Question

我有两个非常大的向量，需要将它们与定界符连接起来以形成唯一的ID。例如：

set.seed(1)

vec1 <- sample(1:10, 10000000, replace = T)
vec2 <- sample(1:1000000000, 10000000))

我当前正在使用paste0（）：

system.time({    

uniq_id <- paste0(vec1, "_", vec2)

})

但是，由于vec1和vec2的大小，这非常慢。是否有性能更高的替代方法？

Answer 1

一种更有效的方法是stringi::stri_c

library(microbenchmark)
b <- microbenchmark(
  paste = paste0(vec1, "_", vec2),
  stringi = stringi::stri_c(vec1, vec2, sep = "_"),
  times = 10
)

结果

b
#Unit: seconds
#    expr      min       lq     mean   median       uq      max neval cld
#   paste 5.475398 5.509957 5.544477 5.542728 5.566904 5.632173    10   b
# stringi 3.862541 3.871826 3.896242 3.897264 3.914894 3.934175    10  a

Answer 2

比较 paste、paste0（R 版本 4.1.0）、stringi::stri_c（版本 1.6.2）和 stringr::str_c（版本 1.4.0）我无法观察到性能差异很大，但这可能取决于将连接的内容。如果使用数字或字符，以及字符是否由数字或字母组成，则有很大不同。当只有字母 stringi 和 stringr 时，接缝比粘贴快。

M <- alist(
    paste0 = paste0(vec1, "_", vec2)
  , paste = paste(vec1, "_", vec2, sep = "")
  , pasteS = paste(vec1, vec2, sep = "_")
  , stringi = stringi::stri_c(vec1, "_", vec2)
  , stringiS = stringi::stri_c(vec1, vec2, sep = "_")
  , stringr = stringr::str_c(vec1, "_", vec2)
  , stringrS = stringr::str_c(vec1, vec2, sep = "_")
)

set.seed(42)
n <- 1e5
vec1 <- sample(1:10, n, TRUE)
vec2 <- sample(1:1000000000, n, TRUE)
bench::mark(exprs = M)
#  expression     min  median `itr/sec` mem_alloc `gc/sec` n_itr  n_gc total_time
#  <bch:expr> <bch:t> <bch:t>     <dbl> <bch:byt>    <dbl> <int> <dbl>   <bch:tm>
#1 paste0      62.8ms  63.9ms      15.6    2.29MB     2.23     7     1      447ms
#2 paste       61.9ms    63ms      15.9    2.29MB     0        8     0      503ms
#3 pasteS      57.5ms  58.6ms      17.1    2.29MB     2.13     8     1      468ms
#4 stringi     57.1ms  57.6ms      17.2    2.29MB     0        9     0      524ms
#5 stringiS    56.2ms  66.2ms      14.4    2.29MB     2.40     6     1      417ms
#6 stringr     57.9ms  62.9ms      14.8    2.29MB     0        8     0      541ms
#7 stringrS      55ms  61.4ms      15.3    2.29MB     0        8     0      523ms

vec1 <- as.character(vec1)
vec2 <- as.character(vec2)
bench::mark(exprs = M)
#  expression     min  median `itr/sec` mem_alloc `gc/sec` n_itr  n_gc total_time
#  <bch:expr> <bch:t> <bch:t>     <dbl> <bch:byt>    <dbl> <int> <dbl>   <bch:tm>
#1 paste0      34.2ms  35.3ms      28.2     781KB     2.17    13     1      460ms
#2 paste       35.1ms  35.7ms      27.9     781KB     0       14     0      502ms
#3 pasteS        32ms  33.5ms      29.9     781KB     2.14    14     1      468ms
#4 stringi     33.7ms  35.6ms      28.1     781KB     0       15     0      534ms
#5 stringiS    32.6ms  33.9ms      29.6     781KB     2.12    14     1      472ms
#6 stringr     34.6ms  34.9ms      28.5     781KB     0       15     0      526ms
#7 stringrS    33.1ms  33.4ms      29.7     781KB     2.12    14     1      471ms

set.seed(42)
n <- 1e5
vec1 <- as.character(sample(0:9, n, TRUE))
vec2 <- as.character(sample(0:9, n, TRUE))
bench::mark(exprs = M)
#  expression     min  median `itr/sec` mem_alloc `gc/sec` n_itr  n_gc total_time
#  <bch:expr> <bch:t> <bch:t>     <dbl> <bch:byt>    <dbl> <int> <dbl>   <bch:tm>
#1 paste0      18.9ms    19ms      52.4     781KB     2.02    26     1      496ms
#2 paste       18.9ms    19ms      52.5     781KB     0       27     0      514ms
#3 pasteS      15.2ms  15.3ms      65.3     781KB     2.04    32     1      490ms
#4 stringi     15.1ms  15.1ms      65.7     781KB     0       33     0      502ms
#5 stringiS    13.5ms  13.5ms      73.7     781KB     2.05    36     1      489ms
#6 stringr     15.1ms  15.2ms      65.7     781KB     2.05    32     1      487ms
#7 stringrS    13.4ms  13.5ms      73.3     781KB     0       37     0      505ms

set.seed(42)
n <- 1e5
vec1 <- sample(letters, n, TRUE)
vec2 <- sample(LETTERS, n, TRUE)
bench::mark(exprs = M)
#  expression     min  median `itr/sec` mem_alloc `gc/sec` n_itr  n_gc total_time
#  <bch:expr> <bch:t> <bch:t>     <dbl> <bch:byt>    <dbl> <int> <dbl>   <bch:tm>
#1 paste0     15.98ms 16.02ms      61.5     781KB     2.05    30     1      488ms
#2 paste      16.02ms 16.09ms      62.1     781KB     2.07    30     1      483ms
#3 pasteS     11.96ms 12.03ms      83.0     781KB     2.02    41     1      494ms
#4 stringi     7.97ms  8.07ms     123.      781KB     4.18    59     2      478ms
#5 stringiS    6.37ms  6.43ms     154.      781KB     4.12    75     2      486ms
#6 stringr     7.97ms  8.02ms     124.      781KB     2.04    61     1      491ms
#7 stringrS    6.43ms  6.49ms     153.      781KB     4.09    75     2      489ms

在R中粘贴字符串的最有效方法是什么？

2 个答案: