k-means:每次执行相同的集群 [英] k-means: Same clusters for every execution

问题描述

是否有可能为特定数据集的每次执行获得相同的 kmeans 集群.就像对于随机值一样，我们可以使用固定种子.是否可以停止聚类的随机性?

Is it possible to get same kmeans clusters for every execution for a particular data set. Just like for a random value we can use a fixed seed. Is it possible to stop randomness for clustering?

推荐答案

是的.在进行聚类之前，使用 set.seed 为随机值设置种子.

Yes. Use set.seed to set a seed for the random value before doing the clustering.

使用kmeans中的例子:

set.seed(1)
x <- rbind(matrix(rnorm(100, sd = 0.3), ncol = 2),
           matrix(rnorm(100, mean = 1, sd = 0.3), ncol = 2))
colnames(x) <- c("x", "y")


set.seed(2)
XX <- kmeans(x, 2)

set.seed(2)
YY <- kmeans(x, 2)

测试相等性:

identical(XX, YY)
[1] TRUE

这篇关于k-means:每次执行相同的集群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！