测试向量是否包含在另一个向量中,包括重复

时间:2015-12-23 23:10:37

标签: r

我一直在努力解决这个问题:给定两个向量,每个向量包含可能重复的元素,如何测试另一个是否完全包含在另一个中? %in%不考虑重复。我想不出一个优雅的解决方案,它不依赖apply家族的某些东西。

x      <- c(1, 2, 2, 2)
values <- c(1, 1, 1, 2, 2, 3, 4, 5, 6)

# returns TRUE, but x[x == 2] is greater than values[values == 2]
all(x %in% values)

# inelegant solution
"%contains%" <- 
    function(values, x){
                   n <- intersect(x, values)
                   all( sapply(n, function(i) sum(values == i) >= sum(x == i)) )
                       }

# which yields the following:
> values %contains% x
 [1] FALSE
> values <- c(values, 2)
> values %contains% x
 [2] TRUE

基准更新

除了Marat提供的答案之外,我可能还找到了另一种解决方案

# values and x must all be non-negative - can change the -1 below accordingly
"%contains%" <- 
    function(values, x){
            t <- Reduce(function(.x, .values) .values[-which.max(.values == .x)]
                        , x = x
                        , init = c(-1, values))
            t[1] == -1
     }

对目前为止的所有答案进行基准测试,包括使用大小的x来修改marat的邮件

library(microbenchmark)

set.seed(31415)
values <- sample(c(0:100), size = 100000, replace = TRUE)
set.seed(11235)
x_lrg <- sample(c(0:100), size = 1000, replace = TRUE)
x_sml <- c(1, 2, 2, 2)


lapply(list(x_sml, x_lrg), function(x){
    microbenchmark(    hoho_sapply(values, x)
                     , marat_table(values, x)
                     , marat_tlm(values, x)
                     , hoho_reduce(values, x)
                     ,  unit = "relative")
    })

 # Small x
 # [[1]]
 # Unit: relative
 #                  expr       min        lq     mean   median       uq      max neval
 # hoho_sapply(values, x)  1.000000  1.000000 1.000000 1.000000 1.000000 1.000000   100
 # marat_table(values, x) 12.718392 10.966770 7.487895 9.260099 8.648351 1.819833   100
 #   marat_tlm(values, x)  1.354452  1.181094 1.026373 1.088879 1.266939 1.029560   100
 # hoho_reduce(values, x)  2.951577  2.748087 2.069830 2.487790 2.216625 1.097648   100
 #
 # Large x
 # [[2]]
 # Unit: relative
 #                   expr       min        lq      mean    median        uq        max neval
 # hoho_sapply(values, x)  1.158303  1.172352  1.101410  1.177746  1.096661  0.6940260   100
 # marat_table(values, x)  1.000000  1.000000  1.000000  1.000000  1.000000  1.0000000   100
 #   marat_tlm(values, x)  1.099669  1.059256  1.102543  1.071960  1.072881  0.9857229   100
 # hoho_reduce(values, x) 85.666549 81.391495 69.089366 74.173366 66.943621 27.9766047   100

1 个答案:

答案 0 :(得分:7)

尝试使用table,例如:

"%contain%" <- function(values,x) {
    tx <- table(x)
    tv <- table(values)
    z <- tv[names(tx)] - tx
    all(z >= 0 & !is.na(z))
}

一些例子:

> c(1, 1, 1, 2, 2, 3, 4, 5, 6) %contain% c(1,2,2,2)
[1] FALSE
> c(1, 1, 1, 2, 2, 3, 4, 5, 6, 2) %contain% c(1,2,2,2)
[1] TRUE
> c(1, 1, 1, 2, 2, 3, 4, 5, 6) %contain% c(1,2,2)
[1] TRUE
> c(1, 1, 1, 2, 2, 3, 4, 5, 6) %contain% c(1,2,2,7)
[1] FALSE