kmeans.py 文件源码

def process_options(args):    
    options = argparser().parse_args(args)

    if options.max_rank is not None and options.max_rank < 1:
        raise ValueError('max-rank must be >= 1')
    if options.k is not None and options.k < 2:
        raise ValueError('cluster number must be >= 2')

    if options.method == MINIBATCH_KMEANS and not with_sklearn:
        logging.warning('minibatch kmeans not available, using kmeans (slow)')
        options.method = KMEANS

    if options.jobs != 1 and (options.method != KMEANS or not with_sklearn):
        logging.warning('jobs > 1 only supported scikit-learn %s' % KMEANS)
        options.jobs = 1

    wv = wvlib.load(options.vectors[0], max_rank=options.max_rank)

    if options.k is None:
        options.k = int(math.ceil((len(wv.words())/2)**0.5))
        logging.info('set k=%d (%d words)' % (options.k, len(wv.words())))

    if options.normalize:
        logging.info('normalize vectors to unit length')
        wv.normalize()

    words, vectors = wv.words(), wv.vectors()

    if options.whiten:
        logging.info('normalize features to unit variance')
        vectors = scipy.cluster.vq.whiten(vectors)

    return words, vectors, options