R Language
Агрегирование кадров данных
Поиск…
Вступление
Агрегация является одним из наиболее распространенных способов использования R. В R есть несколько способов сделать это, что мы проиллюстрируем здесь.
Агрегация с базой R
Для этого мы будем использовать агрегат функции, который можно использовать следующим образом:
aggregate(formula,function,data)
Следующий код показывает различные способы использования агрегатной функции.
КОД:
df = data.frame(group=c("Group 1","Group 1","Group 2","Group 2","Group 2"), subgroup = c("A","A","A","A","B"),value = c(2,2.5,1,2,1.5))
# sum, grouping by one column
aggregate(value~group, FUN=sum, data=df)
# mean, grouping by one column
aggregate(value~group, FUN=mean, data=df)
# sum, grouping by multiple columns
aggregate(value~group+subgroup,FUN=sum,data=df)
# custom function, grouping by one column
# in this example we want the sum of all values larger than 2 per group.
aggregate(value~group, FUN=function(x) sum(x[x>2]), data=df)
ВЫХОД:
> df = data.frame(group=c("Group 1","Group 1","Group 2","Group 2","Group 2"), subgroup = c("A","A","A","A","B"),value = c(2,2.5,1,2,1.5))
> print(df)
group subgroup value
1 Group 1 A 2.0
2 Group 1 A 2.5
3 Group 2 A 1.0
4 Group 2 A 2.0
5 Group 2 B 1.5
>
> # sum, grouping by one column
> aggregate(value~group, FUN=sum, data=df)
group value
1 Group 1 4.5
2 Group 2 4.5
>
> # mean, grouping by one column
> aggregate(value~group, FUN=mean, data=df)
group value
1 Group 1 2.25
2 Group 2 1.50
>
> # sum, grouping by multiple columns
> aggregate(value~group+subgroup,FUN=sum,data=df)
group subgroup value
1 Group 1 A 4.5
2 Group 2 A 3.0
3 Group 2 B 1.5
>
> # custom function, grouping by one column
> # in this example we want the sum of all values larger than 2 per group.
> aggregate(value~group, FUN=function(x) sum(x[x>2]), data=df)
group value
1 Group 1 2.5
2 Group 2 0.0
Агрегатирование с помощью dplyr
Агрегация с dplyr проста! Для этого вы можете использовать функции group_by () и summary (). Ниже приведены некоторые примеры.
КОД:
# Aggregating with dplyr
library(dplyr)
df = data.frame(group=c("Group 1","Group 1","Group 2","Group 2","Group 2"), subgroup = c("A","A","A","A","B"),value = c(2,2.5,1,2,1.5))
print(df)
# sum, grouping by one column
df %>% group_by(group) %>% summarize(value = sum(value)) %>% as.data.frame()
# mean, grouping by one column
df %>% group_by(group) %>% summarize(value = mean(value)) %>% as.data.frame()
# sum, grouping by multiple columns
df %>% group_by(group,subgroup) %>% summarize(value = sum(value)) %>% as.data.frame()
# custom function, grouping by one column
# in this example we want the sum of all values larger than 2 per group.
df %>% group_by(group) %>% summarize(value = sum(value[value>2])) %>% as.data.frame()
ВЫХОД:
> library(dplyr)
>
> df = data.frame(group=c("Group 1","Group 1","Group 2","Group 2","Group 2"), subgroup = c("A","A","A","A","B"),value = c(2,2.5,1,2,1.5))
> print(df)
group subgroup value
1 Group 1 A 2.0
2 Group 1 A 2.5
3 Group 2 A 1.0
4 Group 2 A 2.0
5 Group 2 B 1.5
>
> # sum, grouping by one column
> df %>% group_by(group) %>% summarize(value = sum(value)) %>% as.data.frame()
group value
1 Group 1 4.5
2 Group 2 4.5
>
> # mean, grouping by one column
> df %>% group_by(group) %>% summarize(value = mean(value)) %>% as.data.frame()
group value
1 Group 1 2.25
2 Group 2 1.50
>
> # sum, grouping by multiple columns
> df %>% group_by(group,subgroup) %>% summarize(value = sum(value)) %>% as.data.frame()
group subgroup value
1 Group 1 A 4.5
2 Group 2 A 3.0
3 Group 2 B 1.5
>
> # custom function, grouping by one column
> # in this example we want the sum of all values larger than 2 per group.
> df %>% group_by(group) %>% summarize(value = sum(value[value>2])) %>% as.data.frame()
group value
1 Group 1 2.5
2 Group 2 0.0
Агрегация с помощью data.table
Группировка с пакетом data.table выполняется с использованием синтаксиса dt[i, j, by]
который можно прочитать вслух, как: « Возьмите dt, подмножество строк с помощью i, затем вычислите j, сгруппированные по. » Внутри оператора dt , несколько списков или групп должны быть помещены в список. Поскольку псевдоним для list()
is .()
, Оба могут использоваться взаимозаменяемо. В приведенных ниже примерах мы используем .()
.
КОД:
# Aggregating with data.table
library(data.table)
dt = data.table(group=c("Group 1","Group 1","Group 2","Group 2","Group 2"), subgroup = c("A","A","A","A","B"),value = c(2,2.5,1,2,1.5))
print(dt)
# sum, grouping by one column
dt[,.(value=sum(value)),group]
# mean, grouping by one column
dt[,.(value=mean(value)),group]
# sum, grouping by multiple columns
dt[,.(value=sum(value)),.(group,subgroup)]
# custom function, grouping by one column
# in this example we want the sum of all values larger than 2 per group.
dt[,.(value=sum(value[value>2])),group]
ВЫХОД:
> # Aggregating with data.table
> library(data.table)
>
> dt = data.table(group=c("Group 1","Group 1","Group 2","Group 2","Group 2"), subgroup = c("A","A","A","A","B"),value = c(2,2.5,1,2,1.5))
> print(dt)
group subgroup value
1: Group 1 A 2.0
2: Group 1 A 2.5
3: Group 2 A 1.0
4: Group 2 A 2.0
5: Group 2 B 1.5
>
> # sum, grouping by one column
> dt[,.(value=sum(value)),group]
group value
1: Group 1 4.5
2: Group 2 4.5
>
> # mean, grouping by one column
> dt[,.(value=mean(value)),group]
group value
1: Group 1 2.25
2: Group 2 1.50
>
> # sum, grouping by multiple columns
> dt[,.(value=sum(value)),.(group,subgroup)]
group subgroup value
1: Group 1 A 4.5
2: Group 2 A 3.0
3: Group 2 B 1.5
>
> # custom function, grouping by one column
> # in this example we want the sum of all values larger than 2 per group.
> dt[,.(value=sum(value[value>2])),group]
group value
1: Group 1 2.5
2: Group 2 0.0