R 如何筛选出在不同（未指定）列中包含两个特定字符串的行？

给定一组8个名称，我想生成5个名称的所有唯一组合。但是，某些名称可能不会同时出现

例如，给定下面的示例数据，如何过滤掉组合了“linda”和“susy”的行

# 7 names
names <- c("joe", "mark", "mary", "john", "linda", "susy", "peter", "annie")

# All unique combinations of 5 names
cbn <- t(combn(names, 5))

#7个名称
names这里有一个带两个参数的小函数：
data
和
x
，它完成了您要查找的内容

f <- function(data, x) {
  data[rowSums(`dim<-`(data %in% x, dim(data))) < length(x), ]
}

结果

#      [,1]   [,2]   [,3]    [,4]    [,5]   
# [1,] "joe"  "mark" "mary"  "john"  "linda"
# [2,] "joe"  "mark" "mary"  "john"  "susy" 
# [3,] "joe"  "mark" "mary"  "john"  "peter"
# [4,] "joe"  "mark" "mary"  "john"  "annie"
# [5,] "joe"  "mark" "mary"  "linda" "peter"
# [6,] "joe"  "mark" "mary"  "linda" "annie"
# [7,] "joe"  "mark" "mary"  "susy"  "peter"
# [8,] "joe"  "mark" "mary"  "susy"  "annie"
# [9,] "joe"  "mark" "mary"  "peter" "annie"
#[10,] "joe"  "mark" "john"  "linda" "peter"
#[11,] "joe"  "mark" "john"  "linda" "annie"
#[12,] "joe"  "mark" "john"  "susy"  "peter"
#[13,] "joe"  "mark" "john"  "susy"  "annie"
#[14,] "joe"  "mark" "john"  "peter" "annie"
#[15,] "joe"  "mark" "linda" "peter" "annie"
#[16,] "joe"  "mark" "susy"  "peter" "annie"
#[17,] "joe"  "mary" "john"  "linda" "peter"
#[18,] "joe"  "mary" "john"  "linda" "annie"
#[19,] "joe"  "mary" "john"  "susy"  "peter"
#[20,] "joe"  "mary" "john"  "susy"  "annie"
#[21,] "joe"  "mary" "john"  "peter" "annie"
#[22,] "joe"  "mary" "linda" "peter" "annie"
#[23,] "joe"  "mary" "susy"  "peter" "annie"
#[24,] "joe"  "john" "linda" "peter" "annie"
#[25,] "joe"  "john" "susy"  "peter" "annie"
#[26,] "mark" "mary" "john"  "linda" "peter"
#[27,] "mark" "mary" "john"  "linda" "annie"
#[28,] "mark" "mary" "john"  "susy"  "peter"
#[29,] "mark" "mary" "john"  "susy"  "annie"
#[30,] "mark" "mary" "john"  "peter" "annie"
#[31,] "mark" "mary" "linda" "peter" "annie"
#[32,] "mark" "mary" "susy"  "peter" "annie"
#[33,] "mark" "john" "linda" "peter" "annie"
#[34,] "mark" "john" "susy"  "peter" "annie"
#[35,] "mary" "john" "linda" "peter" "annie"
#[36,] "mary" "john" "susy"  "peter" "annie"

cbn
#      [,1]   [,2]   [,3]    [,4]    [,5]   
# [1,] "joe"  "mark" "mary"  "linda" "peter"
# [2,] "joe"  "mark" "mary"  "linda" "annie"
# [3,] "joe"  "mark" "mary"  "susy"  "peter"
# [4,] "joe"  "mark" "mary"  "susy"  "annie"
# [5,] "joe"  "mark" "mary"  "peter" "annie"
# [6,] "joe"  "mark" "linda" "peter" "annie"
# [7,] "joe"  "mark" "susy"  "peter" "annie"
# [8,] "joe"  "mary" "linda" "peter" "annie"
# [9,] "joe"  "mary" "susy"  "peter" "annie"
#[10,] "mark" "mary" "john"  "linda" "peter"
#[11,] "mark" "mary" "john"  "linda" "annie"
#[12,] "mark" "mary" "john"  "susy"  "peter"
#[13,] "mark" "mary" "john"  "susy"  "annie"
#[14,] "mark" "mary" "john"  "peter" "annie"
#[15,] "mark" "mary" "linda" "peter" "annie"
#[16,] "mark" "mary" "susy"  "peter" "annie"
#[17,] "mark" "john" "linda" "peter" "annie"
#[18,] "mark" "john" "susy"  "peter" "annie"
#[19,] "mary" "john" "linda" "peter" "annie"
#[20,] "mary" "john" "susy"  "peter" "annie"


当必须迭代检查多个组合时，可以使用for循环

x <- c("linda", "susy")
y <- c("joe", "john")

