生信星球培训第四十六期

DAY6--如晤

2020-03-26  本文已影响0人  如晤_ea28
学习R包,以dplyr为例

1.配置镜像

你还在每次配置Rstudio的下载镜像吗?
目的:为了加速包的下载
为免去打开Rstudio都要运行一遍镜像配置的麻烦,就需要用到R的配置文件.Rprofile

2.安装

R包安装命令(根据包存在的地址选择)

`install.packages(“包”) `#安装包存在于CRAN网站
`BiocManager::install(“包”)` #安装包存在于biocductor

(_install本质上也是调用install.packages)

3.加载

library(包)或者
require(包)

实例总结:dplyr下载-安装-加载

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)
#先赋值:示例数据直接使用内置数据集iris的简化版
test <- iris[c(1:2,51:52,101:102),]

1.mutate(),新增列

> 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

2.select(),按列筛选

#(1)按列号筛选
> 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(1,5))
    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
> 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

> 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

> 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

> summarise(test, mean(Sepal.Length), sd(Sepal.Length))
#对指定行计算平均值和标准差
  mean(Sepal.Length) sd(Sepal.Length)
1           5.916667        0.8084965

> group_by(test, Species)
#按照Species分组
# 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分组后再计算每组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
  1. 管道操作%>%
    (加载任意一个tidyverse包即可用管道符号)
> 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统计某列的unique值.count

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

两个表test1\2

> test1 <- data.frame(x = c('b','e','f','x'), 
+                     z = c("A","B","C",'D'),
+                     stringsAsFactors = F)
> test2 <- data.frame(x = c('a','b','c','d','e','f'), 
+                     y = c(1,2,3,4,5,6),
+                     stringsAsFactors = F)

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

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

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

> 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
创建表格

> 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

合并表格

> bind_rows(test1, test2)#函数需要两个表格列数相同
  x  y
1 1 10
2 2 20
3 3 30
4 4 40
5 5 50
6 6 60
> bind_cols(test1, test3)#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

(在相当于base包里的cbind()函数和rbind()函数;注意,bind_rows(),而bind_cols()函数则)

上一篇下一篇

猜你喜欢

热点阅读