permuting columns of a matrix with replacement and clustering

Question

How can I permute the columns of a matrix with replacement in R? I found one function called rmperm {sna} but it permutes both columns and rows whereas I just want to permute my columns.

Edit: I have to permute the matrix 1000 times and then do hierarchical clustering so I have the final tree after 1000 randomizations.

Many thanks.

Answer 1

Try the sample() function.

> m <- matrix(as.integer(runif(9,0,9)),ncol=3)
> m
     [,1] [,2] [,3]
[1,]    5    0    5
[2,]    6    0    0
[3,]    2    1    3
> permuted <- m[,sample(ncol(m), 10, replace=TRUE)]
> permuted
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,]    5    0    5    5    5    5    0    5    5     5
[2,]    0    0    0    0    6    0    0    0    6     0
[3,]    3    1    3    3    2    3    1    3    2     3

The first argument to sample() specifies the range of the sample (1:x), the second argument specifies the number of items to choose (size), and the replace parameter specifies whether or not we want to use replacement (required if size > x).