day6-学习R包

options("repos"=c(CRAN="http://mirrors.tuna.tsinghua.edu.cn/CRAN/"))
options(BioC_mirror="https://mirrors.westlake.edu.cn/bioconductor")

install.packages("stringr")#安装来自cran的stringr包
BiocManager::install("limma")#安装来自Biocductor的limma包

options("repos" = c(CRAN="https://mirrors.tuna.tsinghua.edu.cn/CRAN/")) 
options(BioC_mirror="http://mirrors.tuna.tsinghua.edu.cn/bioconductor/")
install.packages("dplyr")
library(dplyr)

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

mutate(test, new = Sepal.Length * Sepal.Width)

select(test,1)
select(test,c(1,5))
select(test,Sepal.Length)

select(test, Petal.Length, Petal.Width)
vars <- c("Petal.Length", "Petal.Width")
select(test, one_of(vars))

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

arrange(test, Sepal.Length)#默认从小到大排序
arrange(test, desc(Sepal.Length))#用desc从大到小

summarise(test, mean(Sepal.Length), sd(Sepal.Length))# 计算Sepal.Length的平均值和标准差
# 先按照Species分组，计算每组Sepal.Length的平均值和标准差
group_by(test, Species)
summarise(group_by(test, Species),mean(Sepal.Length), sd(Sepal.Length))

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

count(test,Species)

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

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

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

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

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

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

test1 <- data.frame(x = c(1,2,3,4), y = c(10,20,30,40))
test1
test2 <- data.frame(x = c(5,6), y = c(50,60))
test2
test3 <- data.frame(z = c(100,200,300,400))
test3
bind_rows(test1, test2)
bind_cols(test1, test3)

?sd

browseVignettes("limma")