选择n个后续分组变量并在r中应用函数

以下是示例数据：

 myd <- data.frame (matrix (sample (c("AB", "BB", "AA"), 100*100, 
 replace = T), ncol = 100))
 variablenames= paste (rep (paste ("MR.", 1:10,sep = ""), 
  each = 10), 1:100, sep = ".")
  names(myd) <- variablenames

---

myd我建议重新编码myfun以获取矩阵并使用plotrix软件包中的Pastecol

library(plotrix)

myfun = function(x){
    out = pasteCols(t(x), sep = ":")
    # some code
    return(out)
}  

然后，非常简单：对于每个组，使用模和整数除法计算调用myfun时要使用的第一列和最后一列的索引：

rubiques_solution = function(group, myd, num_to_group){
   # loop over groups
   for(g in unique(group)){
      var_index = which(group == g)
      num_var = length(var_index)

      # test to make sure num_to_group is smaller than the number of variable
      if(num_var < num_to_group){
         stop("num_to_group > number of variable in at least one group")
         }

      # number of calls to myfun
      num_calls = num_var %/% num_to_group

      # the idea here is that we create the first and last column
      # in which we are interested for each call
      first = seq(from = var_index[1], by = num_to_group, length = num_calls)
      last = first + num_to_group -1
      # the last call will contain possibly more varialbe, we adjust here:
      last[length(last)] = last[length(last)] + (num_var %% num_to_group)

      for(i in num_calls){
         # maybe do something with the return value of myfun ?
         myfun(myd[,first[i]:last[i]])
      }
   }  
}  

group = rep(1:10, each = 10) # same than yours
myd = data.frame (matrix (sample (c("AB", "BB", "AA"), 100*100, replace = T), ncol = 100)) # same than yours
num_to_group = 2 # this is your first example
rubiques_solution(group, myd, num_to_group)

rubiques\u solution=函数（组、myd、num\u到组）{
#循环组
对于（唯一（组）中的g）{
var_指数=哪个（组==g）
num\u var=长度（var\u索引）
#测试以确保num_to_group小于变量的数量
if（数值变量<数值到数值组）{
停止（“num_to_group>至少一个组中的变量数”）
}
#呼叫myfun的次数
num\u calls=num\u var%/%num\u到组
#这里的想法是我们创建第一列和最后一列
#我们对每个电话都感兴趣
first=seq（from=var\u index[1]，by=num\u to\u group，length=num\u调用）
最后=第一个+第二组的数量-1
#最后一个调用可能包含更多变量，我们在这里进行调整：
上次[长度（上次）]=上次[长度（上次）]+（数值变量%%num数值到数值组）
for（i在num_调用中）{
#也许用myfun的返回值做点什么？
myfun（myd[，first[i]：last[i]]）
}
}  
}  
组=代表（1:10，每个=10）#与您的相同
myd=data.frame（矩阵（样本（c（“AB”、“BB”、“AA”），100*100，替换=T，ncol=100））#与您的相同
num_to_group=2#这是您的第一个示例
rubiques_解决方案（组、myd、num_到组）

希望我正确理解了这个问题。
创建一个函数，将您的数据分割成适当的列表，并对列表应用您想要的任何函数

此函数将创建第二个分组变量。（问题中提供了第一个分组变量（
group
），如果更改该值，还应在下面的函数中更改
DIM
）

以下是我们将拆分的组
myd
。在本例中，我们首先将
myd
拆分为10个列组，然后将每组拆分为3个列组，最后一个组除外，该组将有4个列（3+3+4=10）

注意：要更改分组依据的列数，例如，一次按两个变量分组，请将
group2=rep（myfun（3），length.out=100）更改为
group2=rep（myfun（2），length.out=100）

现在我们有了清单，我们可以做很多有趣的事情。您想将列粘贴在一起，并用冒号分隔。下面是你怎么做到的

# Do what you want with the list
# For example, to paste the columns together:
FINAL = lapply(temp, function(x) apply(x, 1, paste, collapse=":"))
names(FINAL) = NAMES

