for loop with lists R - r

Question

I want to create two lists of data frames in a for loop, but I cannot use assign:
dat <- data.frame(name = c(rep("a", 10), rep("b", 13)),
x = c(1,3,4,4,5,3,7,6,5,7,8,6,4,3,9,1,2,3,5,4,6,3,1),
y = c(1.1,3.2,4.3,4.1,5.5,3.7,7.2,6.2,5.9,7.3,8.6,6.3,4.2,3.6,9.7,1.1,2.3,3.2,5.7,4.8,6.5,3.3,1.2))
a <- dat[dat$name == "a",]
b <- dat[dat$name == "b",]
samp <- vector(mode = "list", length = 100)
h <- list(a,b)
hname <- c("a", "b")
for (j in 1:length(h)) {
for (i in 1:100) {
samp[[i]] <- sample(1:nrow(h[[j]]), nrow(h[[j]])*0.5)
assign(paste("samp", hname[j], sep="_"), samp[[i]])
}
}
Instead of lists named samp_a and samp_b I get vectors which contain the result of the 100th sample. I want to get a list samp_a and samp_b, which have all the different samples for dat[dat$name == a,] and dat[dat$name == a,].
How could I do this?

Answer 1

How about creating two different lists and avoiding using assign:
Option 1:
# create empty list
samp_a <-list()
samp_b <- list()
for (j in seq(h)) {
# fill samp_a list
if(j == 1){
for (i in 1:100) {
samp_a[[i]] <- sample(1:nrow(h[[j]]), nrow(h[[j]])*0.5)
}
# fill samp_b list
} else if(j == 2){
for (i in 1:100) {
samp_b[[i]] <- sample(1:nrow(h[[j]]), nrow(h[[j]])*0.5)
}
}
}
You could use assign too, shorter answer:
Option 2:
for (j in seq(hname)) {
l = list()
for (i in 1:100) {
l[[i]] <- sample(1:nrow(h[[j]]), nrow(h[[j]])*0.5)
}
assign(paste0('samp_', hname[j]), l)
rm(l)
}

Answer 2

You could easily use an lapply for this using the rep function. Unless you want a random x, paired with a random y. This will maintain the existing paired order.
dat <- data.frame(name = c(rep("a", 10), rep("b", 13)),
x = c(1,3,4,4,5,3,7,6,5,7,8,6,4,3,9,1,2,3,5,4,6,3,1),
y = c(1.1,3.2,4.3,4.1,5.5,3.7,7.2,6.2,5.9,7.3,8.6,6.3,4.2,3.6,9.7,1.1,2.3,3.2,5.7,4.8,6.5,3.3,1.2))
a <- dat[dat$name == "a",]
b <- dat[dat$name == "b",]
h <- list(a,b)
hname <- c("a", "b")
testfunc <- function(df) {
#df[sample(nrow(df), nrow(df)*0.5), ] #gives you the values in your data frame
sample(nrow(df), nrow(df)*0.5) # just gives you the indices
}
lapply(h, testfunc) # This gives you the standard lapply format, and only gives one a, and one b
samp <- lapply(rep(h, 100), testfunc) # This shows you how to replicate the function n times, giving you 100 a and 100 b data.frames in a list
samp_a <- samp[c(TRUE, FALSE)] # Applies a repeating T/F vector, selecting the odd data.frames, which in this case are the `a` frames.
samp_b <- samp[c(FALSE, TRUE)] # And here, the even data.frames, which are the `b` frames.