Performance （我无法击败所有现有的答案；）因为ddply只适用于数据帧，所以这个示例会产生最差的性能。我希望在将来的版本中为这种类型的常见操作提供更好的接口。仅供参考：您不能在CRAN包中使用。内部调用，请参阅。@JoshuaUlrich当答案在近2年前编写时，您可以

---

（我无法击败所有现有的答案；）因为ddply只适用于数据帧，所以这个示例会产生最差的性能。我希望在将来的版本中为这种类型的常见操作提供更好的接口。仅供参考：您不能在CRAN包中使用

。内部
调用，请参阅。@JoshuaUlrich当答案在近2年前编写时，您可以使用iirc。我将把这个答案更新为
数据。现在表
自动优化
平均值
（不在内部调用
.Internal
。@MatthewDowle:是的，我不确定它何时/是否会改变。我只知道现在是这样。你的回答很好，只是不能打包使用。@AleksandrBlekh谢谢。我已将您的评论链接到现有功能请求。让我们搬到那里去。您的示例代码很好地显示了
for
循环，这很好。你能为这个问题添加更多关于“SEM分析”的信息吗？例如，我猜SEM=扫描电子显微镜？了解更多关于应用程序的信息会让我们更感兴趣，并帮助我们确定优先级。更新得不错。谢谢与此数据集相比，我认为您的机器是一头野兽。。二级缓存的大小是多少（如果存在，还有三级缓存）？i7二级缓存是2x256 KB 8路，三级缓存是4 MB 16路。128 GB SSD，Dell Inspiron上的Win 7可让您重新格式化示例。我有点困惑。data.table（在本例中）比dplyr好吗？如果是，在什么情况下。问题是性能。您只提供了连接的语法。虽然有帮助，但它不能回答问题。这个答案缺乏基准数据，使用OP的例子来显示它的性能更好，或者至少具有很强的竞争力。
N <- 1e6
d1 <- data.frame(x=sample(N,N), y1=rnorm(N))
d2 <- data.frame(x=sample(N,N), y2=rnorm(N))

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

system.time({
    d <- d1
    d$y2 <- d2$y2[match(d1$x,d2$x)]
})

DF1 = data.frame(a = c(1, 1, 2, 2), b = 1:4)
DF2 = data.frame(b = c(1, 2, 3, 3, 4), c = letters[1:5])
merge(DF1, DF2)
    b a c
  1 1 1 a
  2 2 1 b
  3 3 2 c
  4 3 2 d
  5 4 2 e
DF1$c = DF2$c[match(DF1$b, DF2$b)]
DF1$c
[1] a b c e
Levels: a b c d e

> DF1
  a b c
1 1 1 a
2 1 2 b
3 2 3 c
4 2 4 e

library(plyr)
library(data.table)
library(sqldf)

set.seed(123)
N <- 1e5
d1 <- data.frame(x=sample(N,N), y1=rnorm(N))
d2 <- data.frame(x=sample(N,N), y2=rnorm(N))

g1 <- sample(1:1000, N, replace = TRUE)
g2<- sample(1:1000, N, replace = TRUE)
d <- data.frame(d1, g1, g2)

library(rbenchmark)

benchmark(replications = 1, order = "elapsed",
   merge = merge(d1, d2),
   plyr = join(d1, d2),
   data.table = { 
      dt1 <- data.table(d1, key = "x")
      dt2 <- data.table(d2, key = "x")
      data.frame( dt1[dt2,list(x,y1,y2=dt2$y2)] )
      },
   sqldf = sqldf(c("create index ix1 on d1(x)",
      "select * from main.d1 join d2 using(x)"))
)

set.seed(123)
N <- 1e5
g1 <- sample(1:1000, N, replace = TRUE)
g2<- sample(1:1000, N, replace = TRUE)
d <- data.frame(x=sample(N,N), y=rnorm(N), g1, g2)

benchmark(replications = 1, order = "elapsed",
   aggregate = aggregate(d[c("x", "y")], d[c("g1", "g2")], mean), 
   data.table = {
      dt <- data.table(d, key = "g1,g2")
      dt[, colMeans(cbind(x, y)), by = "g1,g2"]
   },
   plyr = ddply(d, .(g1, g2), summarise, avx = mean(x), avy=mean(y)),
   sqldf = sqldf(c("create index ix on d(g1, g2)",
      "select g1, g2, avg(x), avg(y) from main.d group by g1, g2"))
)

Joining by: x
        test replications elapsed relative user.self sys.self user.child sys.child
3 data.table            1    0.34 1.000000      0.31     0.01         NA        NA
2       plyr            1    0.44 1.294118      0.39     0.02         NA        NA
1      merge            1    1.17 3.441176      1.10     0.04         NA        NA
4      sqldf            1    3.34 9.823529      3.24     0.04         NA        NA

        test replications elapsed  relative user.self sys.self user.child sys.child
4      sqldf            1    2.81  1.000000      2.73     0.02         NA        NA
1  aggregate            1   14.89  5.298932     14.89     0.00         NA        NA
2 data.table            1  132.46 47.138790    131.70     0.08         NA        NA
3       plyr            1  212.69 75.690391    211.57     0.56         NA        NA

