Day6-R包

## 设置镜像
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)
# 示例数据使用内置数据集iris第1,2,51,52,101,102行数据
test <- iris[c(1:2,51:52,101:102),]


# 1.mutate()，新增列为Sepal.Length与Sepal.Width两列的乘积
mutate(test, new = Sepal.Length * Sepal.Width)
# 2.select()，按列筛选
# 按列号筛选
select(test,1)
select(test,c(1,5))
# 按列名筛选
select(test,Sepal.Length)
select(test,Petal.Length,Petal.Width)
vars <- c("Petal.Length","Petal.Width")
select(test,one_of(vars))
# 3.filter()，按行筛选
filter(test,Species=="setosa")
filter(test,Species=="setosa"&Sepal.Length>5)
filter(test,Species %in% c("setosa","versicolor"))
# 4.arrange(),排序
arrange(test,Sepal.Length)
arrange(test,desc(Sepal.Length))
# 5.summarise():汇总
# 计算Sepal.Length的平均值和标准差
summarise(test, mean(Sepal.Length), sd(Sepal.Length))
# 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%>%
test %>% 
  group_by(Species) %>% 
  summarise(mean(Sepal.Length), sd(Sepal.Length))
# count统计某列的unique值
count(test,Species)


## dplyr处理关系数据
# 将两个表进行连接
test1 <- data.frame(x=c('b','e','f','x'),
                    z=c("A","B","C","D"))
test1
test2 <- data.frame(x=c('a','b','c','d','e','f'),
                    y=c(1,2,3,4,5,6))
test2
# 1.inner_join内连接
inner_join(test1,test2,by='x')
# 2.left_join左连接
left_join(test1,test2,by='x')
left_join(test2,test1,by='x')
# 3.full_join全连接
full_join(test1,test2,by='x')
# 4.semi_join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')
# 5.anti_join反连接：返回无法与y表匹配的x表的所记录
anti_join(x = test2, y = test1, by = 'x')
# 6.合并
# 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)