1. 安装加载R包
1. 镜像设置
(1) 输入命令file.edit("~/.Rprofile")
,打开如下图:
(2) 在弹出的框中输入:
options("repos"=c(CRAN="https://mirrors.tuna.tsinghua.edu.cn/CRAN/"))
options(BioC_mirror="https://mirrors.ustc.edu.cn/bioc/")
(3) 保存重启Rstudio,运行 options()$repos
和options()$BioC_mirror
发现配置好了
2. 安装
根据需求选取
install.packages("安装包的名字") #从CRAN下载
BiocManager::install("安装包的名字") #从biocductor下载
3. 加载
以下命令均可
library(包)
require(包)
合在一起可一步完成
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) #下载dplyr为例
示例数据:
test <- iris[c(1:2,51:52,101:102),] #直接使用内置数据集iris的简化版
对test赋值
2. dplyr五个基础函数
1. 新增列: mutate()
mutate(test, new = Sepal.Length * Sepal.Width)
Sepal.Length Sepal.Width Petal.Length
1 5.1 3.5 1.4
2 4.9 3.0 1.4
3 7.0 3.2 4.7
4 6.4 3.2 4.5
5 6.3 3.3 6.0
6 5.8 2.7 5.1
Petal.Width Species new #新增的new=Sepal.Length * Sepal.Width
1 0.2 setosa 17.85
2 0.2 setosa 14.70
3 1.4 versicolor 22.40
4 1.5 versicolor 20.48
5 2.5 virginica 20.79
6 1.9 virginica 15.66
2.按列筛选: select()
(1)按列号筛选
> select(test,1) # test的第1列
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)) # test的第1和5列
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) # 叫Sepal.Length的那列
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
> 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. 按行筛选:filter()
> filter(test, Species == "setosa") #test中含有setosa的行
Sepal.Length Sepal.Width Petal.Length
1 5.1 3.5 1.4
2 4.9 3.0 1.4
Petal.Width Species
1 0.2 setosa
2 0.2 setosa
> filter(test, Species == "setosa"&Sepal.Length > 5 ) #含有setosa且Sepal.Length > 5
Sepal.Length Sepal.Width Petal.Length
1 5.1 3.5 1.4
Petal.Width Species
1 0.2 setosa
> filter(test, Species %in% c("setosa","versicolor")) # Species中含versicolor和virginica的行
Sepal.Length Sepal.Width Petal.Length
1 5.1 3.5 1.4
2 4.9 3.0 1.4
3 7.0 3.2 4.7
4 6.4 3.2 4.5
Petal.Width Species
1 0.2 setosa
2 0.2 setosa
3 1.4 versicolor
4 1.5 versicolor
4. 按某1列或某几列对整个表格进行排序
> arrange(test, Sepal.Length) #按Sepal.Length这一列排序,默认从小到大排序
Sepal.Length Sepal.Width Petal.Length
1 4.9 3.0 1.4
2 5.1 3.5 1.4
3 5.8 2.7 5.1
4 6.3 3.3 6.0
5 6.4 3.2 4.5
6 7.0 3.2 4.7
Petal.Width Species
1 0.2 setosa
2 0.2 setosa
3 1.9 virginica
4 2.5 virginica
5 1.5 versicolor
6 1.4 versicolor
> arrange(test, desc(Sepal.Length)) #用desc按Sepal.Length从大到小
Sepal.Length Sepal.Width Petal.Length
1 7.0 3.2 4.7
2 6.4 3.2 4.5
3 6.3 3.3 6.0
4 5.8 2.7 5.1
5 5.1 3.5 1.4
6 4.9 3.0 1.4
Petal.Width Species
1 1.4 versicolor
2 1.5 versicolor
3 2.5 virginica
4 1.9 virginica
5 0.2 setosa
6 0.2 setosa
5.汇总:summarise()
结合group_by()
> 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
> 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)) #按Species分组求Sepal.Length的平均值和标准差
# 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
3. dplyr两个实用技能
1. 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)`
<fct> <dbl> <dbl>
1 setosa 5 0.141
2 versicolor 6.7 0.424
3 virginica 6.05 0.354
2. 统计元素个数:count()
> count(test,Species)
# A tibble: 3 x 2
Species n
<fct> <int>
1 setosa 2
2 versicolor 2
3 virginica 2
3. 处理关系数据
2个表如下举例
> 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
1. 内联,取交集, 合并:inner_join()
> inner_join(test1, test2, by = "x")
x z y
1 b A 2
2 e B 5
3 f C 6
2. 左联: 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. 全联, 取并集: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:其中一列的交集,和对应的x表:semi_join()
> 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(某列补集):anti_join()
> anti_join(x = test2, y = test1, by = 'x')
x y
1 a 1
2 c 3
3 d 4
6. 简单合并
bind_rows()
两个表格列数一样
bind_cols()
两个数据框行数一样
> 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
网友评论