学习小组Day6笔记-青青

R包--dplyr为例

安装与加载

1. 镜像设置
   Tools>Global options>Pakages>CRAN
   options()$repos检查镜像网站
   options("repos" = c(CRAN="https://mirrors.tuna.tsinghua.edu.cn/CRAN/"))
options(BioC_mirror="https://mirrors.ustc.edu.cn/bioc/")
2. 安装
   install.packages(“dplyr”)/BiocManager::install(“dplyr”)
   出现问题：重新设置镜像；不存在叫‘pillar’这个名字的程辑包：下载pillar
3. 加载
   library(包)
require(包)
4. 示例数据
   test <- iris[c(1:2,51:52,101:102),]

dplyr五个基础函数

1. mutate(),新增列
   mutate(test, new = Sepal.Length * Sepal.Width)
2. select(),按列筛选
   (1) 按列号
   select(test,1)
select(test,c(1,5))
select(test,Sepal.Length)
   (2) 按列名
   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")
filter(test, Species == "setosa"&Sepal.Length > 5 )
filter(test, Species %in% c("setosa","versicolor"))
4. arrange(),按某1列或几列对表格排序
   (1) 默认从小到大排序
   arrange(test, Sepal.Length)
   (2) 用desc从大到小
   arrange(test, desc(Sepal.Length))
5. summarise(),汇总
   结合group_by更好
   (1) 计算Sepal.Length的平均值和标准差
   summarise(test, mean(Sepal.Length), sd(Sepal.Length))
   (2) 先按Species分组，再进行计算上述
   group_by(test, Species)
summarise(group_by(test, Species),mean(Sepal.Length), sd(Sepal.Length))

dplyr实用技能

1. 管道操作 %>% (cmd/ctr + shift + M)
   tidyverse包的加载
   test %>%
group_by(Species) %>%
summarise(mean(Sepal.Length), sd(Sepal.Length))
2. count统计某列unique值
   count(test,Species)

dplyr处理关系数据

连接两个表，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)
test2 <- data.frame(x = c('a','b','c','d','e','f'), y = c(1,2,3,4,5,6),stringsAsFactors = F)

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
   返回与y表匹配的x表的记录
   semi_join(x = test1, y = test2, by = 'x')
5. 反连接
   返回无法与y表匹配的x表的记录
   anti_join(x = test2, y = test1, by = 'x')
6. 简单合并
   bind_rows() --列数相同
   bind_cols() --行数相同
   test1 <- data.frame(x = c(1,2,3,4), y = c(10,20,30,40))
test2 <- data.frame(x = c(5,6), y = c(50,60))
test3 <- data.frame(z = c(100,200,300,400))
bind_rows(test1, test2)
bind_cols(test1, test3)