r - 第 1 组的唯一值，然后是第 1 组和第 2 组，依此类推

Question

我有一个包含 5 个不同组的数据框:

   id group
1  L1     1
2  L2     1
3  L1     2
4  L3     2
5  L4     2
6  L3     3
7  L5     3
8  L6     3
9  L1     4
10 L4     4
11 L2     5

我想知道是否有可能获得唯一的 id从第 1 组开始，第 1 组和第 2 组，第 1 组、第 2 组和第 3 组等等，没有循环。我正在用 dplyr 寻找方法或 data.table包裹。

预期成绩 :

    group      id
1   1          c("L1", "L2")
2   1,2        c("L1", "L2", "L3", "L4")
3   1,2,3      c("L1", "L2", "L3", "L4", "L5")
4   1,2,3,4    c("L1", "L2", "L3", "L4", "L5")
5   1,2,3,4,5  c("L1", "L2", "L3", "L4", "L5")  

数据 :

structure(list(id = c("L1", "L2", "L1", "L3", "L4", "L3", "L5", 
"L6", "L1", "L4", "L2"), group = structure(c(1L, 1L, 2L, 2L, 
2L, 3L, 3L, 3L, 4L, 4L, 5L), .Label = c("1", "2", "3", "4", "5"
), class = "factor")), .Names = c("id", "group"), row.names = c(NA, 
-11L), class = "data.frame")

Answer 1

使用基础 R，您可以执行以下操作:

# create the "growing" sets of groups
combi_groups <- lapply(seq_along(unique(df$group)), function(i) unique(df$group)[1:i])

# get the unique ID for each set of groups
uniq_ID <- setNames(lapply(combi_groups, function(x) unique(df$id[df$group %in% x])), 
                    sapply(combi_groups, paste, collapse=","))

# $`1`
# [1] "L1" "L2"

# $`1,2`
# [1] "L1" "L2" "L3" "L4"

# $`1,2,3`
# [1] "L1" "L2" "L3" "L4" "L5" "L6"

# $`1,2,3,4`
# [1] "L1" "L2" "L3" "L4" "L5" "L6"

# $`1,2,3,4,5`
# [1] "L1" "L2" "L3" "L4" "L5" "L6" 

如果您想按照预期的输出进行格式化:

data.frame(group=sapply(combi_groups, paste, collapse=", "), id=sapply(uniq_ID, function(x) paste0("c(", paste0("\"", x, "\"", collapse=", "), ")")))
#          group                                    id
#1             1                         c("L1", "L2")
#2          1, 2             c("L1", "L2", "L3", "L4")
#3       1, 2, 3 c("L1", "L2", "L3", "L4", "L5", "L6")
#4    1, 2, 3, 4 c("L1", "L2", "L3", "L4", "L5", "L6")
#5 1, 2, 3, 4, 5 c("L1", "L2", "L3", "L4", "L5", "L6")

格式化的另一种可能性:

data.frame(group=rep(names(uniq_ID), sapply(uniq_ID, length)), id=unlist(uniq_ID))

或者，如果您想拥有 uniq_ID在列中:

library(data.table)
data.table(group=sapply(combi_groups, paste, collapse=", "), id=uniq_ID)
#           group                id
#1:             1             L1,L2
#2:          1, 2       L1,L2,L3,L4
#3:       1, 2, 3 L1,L2,L3,L4,L5,L6
#4:    1, 2, 3, 4 L1,L2,L3,L4,L5,L6
#5: 1, 2, 3, 4, 5 L1,L2,L3,L4,L5,L6

data.table(group=sapply(combi_groups, paste, collapse=", "), id=uniq_ID)[2, id]
[[1]]
[1] "L1" "L2" "L3" "L4"