请问大家，有谁做过 k-means的并行计算？ 需要利用parallel包，想请教一下，谢谢！

library(parallel)

library(BLR)



data(wheat)



mc = mclapply(2:6, function(x,centers)kmeans(x, centers), x=X)



> summary(mc)

     Length Class  Mode

[1,] 9      kmeans list

[2,] 9      kmeans list

[3,] 9      kmeans list

[4,] 9      kmeans list

[5,] 9      kmeans list

(pars = expand.grid(i=1:3, cent=2:4))



  i cent

1 1    2

2 2    2

3 3    2

4 1    3

5 2    3

6 3    3

7 1    4

8 2    4

9 3    4



L=list()

# zikes horrible

pars2=apply(pars,1,append, L)

mc = mclapply(pars2, function(x,pars)kmeans(x, centers=pars$cent,nstart=pars$i ), x=X)



> summary(mc)

      Length Class  Mode

 [1,] 9      kmeans list

 [2,] 9      kmeans list

 [3,] 9      kmeans list

 [4,] 9      kmeans list

 [5,] 9      kmeans list

 [6,] 9      kmeans list

 [7,] 9      kmeans list

 [8,] 9      kmeans list

 [9,] 9      means list

或者是用clusterApply函数：

library(parallel)

nw <- detectCores()

cl <- makeCluster(nw)

clusterSetRNGStream(cl, iseed=1234)

set.seed(88)

mydata <- matrix(rnorm(5000 * 100), nrow=5000, ncol=100)



# Parallelize over the "nstart" argument

nstart <- 100

# Create vector of length "nw" where sum(nstartv) == nstart

nstartv <- rep(ceiling(nstart / nw), nw)

results <- clusterApply(cl, nstartv,

        function(n, x) kmeans(x, 3, nstart=n, iter.max=1000),

        mydata)

# Pick the best result

i <- sapply(results, function(result) result$tot.withinss)

result <- results[[which.min(i)]]

print(result$tot.withinss)