如何使用两个规则有效地将数据帧子集化为列表列表

debugcn 发表于 Dev

克兰茨

我将不胜感激任何帮助有效地将数据帧子集划分为几个块以传递给基于imput和的列表列表Weights_x，其中x = {1, 2, ..., 10}.

这个问题和我的尝试都是基于这个和这个。不同的是，现在我想创建一个列表列表，其中每个列表只有一个值imput和一列变量Weights_x。

我下面的代码从@DarrenTsai 扩展而来，适用于的几列Weights_x，但我有100 imput * 1000 weights要创建的子集。因此，我需要一种更有效的方法，无需太多代码即可完成相同的结果。

我的数据：

dat <- structure(list(id = c(1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 3, 3, 3, 
3, 3, 4, 4, 4, 4, 4), imput = c(1, 2, 3, 4, 5, 1, 2, 3, 4, 5, 
1, 2, 3, 4, 5, 1, 2, 3, 4, 5), A = c(1, 1, 1, 1, 1, 1, 1, 1, 
1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), B = c(1, 1, 1, 1, 1, 0, 
0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0), Pass = c(278, 278, 
278, 278, 278, 100, 100, 100, 100, 100, 153, 153, 153, 153, 153, 
79, 79, 79, 79, 79), Fail = c(740, 743, 742, 743, 740, 7581, 
7581, 7581, 7581, 7581, 1231, 1232, 1235, 1235, 1232, 1731, 1732, 
1731, 1731, 1731), Weights_1 = c(4, 3, 4, 3, 3, 1, 2, 1, 2, 1, 
12, 12, 11, 12, 12, 3, 5, 3, 3, 3), Weights_2 = c(3, 3, 3, 3, 
3, 1, 1, 1, 1, 1, 12, 12, 12, 12, 12, 3, 3, 3, 3, 3), Weights_3 = c(4, 
3, 3, 3, 3, 1, 2, 1, 1, 1, 12, 12, 11, 12, 12, 3, 3, 3, 3, 3), 
    Weights_4 = c(3, 3, 4, 3, 3, 1, 1, 1, 2, 1, 12, 12, 13, 12, 
    12, 3, 2, 3, 3, 3), Weights_5 = c(3, 3, 3, 3, 3, 1, 0, 1, 
    1, 1, 12, 12, 12, 12, 12, 3, 3, 3, 3, 3), Weights_6 = c(4, 
    3, 3, 3, 3, 1, 1, 1, 1, 1, 12, 12, 12, 12, 12, 3, 3, 3, 3, 
    3), Weights_7 = c(3, 3, 3, 3, 3, 1, 1, 1, 1, 1, 12, 12, 12, 
    12, 12, 3, 3, 3, 3, 3), Weights_8 = c(3, 3, 3, 3, 3, 1, 1, 
    1, 1, 1, 15, 12, 12, 12, 12, 3, 3, 3, 3, 3), Weights_9 = c(3, 
    3, 3, 4, 3, 1, 1, 1, 1, 1, 12, 12, 12, 12, 12, 2, 3, 3, 3, 
    3), Weights_10 = c(3, 3, 4, 3, 3, 1, 1, 1, 1, 1, 12, 10, 
    12, 12, 12, 3, 3, 3, 3, 3)), class = "data.frame", row.names = c(NA, 
-20L))

我的方法：

##Weights = `Weights_1`
myvars_1 <- c("id", "imput", "A", "B", "Pass", "Fail", "Weights_1")
dat_1 <- dat[myvars_1]


mylist_1 <- by(dat_1, dat$imput, function(x){
  nn <- x$Fail + x$Pass
  weights <- x$Weights_1
  return(list(N = nrow(x), ncases = x$Pass, A = x$A, B = x$B,
              id = x$id, P = x$imput, nn = nn, weights = weights))
})

##Weights = `Weights_2`
myvars_2 <- c("id", "imput", "A", "B", "Pass", "Fail", "Weights_2")
dat_2 <- dat[myvars_2]


mylist_2 <- by(dat_2, dat$imput, function(x){
  nn <- x$Fail + x$Pass
  weights <- x$Weights_2
  return(list(N = nrow(x), ncases = x$Pass, A = x$A, B = x$B,
              id = x$id, P = x$imput, nn = nn, weights = weights))
})

##Weights = `Weights_3`
myvars_3 <- c("id", "imput", "A", "B", "Pass", "Fail", "Weights_3")
dat_3 <- dat[myvars_3]


mylist_3 <- by(dat_3, dat$imput, function(x){
  nn <- x$Fail + x$Pass
  weights <- x$Weights_3
  return(list(N = nrow(x), ncases = x$Pass, A = x$A, B = x$B,
              id = x$id, P = x$imput, nn = nn, weights = weights))
})

