options("repos"=c(CRAN="https://mirrors.tuna.tsinghua.edu.cn/CRAN/"))
options(BioC_mirror="https://mirrors.ustc.edu.cn/bioc/") #以上都是镜像设置,为了加速下载R包
install.packages('dplyr') #安装“dplyr”包
library(dplyr) #加载“dplyr”包
使用 iris的简化版
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
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))
(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))
count(test,Species)
即将两个表进行连接
test1 <- data.frame(x = c('b','e','f','x'), z = c("A","B","C",'D'))
test2 <- data.frame(x = c('a','b','c','d','e','f'), y = c(1,2,3,4,5,6))
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')
anti_join(x = test2, y = test1, by = 'x')
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)
bind_cols(test1, test3)
原创声明:本文系作者授权腾讯云开发者社区发表,未经许可,不得转载。
如有侵权,请联系 cloudcommunity@tencent.com 删除。
原创声明:本文系作者授权腾讯云开发者社区发表,未经许可,不得转载。
如有侵权,请联系 cloudcommunity@tencent.com 删除。