コード例 #1
0
            '--logfile',
            dest='logfile',
            help=str.format(
                'name of file to write log contents to (empty for stdout)'),
            default=None)
        (options, args) = parser.parse_args()
        if len(args) != 1 or (not options.entity_embf) or (
                not options.ctx_embf) or (options.entity_defnf
                                          and not options.word_embf):
            parser.print_help()
            exit()
        (mentionf, ) = args
        return mentionf, options

    mentionf, options = _cli()
    log.start(logfile=options.logfile, stdout_also=True)

    if options.tab_separated:
        sep = '\t'
    else:
        sep = ' '

    t_sub = log.startTimer('Reading entity embeddings from %s...' %
                           options.entity_embf,
                           newline=False)
    entity_embeds = pyemblib.read(options.entity_embf, separator=sep)
    log.stopTimer(t_sub,
                  message='Read %d embeddings ({0:.2f}s)' % len(entity_embeds))

    t_sub = log.startTimer('Reading context embeddings from %s...' %
                           options.ctx_embf,
コード例 #2
0
        parser.add_option('--dataset', dest='dataset',
                help='analogy dataset to run on',
                type='choice', choices=datasets.aslist(), default=None)
        parser.add_option('--to-lower', dest='to_lower',
                action='store_true', default=False,
                help='lowercase all analogies')
        parser.add_option('-l', '--logfile', dest='logfile',
                help='name of file to write log contents to (empty for stdout)',
                default=None)
        (options, args) = parser.parse_args()
        if len(args) != 1 or not options.dataset:
            parser.print_help()
            exit()
        return args, options
    (vocabf,), options = _cli()
    log.start(logfile=options.logfile)

    config = configparser.ConfigParser()
    config.read(options.config)

    analogy_file = datasets.getpath(options.dataset, config, eval_mode.ALL_INFO)

    configlogger.writeConfig(log, settings=[
        ('Config file', options.config),
        ('Dataset', options.dataset),
        ('Path to dataset', analogy_file),
        ('Lowercasing analogies', options.to_lower),
        ('Output vocab file', vocabf),
    ], title='Vocabulary extraction from analogy dataset')

    log.writeln('Reading %s analogies from %s...' % (options.dataset, analogy_file))
コード例 #3
0
ファイル: significance.py プロジェクト: OSU-slatelab/JET
                                    '%s -- A vs B' % ds)
        (at, at_size) = correlation(lbl_scores_1, gold_1,
                                    '%s -- A vs GOLD' % ds)
        (bt, bt_size) = correlation(lbl_scores_2, gold_2,
                                    '%s -- B vs GOLD' % ds)

        log.writeln("\n -- %s Agreement summary --" % ds)
        log.writeln("  |r_bt - r_at| = %f" % abs(at - bt))
        log.writeln("  r_ab = %f (%d)" % (ab, ab_size))
        log.writeln("  r_at = %f (%d)" % (at, at_size))
        log.writeln("  r_bt = %f (%d)" % (bt, bt_size))


if __name__ == '__main__':

    def _cli():
        import optparse
        parser = optparse.OptionParser(usage='Usage: %prog LOG1 LOG2')
        parser.add_option('-l', '--logfile', dest='logfile')
        (options, args) = parser.parse_args()
        if len(args) != 2:
            parser.print_help()
            exit()
        return args, options.logfile

    (f1, f2), logfile = _cli()
    log.start(logfile=logfile, stdout_also=True)
    log.writeln('A: %s' % f1)
    log.writeln('B: %s' % f2)
    getStatistics(f1, f2)