Question

我想描述 R 中dt之后每个ID的三元组值N1 - N3之间的关系：

id    N1    N2    N3   
1     3     2     1     
2     3     2     2     
3     3     4     1     
4     2     3     2     
5     1     2     3     
6     2     2     4     
7     2     2     2     
8     2     1     3

我想创建一个新列，它给出了三个N列中值之间关系类型的分类，如下所示：

id    N1    N2    N3    type1
1     3     2     1     A
2     3     2     2     A
3     3     4     1     B
4     2     3     2     B
5     1     2     3     C
6     2     2     4     C
7     2     2     2     D
8     2     1     3     E

类型A适用于N1 ＆gt; N2和N3，N2＆gt;时的三元组N3。

类型B适用于N2 ＆gt; N1和N3的三元组。

类型C适用于N3 ＆gt; N1和N2，N2＆gt;时的三元组N1

当所有三个D值相等时，类型N适用于三元组。

类型E适用于N2 ＆lt; N1和N3

的三元组

Answer 1

data.table解决方案：

require(data.table)
dt <- data.table(id=1:8, N1=c(3,3,3,2,2,2,2,2), N2=c(2,2,4,3,1,2,2,1), N3=c(1,2,1,2,3,4,2,3))
dt[N1 > N2 & N1 > N3 & N2 > N3, type1 := 'A']
dt[N2 > N1 & N2 > N3, type1 := 'B']
dt[N3 > N1 & N3 > N2 & N2 > N1, type1 := 'C']
dt[N1 == N2 & N1 == N3, type1 := 'D']
dt[N2 < N1 & N2 < N3, type1 := 'E']

dt

   id N1 N2 N3 type1
1:  1  3  2  1     A
2:  2  3  2  2    NA
3:  3  3  4  1     B
4:  4  2  3  2     B
5:  5  2  1  3     E
6:  6  2  2  4    NA
7:  7  2  2  2     D
8:  8  2  1  3     E

Answer 2

您可以使用嵌套ifelse语句执行此操作，使用with(dat, ...)以避免重复输入dat$：

dat$type1 = with(dat, ifelse(N1 > N2 & N1 > N3, "A",
                        ifelse(N2 > N1 & N2 > N3, "B",
                          ifelse(N3 > N1 & N3 > N2, "C",
                            ifelse(N1 == N2 & N1 == N3, "D",
                              ifelse(N2 < N1 & N2 < N3, "E", NA))))))
dat
#   id N1 N2 N3 type1
# 1  1  3  2  1     A
# 2  2  3  2  2     A
# 3  3  3  4  1     B
# 4  4  2  3  2     B
# 5  5  2  1  3     C
# 6  6  2  2  4     C
# 7  7  2  2  2     D
# 8  8  2  1  3     C

数据：

dat = structure(list(id = 1:8, N1 = c(3L, 3L, 3L, 2L, 2L, 2L, 2L, 2L
), N2 = c(2L, 2L, 4L, 3L, 1L, 2L, 2L, 1L), N3 = c(1L, 2L, 1L, 
2L, 3L, 4L, 2L, 3L)), .Names = c("id", "N1", "N2", "N3"), row.names = c(NA, 
-8L), class = "data.frame")

Answer 3

使用dplyr：

library(dplyr)
df %>%
  mutate(type1 = ifelse(N1 > N2 & N1 > N3 & N2 > N3, "A",
                        ifelse(N2 > N1 & N2 > N3, "B",
                               ifelse(N3 > N1 & N3 > N2 & N2 > N1, "C",
                                      ifelse(N1 == N2 & N1 == N3, "D",
                                             ifelse(N2 < N1 & N2 < N3, "E", NA))))))

<强>输出

  id N1 N2 N3 type1
1  1  3  2  1     A
2  2  3  2  2  <NA>
3  3  3  4  1     B
4  4  2  3  2     B
5  5  2  1  3     E
6  6  2  2  4  <NA>
7  7  2  2  2     D
8  8  2  1  3     E

数据

df <- structure(list(id = 1:8, N1 = c(3L, 3L, 3L, 2L, 2L, 2L, 2L, 2L
), N2 = c(2L, 2L, 4L, 3L, 1L, 2L, 2L, 1L), N3 = c(1L, 2L, 1L, 2L, 3L, 4L, 2L, 3L)), .Names = c("id", "N1", "N2", "N3"), row.names = c(NA, -8L), class = "data.frame")

三列中行配对值的比较

3 个答案: