学习小组Day6笔记--王宇晗

install.packages("dplyr")
library(dplyr)
test <- iris[c(1:2,51:52,101:102),]
#mutate(),新增列
mutate(test, new = Sepal.Length * Sepal.Width)
#select(),按列筛选
select(test,1)
select(test,c(1,5))
select(test,Sepal.Length)
select(test, Petal.Length, Petal.Width)
vars <- c("Petal.Length", "Petal.Width")
select(test, one_of(vars))
#filter()筛选行
filter(test, Species == "setosa")
filter(test, Species == "setosa"&Sepal.Length > 5 )
filter(test, Species %in% c("setosa","versicolor"))
#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
#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))
#管道操作%>%(ctrl+shift+m)
test %>% 
  group_by(Species) %>% 
  summarise(mean(Sepal.Length), sd(Sepal.Length))
#count统计某列的unique值
count(test,Species)
#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
#內连inner_join,取交集
inner_join(test1, test2, by = "x")
#左连left_join
left_join(test1, test2, by = 'x')
left_join(test2, test1, by = 'x')
#全连full_join
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
semi_join(x = test1, y = test2, by = 'x')
#反连接：返回无法与y表匹配的x表的所记录anti_join
anti_join(x = test2, y = test1, by = 'x')
#简单合并 在相当于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
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)