学习小组Day6-guocheng

dplyr包的运用

rm(list = ls())
options(stringsAsFactors = F)
test <- iris[c(1:2,51:52,101:102),]

library(dplyr)

#mutate(),新增列
colnames(test)
mutate(test, new.space=Sepal.Length * Sepal.Width )

#select(),按列筛选
select(test,c(2:4))

#filter()筛选行
filter(test, Species=='virginica'    )

filter(test, test$Sepal.Length >=5 & test$Sepal.Length<6 )

filter(test, Species %in% c('versicolor','virginica') )

#arrange(),按某1列或某几列对整个表格进行排序
arrange(test,Sepal.Length)
arrange(test,desc(Sepal.Length))

#summarise()：汇总
summarise(test,mean(Sepal.Width),sd(Sepal.Width))

# 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))


#管道操作 %>% (cmd/ctr + shift + M)
library(tidyverse)
test %>%
  group_by(Species) %>%
  summarise(mean(Sepal.Width))



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)


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


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

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

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


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