问将数据集拆分为多个数据集，其中r中有随机列

EN

mydf <- data.frame (matrix(sample(1:10, 130, replace = TRUE), ncol = 13))

## Number of columns for each sub-dataset
size <- 3

nb.cols <- ncol(mydf)
nb.groups <- nb.cols %/% size
reshuffled <- sample.int(nb.cols, replace=FALSE)
groups <- c(rep(1:nb.groups, each=size), rep(nb.groups+1, nb.cols %% size))
dfs <- lapply(split(reshuffled, groups), function(v) mydf[,v,drop=FALSE])

for (i in 1:length(dfs)) write.csv(dfs[[i]], file=paste("data",i,".csv",sep=""))

mydf <- data.frame (matrix(sample(1:10, 130, replace = TRUE), ncol = 13))
size <- 3
by(t(mydf), 
   INDICES=sample(as.numeric(gl((ncol(mydf) %/% size) + 1, size, ncol(mydf))), 
                  ncol(mydf), 
                  replace=FALSE), 
   FUN=function(x) write.csv(t(x), paste(rownames(x), collapse='-'), row.names=F))

set.seed(1234)
#I increased the number of rows in the data frame to 100
mydf <- data.frame (matrix(sample(x = 1:100, size = 1300, replace = TRUE), 
                    ncol = 13))

index_list      <- list()       #Will store the indices for all partitions
indices         <- 1:nrow(mydf) #Initially contains all indices for the dataset 'mydf'
numb_partitions <- 7            #Specifies the number of partitions

sequence <- floor(((nrow(mydf)*1:numb_partitions)/numb_partitions))
sequence <- c(0, sequence)

#'sequence_diff' will contain the number of instances for each partition.
sequence_diff <- vector()
for(j in 1:numb_partitions){
    sequence_diff[j] <- sequence[j+1] - sequence[j]   
}  

#Inspect 'sequence_diff' and verify it's elements sum up to the total 
#number of rows in 'mydf' (100).
> sequence_diff
[1] 14 14 14 15 14 14 15
> sum(sequence_diff)
[1] 100 #Correct!

for(i in 1:numb_partitions){

  #Use a different seed for each sampling iteration.
  set.seed(seed = i)

  #Sample from object 'indices' of size 1/'numb_partitions'
  indices_partition <- sample(x = indices, 
                              size = sequence_diff[i], 
                              replace = FALSE)

  #Remove the selected indices from 'indices' so these indices will not be 
  #selected in successive iterations.
  indices           <- setdiff(x = indices, y = indices_partition)

  #Store the indices for the i-th iteration in the list 'index_list'. This 
  #is just to verify later that 
  #the procedure has divided all indices in 'numb_partitions' disjunct sets.
  index_list[[i]]   <- indices_partition

  #Dynamically create a new object that is named 'mydfx' in which x is the 
  #i-th partition. 
  assign(x = paste0("mydf", i), value = mydf[indices_partition,])

  write.csv(x = get(x = paste0("mydf", i)),  #Dynamically get the object from environment.
            file = paste0("mydf", i,".csv"), #Dynamically assgin a name to the csv-file.
            sep = ",", 
            col.names = T, 
            row.names = FALSE    
}

#Check whether all index subsets are mutually exclusive: union should have 100 
#unique elements. 
length(unique(unlist(index_list)))
[1] 100 #Correct!