说明：  Affinity Propagation (AP) 聚类是2007年在Science杂志上提出的一种新的聚类算法。它根据N个数据点之间的相似度进行聚类,这些相似度可以是对称的,即两个数据点互相之间的相似度一样(如欧氏距离) 也可以是不对称的,即两个数据点互相之间的相似度不等。
(Affinity Propagation (AP) Clustering is a new clustering algorithm in 2007 in Science magazine raised. It clustering based on the similarity between the N data points, these similarities may be symmetrical, ie, the similarity between the two data points to each other, like (eg Euclidean distance) can also be asymmetrical, ie the similarity between the two data points each month.)