r - 优化基础R中的重新编码

Question

我正在基于一些相当长的字符串重新编码变量，这里以字符串A，B，C，D，E和G为例。我想知道是否有一种方法可以对此进行编码而不必重复引用df$foo使用base R 12次？也许我可以探索一些更智能，更快捷的方法？这真的是在R中最聪明的方法吗？

df <- data.frame(
  foo = 1000:1010,
  bar = letters[1:11])
df  
    foo bar
1  1000   a
2  1001   b
3  1002   c
4  1003   d
5  1004   e
6  1005   f
7  1006   g
8  1007   h
9  1008   i
10 1009   j
11 1010   k

A  <- c(1002)
B  <- c(1007, 1008)
C  <- c(1001, 1003)
D  <- c(1004, 1006)
E  <- c(1000, 1005)
G  <- c(1010, 1009)

df$foo[df$foo %in% A] <- 1
df$foo[df$foo %in% B] <- 2
df$foo[df$foo %in% C] <- 3
df$foo[df$foo %in% D] <- 4
df$foo[df$foo %in% E] <- 5
df$foo[df$foo %in% G] <- 7
df
   foo bar
1    5   a
2    3   b
3    1   c
4    3   d
5    4   e
6    5   f
7    4   g
8    2   h
9    2   i
10   7   j
11   7   k

更新于2013-03-11 05:28:061Z，

我重写了五个功能解决方案，以便能够使用microbenchmark软件包进行比较，结果是泰勒·林克和弗洛德尔的解决方案是最快的解决方案(请参见下面的结果)，并不是说这个问题仅涉及速度。我也在寻找解决方案中的简洁性和智能性。出于好奇，我还使用了汽车包装中的 Recode函数添加了一个解决方案。请随时让我知道我是否可以以更优化的方式重写解决方案，或者microbenchmark软件包不是比较这些功能的最佳方法。

df <- data.frame(
  foo = sample(1000:1010, 1e5+22, replace = TRUE),
  bar = rep(letters, 3847))
str(df)

A  <- c(1002)
B  <- c(1007, 1008)
C  <- c(1001, 1003)
D  <- c(1004, 1006)
E  <- c(1000, 1005)
G  <- c(1010, 1009)

# juba's solution
juba <- function(df,foo) within(df, {foo[foo %in% A] <- 1; foo[foo %in% B] <- 2;foo[foo %in% C] <- 3;foo[foo %in% D] <- 4;foo[foo %in% E] <- 5;foo[foo %in% G] <- 7})
# Arun's solution
Arun <- function(df,x) factor(df[,x], levels=c(A,B,C,D,E,G), labels=c(1, rep(c(2:5, 7), each=2)))
# flodel's solution
flodel <- function(df,x) rep(c(1, 2, 3, 4, 5, 7), sapply(list(A, B, C, D, E, G), length))[match(df[,x], unlist(list(A, B, C, D, E, G)))]
# Tyler Rinker's solution
TylerRinker <- function(df,x)  data.frame(vals = unlist(list(A  = c(1002),B  = c(1007, 1008),C  = c(1001, 1003),D  = c(1004, 1006),E  = c(1000, 1005), G = c(1010, 1009))), labs = c(1, rep(c(2:5, 7), each=2)))[match(df[,x], unlist(list(A  = c(1002),B  = c(1007, 1008),C  = c(1001, 1003),D  = c(1004, 1006),E  = c(1000, 1005), G = c(1010, 1009)))), 2] 
# agstudy's solution
agstudy <- function(df,foo) merge(df,data.frame(foo=unlist(list(A, B, C, D, E, G)), val =rep((1:7)[-6],rapply(list(A, B, C, D, E, G), length))))
# Recode from the car package
ReINcar <- function(df,x) Recode(df[,x], "A='A'; B='B'; C='C'; D='D'; E='E'; G='G'")

# install.packages("microbenchmark", dependencies = TRUE)
require(microbenchmark)

# run test
res <- microbenchmark(juba(df, foo), Arun(df, 1), flodel(df, 1), TylerRinker(df,1) ,agstudy(df, foo), ReINcar(df, 1), times = 25)
There were 15 warnings (use warnings() to see them) # warning duo to x's solution

## Print results:
print(res)

数字，

   Unit: milliseconds
                   expr        min         lq     median         uq        max neval
          juba(df, foo)  37.944355  39.521603  41.987174  46.385974  79.559750    25
            Arun(df, 1)  23.833334  24.115776  24.648842  26.987431  55.466448    25
          flodel(df, 1)   3.586179   3.637024   3.956814   6.468735  28.404166    25
     TylerRinker(df, 1)   3.919563   4.115994   4.529926   5.532688   8.508956    25
       agstudy(df, foo) 301.487732 324.641734 334.801005 352.753496 415.421212    25
         ReINcar(df, 1)  73.655566  77.903088  81.745037 101.038791 125.158208    25


### Plot results:
boxplot(res)

微基准结果的箱形图

Answer 1

这是一种通用的(可伸缩的)方法，也非常快:

sets <- list(A, B, C, D, E, G)
vals <-    c(1, 2, 3, 4, 5, 7)

keys   <- unlist(sets)
values <- rep(vals, sapply(sets, length))
df$foo <- values[match(df$foo, keys)]