5

R 中的“顺序”看起来像 Stata 中的“排序”。例如,这是一个数据集(仅列出了变量名称):

v1 v2 v3 v4 v5 v6 v7 v8 v9 v10 v11 v12 v13 v14 v15 v16 v17 v18

这是我期望的输出:

v1 v2 v3 v4 v5 v7 v8 v9 v10 v11 v12 v17 v18 v13 v14 v15 v6 v16

在 R 中,我有两种方法:

data <- data[,c(1:5,7:12,17:18,13:15,6,16)]

或者

names <- c("v1", "v2", "v3", "v4", "v5", "v7", "v8", "v9", "v10", "v11", "v12",  "v17", "v18", "v13", "v14", "v15", "v6", "v16")
data <- data[names]

为了在 Stata 中获得相同的输出,我可以运行 2 行:

order v17 v18, before(v13)
order v6 v16, last

在上面的理想数据中,我们可以知道我们要处理的变量的位置。但在大多数实际情况下,我们有像“年龄”“性别”这样没有位置指示符的变量,而且我们在一个数据集中可能有超过 50 个变量。那么Stata中“订单”的优势可能会更加明显。我们不需要知道变量的确切位置,只需输入它的名称:

order age, after(gender)

R 中是否有一个基本函数来处理这个问题,或者我可以得到一个包吗?提前致谢。

tweetinfo <- data.frame(uid=1:50, mid=2:51, annotations=3:52, bmiddle_pic=4:53, created_at=5:54, favorited=6:55, geo=7:56, in_reply_to_screen_name=8:57, in_reply_to_status_id=9:58, in_reply_to_user_id=10:59, original_pic=11:60, reTweetId=12:61, reUserId=13:62, source=14:63, thumbnail_pic=15:64, truncated=16:65)
noretweetinfo <- data.frame(uid=21:50, mid=22:51, annotations=23:52, bmiddle_pic=24:53, created_at=25:54, favorited=26:55, geo=27:56, in_reply_to_screen_name=28:57, in_reply_to_status_id=29:58, in_reply_to_user_id=30:59, original_pic=31:60, reTweetId=32:61, reUserId=33:62, source=34:63, thumbnail_pic=35:64, truncated=36:65)
retweetinfo <- data.frame(uid=41:50, mid=42:51, annotations=43:52, bmiddle_pic=44:53, created_at=45:54, deleted=46:55, favorited=47:56, geo=48:57, in_reply_to_screen_name=49:58, in_reply_to_status_id=50:59, in_reply_to_user_id=51:60, original_pic=52:61, source=53:62, thumbnail_pic=54:63, truncated=55:64)
tweetinfo$type <- "ti"
noretweetinfo$type <- "nr"
retweetinfo$type <- "rt"
gtinfo <- rbind(tweetinfo, noretweetinfo)
gtinfo$deleted=""
gtinfo <- gtinfo[,c(1:16,18,17)]
retweetinfo <- transform(retweetinfo, reTweetId="", reUserId="")
retweetinfo <- retweetinfo[,c(1:5,7:12,17:18,13:15,6,16)]
gtinfo <- rbind(gtinfo, retweetinfo)
write.table(gtinfo, file="C:/gtinfo.txt", row.names=F, col.names=T, sep="\t", quote=F)
# rm(list=ls(all=T))
4

6 回答 6

3

因为我在拖延和尝试不同的事情,所以这是我掀起的一个功能。最终,它取决于append

moveme <- function(invec, movecommand) {
  movecommand <- lapply(strsplit(strsplit(movecommand, ";")[[1]], ",|\\s+"), 
                        function(x) x[x != ""])
  movelist <- lapply(movecommand, function(x) {
    Where <- x[which(x %in% c("before", "after", "first", "last")):length(x)]
    ToMove <- setdiff(x, Where)
    list(ToMove, Where)
  })
  myVec <- invec
  for (i in seq_along(movelist)) {
    temp <- setdiff(myVec, movelist[[i]][[1]])
    A <- movelist[[i]][[2]][1]
    if (A %in% c("before", "after")) {
      ba <- movelist[[i]][[2]][2]
      if (A == "before") {
        after <- match(ba, temp)-1
      } else if (A == "after") {
        after <- match(ba, temp)
      }    
    } else if (A == "first") {
      after <- 0
    } else if (A == "last") {
      after <- length(myVec)
    }
    myVec <- append(temp, values = movelist[[i]][[1]], after = after)
  }
  myVec
}

以下是一些代表数据集名称的示例数据:

x <- paste0("v", 1:18)

现在想象一下,我们想要“v17”和“v18”在“v3”之前,最后是“v6”和“v16”,开头是“v5”:

moveme(x, "v17, v18 before v3; v6, v16 last; v5 first")
#  [1] "v5"  "v1"  "v2"  "v17" "v18" "v3"  "v4"  "v7"  "v8"  "v9"  "v10" "v11" "v12"
# [14] "v13" "v14" "v15" "v6"  "v16"

因此,对于data.frame名为“df”的明显用法是:

df[moveme(names(df), "how you want to move the columns")]

而且,对于一个data.table名为“DT”(正如@mnel 指出的那样,它的内存效率会更高):

setcolorder(DT, moveme(names(DT), "how you want to move the columns"))

请注意,复合移动由分号指定。

公认的动作是:

  • before(将指定的列移动到另一个命名列之前)
  • after(将指定的列移动到另一个命名列之后)
  • first(将指定的列移动到第一个位置)
  • last(将指定的列移动到最后一个位置)
于 2013-08-24T16:29:44.917 回答
2

