安装、加载R包和dplyr包的使用
一、镜像设置
1.初级模式设置
26980503-d2c93307b1b95e10.png
2. options函数就是设置R运行过程中的一些选项设置
##检验镜像环境
options()$repos
# CRAN和Bioconductor镜像设置
options("repos" = c(CRAN="https://mirrors.tuna.tsinghua.edu.cn/CRAN/")) #对应清华源
options(BioC_mirror="https://mirrors.ustc.edu.cn/bioc/") #对应中科大源
##检验Bioconductor镜像
options()$BioC_mirror
##R的配置文件 .Rprofile
file.edit('~/.Rprofile')
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
options()$repos
options()$BioC_mirror
二、包的安装与加载
1. R包安装
CRAN网站 install.packages(“包”)
Biocductor BiocManager::install(“包”)
2. R包加载
library(包)
require(包)
3. 安装加载三部曲
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)
三、dplyr包的应用
1. 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
51 7.0 3.2 4.7 1.4 versicolor 22.40
52 6.4 3.2 4.5 1.5 versicolor 20.48
101 6.3 3.3 6.0 2.5 virginica 20.79
102 5.8 2.7 5.1 1.9 virginica 15.666
2. select(),按列筛选
(1) 按列号筛选
> test <- iris[c(1:2,51:52,101:102),]
> 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
(2) 按列名筛选
> 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
> 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
> 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
> 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
4. arrange(),按某1列或某几列对整个表格进行排序
-
?desc
将一个向量转换为将按降序排序的格式。这在arrange()中很有用。
> 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
> arrange(test, Sepal.Length) #默认从小到大排序
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)) #用desc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
5. summarise():汇总
(1) 直接汇总
> 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
> # 计算Sepal.Length的平均值和标准差
> summarise(test, mean(Sepal.Length), sd(Sepal.Length))
mean(Sepal.Length) sd(Sepal.Length)
1 5.916667 0.8084965
(2)对数据进行“ group_by ”汇总操作
> 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
> # 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 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))
# 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 0.35
四、dplyr两个实用技能
1. 管道操作 %>% (cmd/ctr + shift + M)(加载任意一个tidyverse包即可用管道符号)
> ?tidyverse
No documentation for ‘tidyverse’ in specified packages and libraries:
you could try ‘??tidyverse’
> ??tidyverse
> 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
> 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
2. count统计某列的unique值
> 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
> count(test,Species)
Species n
1 setosa 2
2 versicolor 2
3 virginica 2
五、dplyr处理关系数据
- 即将2个表进行连接,注意:不要引入factor
stringsAsFactors:
default.stringsAsFactors的默认设置,在R < 4.1.0中,它被用来提供data.fram和read.table的stringsAsFactors参数的默认值。
> options(stringsAsFactors = F)
> ?options
> ?data.frame
> 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
1.內连inner_join,取交集
> 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
> 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
> 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
> test1
x z
1 b A
2 e B
3 f C
4 x D
> test2
x y
1 a 1
2 b 2
3 c 3
4 d 4
5 e 5
6 f 6
> 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表的所有记录anti_join
> test1
x z
1 b A
2 e B
3 f C
4 x D
> test2
x y
1 a 1
2 b 2
3 c 3
4 d 4
5 e 5
6 f 6
> anti_join(x = test2, y = test1, by = 'x')
x y
1 a 1
2 c 3
3 d 4
6.简单合并
在相当于base包里的cbind()函数和rbind()函数;
注意,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
> 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