Random Sampling

This function takes n samples of size nrow(x) from the elements of x. Two types of sampling are available: sampling with or without replacement.

Usage

sampleData(x, method = c("none", "permutation", "bootstrap"), n = 1L)

Arguments

x

numerical matrix, features-by-samples

method

string, the sampling method to use. Available options are:

Three options are available:

none

a sequence from 1 to nrow(x) is returned

permutation

random sampling without replacement

bootstrap

random sampling with replacement

n

integer, number of repeated samples to generate

Value

A list of length n where each element is a vector of indices representing the sampled data.

See also

sample

Author

Alessandro Barberis

Examples

#set seed for reproducibility
set.seed(seed = 5381L)

#Define row/col size
nr = 20
nc = 10

#Create input matrix
x = matrix(
 data = stats::runif(n = nr*nc, min = 0, max = 1000),
 nrow = nr,
 ncol = nc,
 dimnames = list(
   paste0("g",seq(nr)),
   paste0("S",seq(nc))
 )
)

#Take one sample via permutation
#(duplicated elements are not possible)
sampleData(
 x = x,
 method = 'permutation',
 n = 1
)
#> [[1]]
#>  [1] 11  9  7 10 19 13  2  4 17 18 12  3  5  8 20  6 15 14 16  1
#> 

#Take one sample via bootstrap
#(duplicated elements are possible)
sampleData(
 x = x,
 method = 'bootstrap',
 n = 1
)
#> [[1]]
#>  [1] 19  5 20  5 19  5 11  2  5  7  1 13 16 15  8  8 14 17 16  2
#>