学习R包

学习R包

生信必备Biocductor上生信分析R包
以dplyr为例

1. 配置Rstudio镜像

#代码源生信星球
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

2. 安装
   install.packages(' ')
BiocManager::install(" ")
3. 加载
   library()
require()

dplyr五个基础函数

> test <-  iris[c(1:2,51:52,101:102),]
> test
    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
51           7.0         3.2          4.7         1.4
52           6.4         3.2          4.5         1.5
101          6.3         3.3          6.0         2.5
102          5.8         2.7          5.1         1.9
       Species
1       setosa
2       setosa
51  versicolor
52  versicolor
101  virginica
102  virginica
> library(dplyr)

1. mutate() 新增列

> mutate(test,new=Sepal.Length* Sepal.Width)
    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
51           7.0         3.2          4.7         1.4
52           6.4         3.2          4.5         1.5
101          6.3         3.3          6.0         2.5
102          5.8         2.7          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
   按列号筛选
   select(test,1)
select(test,c(1,5))
select(test,Sepal.Length)
   按列名筛选
   select(test, Petal.Length, Petal.Width)

   vars <- c("Petal.Length", "Petal.Width")
select(test, one_of(vars))

> select(test,Sepal.Length)
    Sepal.Length
1            5.1
2            4.9
51           7.0
52           6.4
101          6.3
102          5.8

3. filter()筛选行

filter(test, Species == "setosa")
#筛选Species == setosa的行
filter(test, Species == "setosa"&Sepal.Length > 5 )
#筛选Species == setosa并且Sepal.Length>5的行
filter(test, Species %in% c("setosa","versicolor"))
#筛选Species 属于 setosa或versicolor的行

4. arrange(),按某1列或某几列队整个表格进行排序

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

5.summarise()汇总

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))

dplyr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))
###等同于summarise(group_by(test, Species),mean(Sepal.Length), sd(Sepal.Length))

2. count统计某列的unique值
   count(test,Species)

dplyr 处理关系数据

> 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

The mutating joins add columns from y to x, matching rows based on the keys:
inner_join(): includes all rows in x and y.
left_join(): includes all rows in x.
right_join(): includes all rows in y.
full_join(): includes all rows in x or y.
If a row in x matches multiple rows in y, all the rows in y will be returned once for each matching row in x.

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

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

简单合并
cbind() rbind()
bind_rows()函数需要两个表格列数相同，而bind_cols()函数则需要两个数据框有相同的行数