clustering.py 文件源码

def ckmeans(X, K, datasetID=-1, params=()):
    global kmeans_init

    pnames  = [     'init', 'max_iter', 'n_jobs',  'distance']
    #dflts  = ['k-means++',        300,       -1, 'euclidean']
    dflts   = [       'KA',        300,       -1, 'euclidean']
    if isinstance(params, np.ndarray):
        paramsloc = params.tolist()
    else:
        paramsloc = params
    (init, max_iter, n_jobs, distance) = ds.resolveargumentpairs(pnames, dflts, paramsloc)

    if datasetID in kmeans_init:
        init = kmeans_init[datasetID][0:K]
    elif init == 'KA':
        init = initclusterKA(X, K, distance)
    elif init == 'KA_memorysaver':
        init = initclusterKA_memorysaver(X, K, distance)

    C = skcl.KMeans(K, init=init, max_iter=max_iter, n_jobs=n_jobs).fit(X).labels_
    return clustVec2partMat(C, K)