小编dat*_*urf的帖子

例如(不确定是否最具代表性的例子):

N <- 1e6
d1 <- data.frame(x=sample(N,N), y1=rnorm(N))
d2 <- data.frame(x=sample(N,N), y2=rnorm(N))

这是我到目前为止所得到的:

d <- merge(d1,d2)
# 7.6 sec

library(plyr)
d <- join(d1,d2)
# 2.9 sec

library(data.table)
dt1 <- data.table(d1, key="x")
dt2 <- data.table(d2, key="x")
d <- data.frame( dt1[dt2,list(x,y1,y2=dt2$y2)] )
# 4.9 sec

library(sqldf)
sqldf()
sqldf("create index ix1 on d1(x)")
sqldf("create index ix2 on d2(x)")
d <- sqldf("select * from d1 inner join d2 on d1.x=d2.x")
sqldf()
# 17.4 sec