benchmark(replications = 1, order = "elapsed", 
  aggregate = aggregate(d[c("x", "y")], d[c("g1", "g2")], mean),
  data.tableBad = {
     dt <- data.table(d, key = "g1,g2") 
     dt[, colMeans(cbind(x, y)), by = "g1,g2"]
  }, 
  data.tableGood = {
     dt <- data.table(d, key = "g1,g2") 
     dt[, list(mean(x),mean(y)), by = "g1,g2"]
  }, 
  plyr = ddply(d, .(g1, g2), summarise, avx = mean(x), avy=mean(y)),
  sqldf = sqldf(c("create index ix on d(g1, g2)",
      "select g1, g2, avg(x), avg(y) from main.d group by g1, g2"))
  ) 

            test replications elapsed relative user.self sys.self
3 data.tableGood            1    0.15    1.000      0.16     0.00
5          sqldf            1    1.01    6.733      1.01     0.00
2  data.tableBad            1    1.63   10.867      1.61     0.01
1      aggregate            1    6.40   42.667      6.38     0.00
4           plyr            1  317.97 2119.800    265.12    51.05

packageVersion("data.table")
# [1] ‘1.8.2’
packageVersion("plyr")
# [1] ‘1.7.1’
packageVersion("sqldf")
# [1] ‘0.4.6.4’
R.version.string
# R version 2.15.1 (2012-06-22)

              test replications elapsed   relative user.self sys.self
4   data.tableBest            1   0.532   1.000000     0.488    0.020
7            sqldf            1   2.059   3.870301     2.041    0.008
3 data.tableBetter            1   9.580  18.007519     9.213    0.220
1        aggregate            1  14.864  27.939850    13.937    0.316
2  data.tableWorst            1 152.046 285.800752   150.173    0.556
6 plyrwithInternal            1 198.283 372.712406   189.391    7.665
5             plyr            1 225.726 424.296992   208.013    8.004

            test replications elapsed relative user.self sys.self
5          dplyr            1    0.25     1.00      0.25     0.00
3 data.tableGood            1    0.28     1.12      0.27     0.00
6          sqldf            1    0.58     2.32      0.57     0.00
2  data.tableBad            1    1.10     4.40      1.09     0.01
1      aggregate            1    4.79    19.16      4.73     0.02
4           plyr            1  186.70   746.80    152.11    30.27

packageVersion("data.table")
[1] ‘1.8.10’
packageVersion("plyr")
[1] ‘1.8’
packageVersion("sqldf")
[1] ‘0.4.7’
packageVersion("dplyr")
[1] ‘0.1.2’
R.version.string
[1] "R version 3.0.2 (2013-09-25)"

dplyr = summarise(dt_dt, avx = mean(x), avy = mean(y))

dt <- tbl_dt(d)
dt_dt <- group_by(dt, g1, g2)

            test replications elapsed relative user.self sys.self
2 data.tableGood            1    0.02      1.0      0.02     0.00
3          dplyr            1    0.04      2.0      0.04     0.00
4          sqldf            1    0.46     23.0      0.46     0.00
1      aggregate            1    6.11    305.5      6.10     0.02

            test replications elapsed relative user.self sys.self
2 data.tableGood            1    0.02        1      0.02     0.00
3          dplyr            1    0.02        1      0.02     0.00
4          sqldf            1    0.44       22      0.43     0.02
1      aggregate            1    6.14      307      6.10     0.01

packageVersion("data.table")
[1] '1.9.0'
packageVersion("dplyr")
[1] '0.1.2'

            test replications elapsed relative user.self sys.self
5          dplyr            1    0.01        1      0.02     0.00
3 data.tableGood            1    0.02        2      0.01     0.00
6          sqldf            1    0.47       47      0.46     0.00
1      aggregate            1    6.16      616      6.16     0.00
2  data.tableBad            1   15.45     1545     15.38     0.01
4           plyr            1  110.23    11023     90.46    19.52

N <- 1e8
g1 <- sample(1:50000, N, replace = TRUE)
g2<- sample(1:50000, N, replace = TRUE)
d <- data.frame(x=sample(N,N), y=rnorm(N), g1, g2)

            test replications elapsed relative user.self sys.self
1          dplyr            1   14.88        1      6.24     7.52
2 data.tableGood            1   28.41        1     18.55      9.4

require(data.table)
require(dplyr)
require(rbenchmark)

N <- 1e8
g1 <- sample(1:50000, N, replace = TRUE)
g2 <- sample(1:50000, N, replace = TRUE)
d <- data.frame(x=sample(N,N), y=rnorm(N), g1, g2)

benchmark(replications = 5, order = "elapsed", 
  data.table = {
     dt <- as.data.table(d) 
     dt[, lapply(.SD, mean), by = "g1,g2"]
  }, 
  dplyr_DF = d %.% group_by(g1, g2) %.% summarise(avx = mean(x), avy=mean(y))
) 

        test replications elapsed relative user.self sys.self
1 data.table            5   15.35     1.00     13.77     1.57
2   dplyr_DF            5  137.84     8.98    136.31     1.44

Outer join: merge(x = df1, y = df2, by = "CustomerId", all = TRUE)

Left outer: merge(x = df1, y = df2, by = "CustomerId", all.x = TRUE)

Right outer: merge(x = df1, y = df2, by = "CustomerId", all.y = TRUE)

Cross join: merge(x = df1, y = df2, by = NULL)