def predict(files,
model_path,
output_dir,
format,
third=False,
disambiguate=False):
# Must specify output format
if format not in Note.supportedFormats():
print >> sys.stderr, '\n\tError: Must specify output format'
print >> sys.stderr, '\tAvailable formats: ', ' | '.join(
Note.supportedFormats())
print >> sys.stderr, ''
exit(1)
# Load model
model = Model.load(model_path)
# Tell user if not predicting
if not files:
print >> sys.stderr, "\n\tNote: You did not supply any input files\n"
exit()
if enabled["UMLS"] is not None and disambiguate is True:
from disambiguation import cui_disambiguation
# For each file, predict concept labels
n = len(files)
for i, txt in enumerate(sorted(files)):
note = Note(format)
note.read(txt)
# Output file
extension = note.getExtension()
fname = os.path.splitext(os.path.basename(txt))[0] + '.' + extension
out_path = os.path.join(output_dir, fname)
#if os.path.exists(out_path):
# print '\tWARNING: prediction file already exists (%s)' % out_path
# continue
if format == "semevaL":
note.setFileName(os.path.split(txt)[-1])
# Predict concept labels
labels = model.predict(note, third)
# Get predictions in proper format
output = note.write(labels)
# TODO: make a flag to enable or disable looking up concept ids.
if format == "semeval":
print "\nencoding concept ids"
if enabled["UMLS"] is not None and disambiguate is True:
output = cui_disambiguation.disambiguate(
output, txt, model.get_cui_freq())
# Output the concept predictions
print '\n\nwriting to: ', out_path
with open(out_path, 'w') as f:
print >> f, output
print
