def test_patterns(self):
fg = TmVarDictionaryFeatureGenerator()
self.assertTrue(fg.patterns[0].match('c.2708_2711delTTAG'))
self.assertTrue(fg.patterns[1].match('IVS2-58_55insT'))
self.assertTrue(fg.patterns[2].match('c.467C>A'))
self.assertTrue(fg.patterns[3].match('IVS3+18C>T '))
self.assertTrue(fg.patterns[4].match('c.A436C'))
self.assertTrue(fg.patterns[5].match('A436C'))
self.assertTrue(fg.patterns[6].match('912delTA'))
self.assertTrue(fg.patterns[7].match('p.G204VfsX28'))
self.assertTrue(fg.patterns[8].match('p.G204V'))
self.assertTrue(fg.patterns[9].match('p.Ser157Ser'))
self.assertTrue(fg.patterns[10].match('p.Ser119fsX'))
def get_prepare_pipeline_for_best_model(use_windows=True,
we_params=None,
nl_features=None):
"""
Helper method that returns an instance of PrepareDatasetPipeline
which uses the best configuration for predicating mutation mentions.
if we_params is empty dict, no we is applied
:returns nalaf.structures.dataset_pipelines.PrepareDatasetPipeline
"""
default_we_params = {
'additive': None,
'multiplicative': None,
'location': None
}
we_params = default_we_params if we_params is None else we_params
generators = [
SpacyLemmatizer(),
SentenceMarkerFeatureGenerator(),
TmVarFeatureGenerator(get_mutation_features=True),
TmVarDictionaryFeatureGenerator(),
]
include = []
if nl_features:
f = NLMentionFeatureGenerator(nl_features['threshold'])
if nl_features['window']:
include.extend(['tag_dict[0]', 'nl_tag_dict[0]'])
generators.append(f)
if use_windows:
include.extend([
'pattern0[0]', 'pattern1[0]', 'pattern2[0]', 'pattern3[0]',
'pattern4[0]', 'pattern5[0]', 'pattern6[0]', 'pattern7[0]',
'pattern8[0]', 'pattern9[0]', 'pattern10[0]', 'stem[0]'
])
f = WindowFeatureGenerator(template=(-4, -3, -2, -1, 1, 2, 3, 4),
include_list=include)
generators.append(f)
if we_params:
generators.append(
get_word_embeddings_feature_generator(we_params['location'],
we_params['additive'],
we_params['multiplicative']))
return PrepareDatasetPipeline(feature_generators=generators)
def test_generate_patterns_245(self):
dataset = StringReader('token c.A436C token').read()
NLTKSplitter().split(dataset)
TmVarTokenizer().tokenize(dataset)
TmVarDictionaryFeatureGenerator().generate(dataset)
token_features = [{key: value for key, value in token.features.items() if value is not 'O'}
for token in dataset.tokens()]
self.assertEqual(token_features[0], {})
self.assertEqual(token_features[1], {'pattern4[0]': 'B', 'pattern2[0]': 'B'})
self.assertEqual(token_features[2], {'pattern4[0]': 'I', 'pattern2[0]': 'I'})
self.assertEqual(token_features[3], {'pattern4[0]': 'I', 'pattern2[0]': 'I', 'pattern5[0]': 'B'})
self.assertEqual(token_features[4], {'pattern4[0]': 'I', 'pattern2[0]': 'I', 'pattern5[0]': 'I'})
self.assertEqual(token_features[5], {'pattern4[0]': 'E', 'pattern2[0]': 'I', 'pattern5[0]': 'E'})
self.assertEqual(token_features[6], {})