4

目前这是我测试数字相等性的方法，如果x是数字和y向量，它就可以工作。

almostEqual <- function(x, y, tolerance=1e-8) {
  diff <- abs(x - y)
  mag <- pmax( abs(x), abs(y) )
  ifelse( mag > tolerance, diff/mag <= tolerance, diff <= tolerance)
}

示例：

almostEqual(1,c(1,1.00000000000001,1.00002))
[1]  TRUE  TRUE FALSE

你能让它更快吗（只使用基础 R）？

编辑：我建议这个我觉得有用

"%~=%" <- almostEqual;
"%~in%" <- function(x,y){ sapply(x,FUN=function(a,b){any(almostEqual(a,b))},y)};
4

1 回答 1

3

一ifelse开始就省钱可以节省 57%...

almostEqual2 <- function(x, y, tolerance=1e-8) {
  diff <- abs(x - y)
  mag <- pmax( abs(x), abs(y) )
  out <- logical(length(y))
  out[ mag > tolerance ] <- (diff/mag <= tolerance)[ mag > tolerance]
  out[ ! mag > tolerance ] <- (diff <= tolerance)[! mag > tolerance]
  return( out )
}


require(microbenchmark)

set.seed(1)
x <- 1
y <- rnorm(1e6)

bm <- microbenchmark( almostEqual(x,y,tol=0.5) , almostEqual2(x,y,tol=0.5) , times = 25 )
print( bm , digits = 3 , unit = "relative" , order = "median" )
#Unit: relative
#                          expr  min   lq median   uq  max neval
# almostEqual2(x, y, tol = 0.5) 1.00 1.00   1.00 1.00 1.00    25
#  almostEqual(x, y, tol = 0.5) 2.09 1.76   1.73 1.86 1.82    25

使用 Rcpp

我不明白为什么你不会在 CRAN 之外使用最依赖的包base，但如果你愿意的话，你可以实现比我之前的努力提高 5 倍（在 OP 上 10 倍）并且它还可以处理NA 优雅地...

#include <Rcpp.h>

using namespace Rcpp;

//[[Rcpp::export]]


LogicalVector all_equalC( double x , NumericVector y , double tolerance ){
  NumericVector diff = abs( x - y );
  NumericVector mag = pmax( abs(x) , abs(y) );
  LogicalVector res = ifelse( mag > tolerance , diff/mag <= tolerance , diff <= tolerance );
  return( res );
}

使用Rcpp::sourceCpp('path/to/file.cpp'). 结果...

bm <- microbenchmark( almostEqual(x,y,tol=0.5) , almostEqual2(x,y,tol=0.5) , all_equalC(x,y,tolerance=0.5) , times = 25 )
print( bm , digits = 3 , unit = "relative" , order = "median" )
#Unit: relative
#                              expr  min   lq median   uq   max neval
# all_equalC(x, y, tolerance = 0.5) 1.00 1.00   1.00 1.00  1.00    25
#     almostEqual2(x, y, tol = 0.5) 4.50 4.39   5.39 5.24  7.32    25
#      almostEqual(x, y, tol = 0.5) 8.69 9.34   9.24 9.96 10.91    25
于 2013-09-17T14:16:08.213 回答