def test_something(self):
parser = SpacySentenceParser()
sentence = 'M._tuberculosis is the cause of tuberculosis and chronic_obstructive_syndrome, ' \
'also M._tuberculosis is a propionic acid producer.'
bacteria = EntityCollection([Entity('M._tuberculosis', '111', BACTERIA_TAG),
Entity('M._tuberculosis', '111', BACTERIA_TAG)], tag=BACTERIA_TAG)
nutrients = EntityCollection([Entity('propionic', '123', NUTRIENT_TAG)])
diseases = EntityCollection([Entity('tuberculosis', 'a', DISEASE_TAG),
Entity('tuberculosis', 'a', DISEASE_TAG),
Entity('tuberculosis', 'a', DISEASE_TAG),
Entity('chronic_obstructive_syndrome', 'a1', DISEASE_TAG),
Entity('obstructive_syndrome', 'b1', DISEASE_TAG)])
not_overlapped_collections = [EntityCollection([bacteria.entities[0], bacteria.entities[1]]),
EntityCollection([diseases.entities[1], diseases.entities[3]]),
EntityCollection([nutrients.entities[0]])]
parser_output = parser.parse_sentence(sentence, not_overlapped_collections[0].entities +
not_overlapped_collections[1].entities +
not_overlapped_collections[2].entities)
expected_bact_tags = [0, 10]
expected_nut_tags = [13]
expected_dis_tags = [5, 7]
actual_bact_tags = [i for i, tag in parser_output.tags.items() if tag == BACTERIA_TAG]
actual_nut_tags = [i for i, tag in parser_output.tags.items() if tag == NUTRIENT_TAG]
actual_dis_tags = [i for i, tag in parser_output.tags.items() if tag == DISEASE_TAG]
self.assertCountEqual(expected_bact_tags, actual_bact_tags)
self.assertCountEqual(expected_nut_tags, actual_nut_tags)
self.assertCountEqual(expected_dis_tags, actual_dis_tags)
from nltk import StanfordTokenizer
from ohmygut.core.sentence_processing import SpacySentenceParser
from ohmygut.paths import stanford_jar_path
"""
A help script to plot sentence graph
TODO: make as command line utility?
"""
sentence = "B.-vulgatus protects against Escherichia coli-induced colitis in gnotobiotic interleukin-2 deficient mice."
# sentence = "Intriguingly, others have previously reported that pediatric IBD patients " \
# "have increased serum antibody titers against a TonB-dependent receptor from " \
# "human commensal Bacteroides caccae named OmpW."
stanford_tokenizer = StanfordTokenizer(path_to_jar=stanford_jar_path)
parser = SpacySentenceParser()
parser_output = parser.parse_sentence(sentence, entities='')
parser_output.draw("path.png")