Szukaj…


Wprowadzenie

Agregacja jest jednym z najczęstszych zastosowań R. Istnieje kilka sposobów, aby to zrobić w R, które zilustrujemy tutaj.

Agregacja z zasadą R.

W tym celu użyjemy funkcji agregującej, której można użyć w następujący sposób:

aggregate(formula,function,data)

Poniższy kod pokazuje różne sposoby korzystania z funkcji agregującej.

KOD:

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)

WYNIK:

> 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

Agregowanie za pomocą dplyr

Agregowanie za pomocą dplyr jest łatwe! Możesz użyć do tego funkcji group_by () i summarize (). Niektóre przykłady podano poniżej.

KOD:

# 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()

WYNIK:

> 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

Agregowanie za pomocą data.table

Grupowanie z pakietem data.table odbywa się za pomocą składni dt[i, j, by] można odczytać na głos: „ Weź dt, podzbiór wierszy za pomocą i, a następnie oblicz j, pogrupowane według. ” W instrukcji dt , wiele obliczeń lub grup należy umieścić na liście. Ponieważ alias dla list() to .() , Oba mogą być używane zamiennie. W poniższych przykładach używamy .() .

KOD:

# 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]

WYNIK:

> # 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


Modified text is an extract of the original Stack Overflow Documentation
Licencjonowany na podstawie CC BY-SA 3.0
Nie związany z Stack Overflow