methods_kharita.py 文件源码

def getpossibleedges(datapointwts,seeds):
#    datapointwts = densify(datapointwts);
    X = [(xx[0], xx[1]) for xx in datapointwts];    S = [(xx[0], xx[1]) for xx in seeds];cluster = {};p2cluster = []; gedges = {}; gedges1 = {}; nedges = {};
    nbrs = NearestNeighbors(n_neighbors=5, algorithm='ball_tree').fit(S)
    distances, indices = nbrs.kneighbors(X)
    for cd in range(len(seeds)):
        cluster[cd] = []
    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 ii, xx in enumerate(datapointwts):
        if ii>1:
            if datapointwts[ii-1][-1]<datapointwts[ii][-1] and datapointwts[ii-1][-1]>datapointwts[ii][-1]-11:
                cd1 = p2cluster[ii-1]; cd2 = p2cluster[ii];
            if not cd1== cd2:
                gedges1[(cd1,cd2)] =  gedges1.get((cd1,cd2),0)+1;
    return(gedges1)