Question

有任何想法可以更有效地实现以下功能吗？

prod_A_B <- function(A, B, i = NULL, j = NULL) {

  if (is.null(i) & is.null(j)) {
    A * B
  } else if (!is.null(i) & is.null(j)) {
    A[i, ] * B[i, ]
  } else if (!is.null(i) & !is.null(j)) {
    A[i, j] * B[i, j]
  }

}

特别是，是否可以更简洁地实现条件语句，从而减少运行时间？

以下是一些基准：

n <- 1e5
d <- 200
A <- matrix(rnorm(n*d), nrow = n, ncol = d)
B <- matrix(rnorm(n*d), nrow = n, ncol = d)

pr1 <- pr2 <- matrix(0, nrow=n, ncol =d)

tm <- microbenchmark(
  {for(i in 1:n) pr1[i,] <- prod_A_B(A, B, i)},
  {for(i in 1:n) pr2[i, ] <- A[i,] * B[i,]}, 
  times=100L)

print(tm)

Unit: milliseconds
       min       lq     mean   median       uq      max neval
 1164.4078 1208.348 1234.607 1224.097 1254.059 1370.098   100
  969.9961 1004.821 1036.738 1021.025 1056.182 1278.767   100

鉴于矩阵大小，差异并不大，但我仍然想知道我是否可以稍微提高性能......

谢谢！

Answer 1

您可以通过简化逻辑谓词来节省一些时间，并且还可以删除多个函数调用，如下所示：

prod2_A_B <- function(A, B, i = NULL, j = NULL) {

  ni <- is.null(i)
  nj <- is.null(j)

  if (ni & nj) {
    A * B
  } else if (nj) { # must be !ni
    A[i, ] * B[i, ]
  } else {         # must be !ni & !nj
    A[i, j] * B[i, j]
  }

}


n <- 1e5
d <- 200
pr1 <- pr2 <- pr <- matrix(0, nrow=n, ncol =d)
A <- matrix(rnorm(n*d), nrow = n, ncol = d)
B <- matrix(rnorm(n*d), nrow = n, ncol = d)
library(microbenchmark)
tm <- microbenchmark(
  {for(i in 1:n) pr1[i,] <- prod_A_B(A, B, i)},
  {for(i in 1:n) pr2[i,] <- prod2_A_B(A, B, i)},
  {for(i in 1:n) pr[i,] <- A[i,] * B[i,]}, 
  times=100L)

print(tm)

Unit: milliseconds
                                           expr      min       lq     mean   median       uq      max neval cld
  {for (i in 1:n) pr1[i, ] <- prod_A_B(A, B, i)}  937.9470 944.6690 969.7894 952.2308 964.4701 1390.467   100   c
  {for (i in 1:n) pr2[i, ] <- prod2_A_B(A, B, i)} 898.6802 908.3323 929.7343 914.6826 929.4356 1211.623   100  b 
  {for (i in 1:n) pr[i, ] <- A[i, ] * B[i, ]}     661.2350 666.7071 688.8127 672.6218 679.9028 1005.342   100 a

R函数效率

1 个答案: