几个选项,全部使用:
myVector<-c(1,2,3,2,3,3,1)
因素
newvals <- c(.2,.4,.5)
newvals[as.factor(myVector)]
#[1] 0.2 0.4 0.5 0.4 0.5 0.5 0.2
命名向量
newvals <- c(`1`=.2,`2`=.4,`3`=.5)
newvals
# 1 2 3
#0.2 0.4 0.5
newvals[as.character(myVector)]
# 1 2 3 2 3 3 1
#0.2 0.4 0.5 0.4 0.5 0.5 0.2
查找表
mapdf <- data.frame(old=c(1,2,3),new=c(.2,.4,.5))
mapdf$new[match(myVector,mapdf$old)]
#[1] 0.2 0.4 0.5 0.4 0.5 0.5 0.2
量化以下@Joe 评论并解决@Ananda 评论的基准。
myVector <- c(1,2,3,2,3,3,1)
# setup for the benchmarking
test <- sample(myVector,1e6,replace=TRUE)
newvals <- c(.2,.4,.5)
newvalsvec <- c(`1`=.2,`2`=.4,`3`=.5)
mapdf <- data.frame(old=c(1,2,3),new=c(.2,.4,.5))
microbenchmark(
newvals[as.factor(test)],
newvalsvec[as.character(test)],
mapdf$new[match(test,mapdf$old)],
newvals[test],
times=10L
)
#Unit: milliseconds
# expr min lq median uq max
#factor 1863.40146 1876.04197 1890.99147 1913.13046 2014.23609
#namedvector 1809.26883 1812.76272 1837.18852 1851.42954 1858.44996
#lookup 38.48697 38.83405 39.90146 69.65140 71.75051
#newvals[test] 34.07380 34.55885 50.61287 65.69495 66.08699