methods_kharita.py 文件源码

def splitclustersparallel(datapointwts,seeds):
    X = [(xx[0], xx[1]) for xx in datapointwts];    S = [(xx[0], xx[1]) for xx in seeds];cluster = {};p2cluster = []; gedges = {}; gedges1 = {}; nedges = {}; std = {}; seeds1 = []; seedweight = []; roadwidth = [];
    nbrs = NearestNeighbors(n_neighbors=20, algorithm='ball_tree').fit(S)
    distances, indices = nbrs.kneighbors(X)
    for cd in range(len(seeds)):
        cluster[cd] = []; roadwidth.append(0);
    for ii, ll in enumerate(indices):
        dd = [taxidist(seeds[xx], datapointwts[ii][:-1],theta) for xx in ll]
        cd = ll[dd.index(min(dd))];
        cluster[cd].append(datapointwts[ii])
        p2cluster.append(cd)
    for cl in cluster:
        mang = seeds[cl][-1];
        scl = seeds[cl]
        if len(cluster[cl]) > 10:
            std[cl] = np.percentile([angledist(xx[2], mang) for xx in cluster[cl]], 90)
            roadwidth[cl] = 1+5*np.std([geodist(scl,xx)*np.sin(anglebetweentwopoints(scl,xx)-scl[-1])  for xx in cluster[cl]])
            print(cl,scl,[(anglebetweentwopoints(scl,xx),scl[-1])  for xx in cluster[cl]])