學習R包
思維導圖
鏡像設置
- 1.R的配置文件 .Rprofile
file.edit('~/.Rprofile')
- 2.中科大源
options(BioC_mirror="https://mirrors.ustc.edu.cn/bioc/")
- 3.清華源
options("repos" = c(CRAN="[https://mirrors.tuna.tsinghua.edu.cn/CRAN/](https://mirrors.tuna.tsinghua.edu.cn/CRAN/)"))
4.重啟Rstudio
-
5.驗證
options()$repos options()$BioC_mirror驗證鏡像配置
安裝
install.packages(“包”)
BiocManager::install(“包”)
install.packages(“ggplot2”)
BiocManager::install(“clusterProfiler”)
加載
library(包)
require(包)
library(“ggplot2”)
require(“ggplot2”)
dplyr五個基礎函數(shù)
-
1.mutate(),新增列
test <- iris[c(1:2,51:52,101:102),] mutate(test, new = Sepal.Length * Sepal.Width)
mutate(),新增列
- 2.select(),按列篩選
(1)按列號篩選
select(test,1)
select(test,c(1,5))
select(),按列號篩選
(2)按列名篩選
select(test,Sepal.Length)
select(test, Petal.Length, Petal.Width)
select(),按列名篩選
-
3.filter(),篩選行
filter(test, Species == "setosa") filter(test, Species == "setosa"&Sepal.Length > 5 ) filter(test, Species %in% c("setosa","versicolor"))
filter(),篩選行
- 4.arrange(),按某1列或某幾列對整個表格進行排序
arrange(test, Sepal.Length)#默認從小到大排序
arrange(test, desc(Sepal.Length))#用desc從大到小
arrange(),按列排序
- 5.summarise(),匯總
summarise(test, mean(Sepal.Length), sd(Sepal.Length))# 計算Sepal.Length的平均值和標準差
summarise(),匯總
dplyr兩個實用技能
- 1.管道操作 %>% (cmd/ctr + shift + M)
test %>%
group_by(Species) %>%
summarise(mean(Sepal.Length), sd(Sepal.Length))
管道操作
- 2.count,統(tǒng)計某列的unique值
count(test,Species)
count,統(tǒng)計某列的unique值
dplyr處理關系數(shù)據
test1 <- data.frame(x = c('b','e','f','x'),
z = c("A","B","C",'D'),
stringsAsFactors = F)
test1
test1
test2 <- data.frame(x = c('a','b','c','d','e','f'),
y = c(1,2,3,4,5,6),
stringsAsFactors = F)
test2
test2
- 1.內連inner_join,取交集
inner_join(test1, test2, by = "x")
內連inner_join,取交集
- 2.左連left_join
left_join(test1, test2, by = 'x')
left_join(test2, test1, by = 'x')
內連inner_join,取交集
- 3.全連full_join
full_join( test1, test2, by = 'x')
全連full_join
- 4.半連接semi_join,返回能夠與y表匹配的x表所有記錄
semi_join(x = test1, y = test2, by = 'x')
半連接semi_join,返回能夠與y表匹配的x表所有記錄
- 5.反連接anti_join,返回無法與y表匹配的x表的所記錄
anti_join(x = test2, y = test1, by = 'x')
反連接anti_join
- 6.簡單合并
test1 <- data.frame(x = c(1,2,3,4), y = c(10,20,30,40))
test1
test1
test2 <- data.frame(x = c(5,6), y = c(50,60))
test2
test2
test3 <- data.frame(z = c(100,200,300,400))
test3
test3
bind_rows()
bind_rows(test1, test2)
bind_rows()
bind_cols()
bind_cols(test1, test3)
bind_cols()
