R包

1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

2安装

install.packages("ape") BiocManager::install("ape")

3浏览

library("ape") require("ape")

4 ''dplyr''包

新增列 mutate（）

> library(dplyr)
> test <- iris[c(1:2,51:52,101:102),]
> 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

筛选列 select()

> select(test,c(1,3)) #按照列号筛选第1和3列
    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, Petal.Length, Species) #按照列筛选
    Petal.Length    Species
1            1.4     setosa
2            1.4     setosa
51           4.7 versicolor
52           4.5 versicolor
101          6.0  virginica
102          5.1  virginica

筛选行 filter()

> filter(test, Species %in% c("setosa","versicolor")&Sepal.Length > 5)
  Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
1          5.1         3.5          1.4         0.2     setosa
2          7.0         3.2          4.7         1.4 versicolor
3          6.4         3.2          4.5         1.5 versicolor 

按某1列或某几列对整个表格进行排序arrange()

> arrange(test, desc(Petal.Width))   #用desc从大到小，默认为从小到大
  Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
1          6.3         3.3          6.0         2.5  virginica
2          5.8         2.7          5.1         1.9  virginica
3          6.4         3.2          4.5         1.5 versicolor
4          7.0         3.2          4.7         1.4 versicolor
5          5.1         3.5          1.4         0.2     setosa
6          4.9         3.0          1.4         0.2     setosa

summarise() 汇总计算 count（） 计数

>group_by(test, Species)#根据species分组
> summarise(group_by(test, Species),mean(Petal.Length), sd(Petal.Length),mean(Sepal.Width))#计算分组下的mean和sd
# A tibble: 3 x 4
  Species    `mean(Petal.Length)` `sd(Petal.Length)` `mean(Sepal.Width)`
  <fct>                     <dbl>              <dbl>               <dbl>
1 setosa                     1.4               0                    3.25
2 versicolor                 4.6               0.141                3.2 
3 virginica                  5.55              0.636                3   

> count(test,Species) #统计species的unique值
# A tibble: 3 x 2
  Species        n
  <fct>      <int>
1 setosa         2
2 versicolor     2
3 virginica      2

dplyr处理关系数据

> inner_join(test1, test2, by = "x") #內连inner_join,取交集 
  x z y
1 b A 2
2 e B 5
3 f C 6
> left_join(test2, test1, by = 'x')   #左连left_join
  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
> full_join( test1, test2, by = 'x')  #全连full_join
  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')  #半连接：返回能够与y表匹配的x表所有记录semi_join
  x z
1 b A
2 e B
3 f C
> anti_join(x = test2, y = test1, by = 'x')  #反连接：返回无法与y表匹配的x表的所记录anti_join
  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)  #简单合并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
  x  y   z
1 1 10 100
2 2 20 200
3 3 30 300
4 4 40 400