如何按组对变量求和

使用 aggregate：

aggregate(x$Frequency, by=list(Category=x$Category), FUN=sum)
  Category  x
1    First 30
2   Second  5
3    Third 34

在上面的示例中，可以在 list 中指定多个维度。可以通过 cbind 合并相同数据类型的多个聚合指标：

aggregate(cbind(x$Frequency, x$Metric2, x$Metric3) ...

（嵌入@thelatemail 评论），aggregate 也有公式界面

aggregate(Frequency ~ Category, x, sum)

或者，如果您想聚合多列，可以使用 . 表示法（也适用于一列）

aggregate(. ~ Category, x, sum)

或 tapply：

tapply(x$Frequency, x$Category, FUN=sum)
 First Second  Third 
    30      5     34 

使用这些数据：

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

---

您还可以为此目的使用 dplyr 包：

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，对于多个汇总列（也适用于一列）：

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

以下是一些关于如何使用内置数据集 mtcars 使用 dplyr 函数按组汇总数据的更多示例：

# 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 %>% 运算符，请参阅 introduction to dplyr。

---

rcs 提供的答案很简单。但是，如果您正在处理更大的数据集并需要提高性能，则有一个更快的替代方案：

library(data.table)
data = data.table(Category=c("First","First","First","Second","Third", "Third", "Second"), 
                  Frequency=c(10,15,5,2,14,20,3))
data[, sum(Frequency), by = Category]
#    Category V1
# 1:    First 30
# 2:   Second  5
# 3:    Third 34
system.time(data[, sum(Frequency), by = Category] )
# user    system   elapsed 
# 0.008     0.001     0.009 

让我们将其与使用 data.frame 和上面的内容进行比较：

data = data.frame(Category=c("First","First","First","Second","Third", "Third", "Second"),
                  Frequency=c(10,15,5,2,14,20,3))
system.time(aggregate(data$Frequency, by=list(Category=data$Category), FUN=sum))
# user    system   elapsed 
# 0.008     0.000     0.015 

如果您想保留该列，请使用以下语法：

data[,list(Frequency=sum(Frequency)),by=Category]
#    Category Frequency
# 1:    First        30
# 2:   Second         5
# 3:    Third        34

使用更大的数据集，这种差异将变得更加明显，如下面的代码所示：

data = data.table(Category=rep(c("First", "Second", "Third"), 100000),
                  Frequency=rnorm(100000))
system.time( data[,sum(Frequency),by=Category] )
# user    system   elapsed 
# 0.055     0.004     0.059 
data = data.frame(Category=rep(c("First", "Second", "Third"), 100000), 
                  Frequency=rnorm(100000))
system.time( aggregate(data$Frequency, by=list(Category=data$Category), FUN=sum) )
# user    system   elapsed 
# 0.287     0.010     0.296 

对于多个聚合，您可以组合 lapply 和 .SD 如下

data[, lapply(.SD, sum), by = Category]
#    Category Frequency
# 1:    First        30
# 2:   Second         5
# 3:    Third        34

---

您还可以使用 by() 函数：

x2 <- by(x$Frequency, x$Category, sum)
do.call(rbind,as.list(x2))

那些其他包（plyr、reshape）具有返回 data.frame 的好处，但值得熟悉 by()，因为它是一个基本函数。

---

几年后，只是为了添加另一个简单的基本 R 解决方案，由于某种原因这里不存在 - xtabs

xtabs(Frequency ~ Category, df)
# Category
# First Second  Third 
#    30      5     34 

或者如果你想要一个 data.frame 回来

as.data.frame(xtabs(Frequency ~ Category, df))
#   Category Freq
# 1    First   30
# 2   Second    5
# 3    Third   34

---

library(plyr)
ddply(tbl, .(Category), summarise, sum = sum(Frequency))

---

如果 x 是包含您的数据的数据框，则以下内容将执行您想要的操作：

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

---

虽然我最近在大多数这些类型的操作中转换为 dplyr，但对于某些事情，sqldf 包仍然非常好（恕我直言，更具可读性）。

以下是如何使用 sqldf 回答此问题的示例

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

---

只是添加第三个选项：

require(doBy)
summaryBy(Frequency~Category, data=yourdataframe, FUN=sum)

编辑：这是一个非常古老的答案。现在我建议使用 dplyr 中的 group_by 和 summarise，如 @docendo 答案中所示。

---

另一种在矩阵或数据框中按组返回和的解决方案又短又快：

rowsum(x$Frequency, x$Category)

