def extract_disease_ontology_keywords(article):
pc_article = pubcrawler.Article(article)
anno_doc = AnnoDoc(pc_article.body)
resolved_keyword_tier = anno_doc.require_tiers('resolved_keywords',
via=keyword_annotator)
disease_ontology_keyword_dict = {}
for span in resolved_keyword_tier:
for resolution in span.metadata['resolutions']:
entity = resolution['entity']
if entity['type'] == 'disease':
disease_ontology_keyword_dict[entity['id']] = {
"keyword": entity['label'],
"uri": entity['id']
}
return ({
'index.keywords': 1,
'keywords': {
'disease-ontology': list(disease_ontology_keyword_dict.values())
}
})
def extract_geonames(article, store_all=False):
pc_article = pubcrawler.Article(article)
anno_doc = AnnoDoc(pc_article.body)
geoname_tier = anno_doc.require_tiers('geonames', via=geoname_annotator)
geoname_dicts = {}
for span in geoname_tier:
geoname = span.metadata['geoname']
result = {}
if store_all:
for key in GEONAME_ATTRS + ['score']:
result[key] = geoname[key]
else:
result['geonameid'] = geoname['geonameid']
geoname_dicts[result['geonameid']] = result
return ({
'index.geonames': 1,
'geonames': {
'culled': list(geoname_dicts.values())
}
})
def test_incident_2(self):
doc = AnnoDoc('There were 2 new cases in California in 2012.')
case_counts = doc.require_tiers('infections', via=InfectionAnnotator)
attribute_remappings = {'infection': 'case'}
for span in case_counts:
span.metadata['attributes'] = [
attribute_remappings.get(attribute, attribute)
for attribute in span.metadata['attributes']
]
doc.add_tier(self.annotator, case_counts=case_counts)
test_utils.assertHasProps(
doc.tiers['incidents'].spans[0].metadata, {
'value':
2,
'type':
'caseCount',
'dateRange': [
datetime.datetime(2012, 1, 1, 0, 0),
datetime.datetime(2013, 1, 1, 0, 0)
]
})
