带库的R分数（质量）

Question

y = c("-1", "1", "1", ...)

    y = c("-1/2", "1", "1", ...)
    y = as.numeric(y);

 sapply(y , function(x) {

     eval(parse(text=x));
  });

Answer 1

eval(parse(text))非常慢--正如您所知道的，您可以编写一个更快的函数：

y = c("-1/2", "1", "1", "1/2")
fixnums <- function(x){
  temp <- as.numeric(x)
  temp[is.na(temp)] <- lapply(strsplit(x[is.na(temp)], "/"), function(x) as.numeric(x[1])/as.numeric(x[2]))
  unlist(temp)
}
fixnums(y)

@Davidarenburg在下面的评论中建议了一个更快的版本，避免了lapply:

davidfixnums <- function(x){
  temp <- as.numeric(x)
  temp2 <- as.numeric(unlist(strsplit(y[is.na(temp)], "/", fixed = TRUE)))
  temp[is.na(temp)] <- temp2[c(T, F)]/temp2[c(F, T)]
  temp
}

一些基准，使用@Akrun和@Davidarenburgs建议：

library(microbenchmark)
set.seed(1234)
y <- sample(c("-1/2", "1", "1", "1/2"), 10000, replace = TRUE)

akrunfixnums <- function(y){
  x1 <- as.numeric(y)
  x1[is.na(x1)] <- vapply(y[is.na(x1)], function(x) 
    eval(parse(text=x)), numeric(1))
  x1
}

microbenchmark(fixnums(y), davidfixnums(y), akrunfixnums(y))

Unit: milliseconds
            expr        min         lq       mean     median        uq       max neval cld
      fixnums(y)  22.643745  23.157345  25.326465  23.435554  23.98544 154.16316   100  b 
 davidfixnums(y)   6.676234   6.778378   6.957626   6.824459   6.93025  10.12763   100 a  
 akrunfixnums(y) 845.404840 858.031737 869.886625 865.255363 875.54351 960.86497   100   c