---

当您需要在不同的列上应用不同的聚合函数（并且您必须/想要坚持使用基础 R）时，我发现 ave 非常有用（且高效）：

例如

鉴于此输入：

DF <-                
data.frame(Categ1=factor(c('A','A','B','B','A','B','A')),
           Categ2=factor(c('X','Y','X','X','X','Y','Y')),
           Samples=c(1,2,4,3,5,6,7),
           Freq=c(10,30,45,55,80,65,50))

> DF
  Categ1 Categ2 Samples Freq
1      A      X       1   10
2      A      Y       2   30
3      B      X       4   45
4      B      X       3   55
5      A      X       5   80
6      B      Y       6   65
7      A      Y       7   50

我们想按 Categ1 和 Categ2 分组并计算 Samples 的总和和 Freq 的平均值。
这是使用 ave 的可能解决方案：

# create a copy of DF (only the grouping columns)
DF2 <- DF[,c('Categ1','Categ2')]

# add sum of Samples by Categ1,Categ2 to DF2 
# (ave repeats the sum of the group for each row in the same group)
DF2$GroupTotSamples <- ave(DF$Samples,DF2,FUN=sum)

# add mean of Freq by Categ1,Categ2 to DF2 
# (ave repeats the mean of the group for each row in the same group)
DF2$GroupAvgFreq <- ave(DF$Freq,DF2,FUN=mean)

# remove the duplicates (keep only one row for each group)
DF2 <- DF2[!duplicated(DF2),]

结果 ：

> DF2
  Categ1 Categ2 GroupTotSamples GroupAvgFreq
1      A      X               6           45
2      A      Y               9           40
3      B      X               7           50
6      B      Y               6           65

---

您可以使用 package Rfast 中的函数 group.sum。

Category <- Rfast::as_integer(Category,result.sort=FALSE) # convert character to numeric. R's as.numeric produce NAs.
result <- Rfast::group.sum(Frequency,Category)
names(result) <- Rfast::Sort(unique(Category)
# 30 5 34

Rfast 有许多组函数，group.sum 就是其中之一。

---

从 dplyr 1.0.0 开始，可以使用 across() 函数：

df %>%
 group_by(Category) %>%
 summarise(across(Frequency, sum))

  Category Frequency
  <chr>        <int>
1 First           30
2 Second           5
3 Third           34

如果对多个变量感兴趣：

df %>%
 group_by(Category) %>%
 summarise(across(c(Frequency, Frequency2), sum))

  Category Frequency Frequency2
  <chr>        <int>      <int>
1 First           30         55
2 Second           5         29
3 Third           34        190

并使用选择助手选择变量：

df %>%
 group_by(Category) %>%
 summarise(across(starts_with("Freq"), sum))

  Category Frequency Frequency2 Frequency3
  <chr>        <int>      <int>      <dbl>
1 First           30         55        110
2 Second           5         29         58
3 Third           34        190        380

样本数据：

df <- read.table(text = "Category Frequency Frequency2 Frequency3
                 1    First        10         10         20
                 2    First        15         30         60
                 3    First         5         15         30
                 4   Second         2          8         16
                 5    Third        14         70        140
                 6    Third        20        120        240
                 7   Second         3         21         42",
                 header = TRUE,
                 stringsAsFactors = FALSE)

---

使用 cast 而不是 recast（注意 'Frequency' 现在是 'value'）

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

install.packages("reshape")

result<-cast(df, Category ~ . ,fun.aggregate=sum)

要得到：

Category (all)
First     30
Second    5
Third     34

---

library(tidyverse)

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

count(x, Category, wt = Frequency)

---

按组对变量求和的好方法是

rowsum(numericToBeSummedUp, groups)

来自基地。这里只有 collapse::fsum 和 Rfast::group.sum 更快。

关于速度和内存消耗

collapse::fsum(numericToBeSummedUp, groups)

是给定示例中最好的，使用分组数据框时可以加快速度。

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

这与将数据集拆分为每组的子数据集的时间很接近。

不同方法的基准测试表明，对单列求和，collapse::fsum 比 Rfast::group.sum 快两倍，比 rowsum 快 7 倍。紧随其后的是 tapply、data.table、by 和 dplyr。 xtabs 和 aggregate 最慢。

聚合两列 collapse::fsum 也是最快的，比 Rfast::group.sum 快 3 倍，比 rowsum 快 5 倍。紧随其后的是 data.table、tapply、by 和 dplyr。同样，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)

一些方法允许执行可能有助于加速聚合的任务。

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)

总结一栏。

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

总结两列

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

---