dest='logfile',
help='file to write log messages to')
(options, args) = parser.parse_args()
if not options.corpus_f:
parser.print_help()
parser.error('Must provide --corpus')
if not options.annotations_f:
parser.print_help()
parser.error('Must provide --annotations')
if not options.term_strings_f:
parser.print_help()
parser.error('Must provide --term-strings')
return options
options = _cli()
log.start(options.logfile)
log.writeConfig([
('Corpus file', options.corpus_f),
('Annotations file', options.annotations_f),
('Term strings file', options.term_strings_f),
], 'JET annotation validation')
log.writeln('Reading term->strings mapping from %s...' %
options.term_strings_f)
term_map = readTermMap(options.term_strings_f)
log.writeln('Mapped strings for {0:,} terms.\n'.format(len(term_map)))
log.writeln('Validating corpus annotations...')
validate(options.corpus_f, options.annotations_f, term_map)
log.writeln('Done!\n')
if len(args) != 1:
_bail('Must supply only MENTIONS')
elif (options.use_entity_embeddings
and len(options.entity_embfs) == 0):
_bail('Must supply --entities')
elif (options.use_ctx_embeddings and not options.ctx_embf):
_bail('Must supply --ctxs')
elif (options.dev_size <= 0 or options.dev_size >= 1):
_bail('--dev-size must be between (0,1)')
(mentionf, ) = args
return mentionf, options
## Getting configuration settings
mentionf, options = _cli()
log.start(logfile=options.logfile, stdout_also=True)
entity_settings = [('Entities %d' % i, options.entity_embfs[i])
for i in range(len(options.entity_embfs))]
log.writeConfig(
[
('Mention file', mentionf),
('Entity embedding settings', entity_settings),
('Word/ctx embeddings', options.ctx_embf),
('Word vocabulary (unused if empty)', options.word_vocabf),
('Writing predictions to', options.preds_file),
('Using feature normalization', options.normalize_features),
('Classification algorithm', options.classifier),
('Training settings', [
('Cross validation splits file',
options.cross_validation_file),
('Number of folds', options.n_folds),
'-l',
'--logfile',
dest='logfile',
help='name of file to write log contents to (empty for stdout)',
default=None)
(options, args) = parser.parse_args()
if not options.splitsf:
parser.print_help()
parser.error('Must provide --splits')
if len(args) != 2:
parser.print_help()
exit()
return args, options
(mentionf, predsf), options = _cli()
log.start(logfile=options.logfile)
log.writeConfig([
('Mention file', mentionf),
('Key remapping file', options.keymapf),
('Predictions file', predsf),
('No scores in predictions', options.no_scores),
('Cross-validation splits file', options.splitsf),
('Evaluating on development data', options.dev),
], 'BTRIS Mobility code-level predictions analysis')
log.writeln('Reading mentions from %s...' % mentionf)
mentions = mention_file.read(mentionf)
log.writeln('Read {0:,} mentions.\n'.format(len(mentions)))
log.writeln('Reading splits from %s...' % options.splitsf)
elif not options.output_file:
parser.error('Must provide --output')
elif not options.vocab_file:
parser.error('Must provide --vocab-file')
elif options.overlap < 0 or options.overlap >= 1:
parser.error('--overlap must be between [0,1)')
return options
options = _cli()
output_tokens = '%s.tokens' % options.output_file
output_subsequences = '%s.subsequences' % options.output_file
output_overlaps = '%s.overlaps' % options.output_file
output_log = '%s.log' % options.output_file
log.start(output_log)
log.writeConfig([
('Input file', options.input_file),
('Output settings', [
('Base path', options.output_file),
('Tokenized file', output_tokens),
('Subsequences file', output_subsequences),
('Overlaps file', output_overlaps),
('Log file', output_log),
]),
('Max subsequence length', options.max_sequence_length),
('Overlap fraction', options.overlap),
('BERT vocab file', options.vocab_file)
])
options.max_sequence_length -= 2