Day6-学习R包
准备工作:
options("repos" = c(CRAN="https://mirrors.tuna.tsinghua.edu.cn/CRAN/"))
options(BioC_mirror="https://mirrors.ustc.edu.cn/bioc/")
install.packages("dplyr")
library(dplyr)
学习使用dplyr五个基础函数
1.mutate(),新增列,增加的列在最后一列
mutate(test, new = Sepal.Length * Sepal.Width)
2.select(),按列筛选
(1)按列号筛选
select(test,1)
select(test,c(1,5))
select(test,Sepal.Length)
select(test, Species, everything())#重新排序列名,Species在第一列
(2)按列名筛选
select(test, Petal.Length, Petal.Width)
vars <- c("Petal.Length", "Petal.Width")
select(test, one_of(vars))
3.filter()筛选行
filter(test, Species == "setosa")
两个条件一起
filter(test, Species == "setosa"&Sepal.Length > 5 )
filter(test, Species %in% c("setosa","versicolor"))
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
5.summarise():汇总 ;结合group_by使用实用性强
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)
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
将2个表进行连接,注意:不要引入factor
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
5.反连接:返回无法与y表匹配的x表的所记录anti_join
semi_join(x = test1, y = test2, by = 'x')
anti_join(x = test2, y = test1, by = 'x')
6.简单合并
merge函数也可以