1.镜像设置

options("repos" = c(CRAN="https://mirrors.tuna.tsinghua.edu.cn/CRAN/")) 
options(BioC_mirror="https://mirrors.ustc.edu.cn/bioc/") 

此过程可参考生信星球指南

镜像设置

2.dplyr的五个基本函数

2.1 mutate(),新增列

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

2.1 mutate(),新增列

2.2 select(),按列筛选

(1)按列号筛选

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

2.2 select(),按列筛选，(1)按列号筛选

(2)按列名筛选

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

2.2 select(),按列筛选，(2)按列名筛选

2.3 filter()筛选行

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

2.3 filter()筛选行

2.4 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

2.4 arrange(),按某1列或某几列对整个表格进行排序

2.5 summarise()：汇总

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))

2.5 summarise()：汇总

3.dplyr两个实用技能

3.1 管道操作 %>% (cmd/ctr + shift + M)

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

3.2 count统计某列的unique值

count(test,Species)

3.dplyr两个实用技能

4.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 

4.1 內连inner_join,取交集

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

4.2 左连left_join

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

4.1和4.2

4.3 全连full_join

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

4.4 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')

4.5 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')

4.3、4.4、4.5

4.6 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)

4.6 学习小组Day6笔记--高晨Xmind

以上代码来源于生信星球