dbscan.py 文件源码

def main(argv=None):
    if argv is None:
        argv = sys.argv

    try:
        words, vectors, options = process_options(argv[1:])
    except Exception, e:
        if str(e):
            print >> sys.stderr, 'Error: %s' % str(e)
            return 1
        else:
            raise

    dbscan = sklearn.cluster.DBSCAN(eps=options.eps, metric=options.metric)
    dbscan.fit(numpy.array(vectors))
    noisy = sum(1 for l in dbscan.labels_ if l == -1)
    unique = len(set(dbscan.labels_))
    logging.info('%d clusters, %d noisy, %d vectors' % (unique, noisy,
                                                        len(vectors)))
    if noisy >= len(vectors) / 4:
        logging.warning('%d/%d noisy (-1) labels (try higher eps?)' % \
                            (noisy, len(vectors)))
    elif unique < (len(vectors)/2)**0.5:
        logging.warning('only %d clusters (try lower eps?)' % unique)
    write_cluster_ids(words, dbscan.labels_)

    return 0