发表在2014年Science上的聚类方法Clustering by fast search and find of density peaks,不在这赘述介绍了,其matlab代码详细注释下面给出,如果想看该方法的详细解释说明,推荐在阅读原文的基础上,参考这位博主的博文
http://blog.csdn.net/itplus/article/details/38926837
本文版权所有 转载请注明出处
无法看清的,请见我博客
http://blog.sina.com.cn/s/blog_6ca0f5eb0102vdt8.html
如果运行代码报错,
查出Y1 = mdscale(dist, 2, ‘criterion‘,‘metricsstress‘);这句报错
??? Error using ==> mdscale>metricStressCrit at 686
Points in the configuration have co-located. Try a different starting point, or use a different criterion.
Error in ==> mdscale>MDS at 498
[stress,grad] = feval_r(stressFun, Y, disparities, weights);
Error in ==> mdscale at 404
[Y,stress,iter] = MDS(Y0,dissimilarities,weights,stressFun,metric,weighted,options);
Error in ==> cluster_dp at 181
可以修改最后一个参数,把它改成‘metricsstress‘ 或 ‘sammon‘ 或 ‘strain‘