def processOneFile_fda(fileName, annotation_dir, nlp_tool, isTraining, types,
type_filter, isFDA2018, isNorm):
documents = []
annotation_file = get_fda_file(join(annotation_dir, fileName))
# each section is a document
for section in annotation_file.sections:
document = Document()
document.name = fileName[:fileName.find('.')] + "_" + section.id
if section.text is None:
document.text = ""
document.entities = []
document.sentences = []
documents.append(document)
continue
document.text = section.text
entities = []
if isFDA2018 == False and isNorm == True:
for reaction in annotation_file.reactions:
entity = Entity()
entity.name = reaction.name
for normalization in reaction.normalizations:
entity.norm_ids.append(
normalization.meddra_pt_id) # can be none
entity.norm_names.append(normalization.meddra_pt)
entities.append(entity)
else:
for entity in annotation_file.mentions:
if entity.section != section.id:
continue
if types and (entity.type not in type_filter):
continue
entities.append(entity)
document.entities = entities
if opt.nlp_tool == "nltk":
if isTraining:
sentences = get_sentences_and_tokens_from_nltk(
section.text, nlp_tool, document.entities,
annotation_file.ignore_regions, section.id)
else:
sentences = get_sentences_and_tokens_from_nltk(
section.text, nlp_tool, None,
annotation_file.ignore_regions, section.id)
else:
raise RuntimeError("invalid nlp tool")
document.sentences = sentences
documents.append(document)
return documents, annotation_file
def processOneFile_fda(fileName, annotation_dir, types, type_filter, isFDA2018,
isNorm):
documents = []
annotation_file = get_fda_file(os.path.join(annotation_dir, fileName))
# each section is a document
for section in annotation_file.sections:
document = Document()
document.name = fileName[:fileName.find('.')] + "_" + section.id
if section.text is None:
document.text = ""
document.entities = []
document.sentences = []
documents.append(document)
continue
document.text = section.text
entities = []
if isFDA2018 == False and isNorm == True:
for reaction in annotation_file.reactions:
entity = Entity()
entity.name = reaction.name
for normalization in reaction.normalizations:
entity.norm_ids.append(
normalization.meddra_pt_id) # can be none
entity.norm_names.append(normalization.meddra_pt)
entities.append(entity)
else:
for entity in annotation_file.mentions:
if entity.section != section.id:
continue
if types and (entity.type not in type_filter):
continue
entities.append(entity)
document.entities = entities
document.sentences = []
documents.append(document)
return documents, annotation_file
def processOneFile(fileName, annotation_dir, corpus_dir, nlp_tool, isTraining,
types, type_filter):
document = Document()
document.name = fileName[:fileName.find('.')]
ct_snomed = 0
ct_meddra = 0
ct_unnormed = 0
if annotation_dir:
annotation_file = get_bioc_file(join(annotation_dir, fileName))
bioc_passage = annotation_file[0].passages[0]
entities = []
for entity in bioc_passage.annotations:
if types and (entity.infons['type'] not in type_filter):
continue
entity_ = Entity()
entity_.id = entity.id
processed_name = entity.text.replace('\\n', ' ')
if len(processed_name) == 0:
logging.debug("{}: entity {} name is empty".format(
fileName, entity.id))
continue
entity_.name = processed_name
entity_.type = entity.infons['type']
entity_.spans.append(
[entity.locations[0].offset, entity.locations[0].end])
if ('SNOMED code' in entity.infons and entity.infons['SNOMED code'] != 'N/A')\
and ('SNOMED term' in entity.infons and entity.infons['SNOMED term'] != 'N/A'):
entity_.norm_ids.append(entity.infons['SNOMED code'])
entity_.norm_names.append(entity.infons['SNOMED term'])
ct_snomed += 1
elif ('MedDRA code' in entity.infons and entity.infons['MedDRA code'] != 'N/A')\
and ('MedDRA term' in entity.infons and entity.infons['MedDRA term'] != 'N/A'):
entity_.norm_ids.append(entity.infons['MedDRA code'])
entity_.norm_names.append(entity.infons['MedDRA term'])
ct_meddra += 1
else:
logging.debug("{}: no norm id in entity {}".format(
fileName, entity.id))
ct_unnormed += 1
continue
entities.append(entity_)
document.entities = entities
corpus_file = get_text_file(join(corpus_dir, fileName.split('.bioc')[0]))
document.text = corpus_file
if opt.nlp_tool == "spacy":
if isTraining:
sentences = get_sentences_and_tokens_from_spacy(
corpus_file, nlp_tool, document.entities)
else:
sentences = get_sentences_and_tokens_from_spacy(
corpus_file, nlp_tool, None)
elif opt.nlp_tool == "nltk":
if isTraining:
sentences = get_sentences_and_tokens_from_nltk(
corpus_file, nlp_tool, document.entities, None, None)
else:
sentences = get_sentences_and_tokens_from_nltk(
corpus_file, nlp_tool, None, None, None)
elif opt.nlp_tool == "stanford":
if isTraining:
sentences = get_sentences_and_tokens_from_stanford(
corpus_file, nlp_tool, document.entities)
else:
sentences = get_sentences_and_tokens_from_stanford(
corpus_file, nlp_tool, None)
else:
raise RuntimeError("invalid nlp tool")
document.sentences = sentences
return document, ct_snomed, ct_meddra, ct_unnormed