聚类-k均值算法

说明：  K-means算法是基于划分的思想，因此算法易于理解且实现方法简单易行，但需要人工选择初始的聚类数目即算法是带参数的。类的数目确定往往非常复杂和具有不确定性，因此需要专业的知识和行业经验才能较好的确定。而且因为初始聚类中心的选择是随机的，因此会造成部分初始聚类中心相似或者处于数据边缘，造成算法的迭代次数明显增加，甚至会因为个别数据而造成聚类失败的现象。(K-means algorithm is based on the idea of partitioning, so the algorithm is easy to understand and the implementation method is simple and feasible, but it requires manual selection of the initial number of clusters, that is, the algorithm is with parameters. The number of classes is often very complex and uncertain, so professional knowledge and industry experience are needed to better determine. Moreover, because the selection of initial clustering centers is random, some initial clustering centers will be similar or at the edge of data, resulting in a significant increase in the number of iterations of the algorithm, and even the phenomenon of clustering failure due to individual data.)