如何在K均值算法中优化K [英] How to optimal K in K - Means Algorithm

问题描述

可能重复:
在使用k-means聚类时如何确定k?

Possible Duplicate:
How do I determine k when using k-means clustering?

如果我不知道数据，我该如何初始选择K?

How can i choose the K initially, if i do not know about the data?

有人可以帮助我选择K.

Can someone help me in choosing the K.

谢谢 纳文

推荐答案

基本思想是评估样本数据上的聚类评分，通常是聚类内部的距离和聚类之间的距离.该度量值越多，群集越好，基于此确定，您可以选择最佳的串参数.可以在此处找到指标之一 http://alias- i.com/lingpipe/docs/api/com/aliasi/cluster/ClusterScore.html

The base idea is to evaluate cluster scoring on sample data, usally it is distance inside cluster and distance between clusters. The more this measure the better clustering, based on this mesure you can select best clustring paramters. One of metrics can be found here http://alias-i.com/lingpipe/docs/api/com/aliasi/cluster/ClusterScore.html

这篇关于如何在K均值算法中优化K的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！