按组求和变量的一个好方法是

rowsum(numericToBeSummedUp, groups)

从基地。这里只有collapse::fsum和Rfast::group。求和更快。

关于速度和内存消耗

collapse::fsum(numericToBeSummedUp, groups)

在给定的例子中是最好的，当使用分组数据帧时可以加速。

GDF <- collapse::fgroup_by(DF, g) #Create a grouped data.frame with group g
#GDF <- collapse::gby(DF, g)      #Alternative

collapse::fsum(GDF)               #Calculate sum per group

这接近于将数据集分成每组子数据集的时间。

对不同方法的基准测试表明::fsum对单列折叠求和的速度比Rfast::group快两倍。Sum，比rowsum快7倍。紧随其后的是tapply, data。表，由和dplyr。Xtabs和aggregate是最慢的。

聚合两个列折叠::fsum仍然是最快的，比Rfast::group快3倍。求和，比rowsum快5倍。紧随其后的是数据。Table, tapply, by和dplyr。xtabs和aggregate是最慢的。

基准

set.seed(42)
n <- 1e5
DF <- data.frame(g = as.factor(sample(letters, n, TRUE))
              , x = rnorm(n), y = rnorm(n) )

library(magrittr)

有些方法允许执行有助于加快聚合速度的任务。

DT <- data.table::as.data.table(DF)
data.table::setkey(DT, g)

DFG <- collapse::gby(DF, g)
DFG1 <- collapse::gby(DF[c("g", "x")], g)

# Optimized dataset for this aggregation task
# This will also consume time!
DFS <- lapply(split(DF[c("x", "y")], DF["g"]), as.matrix)
DFS1 <- lapply(split(DF["x"], DF["g"]), as.matrix)

对一列求和。

bench::mark(check = FALSE
          , "aggregate" = aggregate(DF$x, DF["g"], sum)
          , "tapply" = tapply(DF$x, DF$g, sum)
          , "dplyr" = DF %>% dplyr::group_by(g) %>% dplyr::summarise(sum = sum(x))
          , "data.table" = data.table::as.data.table(DF)[, sum(x), by = g]
          , "data.table2" = DT[, sum(x), by = g]
          , "by" = by(DF$x, DF$g, sum)
          , "xtabs" = xtabs(x ~ g, DF)
          , "rowsum" = rowsum(DF$x, DF$g)
          , "Rfast" = Rfast::group.sum(DF$x, DF$g)
          , "base Split" = lapply(DFS1, colSums)
          , "base Split Rfast" = lapply(DFS1, Rfast::colsums)
          , "collapse"  = collapse::fsum(DF$x, DF$g)
          , "collapse2"  = collapse::fsum(DFG1)
)
#   expression            min   median `itr/sec` mem_alloc `gc/sec` n_itr  n_gc
#   <bch:expr>       <bch:tm> <bch:tm>     <dbl> <bch:byt>    <dbl> <int> <dbl>
# 1 aggregate         20.43ms  21.88ms      45.7   16.07MB    59.4     10    13
# 2 tapply             1.24ms   1.39ms     687.     1.53MB    30.1    228    10
# 3 dplyr              3.28ms   4.81ms     209.     2.42MB    13.1     96     6
# 4 data.table         1.59ms   2.47ms     410.     4.69MB    87.7    145    31
# 5 data.table2        1.52ms   1.93ms     514.     2.38MB    40.5    190    15
# 6 by                 2.15ms   2.31ms     396.     2.29MB    26.7    148    10
# 7 xtabs              7.78ms   8.91ms     111.    10.54MB    50.0     31    14
# 8 rowsum           951.36µs   1.07ms     830.     1.15MB    24.1    378    11
# 9 Rfast            431.06µs 434.53µs    2268.     2.74KB     0     1134     0
#10 base Split       213.42µs 219.66µs    4342.       256B    12.4   2105     6
#11 base Split Rfast  76.88µs  81.48µs   10923.    65.05KB    16.7   5232     8
#12 collapse         121.03µs 122.92µs    7965.       256B     2.01  3961     1
#13 collapse2         85.97µs  88.67µs   10749.       256B     4.03  5328     2

