本文来自 stack overflow 上的一个帖子
base与data.table适用
SQL版
流行的dplyr
最后看看各种操作的性能吧
data.table 就是牛批！（可惜没有tidyverse易用）
测试代码：
代码语言：javascript复制library(microbenchmark)
library(sqldf)
library(dplyr)
library(data.table)
sapply(c("sqldf","dplyr","data.table"), packageVersion, simplify=FALSE)
n = 5e7
set.seed(108)
df1 = data.frame(x=sample(n,n-1L), y1=rnorm(n-1L))
df2 = data.frame(x=sample(n,n-1L), y2=rnorm(n-1L))
dt1 = as.data.table(df1)
dt2 = as.data.table(df2)
mb = list()
# inner join
microbenchmark(times = 1L,
base = merge(df1, df2, by = "x"),
sqldf = sqldf("SELECT * FROM df1 INNER JOIN df2 ON df1.x = df2.x"),
dplyr = inner_join(df1, df2, by = "x"),
DT = dt1[dt2, nomatch=NULL, on = "x"]) -> mb$inner
# left outer join
microbenchmark(times = 1L,
base = merge(df1, df2, by = "x", all.x = TRUE),
sqldf = sqldf("SELECT * FROM df1 LEFT OUTER JOIN df2 ON df1.x = df2.x"),
dplyr = left_join(df1, df2, by = c("x"="x")),
DT = dt2[dt1, on = "x"]) -> mb$left
# right outer join
microbenchmark(times = 1L,
base = merge(df1, df2, by = "x", all.y = TRUE),
sqldf = sqldf("SELECT * FROM df2 LEFT OUTER JOIN df1 ON df2.x = df1.x"),
dplyr = right_join(df1, df2, by = "x"),
DT = dt1[dt2, on = "x"]) -> mb$right
# full outer join
microbenchmark(times = 1L,
base = merge(df1, df2, by = "x", all = TRUE),
dplyr = full_join(df1, df2, by = "x"),
DT = merge(dt1, dt2, by = "x", all = TRUE)) -> mb$full
lapply(mb, print) -> nul
