bnlearn的并行化(并行包)

Jon*_*nas 4 parallel-processing r

我正在使用该R软件包bnlearn来估计贝叶斯网络结构.它使用parallel包内置并行化.但是,这不起作用.

使用联机帮助页中的示例bnlearn::parallel integration:

library(parallel)
library(bnlearn)

cl = makeCluster(2)

# check it works.
clusterEvalQ(cl, runif(10))    # -> this works

data(learning.test)
res = gs(learning.test, cluster = cl)
Run Code Online (Sandbox Code Playgroud)

我在这里得到错误 "Error in check.cluster(cluster) : cluster is not a valid cluster object."

有人知道怎么做这个吗?

Rol*_*and 6

这是一个错误.请将其报告给软件包维护者.

这是代码check.cluster:

function (cluster) 
{
    if (is.null(cluster)) 
        return(TRUE)
    if (any(class(cluster) %!in% supported.clusters)) 
        stop("cluster is not a valid cluster object.")
    if (!requireNamespace("parallel")) 
        stop("this function requires the parallel package.")
    if (!isClusterRunning(cluster)) 
        stop("the cluster is stopped.")
}
Run Code Online (Sandbox Code Playgroud)

现在,如果你看一下这个类cl:

class(cl)
#[1] "SOCKcluster" "cluster" 
Run Code Online (Sandbox Code Playgroud)

让我们重现一下检查:

bnlearn:::supported.clusters
#[1] "MPIcluster"  "PVMcluster"  "SOCKcluster"

`%!in%` <- function (x, table) {
  match(x, table, nomatch = 0L) == 0L
}
any(class(cl) %!in% bnlearn:::supported.clusters)
#[1] TRUE
Run Code Online (Sandbox Code Playgroud)

cluster不在supported.clusters.我相信,该函数应该只检查集群是否有受支持的类,而不是它是否具有不受支持的类.

作为一种解决方案,您可以改变supported.clusters:

assignInNamespace("supported.clusters", 
                  c("cluster", "MPIcluster",  
                    "PVMcluster", "SOCKcluster"), 
                  "bnlearn")
Run Code Online (Sandbox Code Playgroud)