以下是输出的示例：

lapply(FINAL, function(x) head(x, 5))
# $MR.1.1_MR.1.2_MR.1.3
# [1] "AA:AB:AB" "AB:BB:AA" "BB:AB:AA" "BB:AA:AB" "AA:AA:AA"
# 
# $MR.2.11_MR.2.12_MR.2.13
# [1] "BB:AA:AB" "BB:AB:BB" "BB:AA:AA" "AB:BB:AA" "BB:BB:AA"
# 
# $MR.3.21_MR.3.22_MR.3.23
# [1] "AA:AB:BB" "BB:AA:AA" "AA:AB:BB" "AB:AA:AA" "AB:BB:BB"
# 
# <<<<<<<------SNIP------>>>>>>>>
#
# $MR.1.4_MR.1.5_MR.1.6
# [1] "AB:BB:AA" "BB:BB:BB" "AA:AA:AA" "BB:BB:AB" "AB:AA:AA"
# 
# $MR.2.14_MR.2.15_MR.2.16
# [1] "AA:BB:AB" "BB:BB:BB" "BB:BB:AB" "AA:BB:AB" "BB:BB:BB"
# 
# $MR.3.24_MR.3.25_MR.3.26
# [1] "AA:AB:BB" "BB:AA:BB" "BB:AB:BB" "AA:AB:AA" "AB:AA:AA"
# 
# <<<<<<<------SNIP------>>>>>>>>
#
# $MR.1.7_MR.1.8_MR.1.9_MR.1.10
# [1] "AB:AB:AA:AB" "AB:AA:BB:AA" "BB:BB:AA:AA" "AB:BB:AB:AA" "AB:BB:AB:BB"
# 
# $MR.2.17_MR.2.18_MR.2.19_MR.2.20
# [1] "AB:AB:BB:BB" "AB:AB:BB:BB" "AB:AA:BB:BB" "AA:AA:AB:AA" "AB:AB:AB:AB"
# 
# $MR.3.27_MR.3.28_MR.3.29_MR.3.30
# [1] "BB:BB:AB:BB" "BB:BB:AA:AA" "AA:BB:AB:AA" "AA:BB:AB:AA" "AA:AB:AA:BB"
# 
# $MR.4.37_MR.4.38_MR.4.39_MR.4.40
# [1] "BB:BB:AB:AA" "AA:BB:AA:BB" "AA:AA:AA:AB" "AB:AA:BB:AB" "BB:BB:BB:BB"
# 
# $MR.5.47_MR.5.48_MR.5.49_MR.5.50
# [1] "AB:AA:AA:AB" "AB:AA:BB:AA" "AB:BB:AA:AA" "AB:BB:BB:BB" "BB:AA:AB:AA"
# 
# $MR.6.57_MR.6.58_MR.6.59_MR.6.60
# [1] "BB:BB:AB:AA" "BB:AB:BB:AA" "AA:AB:AB:BB" "BB:AB:AA:AB" "AB:AA:AB:BB"
# 
# $MR.7.67_MR.7.68_MR.7.69_MR.7.70
# [1] "BB:AB:BB:AA" "BB:AB:BB:AA" "BB:AB:BB:AB" "AB:AA:AA:AA" "AA:AA:AA:AB"
# 
# $MR.8.77_MR.8.78_MR.8.79_MR.8.80
# [1] "AA:AB:AA:AB" "AB:AA:AB:BB" "BB:BB:AA:AB" "AB:BB:BB:BB" "AB:AA:BB:AB"
# 
# $MR.9.87_MR.9.88_MR.9.89_MR.9.90
# [1] "AA:BB:AB:AA" "AA:AB:BB:BB" "AA:BB:AA:BB" "AB:AB:AA:BB" "AB:AA:AB:BB"
# 
# $MR.10.97_MR.10.98_MR.10.99_MR.10.100
# [1] "AB:AA:BB:AB" "AB:AA:AB:BB" "BB:AB:AA:AA" "BB:BB:AA:AA" "AB:AB:BB:AB"

