删除R中的重复行，并将删除行的条目添加到保留的行中

Question

我有这样的数据：

df <-

a b c
1 2 3
1 2 4
1 2 5
1 2 9

2 3 3
2 3 4
2 3 5
2 3 9

3 4 3
3 4 4
3 4 5
3 4 9

我希望删除基于列a的重复行，但保留列c中的值，如下所示：

df2 <-

a b c c1 c2 c3
1 2 3 4  5  9
2 3 3 4  5  9
3 4 3 4  5  9

我知道如何删除重复项，如下所示：

df2 <-df[!(df$a=="1"),]

但是现在已经知道如何将值添加到保留的行中。

Answer 1

我们可以在对dataset的行unlist进行子集设置时排除c，然后与整个'c‘列连接

c(unlist(df[!duplicated(df$a), 1:2]), c = df$c)
#  a  b c1 c2 c3 c4 
#  1  2  3  4  5  9 

如果我们需要与预期的名称相同的名称

c(unlist(df[!duplicated(df$a), 1:2]), 
      setNames(df$c, make.unique(rep('c', nrow(df)),  sep="")))
# a  b  c c1 c2 c3 
#  1  2  3  4  5  9 

使用新的示例

library(dplyr)
library(tidyr)
df2 %>% 
    group_by(a) %>%
    summarise(b = first(b), c = list(as.list(c))) %>% 
    unnest_wider(c(c))%>% 
    rename_at(vars(starts_with('.')), ~ str_c('c', seq_along(.)))
# A tibble: 2 x 6
#      a     b    c1    c2    c3    c4
#  <int> <int> <int> <int> <int> <int>
#1     1     2     3     4     5     9
#2     2     2     3     4     5     9

或使用再次更新的示例

df3 %>%
   group_by(a) %>% 
   summarise(b = first(b), c = list(as.list(c))) %>% 
   unnest_wider(c(c))%>% 
   rename_at(vars(starts_with('.')), ~ str_c('c', seq_along(.)))
# A tibble: 3 x 6
#      a     b    c1    c2    c3    c4
#  <int> <int> <int> <int> <int> <int>
#1     1     2     3     4     5     9
#2     2     3     3     4     5     9
#3     3     4     3     4     5     9

或使用data.table

library(data.table)
setDT(df3)[, c(.(b = first(b)),  
       as.data.frame.list(setNames(c, rep('c', .N)))), a] 
#    a b c c.1 c.2 c.3
#1: 1 2 3   4   5   9
#2: 2 3 3   4   5   9
#3: 3 4 3   4   5   9

数据

df <- structure(list(a = c(1L, 1L, 1L, 1L), b = c(2L, 3L, 3L, 4L), 
    c = c(3L, 4L, 5L, 9L)), class = "data.frame", row.names = c(NA, 
-4L))

df2 <- structure(list(a = c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L), b = c(2L, 
3L, 3L, 4L, 2L, 3L, 3L, 4L), c = c(3L, 4L, 5L, 9L, 3L, 4L, 5L, 
9L)), class = "data.frame", row.names = c(NA, -8L))



df3 <- structure(list(a = c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 
3L, 3L), b = c(2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L
), c = c(3L, 4L, 5L, 9L, 3L, 4L, 5L, 9L, 3L, 4L, 5L, 9L)), class = "data.frame", row.names = c(NA, 
-12L))