学习小组Day6笔记-FoMo

R包安装

install.packages(“包”)
BiocManager::install(“包”)

R包加载

library(包)

dplyr包

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

mutate() ：新增列

mutate(test, new = Sepal.Length * Sepal.Width)

select()：按列筛选

可按列号、列名筛选

> 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

filter()：筛选行

> 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    Species
1          5.1         3.5          1.4         0.2     setosa
2          4.9         3.0          1.4         0.2     setosa
3          7.0         3.2          4.7         1.4 versicolor
4          6.4         3.2          4.5         1.5 versicolor

arrange()：按某1列或某几列对整个表格进行排序

> arrange(test,Sepal.Length) # 默认为从小到大
  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)) #使用desc使排序为从大到小
  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

summarise()：汇总

> 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

> group_by(test, Species) #按Species分组
# 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))
# 先按照Species分组，计算每组Sepal.Length的平均值和标准差
# 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

dplyr的两个实用技能

管道操作 %>%（快键键：cmd+shift+M）

管道操作可以连续传参，省去中间变量。左侧作为参数传入右侧函数内部

> 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

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

演示数据

> 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：取交集

> inner_join(test1,test2,by="x") #取x的交集
  x z y
1 b A 2
2 e B 5
3 f C 6

left_jion：左连

> 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

full_join：全连

> 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

semi_join：半连接-返回能够与y表匹配的x表所有记录

> semi_join(x = test1, y = test2,by="x") # x=,y=可以省略
  x z
1 b A
2 e B
3 f C

anti_join：反连接—返回无法与y表匹配的x表的所记录

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

bind_rows,bind_cols：简单合并

相当于base包里的cbind()函数和rbind()函数

bind_rows()函数需要两个数据框列数相同
bind_cols()函数需要两个数据框行数相同

示例数据

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