def test_concept_similarity(self):
cdb = CDB(config=self.config)
np.random.seed(11)
for i in range(500):
cui = "C" + str(i)
type_ids = {'T-' + str(i%10)}
cdb.add_concept(cui=cui, names=prepare_name('Name: ' + str(i), self.maker.nlp, {}, self.config), ontologies=set(),
name_status='P', type_ids=type_ids, description='', full_build=True)
vectors = {}
for cntx_type in self.config.linking['context_vector_sizes']:
vectors[cntx_type] = np.random.rand(300)
cdb.update_context_vector(cui, vectors, negative=False)
res = cdb.most_similar('C200', 'long', type_id_filter=['T-0'], min_cnt=1, topn=10, force_build=True)
assert len(res) == 10
def test_for_linker(self):
self.config = Config()
self.config.general['log_level'] = logging.DEBUG
cdb = CDB(config=self.config)
# Add a couple of names
cdb.add_names(cui='S-229004',
names=prepare_name('Movar', self.nlp, {}, self.config))
cdb.add_names(cui='S-229004',
names=prepare_name('Movar viruses', self.nlp, {},
self.config))
cdb.add_names(cui='S-229005',
names=prepare_name('CDB', self.nlp, {}, self.config))
cdb.add_names(cui='S-2290045',
names=prepare_name('Movar', self.nlp, {}, self.config))
# Check
#assert cdb.cui2names == {'S-229004': {'movar', 'movarvirus', 'movarviruses'}, 'S-229005': {'cdb'}, 'S-2290045': {'movar'}}
cuis = list(cdb.cui2names.keys())
for cui in cuis[0:50]:
vectors = {
'short': np.random.rand(300),
'long': np.random.rand(300),
'medium': np.random.rand(300)
}
cdb.update_context_vector(cui, vectors, negative=False)
d = self.nlp(self.text)
vocab = Vocab.load(self.vocab_path)
cm = ContextModel(cdb, vocab, self.config)
cm.train_using_negative_sampling('S-229004')
self.config.linking['train_count_threshold'] = 0
cm.train('S-229004', d._.ents[1], d)
cm.similarity('S-229004', d._.ents[1], d)
cm.disambiguate(['S-2290045', 'S-229004'], d._.ents[1], 'movar', d)
cdb = CDB(config=config)
np.random.seed(11)
for i in range(500):
cui = "C" + str(i)
type_ids = {'T-' + str(i % 10)}
cdb.add_concept(cui=cui,
names=prepare_name('Name: ' + str(i), maker.nlp, {},
config),
ontologies=set(),
name_status='P',
type_ids=type_ids,
description='',
full_build=True)
vectors = {}
for cntx_type in config.linking['context_vector_sizes']:
vectors[cntx_type] = np.random.rand(300)
cdb.update_context_vector(cui, vectors, negative=False)
res = cdb.most_similar('C200',
'long',
type_id_filter=['T-0'],
min_cnt=1,
topn=10,
force_build=True)
assert len(res) == 10
# Test training reset
cdb.reset_training()
assert len(cdb.cui2context_vectors['C0']) == 0
assert cdb.cui2count_train['C0'] == 0