53', u'Q007', u'Q17', u'Q44'], probabilities=[0.3, 0.3, 0.2, 0.1])
kb.add_alias(alias="random", entities=["Q007"], probabilities=[1.0]) kb.add_alias(alias=u'random', entities=[u'Q007'], probabilities=[1.0])
return kb return kb
@ -44,30 +44,30 @@ def _get_dummy_kb(vocab):
def _check_kb(kb): def _check_kb(kb):
# check entities # check entities
assert kb.get_size_entities() == 4 assert kb.get_size_entities() == 4
for entity_string in ["Q53", "Q17", "Q007", "Q44"]: for entity_string in [u'Q53', u'Q17', u'Q007', u'Q44']:
assert entity_string in kb.get_entity_strings() assert entity_string in kb.get_entity_strings()
for entity_string in ["", "Q0"]: for entity_string in [u'', u'Q0']:
assert entity_string not in kb.get_entity_strings() assert entity_string not in kb.get_entity_strings()
# check aliases # check aliases
assert kb.get_size_aliases() == 3 assert kb.get_size_aliases() == 3
for alias_string in ["double07", "guy", "random"]: for alias_string in [u'double07', u'guy', u'random']:
assert alias_string in kb.get_alias_strings() assert alias_string in kb.get_alias_strings()
for alias_string in ["nothingness", "", "randomnoise"]: for alias_string in [u'nothingness', u'', u'randomnoise']:
assert alias_string not in kb.get_alias_strings() assert alias_string not in kb.get_alias_strings()
# check candidates & probabilities # check candidates & probabilities
candidates = sorted(kb.get_candidates("double07"), key=lambda x: x.entity_) candidates = sorted(kb.get_candidates(u'double07'), key=lambda x: x.entity_)
assert len(candidates) == 2 assert len(candidates) == 2
assert candidates[0].entity_ == "Q007" assert candidates[0].entity_ == u'Q007'
assert 0.6999 < candidates[0].entity_freq < 0.701 assert 0.6999 < candidates[0].entity_freq < 0.701
assert candidates[0].entity_vector == [0, 0, 7] assert candidates[0].entity_vector == [0, 0, 7]
assert candidates[0].alias_ == "double07" assert candidates[0].alias_ == u'double07'
assert 0.899 < candidates[0].prior_prob < 0.901 assert 0.899 < candidates[0].prior_prob < 0.901
assert candidates[1].entity_ == "Q17" assert candidates[1].entity_ == u'Q17'
assert 0.199 < candidates[1].entity_freq < 0.201 assert 0.199 < candidates[1].entity_freq < 0.201
assert candidates[1].entity_vector == [7, 1, 0] assert candidates[1].entity_vector == [7, 1, 0]
assert candidates[1].alias_ == "double07" assert candidates[1].alias_ == u'double07'
assert 0.099 < candidates[1].prior_prob < 0.101 assert 0.099 < candidates[1].prior_prob < 0.101