我明白你的问题。我现在可以提供代码:

move <- function(data,variable,before) {
  m <- data[variable]
  r <- data[names(data)!=variable]
  i <- match(before,names(data))
  pre <- r[1:i-1]
  post <- r[i:length(names(r))]
  cbind(pre,m,post)
}

# Example.
library(MASS)
data(painters)
str(painters)

# Move 'Expression' variable before 'Drawing' variable.
new <- move(painters,"Expression","Drawing")
View(new)
于 2012-09-22T20:20:18.177 回答
2

您可以编写自己的函数来执行此操作。

以下将使用与 stata 类似的语法为您提供列名的新顺序

  • where是一个有 4 种可能性的命名列表

    • list(last = T)
    • list(first = T)
    • list(before = x)x有问题的变量名称在 哪里
    • list(after = x)x有问题的变量名称在 哪里
  • sorted = Tvar_list将按字典顺序排序(命令alphabetic和命令sequential的组合)stata

该函数仅适用于名称,(一旦您将data.frame对象传递为data,并返回重新排序的名称列表

例如

stata.order <- function(var_list, where, sorted = F, data) {
    all_names = names(data)
    # are all the variable names in
    check <- var_list %in% all_names
    if (any(!check)) {
        stop("Not all variables in var_list exist within  data")
    }
    if (names(where) == "before") {
        if (!(where %in% all_names)) {
            stop("before variable not in the data set")
        }
    }
    if (names(where) == "after") {
        if (!(where %in% all_names)) {
            stop("after variable not in the data set")
        }
    }

    if (sorted) {
        var_list <- sort(var_list)
    }
    where_in <- which(all_names %in% var_list)
    full_list <- seq_along(data)
    others <- full_list[-c(where_in)]

    .nwhere <- names(where)
    if (!(.nwhere %in% c("last", "first", "before", "after"))) {
        stop("where must be a list of a named element first, last, before or after")
    }

    do_what <- switch(names(where), last = length(others), first = 0, before = which(all_names[others] == 
        where) - 1, after = which(all_names[others] == where))

    new_order <- append(others, where_in, do_what)
    return(all_names[new_order])
}

tmp <- as.data.frame(matrix(1:100, ncol = 10))

stata.order(var_list = c("V2", "V5"), where = list(last = T), data = tmp)

##  [1] "V1"  "V3"  "V4"  "V6"  "V7"  "V8"  "V9"  "V10" "V2"  "V5" 

stata.order(var_list = c("V2", "V5"), where = list(first = T), data = tmp)

##  [1] "V2"  "V5"  "V1"  "V3"  "V4"  "V6"  "V7"  "V8"  "V9"  "V10"

stata.order(var_list = c("V2", "V5"), where = list(before = "V6"), data = tmp)

##  [1] "V1"  "V3"  "V4"  "V2"  "V5"  "V6"  "V7"  "V8"  "V9"  "V10"

stata.order(var_list = c("V2", "V5"), where = list(after = "V4"), data = tmp)

##  [1] "V1"  "V3"  "V4"  "V2"  "V5"  "V6"  "V7"  "V8"  "V9"  "V10"

# throws an error
stata.order(var_list = c("V2", "V5"), where = list(before = "v11"), data = tmp)

## Error: before variable not in the data set

如果您想有效地进行内存重新排序(通过引用,无需复制),请使用data.table

DT <- data.table(tmp)
# sets by reference, no copying
setcolorder(DT, stata.order(var_list = c("V2", "V5"), where = list(after = "V4"), 
    data = DT))

DT

##     V1 V3 V4 V2 V5 V6 V7 V8 V9 V10
##  1:  1 21 31 11 41 51 61 71 81  91
##  2:  2 22 32 12 42 52 62 72 82  92
##  3:  3 23 33 13 43 53 63 73 83  93
##  4:  4 24 34 14 44 54 64 74 84  94
##  5:  5 25 35 15 45 55 65 75 85  95
##  6:  6 26 36 16 46 56 66 76 86  96
##  7:  7 27 37 17 47 57 67 77 87  97
##  8:  8 28 38 18 48 58 68 78 88  98
##  9:  9 29 39 19 49 59 69 79 89  99
## 10: 10 30 40 20 50 60 70 80 90 100
于 2012-10-02T04:55:22.967 回答
0

这应该给你相同的文件:

#snip
gtinfo <- rbind(tweetinfo, noretweetinfo)
gtinfo$deleted=""
retweetinfo <- transform(retweetinfo, reTweetId="", reUserId="")
gtinfo <- rbind(gtinfo, retweetinfo)
gtinfo <-gtinfo[,c(1:16,18,17)]
#snip

可以在 R 中实现像 Strata 的 order 函数这样的函数,但我认为对此的需求并不大。

于 2012-09-23T09:48:41.160 回答
0

目前还不清楚你想做什么,但你的第一句话让我假设你想对数据集进行排序。

实际上,有一个内置order函数,它返回有序序列的索引。你在找这个吗?

> x <- c(3,2,1)

> order(x)
[1] 3 2 1

> x[order(x)]
[1] 1 2 3
于 2012-09-22T18:34:52.940 回答
0

packagedplyr和 functiondplyr::relocate是 中引入的一个新动词dplyr 1.0.0,完全符合您的要求。

library(dplyr)

data %>% relocate(v17, v18, .before = v13)

data %>% relocate(v6, v16, .after = last_col())

data %>% relocate(age, .after = gender)

于 2020-04-20T07:00:28.310 回答