一、思维导图

二、示例代码
1、dplyr五大函数
install.packages("dplyr")
library(dplyr)
test <- iris[c(1:2,51:52,101:102),]#示例数据
#新增列
mutate(test,new = Sepal.Length * Sepal.Width)
#选择列
##按列号选
select(test,1)
select(test,c(1,5))
select(test,Sepal.Length)
##按列名选
select(test,Petal.Length, Petal.Width)
vars <- c("Petal.Length", "Petal.Width")
select(test,one_of(vars))
#筛选行
filter(test,Species == "setosa")
filter(test, Species == "setosa"&Sepal.Length >5)
#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))#从大到小用desc
#汇总,结合group_by实用性强
summarise(test,mean(Sepal.Length),sd(Sepal.Length))
group_by(test,Species)##先按照species分组,再计算每组均值和标准差
summarise(group_by(test,Species),mean(Sepal.Length), sd(Sepal.Length))
2、dplyr两大实用技能
#管道
test %>%
group_by(Species) %>%
summarise(mean(Sepal.Length),sd(Sepal.Length))
#count统计某列的unique值
count(test,Species)
3、dplyr处理关系数据
注意不要引入因子factor,设置stringsAsFactors = F
options(stringsAsFactors = F)
test1 <- data.frame(x = c('b','e','f','x'),
z = c('A','B','C','D'),
stringsAsFactors = F)
test2 <- data.frame(x = c('a','b','c','d','e','f'),
y = c(1,2,3,4,5,6),
stringsAsFactors = F)
test2
#内连取交集
inner_join(test1, test2, by = "x")
#左连,谁写在前以谁为准
left_join(test1, test2, by = "x")
left_join(test2, test1, by = "x")
#全连
full_join(test1, test2, by = "x")
#半连接。返回能够与y表匹配的x表所有记录
semi_join(x = test1, y = test2, by = "x")
#反连接,返回无法与y表匹配的x表的所有记录
anti_join(x = test2, y = test1, by = 'x')
#简单合并,相当于base包里的cbind()函数和rbind()函数;
#注意,bind_rows()函数需要两个表格列数相同,而bind_cols()函数则需要两个数据框有相同的行数
test3 <- data.frame(x = c(1,2,3,4), y = c(10,20,30,40))
test3
test4 <- data.frame(x = c(5,6), y = c(50,60))
test4
test5 <- data.frame(z = c(100,200,300,400))
test5
bind_rows(test3, test4)
bind_cols(test3, test5)
网友评论