##Weights = `Weights_4`
myvars_4 <- c("id", "imput", "A", "B", "Pass", "Fail", "Weights_4")
dat_4 <- dat[myvars_4]


mylist_4 <- by(dat_4, dat$imput, function(x){
  nn <- x$Fail + x$Pass
  weights <- x$Weights_4
  return(list(N = nrow(x), ncases = x$Pass, A = x$A, B = x$B,
              id = x$id, P = x$imput, nn = nn, weights = weights))
})

##Weights = `Weights_5`
myvars_5 <- c("id", "imput", "A", "B", "Pass", "Fail", "Weights_5")
dat_5 <- dat[myvars_5]


mylist_5 <- by(dat_5, dat$imput, function(x){
  nn <- x$Fail + x$Pass
  weights <- x$Weights_5
  return(list(N = nrow(x), ncases = x$Pass, A = x$A, B = x$B,
              id = x$id, P = x$imput, nn = nn, weights = weights))
})


##Weights = `Weights_6`
myvars_6 <- c("id", "imput", "A", "B", "Pass", "Fail", "Weights_6")
dat_6 <- dat[myvars_6]


mylist_6 <- by(dat_6, dat$imput, function(x){
  nn <- x$Fail + x$Pass
  weights <- x$Weights_6
  return(list(N = nrow(x), ncases = x$Pass, A = x$A, B = x$B,
              id = x$id, P = x$imput, nn = nn, weights = weights))
})


##Weights = `Weights_7`
myvars_7 <- c("id", "imput", "A", "B", "Pass", "Fail", "Weights_7")
dat_7 <- dat[myvars_7]


mylist_7 <- by(dat_7, dat$imput, function(x){
  nn <- x$Fail + x$Pass
  weights <- x$Weights_7
  return(list(N = nrow(x), ncases = x$Pass, A = x$A, B = x$B,
              id = x$id, P = x$imput, nn = nn, weights = weights))
})

##Weights = `Weights_8`
myvars_8 <- c("id", "imput", "A", "B", "Pass", "Fail", "Weights_8")
dat_8 <- dat[myvars_8]


mylist_8 <- by(dat_8, dat$imput, function(x){
  nn <- x$Fail + x$Pass
  weights <- x$Weights_8
  return(list(N = nrow(x), ncases = x$Pass, A = x$A, B = x$B,
              id = x$id, P = x$imput, nn = nn, weights = weights))
})

##Weights = `Weights_9`
myvars_9 <- c("id", "imput", "A", "B", "Pass", "Fail", "Weights_9")
dat_9 <- dat[myvars_9]


mylist_9 <- by(dat_9, dat$imput, function(x){
  nn <- x$Fail + x$Pass
  weights <- x$Weights_9
  return(list(N = nrow(x), ncases = x$Pass, A = x$A, B = x$B,
              id = x$id, P = x$imput, nn = nn, weights = weights))
})

##Weights = `Weights_10`
myvars_10 <- c("id", "imput", "A", "B", "Pass", "Fail", "Weights_10")
dat_10 <- dat[myvars_10]


mylist_10 <- by(dat_10, dat$imput, function(x){
  nn <- x$Fail + x$Pass
  weights <- x$Weights_10
  return(list(N = nrow(x), ncases = x$Pass, A = x$A, B = x$B,
              id = x$id, P = x$imput, nn = nn, weights = weights))
})

##create list of lists
mylistslist <- list(mylist_1, mylist_2, mylist_3, mylist_4, mylist_5, 
                    mylist_6, mylist_7, mylist_8, mylist_9, mylist_10)

在此先感谢您的帮助。

没有人

使用lapply一种解决方案可能是

myvars <- c("id", "imput", "A", "B", "Pass", "Fail")
cols <- which(names(dat) %in% myvars)
ind <- grep('^Weights_\\d+$', names(dat))
out <- lapply(ind, function (k) {
  dat_1 <- dat[c(cols,k)]
  by(dat_1, dat$imput, function(x){
    nn <- x$Fail + x$Pass
    weights <- .subset2(x, ncol(x))
    return(list(N = nrow(x), ncases = x$Pass, A = x$A, B = x$B,
                id = x$id, P = x$imput, nn = nn, weights = weights))
  })
})

本文收集自互联网，转载请注明来源。

如有侵权，请联系[email protected] 删除。