镜像设置
- 1 file.edit('~/.Rprofile')
- 2
options("repos" = c(CRAN="https://mirrors.tuna.tsinghua.edu.cn/CRAN/"))
options(BioC_mirror="https://mirrors.ustc.edu.cn/bioc/") - 3查询
options()$repos 和options()$BioC_mirror
安装加载
install.packages("dplyr"),library(dplyr)
install.packages(“包”)/BiocManager::install(“包”)。取决于你要安装的包存在于CRAN网站还是Biocductor
dplyr的五个基础函数
mutate（）新增列
mutate(test, new = Sepal.Length * Sepal.Width)
select（）按列筛选
1按列号筛选
select(test,1)
select(test,c(1,5))
select(test,Sepal.Length)
2按列名筛选
select(test, Petal.Length, Petal.Width)
vars <- c("Petal.Length", "Petal.Width")
select(test, one_of(vars))
3filter筛选行
filter(test, Species == "setosa")
filter(test, Species == "setosa"&Sepal.Length > 5 )
filter(test, Species %in% c("setosa","versicolor"))
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
5summarise()：汇总
summarise(test, mean(Sepal.Length), sd(Sepal.Length))# 计算Sepal.Length的平均值和标准差
group_by(test, Species)
先按照Species分组，计算每组Sepal.Length的平均值和标准差
summarise(group_by(test, Species),mean(Sepal.Length), sd(Sepal.Length))
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))
2count统计某列的unique值
count(test,Species)
dplyr处理关系数据
options(stringsAsFactors = F)
test1 <- data.frame(x = c('b','e','f','x'),
z = c("A","B","C",'D'),
stringsAsFactors = F)
test1
test2 <- data.frame(x = c('a','b','c','d','e','f'),
y = c(1,2,3,4,5,6),
stringsAsFactors = F)
test2
1.內连inner_join,取交集
inner_join(test1, test2, by = "x")
2.左连left_join
left_join(test1, test2, by = 'x')
left_join(test2, test1, by = 'x')
3.全连full_join
full_join( test1, test2, by = 'x')
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')
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')
6.简单合并
在相当于base包里的cbind()函数和rbind()函数;注意，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
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)```