def main():
argv = parse_args(__doc__, version='version 2')
print(argv)
lemmatizer = Lemmatizer()
ptb2dep = NegBioPtb2DepConverter(lemmatizer, universal=True)
splitter = NegBioSSplitter(newline=argv['--newline_is_sentence_break'])
parser = NegBioParser(model_dir=argv['--bllip-model'])
argv = get_absolute_path(argv, '--neg-patterns',
'negbio/patterns/neg_patterns.txt')
argv = get_absolute_path(argv, '--uncertainty-patterns',
'negbio/patterns/uncertainty_patterns.txt')
mm = pymetamap.MetaMap.get_instance(argv['--metamap'])
neg_detector = negdetect.Detector(argv['--neg-patterns'],
argv['--uncertainty-patterns'])
if argv['--cuis'] == 'None':
cuis = None
else:
cuis = read_cuis(argv['--cuis'])
if argv['text']:
collection = text2bioc.text2collection(argv['SOURCES'])
elif argv['bioc']:
with open(argv['SOURCE']) as fp:
collection = bioc.load(fp)
else:
raise KeyError
pipeline(collection, mm, splitter, parser, ptb2dep, neg_detector, cuis)
with open(os.path.expanduser(argv['--output']), 'w') as fp:
bioc.dump(collection, fp)
def main(argv):
argv = docopt.docopt(__doc__, argv=argv)
print(argv)
splitter = ssplit.NltkSSplitter(newline=True)
parser = parse.Bllip(model_dir=argv['--model'])
ptb2dep = ptb2ud.Ptb2DepConverter(universal=True)
lemmatizer = ptb2ud.Lemmatizer()
neg_detector = negdetect.Detector(argv['--neg-patterns'],
argv['--uncertainty-patterns'])
scan.scan_document(
source=argv['SOURCE'],
directory=argv['--out'],
suffix='.neg.xml',
fn=pipeline,
non_sequences=[splitter, parser, ptb2dep, lemmatizer, neg_detector])
def main(argv):
argv = docopt.docopt(__doc__, argv=argv)
print(argv)
splitter = ssplit.NltkSSplitter(newline=argv['--newline_is_sentence_break'])
parser = parse.Bllip(model_dir=argv['--bllip-model'])
ptb2dep = ptb2ud.Ptb2DepConverter(universal=True)
lemmatizer = ptb2ud.Lemmatizer()
mm = pymetamap.MetaMap.get_instance(argv['--metamap'])
neg_detector = negdetect.Detector(argv['--neg-patterns'], argv['--uncertainty-patterns'])
if argv['--cuis'] == 'None':
cuis = None
else:
cuis = dner_mm.read_cuis(argv['--cuis'])
collection = text2bioc.text2collection(argv['SOURCE'], split_document=argv['--split-document'])
pipeline(collection, mm, splitter, parser, ptb2dep, lemmatizer, neg_detector, cuis)
with open(os.path.expanduser(argv['--out']), 'w') as fp:
bioc.dump(collection, fp)