如何解决困难随机化，基于频率排序
| 我有一个这样的数据框： x = data.frame（A = c（\“ D1 \”，\“ D1 \”，\“ D1 \”，\“ D1 \”，\“ D1 \”，\“ D2 \”，\“ D3 \ “，\” D3 \“，\” D4 \“，\” D4 \“，\” D4 \“，\” D5 \“，\” D5 \“），B = c（\” A1 \“，\ “ A3 \”，\“ A4 \”，\“ A5 \”，\“ A6 \”，\“ A5 \”，\“ A5 \”，\“ A6 \”，\“ A6 \”，\“ A1 \“，\” A2 \“，\” A5 \“，\” A6 \“））A B
D1 A1
D1 A3
D1 A4
D1 A5
D1 A6
D2 A5
D3 A5
D3 A6
D4 A6
D4 A1
D4 A2
D5 A5
D5 A6
A B freq(B)
D1 A1 2
D4 A1 2
D4 A2 1
D1 A3 1
D1 A4 1
D1 A5 4
D2 A5 4
D3 A5 4
D5 A5 4
D1 A6 4
D3 A6 4
D4 A6 4
D5 A6 4
解决方法
我的
permute
require(permute) ## install from R-forge if not available
x <- data.frame(A = c(\"D1\",\"D1\",\"D2\",\"D3\",\"D4\",\"D5\",\"D5\"),B = c(\"A1\",\"A3\",\"A4\",\"A5\",\"A6\",\"A1\",\"A2\",\"A6\"))
x <- x[order(x$B),]
x <- transform(x,freq = rep((lens <- sapply(with(x,split(B,B)),length)),lens))
set.seed(529)
ind <- permuted.index(NROW(x),control = permControl(strata = factor(x$freq)))
R> x[ind,]
A B freq
10 D4 A1 2
1 D1 A1 2
11 D4 A2 1
2 D1 A3 1
3 D1 A4 1
12 D5 A5 4
4 D1 A5 4
9 D4 A6 4
13 D5 A6 4
5 D1 A6 4
6 D2 A5 4
8 D3 A6 4
7 D3 A5 4
R> ind
[1] 2 1 3 4 5 9 6 12 13 10 7 11 8
ctrl <- permControl(strata = factor(x$freq))
n <- 10
set.seed(83)
IND <- replicate(n,permuted.index(NROW(x),control = ctrl))
> IND
[,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] 2 2 1 2 1 2 1 2 1 1
[2,] 1 1 2 1 2 1 2 1 2 2
[3,] 3 5 4 3 5 5 4 5 5 5
[4,] 5 3 5 5 3 4 5 4 4 4
[5,] 4 4 3 4 4 3 3 3 3 3
[6,] 9 12 11 12 6 10 13 10 8 13
[7,] 10 11 6 11 13 7 7 12 7 9
[8,] 8 9 9 10 8 6 11 13 12 10
[9,] 12 10 8 6 9 13 9 6 9 11
[10,] 13 6 12 9 7 9 8 8 13 8
[11,] 6 7 10 13 12 11 6 11 10 7
[12,] 11 8 13 7 11 8 10 7 6 12
[13,] 7 13 7 8 10 12 12 9 11 6
randSampleSpecial <- function(x,replace = TRUE) {
## have we got access to permute?
stopifnot(require(permute))
## generate a random permutation within the levels of freq
ind <- permuted.index(NROW(x),control = permControl(strata = factor(x$freq)))
## split freq into freq classes
ranks <- with(x,split(freq,freq))
## rank the freq classes
Ranked <- rank(as.numeric(names(ranks)))
## split the Bs on basis of freq classes
Bs <- with(x,freq))
## number of unique Bs in freq class
uniq <- sapply(Bs,function(x) length(unique(x)))
## which contain only a single type of B?
repl <- which(uniq == 1)
## if there are no freq classes with only one level of B,return
if(!(length(repl) > 0))
return(ind)
## if not,continue
## which of the freq classes are adjacent to unique class?
other <- which(Ranked %in% (repl + c(1,-1)))
## generate uniform random numbers to decide if we replace
Rand <- runif(length(ranks[[repl]]))
## Which are the rows in `x` that we want to change?
candidates <- with(x,which(freq == as.numeric(names(uniq[repl]))))
## which are the adjacent values we can replace with
replacements <- with(x,which(freq %in% as.numeric(names(uniq[other]))))
## which candidates to replace? Decision is random
change <- sample(candidates,sum(Rand > 0.5))
## if we are changing a candidate,sample from the replacements and
## assign
if(length(change) > 0)
ind[candidates][change] <- sample(ind[replacements],length(change),replace = replace)
## return
ind
}
R> set.seed(35)
R> randSampleSpecial(x)
[1] 2 1 5 3 4 6 9 12 10 11 7 8 13
replicate()
R> IND <- replicate(10,randSampleSpecial(x))
R> IND
[,] 11 3 6 4 2 1 1 2 10 3
[2,] 1 11 1 12 11 11 2 1 1 13
[3,] 4 5 4 3 4 3 4 5 5 4
[4,] 5 4 5 5 5 4 5 3 3 3
[5,] 3 3 3 4 3 5 3 4 4 5
[6,] 11 7 11 12 9 6 7 8 9 9
[7,] 13 12 12 7 11 7 9 10 8 10
[8,] 10 8 9 8 12 12 8 6 13 8
[9,] 7 9 13 10 8 10 13 9 12 11
[10,] 6 11 10 11 10 13 12 13 10 13
[11,] 12 10 6 6 6 9 11 12 7 12
[12,] 9 6 7 9 7 8 10 7 6 7
[13,] 8 13 8 13 13 11 6 11 11 6
1
2
IND
IND
1
2
count
Permdf <- function(x,v){
# some code to allow Permdf(df,var)
mc <- match.call()
v <- as.quoted(mc$v)
y <- unlist(eval.quoted(v,x))
# make bins with values in v per frequency
freqs <- count(x,v)
bins <- split(freqs[[1]],freqs[[2]])
nbins <- length(bins)
# define the output
dfid <- 1:nrow(x)
for (i in 1:nbins){
# which id\'s to change
id <- which(y %in% bins[[i]])
if(length(bins[[i]]) > 1){
# in case there\'s more than one value for that frequency
dfid[id] <- sample(dfid[id])
} else {
bid <- c(i-1,i,i+1)
# control wether id in range
bid <- bid[bid > 0 & bid <=nbins]
# id values to choose from
vid <- which(y %in% unlist(bins[bid]))
# random selection
dfid[id] <- sample(vid,length(id),replace=TRUE)
}
}
#return
dfid
}
Permdf(x,B)
require(plyr)
x <- merge(x,count(x,\"B\"))
ddply(x,\"freq\",function(x) sample(x))
版权声明：本文内容由互联网用户自发贡献，该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 dio@foxmail.com 举报，一经查实，本站将立刻删除。