安装和加载R包
1.镜像设置
2.安装
install.packages(“包”)
BiocManager::install(“包”)
取决于你要安装的包存在于CRAN网站还是Biocductor
3.加载
library(包)
require(包)
dplyr五个基础函数
iris
| 花萼长度 花萼宽度 花瓣长度 花瓣宽度
物种 |
Sepal.Length Sepal.Width Petal.Length Petal.Width Species
test <- iris[c(1:2,51:52,101:102),]为例
1.新增列
mutate()
mutate(test, new = Sepal.Length * Sepal.Width)
2.按列筛选
select()
(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))
3.筛选行
.filter()
`filter(test, Species == "setosa"&Sepal.Length > 5 )
filter(test, Species %in% c("setosa","versicolor"))
4.按某1列或某几列对整个表格进行排序
arrange()
arrange(test, Sepal.Length)#默认从小到大排序
arrange(test, desc(Sepal.Length))#用desc从大到小
arrange(test, Sepal.Length, desc(Sepal.Width))
5.汇总
summarise()
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))
dplyr两个实用技能
1：管道操作
%>% (cmd/ctr + shift + M)
（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))
2：count统计某列的unique值
count(test,Species)
dplyr处理关系数据
- 准备工作：即将2个表进行连接
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,取交集
inner_join
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 <- data.frame(z = c(100,200,300,400))
test3
bind_rows(test1, test2)
bind_cols(test1, test3)
18.png
