Question

I have made a start to create some training and test sets using 10 fold crossvalidation for an artificial dataset:

rows <- 1000

X1<- sort(runif(n = rows, min = -1, max =1))
occ.prob <- 1/(1+exp(-(0.0 + 3.0*X1)))
true.presence <- rbinom(n = rows, size = 1, prob = occ.prob)

# combine data as data frame and save
data <- data.frame(X1, true.presence)

id <- sample(1:10,nrow(data),replace=TRUE)
ListX <- split(data,id) 
fold1 <- data[id==1,] 
fold2 <- data[id==2,] 
fold3 <- data[id==3,] 
fold4 <- data[id==4,] 
fold5 <- data[id==5,] 
fold6 <- data[id==6,] 
fold7 <- data[id==7,] 
fold8 <- data[id==8,] 
fold9 <- data[id==9,] 
fold10 <- data[id==10,] 

trainingset <- subset(data, id %in% c(2,3,4,5,6,7,8,9,10))
testset <- subset(data, id %in% c(1))

I am just wondering whether there are easier ways to achieve this and how I could perform stratified crossvalidation which ensures that the class priors (true.presence) are roughly the same in all folds?

Answer 1

I’m sure that (a) there’s a more efficient way to code this, and (b) there’s almost certainly a function somewhere in a package that will just return the folds, but here’s some simple code that gives you an idea of how one might do this:

rows <- 1000

X1<- sort(runif(n = rows, min = -1, max =1))
occ.prob <- 1/(1+exp(-(0.0 + 3.0*X1)))
true.presence <- rbinom(n = rows, size = 1, prob = occ.prob)

# combine data as data frame and save
dat <- data.frame(X1, true.presence)

require(plyr)
createFolds <- function(x,k){
    n <- nrow(x)
    x$folds <- rep(1:k,length.out = n)[sample(n,n)]
    x
}

folds <- ddply(dat,.(true.presence),createFolds,k = 10)

#Proportion of true.presence in each fold:
ddply(folds,.(folds),summarise,prop = sum(true.presence)/length(true.presence))

   folds      prop
1      1 0.5049505
2      2 0.5049505
3      3 0.5100000
4      4 0.5100000
5      5 0.5100000
6      6 0.5100000
7      7 0.5100000
8      8 0.5100000
9      9 0.5050505
10    10 0.5050505