dplyr包
1.新增列
mutate(test, new = Sepal.Length * Sepal.Width)
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species new
## 1 5.1 3.5 1.4 0.2 setosa 17.85
## 2 4.9 3.0 1.4 0.2 setosa 14.70
## 3 7.0 3.2 4.7 1.4 versicolor 22.40
## 4 6.4 3.2 4.5 1.5 versicolor 20.48
## 5 6.3 3.3 6.0 2.5 virginica 20.79
## 6 5.8 2.7 5.1 1.9 virginica 15.66
2.选择列
select(test,1)
## Sepal.Length
## 1 5.1
## 2 4.9
## 51 7.0
## 52 6.4
## 101 6.3
## 102 5.8
select(test,c(1,5))
## Sepal.Length Species
## 1 5.1 setosa
## 2 4.9 setosa
## 51 7.0 versicolor
## 52 6.4 versicolor
## 101 6.3 virginica
## 102 5.8 virginica
select(test,Sepal.Length)
## Sepal.Length
## 1 5.1
## 2 4.9
## 51 7.0
## 52 6.4
## 101 6.3
## 102 5.8
select(test, Petal.Length, Petal.Width)
## Petal.Length Petal.Width
## 1 1.4 0.2
## 2 1.4 0.2
## 51 4.7 1.4
## 52 4.5 1.5
## 101 6.0 2.5
## 102 5.1 1.9
vars <- c("Petal.Length", "Petal.Width")
select(test, one_of(vars))
## Petal.Length Petal.Width
## 1 1.4 0.2
## 2 1.4 0.2
## 51 4.7 1.4
## 52 4.5 1.5
## 101 6.0 2.5
## 102 5.1 1.9
3.按某列排序
arrange(test, Sepal.Length)#默认从小到大排序
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 4.9 3.0 1.4 0.2 setosa
## 2 5.1 3.5 1.4 0.2 setosa
## 3 5.8 2.7 5.1 1.9 virginica
## 4 6.3 3.3 6.0 2.5 virginica
## 5 6.4 3.2 4.5 1.5 versicolor
## 6 7.0 3.2 4.7 1.4 versicolor
arrange(test, desc(Sepal.Length))#用desc从大到小
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 7.0 3.2 4.7 1.4 versicolor
## 2 6.4 3.2 4.5 1.5 versicolor
## 3 6.3 3.3 6.0 2.5 virginica
## 4 5.8 2.7 5.1 1.9 virginica
## 5 5.1 3.5 1.4 0.2 setosa
## 6 4.9 3.0 1.4 0.2 setosa
4.汇总(好用)
summarise(test, mean(Sepal.Length), sd(Sepal.Length))# 计算Sepal.Length的平均值和标准差
## mean(Sepal.Length) sd(Sepal.Length)
## 1 5.916667 0.8084965
# 先按照Species分组，计算每组Sepal.Length的平均值和标准差
group_by(test, Species)
## # A tibble: 6 x 5
## # Groups: Species [3]
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## * <dbl> <dbl> <dbl> <dbl> <fct>
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3 1.4 0.2 setosa
## 3 7 3.2 4.7 1.4 versicolor
## 4 6.4 3.2 4.5 1.5 versicolor
## 5 6.3 3.3 6 2.5 virginica
## 6 5.8 2.7 5.1 1.9 virginica
summarise(group_by(test, Species),mean(Sepal.Length), sd(Sepal.Length))
## # A tibble: 3 x 3
## Species `mean(Sepal.Length)` `sd(Sepal.Length)`
##
## 1 setosa 5 0.141
## 2 versicolor 6.7 0.424
## 3 virginica 6.05 0.354
5.管道
test %>%
group_by(Species) %>%
summarise(mean(Sepal.Length), sd(Sepal.Length))
## # A tibble: 3 x 3
## Species `mean(Sepal.Length)` `sd(Sepal.Length)`
##
## 1 setosa 5 0.141
## 2 versicolor 6.7 0.424
## 3 virginica 6.05 0.354
6.count统计某列的unique值(table)
count(test,Species)
## # A tibble: 3 x 2
## Species n
##
## 1 setosa 2
## 2 versicolor 2
## 3 virginica 2
7.dplyr处理关系数据(转id可以用到)
options(stringsAsFactors = F)
test1 <- data.frame(x = c('b','e','f','x'),
z = c("A","B","C",'D'),
stringsAsFactors = F)
test1
## x z
## 1 b A
## 2 e B
## 3 f C
## 4 x D
test2 <- data.frame(x = c('a','b','c','d','e','f'),
y = c(1,2,3,4,5,6),
stringsAsFactors = F)
test2
## x y
## 1 a 1
## 2 b 2
## 3 c 3
## 4 d 4
## 5 e 5
## 6 f 6
inner_join(test1, test2, by = "x")#取交集
## x z y
## 1 b A 2
## 2 e B 5
## 3 f C 6
left_join(test1, test2, by = 'x')
## x z y
## 1 b A 2
## 2 e B 5
## 3 f C 6
## 4 x D NA
left_join(test2, test1, by = 'x')
## x y z
## 1 a 1
## 2 b 2 A
## 3 c 3
## 4 d 4
## 5 e 5 B
## 6 f 6 C
full_join( test1, test2, by = 'x')
## x z y
## 1 b A 2
## 2 e B 5
## 3 f C 6
## 4 x D NA
## 5 a
## 6 c
## 7 d
semi_join(x = test1, y = test2, by = 'x')
## x z
## 1 b A
## 2 e B
## 3 f C
anti_join(x = test2, y = test1, by = 'x')
## x y
## 1 a 1
## 2 c 3
## 3 d 4
虽然dplyr包函数可以通过base包达到一样的效果，但是dplyr包方便了很多有木有。