两列相加

bench::mark(check = FALSE
          , "aggregate" = aggregate(DF[c("x", "y")], DF["g"], sum)
          , "tapply" = list2DF(lapply(DF[c("x", "y")], tapply, list(DF$g), sum))
          , "dplyr" = DF %>% dplyr::group_by(g) %>% dplyr::summarise(x = sum(x), y = sum(y))
          , "data.table" = data.table::as.data.table(DF)[,.(sum(x),sum(y)), by = g]
          , "data.table2" = DT[,.(sum(x),sum(y)), by = g]
          , "by" = lapply(DF[c("x", "y")], by, list(DF$g), sum)
          , "xtabs" = xtabs(cbind(x, y) ~ g, DF)
          , "rowsum" = rowsum(DF[c("x", "y")], DF$g)
          , "Rfast" = list2DF(lapply(DF[c("x", "y")], Rfast::group.sum, DF$g))
          , "base Split" = lapply(DFS, colSums)
          , "base Split Rfast" = lapply(DFS, Rfast::colsums)
          , "collapse" = collapse::fsum(DF[c("x", "y")], DF$g)
          , "collapse2" = collapse::fsum(DFG)
            )
#   expression            min   median `itr/sec` mem_alloc `gc/sec` n_itr  n_gc
#   <bch:expr>       <bch:tm> <bch:tm>     <dbl> <bch:byt>    <dbl> <int> <dbl>
# 1 aggregate         25.87ms  26.36ms      37.7   20.89MB   132.       4    14
# 2 tapply             2.65ms   3.23ms     312.     3.06MB    22.5     97     7
# 3 dplyr              4.27ms   6.02ms     164.     3.19MB    13.3     74     6
# 4 data.table         2.33ms   3.19ms     309.     4.72MB    57.0    114    21
# 5 data.table2        2.22ms   2.81ms     355.     2.41MB    19.8    161     9
# 6 by                 4.45ms   5.23ms     190.     4.59MB    22.5     59     7
# 7 xtabs             10.71ms  13.14ms      76.1    19.7MB   145.      11    21
# 8 rowsum             1.02ms   1.07ms     850.     1.15MB    23.8    393    11
# 9 Rfast            841.57µs 846.88µs    1150.     5.48KB     0      575     0
#10 base Split       360.24µs 368.28µs    2652.       256B     8.16  1300     4
#11 base Split Rfast 113.95µs 119.81µs    7540.    65.05KB    10.3   3661     5
#12 collapse         201.31µs 204.83µs    4724.       512B     2.01  2350     1
#13 collapse2        156.95µs 161.79µs    5408.       512B     2.02  2683     1

对于dplyr 1.1.0及以上版本，你可以在总结中使用.by。这个快捷方式避免使用group_by，并返回一个未分组的数据帧:

library(dplyr)
x %>%  
  summarise(Frequency = sum(Frequency), .by = Category)

虽然我最近对大多数这些类型的操作都转换为dplyr，但sqldf包对于某些事情仍然非常好(恕我直言，可读性更强)。

下面是一个示例，说明如何使用sqldf回答这个问题

x <- data.frame(Category=factor(c("First", "First", "First", "Second",
                                  "Third", "Third", "Second")), 
                Frequency=c(10,15,5,2,14,20,3))

sqldf("select 
          Category
          ,sum(Frequency) as Frequency 
       from x 
       group by 
          Category")

##   Category Frequency
## 1    First        30
## 2   Second         5
## 3    Third        34

另一种解决方案是在矩阵或数据帧中按组返回和，并且简短快速:

rowsum(x$Frequency, x$Category)

你也可以使用dplyr包来实现这个目的:

library(dplyr)
x %>% 
  group_by(Category) %>% 
  summarise(Frequency = sum(Frequency))

#Source: local data frame [3 x 2]
#
#  Category Frequency
#1    First        30
#2   Second         5
#3    Third        34

或者，对于多个摘要列(也适用于一个列):

x %>% 
  group_by(Category) %>% 
  summarise(across(everything(), sum))

下面是一些关于如何使用dplyr函数(使用内置数据集mtcars)按组总结数据的例子:

# several summary columns with arbitrary names
mtcars %>% 
  group_by(cyl, gear) %>%                            # multiple group columns
  summarise(max_hp = max(hp), mean_mpg = mean(mpg))  # multiple summary columns

# summarise all columns except grouping columns using "sum" 
mtcars %>% 
  group_by(cyl) %>% 
  summarise(across(everything(), sum))

# summarise all columns except grouping columns using "sum" and "mean"
mtcars %>% 
  group_by(cyl) %>% 
  summarise(across(everything(), list(mean = mean, sum = sum)))

# multiple grouping columns
mtcars %>% 
  group_by(cyl, gear) %>% 
  summarise(across(everything(), list(mean = mean, sum = sum)))

# summarise specific variables, not all
mtcars %>% 
  group_by(cyl, gear) %>% 
  summarise(across(c(qsec, mpg, wt), list(mean = mean, sum = sum)))

# summarise specific variables (numeric columns except grouping columns)
mtcars %>% 
  group_by(gear) %>% 
  summarise(across(where(is.numeric), list(mean = mean, sum = sum)))

有关更多信息，包括%>%操作符，请参阅dplyr介绍。

如果x是一个包含你的数据的数据框架，那么下面的代码将完成你想要的:

require(reshape)
recast(x, Category ~ ., fun.aggregate=sum)