检验RStudio的镜像
options()$repos
options()$BioC_mirror
设置国内镜像
options(BioC_mirror="https://mirrors.ustc.edu.cn/bioc/")
install.packages("dplyr")
library(dplyr)
Warning?
test <- iris[c(1:2,51:52,101:102),]
新增列
mutate(test, new = Sepal.Length * Sepal.Width)
按列号筛选
select(test,c(1,5))
select(test,Sepal.Length)
按列名筛选
vars <- c("Petal.Length", "Petal.Width")
select(test, one_of(vars))
filter()筛选行
选择species中是setosa的行
filter(test, Species == "setosa")
filter(test, Species == "setosa"&Sepal.Length > 5 )
选择是setosa的行和是versicolor的行
filter(test, Species %in% c("setosa","versicolor"))
排序
arrange(test, Sepal.Length)
降序？
arrange(test, desc(Sepal.Length)
summarise(test, mean(Sepal.Length), sd(Sepal.Length)
先按照Species分组，计算每组Sepal.Length的平均值和标准差
group_by(test, Species)
group这步代表？
summarise(group_by(test, Species),mean(Sepal.Length), sd(Sepal.Length))
管道操作是啥？还未理解。
每一行代码意思？
group_by(Species) %>%
summarise(mean(Sepal.Length), sd(Sepal.Length))
计算n有多少个
count(test,Species)
options(stringsAsFactors = F)
创建表为后续练习
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
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
bind_rows(test1, test2)
bind_cols(test1, test3)
