Day6 学习R包(今天依旧是干货满满但是要注重理解)

2024-03-09 23:46:45 浏览数 (1)

一、安装加载R包

1.安装加载

代码语言:R复制
options("repos" = c(CRAN="https://mirrors.tuna.tsinghua.edu.cn/CRAN/")) 
options(BioC_mirror="https://mirrors.ustc.edu.cn/bioc/") 
install.packages("dplyr")
library(dplyr)

2.简化

代码语言:R复制
test <- iris[c(1:2,51:52,101:102),]

二、dplyr五个基础函数

1.mutate(),新增列

代码语言:R复制
> mutate(test, new = Sepal.Length * Sepal.Width)
    Sepal.Length Sepal.Width
1            5.1         3.5
2            4.9         3.0
51           7.0         3.2
52           6.4         3.2
101          6.3         3.3
102          5.8         2.7
    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
       Species   new
1       setosa 17.85
2       setosa 14.70
51  versicolor 22.40
52  versicolor 20.48
101  virginica 20.79
102  virginica 15.66

2.select(),按列筛选

代码语言:R复制
# 按列号筛选
> 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
# 按列名筛选
> 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()筛选行

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

4.arrange(),按某1列或某几列对整个表格进行排序

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

5.summarise():汇总

代码语言:R复制
> summarise(test, mean(Sepal.Length), sd(Sepal.Length))
  mean(Sepal.Length)
1           5.916667
  sd(Sepal.Length)
1        0.8084965
> group_by(test, Species)
# A tibble: 6 × 5
# Groups:   Species [3]
  Sepal.Length Sepal.Width
         <dbl>       <dbl>
1          5.1         3.5
2          4.9         3  
3          7           3.2
4          6.4         3.2
5          6.3         3.3
6          5.8         2.7
# ℹ 3 more variables:
#   Petal.Length <dbl>,
#   Petal.Width <dbl>,
#   Species <fct>
> summarise(group_by(test, Species),mean(Sepal.Length), sd(Sepal.Length))
# A tibble: 3 × 3
  Species   `mean(Sepal.Length)`
  <fct>                    <dbl>
1 setosa                    5   
2 versicol…                 6.7 
3 virginica                 6.05
# ℹ 1 more variable:
#   `sd(Sepal.Length)` <dbl>

三、dplyr两个实用技能

1:管道操作 %>% (cmd/ctr shift M)

代码语言:R复制
> test %>% 
      group_by(Species) %>% 
      summarise(mean(Sepal.Length), sd(Sepal.Length))
# A tibble: 3 × 3
  Species   `mean(Sepal.Length)`
  <fct>                    <dbl>
1 setosa                    5   
2 versicol…                 6.7 
3 virginica                 6.05
# ℹ 1 more variable:
#   `sd(Sepal.Length)` <dbl>

2:count统计某列的unique值

代码语言:R复制
> count(test,Species)
     Species n
1     setosa 2
2 versicolor 2
3  virginica 2

四、dplyr处理关系数据

将表连接

代码语言:R复制
> test1 <- data.frame(x = c('b','e','f','x'), 
                      z = c("A","B","C",'D'))
> test2 <- data.frame(x = c('a','b','c','d','e','f'), 
                      y = c(1,2,3,4,5,6))
> View(test2)
> View(test1)
> View(test)
> View(test)

1.內连inner_join,取交集

代码语言:R复制
> inner_join(test1, test2, by = "x")
  x z y
1 b A 2
2 e B 5
3 f C 6

2.左连left_join

代码语言:R复制
> 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.全连full_join

代码语言:R复制
> 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.半连接:返回能够与y表匹配的x表所有记录semi_join

代码语言:R复制
> semi_join(x = test1, y = test2, by = 'x')
  x z
1 b A
2 e B
3 f C

5.反连接:返回无法与y表匹配的x表的所记录anti_join

代码语言:R复制
> anti_join(x = test2, y = test1, by = 'x')
  x y
1 a 1
2 c 3
3 d 4

6.简单合并

代码语言:R复制
> 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))
> 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

感jio最近要做的事好多,要忙不过来了,思维导图来个简易版

奋力肝ing奋力肝ing
学习R包学习R包

0 人点赞