Day-6 香波🐟

options("repos" = c(CRAN="https://mirrors.tuna.tsinghua.edu.cn/CRAN/")) #对应清华源
options(BioC_mirror="https://mirrors.ustc.edu.cn/bioc/") #对应中科大源

install.packages("dplyr")
library(dplyr)

arrange(test, Sepal.Length)#默认从小到大排序
arrange(test, desc(Sepal.Length))#用desc从大到小

summary(test)#区分base包里的summary和dplyr包里的summarise函数
summarise(test, mean(Sepal.Length), sd(Sepal.Length))# 计算Sepal.Length的平均值和标准差
# 先按照Species分组，计算每组Sepal.Length的平均值和标准差
group_by(test, Species)
summarise(group_by(test, Species),mean(Sepal.Length), sd(Sepal.Length))
summary(test)
 ##Sepal.Length    Sepal.Width     Petal.Length    Petal.Width   
 ##Min.   :4.900   Min.   :2.700   Min.   :1.400   Min.   :0.200  
 ##1st Qu.:5.275   1st Qu.:3.050   1st Qu.:2.175   1st Qu.:0.500  
 ##Median :6.050   Median :3.200   Median :4.600   Median :1.450  
 ##Mean   :5.917   Mean   :3.150   Mean   :3.850   Mean   :1.283  
 ##3rd Qu.:6.375   3rd Qu.:3.275   3rd Qu.:5.000   3rd Qu.:1.800  
 ##Max.   :7.000   Max.   :3.500   Max.   :6.000   Max.   :2.500  
 ##   Species 
 ##setosa    :2  
 ##versicolor:2  
 ##virginica :2 
                              
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 × 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 × 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

test |> 
+     group_by(Species) |> 
+      summarise(mean(Sepal.Length), sd(Sepal.Length))
# A tibble: 3 × 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

> 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))
> inner_join(test1,test2,by="x")
  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
> 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(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
> 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