LunaprimRose 2020.03.18
Day 6.png
Install and load R package
镜像设置
-
CRAN镜像-
TUNA Team, Tsinghua Universityhttps://mirrors.tuna.tsinghua.edu.cn/CRAN/ -
University of Science and Technology of Chinahttps://mirrors.ustc.edu.cn/CRAN/ -
Lanzhou University Open Source Societyhttps://mirror.lzu.edu.cn/CRAN/ -
Tencenthttps://mirrors.cloud.tencent.com/CRAN/ -
Aliyunhttps://mirrors.aliyun.com/CRAN/
-
-
Bioconductor镜像-
TUNA Team, Tsinghua Universityhttps://mirrors.tuna.tsinghua.edu.cn/bioconductor/ -
University of Science and Technology of Chinahttps://mirrors.ustc.edu.cn/bioc/
-
- 初始模式
RStudio - Tools - Global Options - Packegs - Package Managment
- 升级模式
Tuna Team, Tsinghua University 为例
options("repos" = c(CRAN="https://mirrors.tuna.tsinghua.edu.cn/CRAN/"))
options(BioC_mirror="https://mirrors.tuna.tsinghua.edu.cn/bioconductor")
options()$repos
CRAN
"https://mirrors.tuna.tsinghua.edu.cn/CRAN/"
China(Tencent)
"http://mirrors.cloud.tencent.com/CRAN/"
attr(,"RStudio")
[1] TRUE
options()$BioC_mirror
[1] "https://mirrors.tuna.tsinghua.edu.cn/bioconductor"
- 高级模式
file.edit("~/.Rprofile")
options("repos" = c(CRAN="https://mirrors.tuna.tsinghua.edu.cn/CRAN/"))
options(BioC_mirror="https://mirrors.tuna.tsinghua.edu.cn/bioconductor")
Install Packages
- 在线安装
install.packegs('ggplot2')
BiocManager::install('DEseq2')
- 本地安装
install.packages('path_to_packages')
Load Packages
library('ggplot2')
require('ggplot2')
Basic function
-
mutate()新增列
test <- iris[c(1:2,51:52,101:102),]
test
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
51 7.0 3.2 4.7 1.4 versicolor
52 6.4 3.2 4.5 1.5 versicolor
101 6.3 3.3 6.0 2.5 virginica
102 5.8 2.7 5.1 1.9 virginica
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
transmute(test,new = Sepal.Length*Sepal.Width)
new
1 17.85
2 14.70
3 22.40
4 20.48
5 20.79
6 15.66
-
select()按列筛选
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(1,3))
Sepal.Length Petal.Length
1 5.1 1.4
2 4.9 1.4
51 7.0 4.7
52 6.4 4.5
101 6.3 6.0
102 5.8 5.1
select(test,1,Species)
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
-
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()排序
arrange(test,Sepal.Length)
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))
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))
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
*
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)`
1 setosa 5 0.141
2 versicolor 6.7 0.424
3 virginica 6.05 0.354
Practical skills
- 管道操作
test %>% group_by(Species) %>% summarise(mean(Sepal.Length),sd(Sepal.Length))
# A tibble: 3 x 3
Species `mean(Sepal.Length)` `sd(Sepal.Length)`
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
1 setosa 2
2 versicolor 2
3 virginica 2
Manage Relational data
处理表连接时，不要引入
factor
- 内连接
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(test1,test2,by = 'x')
x z y
1 b A 2
2 e B 5
3 f C 6
- 左连接
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
- 全连接
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 1
6 c 3
7 d 4
- 半连接
semi_join(x= test1,y= test2,by = 'x')
x z
1 b A
2 e B
3 f C
- 反连接
anti_join(x=test2,y=test1,by='x')
x y
1 a 1
2 c 3
3 d 4
- 简单合并
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