lappy（最终，功能（x）头（x，5））
#$MR.1.1_MR.1.2_MR.1.3
#[1]“AA:AB:AB”“AB:BB:AA”“BB:AB:AA”“BB:AA:AB”“AA:AA:AA”
# 
#$MR.2.11_MR.2.12_MR.2.13
#[1]“BB:AA:AB”“BB:AB:BB”“BB:AA:AA”“AB:BB:AA”“BB:BB:AA”
# 
#$MR.3.21_MR.3.22_MR.3.23
#[1]“AA:AB:BB”“BB:AA:AA”“AA:AB:BB”“AB:AA:AA”“AB:BB”
# 
# >
#
#$MR.1.4_MR.1.5_MR.1.6
#[1]“AB:BB:AA”“BB:BB:BB”“AA:AA”“BB:BB:AB”“AB:AA:AA”
# 
#$MR.2.14_MR.2.15_MR.2.16
#[1]“AA:BB:AB”“BB:BB:BB”“BB:BB:AB”“AA:BB:AB”“BB:BB:BB”
# 
#$MR.3.24_MR.3.25_MR.3.26
#[1]“AA:AB:BB”“BB:AA:BB”“BB:AB:BB”“AA:AB:AA”“AB:AA”
# 
# >
#
#$MR.1.7_MR.1.8_MR.1.9_MR.1.10
#[1]“AB:AB:AA:AB”“AB:AA:BB:AA”“BB:BB:AA:AA”“AB:BB:AB:AA”“AB:BB:AB:AA”
# 
#$MR.2.17_MR.2.18_MR.2.19_MR.2.20
#[1]“AB:AB:BB:BB”“AB:AB:BB:BB”“AB:AA:BB:BB”“AA:AA:AB:AA”“AB:AB:AB:AB”
# 
#$MR.3.27_MR.3.28_MR.3.29_MR.3.30
#[1]“BB:BB:AB:BB”“BB:BB:AA:AA”“AA:BB:AB:AA”“AA:BB:AB:AA”“AA:AB:BB”
# 
#$MR.4.37_MR.4.38_MR.4.39_MR.4.40
#[1]“BB:BB:AB:AA”“AA:BB:AA:BB”“AA:AA:AB”“AB:AA:BB:AB”“BB:BB:BB:BB”
# 
#$MR.5.47\ MR.5.48\ MR.5.49\ MR.5.50
#[1]“AB:AA:AA:AB”“AB:AA:BB:AA”“AB:BB:AA:AA”“AB:BB:BB:BB”“BB:AA:BB”
# 
#$MR.6.57_MR.6.58_MR.6.59_MR.6.60
#[1]“BB:BB:AB:AA”“BB:AB:BB:AA”“AA:AB:AB:BB”“BB:AB:AA:AB”“AB:AA:AB”
# 
#$MR.7.67_MR.7.68_MR.7.69_MR.7.70
#[1]“BB:AB:BB:AA”“BB:AB:BB:AA”“BB:AB:BB:AB”“AB:AA:AA”“AA:AA:AA:AB”
# 
#$MR.8.77_MR.8.78_MR.8.79_MR.8.80
#[1]“AA:AB:AA:AB”“AB:AA:AB:BB”“BB:BB:AA:AB”“AB:BB:BB”“AB:AA:BB:BB”
# 
#$MR.9.87_MR.9.88_MR.9.89_MR.9.90
#[1]“AA:BB:AB:AA”“AA:AB:BB:BB”“AA:BB:AA:BB”“AB:AB:AA:BB”“AB:AA:BB”
# 
#$MR.10.97_MR.10.98_MR.10.99_MR.10.100
#[1]“AB:AA:BB:AB”“AB:AA:AB:BB”“BB:AB:AA:AA”“BB:BB:AA:AA”“AB:AB:BB:AB”
虽然没有明确的答案，但只是一个想法-你可以创建变量名称Mat Rubique的名称，你能举例说明你的函数是如何应用的吗？你看不到输出，因为在你的例子中，你似乎只调用myfun，所以我就是这么做的，如果你需要像其他答案一样输入一个列表的话（或在数据帧中…相同的东西）
library(plotrix)

myfun = function(x){
    out = pasteCols(t(x), sep = ":")
    # some code
    return(out)
}  

rubiques_solution = function(group, myd, num_to_group){
   # loop over groups
   for(g in unique(group)){
      var_index = which(group == g)
      num_var = length(var_index)

      # test to make sure num_to_group is smaller than the number of variable
      if(num_var < num_to_group){
         stop("num_to_group > number of variable in at least one group")
         }

      # number of calls to myfun
      num_calls = num_var %/% num_to_group

      # the idea here is that we create the first and last column
      # in which we are interested for each call
      first = seq(from = var_index[1], by = num_to_group, length = num_calls)
      last = first + num_to_group -1
      # the last call will contain possibly more varialbe, we adjust here:
      last[length(last)] = last[length(last)] + (num_var %% num_to_group)

      for(i in num_calls){
         # maybe do something with the return value of myfun ?
         myfun(myd[,first[i]:last[i]])
      }
   }  
}  

group = rep(1:10, each = 10) # same than yours
myd = data.frame (matrix (sample (c("AB", "BB", "AA"), 100*100, replace = T), ncol = 100)) # same than yours
num_to_group = 2 # this is your first example
rubiques_solution(group, myd, num_to_group)

myfun = function(LENGTH, DIM = 10) {
  PATTERN = rep(1:(DIM %/% LENGTH), each=LENGTH)
  c(PATTERN, rep(max(PATTERN), DIM %% LENGTH))
}

group <- rep(1:10, each = 10)
# CHANGE THE FOLLOWING LINE ACCORDING
# TO THE NUMBER OF GROUPS THAT YOU WANT
group2 = rep(myfun(3), length.out=100)

