R语言基础-3

R语言基础-3

创建test

test <- iris[c(1:2,51:52,101:102),]

test

关于dplyr的五个基础函数

1. mutant()

> 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. select()

> 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. filter()

> filter(test, Species == "setosa")
  Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1          5.1         3.5          1.4         0.2  setosa
2          4.9         3.0          1.4         0.2  setosa
> filter(test, Species == "setosa" & Sepal.Length >5)
  Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1          5.1         3.5          1.4         0.2  setosa
> filter(test, Species %in% c("setosa", "versicolor"))
  Sepal.Length Sepal.Width Petal.Length Petal.Width  
1          5.1         3.5          1.4         0.2      
2          4.9         3.0          1.4         0.2
3          7.0         3.2          4.7         1.4
4          6.4         3.2          4.5         1.5
      Species
1     setosa
2     setosa
3 versicolor
4 versicolor

4. arrange()

> arrange(test, Sepal.Length)
  Sepal.Length Sepal.Width Petal.Length Petal.Width
1          4.9         3.0          1.4         0.2
2          5.1         3.5          1.4         0.2
3          5.8         2.7          5.1         1.9
4          6.3         3.3          6.0         2.5
5          6.4         3.2          4.5         1.5
6          7.0         3.2          4.7         1.4
     Species
1     setosa
2     setosa
3  virginica
4  virginica
5 versicolor
6 versicolor
> arrange(test,desc(Sepal.Length))
  Sepal.Length Sepal.Width Petal.Length Petal.Width
1          7.0         3.2          4.7         1.4
2          6.4         3.2          4.5         1.5
3          6.3         3.3          6.0         2.5
4          5.8         2.7          5.1         1.9
5          5.1         3.5          1.4         0.2
6          4.9         3.0          1.4         0.2
     Species
1 versicolor
2 versicolor
3  virginica
4  virginica
5     setosa
6     setosa

(5)summarise()

> summarise(test, mean(Sepal.Length), sd(Sepal.Length))
  mean(Sepal.Length) sd(Sepal.Length)
1           5.916667        0.8084965
> 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)`
  <fct>                     <dbl>              <dbl>
1 setosa                     5                 0.141
2 versicolor                 6.7               0.424
3 virginica                  6.05              0.354

关于dplyr的两个实用技能

1. 管道操作 %>% (cmd/ctr + shift + M)

> test %>%
+ group_by(Species) %>%
+ summarise(mean(Sepal.Length), sd(Sepal.Length))
# A tibble: 3 x 3
  Species    `mean(Sepal.Length)` `sd(Sepal.Length)`
  <fct>                     <dbl>              <dbl>
1 setosa                     5                 0.141
2 versicolor                 6.7               0.424
3 virginica                  6.05              0.354

2. count统计某列的unique值

> count(test,Species)
# A tibble: 3 x 2
  Species        n
  <fct>      <int>
1 setosa         2
2 versicolor     2
3 virginica      2

dplyr处理关系数据

已知test1， test2

> 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

1.inner_join() #取交集

> inner_join(test1, test2, by ='x')
  x z y
1 b A 2
2 e B 5
3 f C 6

2. left_join()

> 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 <NA>
2 b 2    A
3 c 3 <NA>
4 d 4 <NA>
5 e 5    B
6 f 6    C

3. full_join()

> 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 <NA>  1
6 c <NA>  3
7 d <NA>  4

4.semi_join()

> semi_join(x= test1,y=test2, by = 'x')
  x z
1 b A
2 e B
3 f C

5. anti_join()

> anti_join(x=test2, y=test1, by = 'x')
  x y
1 a 1
2 c 3
3 d 4

6. bind_rows(), bind_cols()

> test1 <- data.frame(x=c(1,2,3,4), y = c(10,20,30,40))
> test1
  x  y
1 1 10
2 2 20
3 3 30
4 4 40
> test2 <- data.frame(x=c(5,6),y =c(50,60))
> test2
  x  y
1 5 50
2 6 60
> test3 <- data.frame(z =c(100,200,300,400) )
> test3
    z
1 100
2 200
3 300
4 400

> bind_rows(test1,test2)
  x  y
1 1 10
2 2 20
3 3 30
4 4 40
5 5 50
6 6 60
> bind_cols(test1,test3)
  x  y   z
1 1 10 100
2 2 20 200
3 3 30 300
4 4 40 400