结果

#      [,1]   [,2]   [,3]    [,4]    [,5]   
# [1,] "joe"  "mark" "mary"  "john"  "linda"
# [2,] "joe"  "mark" "mary"  "john"  "susy" 
# [3,] "joe"  "mark" "mary"  "john"  "peter"
# [4,] "joe"  "mark" "mary"  "john"  "annie"
# [5,] "joe"  "mark" "mary"  "linda" "peter"
# [6,] "joe"  "mark" "mary"  "linda" "annie"
# [7,] "joe"  "mark" "mary"  "susy"  "peter"
# [8,] "joe"  "mark" "mary"  "susy"  "annie"
# [9,] "joe"  "mark" "mary"  "peter" "annie"
#[10,] "joe"  "mark" "john"  "linda" "peter"
#[11,] "joe"  "mark" "john"  "linda" "annie"
#[12,] "joe"  "mark" "john"  "susy"  "peter"
#[13,] "joe"  "mark" "john"  "susy"  "annie"
#[14,] "joe"  "mark" "john"  "peter" "annie"
#[15,] "joe"  "mark" "linda" "peter" "annie"
#[16,] "joe"  "mark" "susy"  "peter" "annie"
#[17,] "joe"  "mary" "john"  "linda" "peter"
#[18,] "joe"  "mary" "john"  "linda" "annie"
#[19,] "joe"  "mary" "john"  "susy"  "peter"
#[20,] "joe"  "mary" "john"  "susy"  "annie"
#[21,] "joe"  "mary" "john"  "peter" "annie"
#[22,] "joe"  "mary" "linda" "peter" "annie"
#[23,] "joe"  "mary" "susy"  "peter" "annie"
#[24,] "joe"  "john" "linda" "peter" "annie"
#[25,] "joe"  "john" "susy"  "peter" "annie"
#[26,] "mark" "mary" "john"  "linda" "peter"
#[27,] "mark" "mary" "john"  "linda" "annie"
#[28,] "mark" "mary" "john"  "susy"  "peter"
#[29,] "mark" "mary" "john"  "susy"  "annie"
#[30,] "mark" "mary" "john"  "peter" "annie"
#[31,] "mark" "mary" "linda" "peter" "annie"
#[32,] "mark" "mary" "susy"  "peter" "annie"
#[33,] "mark" "john" "linda" "peter" "annie"
#[34,] "mark" "john" "susy"  "peter" "annie"
#[35,] "mary" "john" "linda" "peter" "annie"
#[36,] "mary" "john" "susy"  "peter" "annie"

cbn
#      [,1]   [,2]   [,3]    [,4]    [,5]   
# [1,] "joe"  "mark" "mary"  "linda" "peter"
# [2,] "joe"  "mark" "mary"  "linda" "annie"
# [3,] "joe"  "mark" "mary"  "susy"  "peter"
# [4,] "joe"  "mark" "mary"  "susy"  "annie"
# [5,] "joe"  "mark" "mary"  "peter" "annie"
# [6,] "joe"  "mark" "linda" "peter" "annie"
# [7,] "joe"  "mark" "susy"  "peter" "annie"
# [8,] "joe"  "mary" "linda" "peter" "annie"
# [9,] "joe"  "mary" "susy"  "peter" "annie"
#[10,] "mark" "mary" "john"  "linda" "peter"
#[11,] "mark" "mary" "john"  "linda" "annie"
#[12,] "mark" "mary" "john"  "susy"  "peter"
#[13,] "mark" "mary" "john"  "susy"  "annie"
#[14,] "mark" "mary" "john"  "peter" "annie"
#[15,] "mark" "mary" "linda" "peter" "annie"
#[16,] "mark" "mary" "susy"  "peter" "annie"
#[17,] "mark" "john" "linda" "peter" "annie"
#[18,] "mark" "john" "susy"  "peter" "annie"
#[19,] "mary" "john" "linda" "peter" "annie"
#[20,] "mary" "john" "susy"  "peter" "annie"

另一个解决方案：

创建名称和组合

combs <- list(x, y)

names <- c("joe", "mark", "mary", "john", "linda", "susy", "peter", "annie")
cbn <- combn(names, 5)

那真的很好用！如果要排除多个组合（例如“joe”和“john”），我将如何处理？我能想到的唯一一件事就是写连续的函数，但这看起来很笨拙。所以你想要一个返回值，即每个组合的矩阵或data.frame，对吗？我想要一个矩阵或df，它排除所有包含一些已定义组合的行（例如排除linda和susy对，排除joe和john对）.@NukeDude更新了我的答案-希望这有帮助。
csums <- colSums((cbn == "linda") + (cbn == "susy"))
csums_2 <- colSums((cbn == "joe") + (cbn == "john"))
cbn <- t(cbn[, csums < 2 & csums_2 <2])

> cbn
      [,1]   [,2]   [,3]    [,4]    [,5]   
 [1,] "joe"  "mark" "mary"  "linda" "peter"
 [2,] "joe"  "mark" "mary"  "linda" "annie"
 [3,] "joe"  "mark" "mary"  "susy"  "peter"
 [4,] "joe"  "mark" "mary"  "susy"  "annie"
 [5,] "joe"  "mark" "mary"  "peter" "annie"
 [6,] "joe"  "mark" "linda" "peter" "annie"
 [7,] "joe"  "mark" "susy"  "peter" "annie"
 [8,] "joe"  "mary" "linda" "peter" "annie"
 [9,] "joe"  "mary" "susy"  "peter" "annie"
[10,] "mark" "mary" "john"  "linda" "peter"
[11,] "mark" "mary" "john"  "linda" "annie"
[12,] "mark" "mary" "john"  "susy"  "peter"
[13,] "mark" "mary" "john"  "susy"  "annie"
[14,] "mark" "mary" "john"  "peter" "annie"
[15,] "mark" "mary" "linda" "peter" "annie"
[16,] "mark" "mary" "susy"  "peter" "annie"
[17,] "mark" "john" "linda" "peter" "annie"
[18,] "mark" "john" "susy"  "peter" "annie"
[19,] "mary" "john" "linda" "peter" "annie"
[20,] "mary" "john" "susy"  "peter" "annie"