# Extract group names for matching purposes
temp = split(names(myd), list(group, group2))

# Match the names to myd
temp = lapply(1:length(temp),
              function(x) myd[, which(names(myd) %in% temp[[x]])])

# Extract the names from the list for future reference
NAMES = lapply(temp, function(x) paste(names(x), collapse="_"))

# Do what you want with the list
# For example, to paste the columns together:
FINAL = lapply(temp, function(x) apply(x, 1, paste, collapse=":"))
names(FINAL) = NAMES

lapply(FINAL, function(x) head(x, 5))
# $MR.1.1_MR.1.2_MR.1.3
# [1] "AA:AB:AB" "AB:BB:AA" "BB:AB:AA" "BB:AA:AB" "AA:AA:AA"
# 
# $MR.2.11_MR.2.12_MR.2.13
# [1] "BB:AA:AB" "BB:AB:BB" "BB:AA:AA" "AB:BB:AA" "BB:BB:AA"
# 
# $MR.3.21_MR.3.22_MR.3.23
# [1] "AA:AB:BB" "BB:AA:AA" "AA:AB:BB" "AB:AA:AA" "AB:BB:BB"
# 
# <<<<<<<------SNIP------>>>>>>>>
#
# $MR.1.4_MR.1.5_MR.1.6
# [1] "AB:BB:AA" "BB:BB:BB" "AA:AA:AA" "BB:BB:AB" "AB:AA:AA"
# 
# $MR.2.14_MR.2.15_MR.2.16
# [1] "AA:BB:AB" "BB:BB:BB" "BB:BB:AB" "AA:BB:AB" "BB:BB:BB"
# 
# $MR.3.24_MR.3.25_MR.3.26
# [1] "AA:AB:BB" "BB:AA:BB" "BB:AB:BB" "AA:AB:AA" "AB:AA:AA"
# 
# <<<<<<<------SNIP------>>>>>>>>
#
# $MR.1.7_MR.1.8_MR.1.9_MR.1.10
# [1] "AB:AB:AA:AB" "AB:AA:BB:AA" "BB:BB:AA:AA" "AB:BB:AB:AA" "AB:BB:AB:BB"
# 
# $MR.2.17_MR.2.18_MR.2.19_MR.2.20
# [1] "AB:AB:BB:BB" "AB:AB:BB:BB" "AB:AA:BB:BB" "AA:AA:AB:AA" "AB:AB:AB:AB"
# 
# $MR.3.27_MR.3.28_MR.3.29_MR.3.30
# [1] "BB:BB:AB:BB" "BB:BB:AA:AA" "AA:BB:AB:AA" "AA:BB:AB:AA" "AA:AB:AA:BB"
# 
# $MR.4.37_MR.4.38_MR.4.39_MR.4.40
# [1] "BB:BB:AB:AA" "AA:BB:AA:BB" "AA:AA:AA:AB" "AB:AA:BB:AB" "BB:BB:BB:BB"
# 
# $MR.5.47_MR.5.48_MR.5.49_MR.5.50
# [1] "AB:AA:AA:AB" "AB:AA:BB:AA" "AB:BB:AA:AA" "AB:BB:BB:BB" "BB:AA:AB:AA"
# 
# $MR.6.57_MR.6.58_MR.6.59_MR.6.60
# [1] "BB:BB:AB:AA" "BB:AB:BB:AA" "AA:AB:AB:BB" "BB:AB:AA:AB" "AB:AA:AB:BB"
# 
# $MR.7.67_MR.7.68_MR.7.69_MR.7.70
# [1] "BB:AB:BB:AA" "BB:AB:BB:AA" "BB:AB:BB:AB" "AB:AA:AA:AA" "AA:AA:AA:AB"
# 
# $MR.8.77_MR.8.78_MR.8.79_MR.8.80
# [1] "AA:AB:AA:AB" "AB:AA:AB:BB" "BB:BB:AA:AB" "AB:BB:BB:BB" "AB:AA:BB:AB"
# 
# $MR.9.87_MR.9.88_MR.9.89_MR.9.90
# [1] "AA:BB:AB:AA" "AA:AB:BB:BB" "AA:BB:AA:BB" "AB:AB:AA:BB" "AB:AA:AB:BB"
# 
# $MR.10.97_MR.10.98_MR.10.99_MR.10.100
# [1] "AB:AA:BB:AB" "AB:AA:AB:BB" "BB:AB:AA:AA" "BB:BB:AA:AA" "AB:AB:BB:AB"