学习R包

思维导图

镜像设置

• 1.R的配置文件 .Rprofile

file.edit('~/.Rprofile')

• 2.中科大源

options(BioC_mirror="https://mirrors.ustc.edu.cn/bioc/") 

• 3.清华源

options("repos" = c(CRAN="[https://mirrors.tuna.tsinghua.edu.cn/CRAN/](https://mirrors.tuna.tsinghua.edu.cn/CRAN/)")) 

• 4.重启Rstudio

• 5.验证

  options()$repos
  options()$BioC_mirror
  

  验证镜像配置

安装

install.packages(“包”)
BiocManager::install(“包”)

 install.packages(“ggplot2”)
 BiocManager::install(“clusterProfiler”)

加载

library(包)
require(包)

library(“ggplot2”)
require(“ggplot2”)

dplyr五个基础函数

• 1.mutate(),新增列

  test <- iris[c(1:2,51:52,101:102),]
  mutate(test, new = Sepal.Length * Sepal.Width)
  

mutate(),新增列

• 2.select(),按列筛选

(1)按列号筛选

  select(test,1)
  select(test,c(1,5))

select(),按列号筛选

(2)按列名筛选

select(test,Sepal.Length)
select(test, Petal.Length, Petal.Width)

select(),按列名筛选

• 3.filter(),筛选行

  filter(test, Species == "setosa")
  filter(test, Species == "setosa"&Sepal.Length > 5 )
  filter(test, Species %in% c("setosa","versicolor"))
  

filter(),筛选行

• 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
arrange(test, desc(Sepal.Length))#用desc从大到小

arrange(),按列排序

• 5.summarise(),汇总

summarise(test, mean(Sepal.Length), sd(Sepal.Length))# 计算Sepal.Length的平均值和标准差

summarise(),汇总

dplyr两个实用技能

• 1.管道操作 %>% (cmd/ctr + shift + M)

test %>% 
  group_by(Species) %>% 
  summarise(mean(Sepal.Length), sd(Sepal.Length))  

管道操作

• 2.count,统计某列的unique值

count(test,Species)

count,统计某列的unique值

dplyr处理关系数据

test1 <- data.frame(x = c('b','e','f','x'), 
                    z = c("A","B","C",'D'),
                    stringsAsFactors = F)
test1

test1

test2 <- data.frame(x = c('a','b','c','d','e','f'), 
                    y = c(1,2,3,4,5,6),
                    stringsAsFactors = F)
test2

test2

• 1.內连inner_join,取交集

inner_join(test1, test2, by = "x")

內连inner_join,取交集

• 2.左连left_join

left_join(test1, test2, by = 'x')
left_join(test2, test1, by = 'x')

內连inner_join,取交集

• 3.全连full_join

full_join( test1, test2, by = 'x')

全连full_join

• 4.半连接semi_join,返回能够与y表匹配的x表所有记录

semi_join(x = test1, y = test2, by = 'x')

半连接semi_join,返回能够与y表匹配的x表所有记录

• 5.反连接anti_join,返回无法与y表匹配的x表的所记录

anti_join(x = test2, y = test1, by = 'x')

反连接anti_join

• 6.简单合并

test1 <- data.frame(x = c(1,2,3,4), y = c(10,20,30,40))
test1

test1

test2 <- data.frame(x = c(5,6), y = c(50,60))
test2

test2

test3 <- data.frame(z = c(100,200,300,400))
test3

test3

bind_rows()

bind_rows(test1, test2)

bind_rows()

bind_cols()

bind_cols(test1, test3)

bind_cols()