R的一些常規(guī)操作
包的安裝
install.packages("包")
BioManager::install("包")
包的加載
library（包）
require（包）
注意嚴(yán)格區(qū)分大小寫
library(dplyr)
test<-iris[c(1:2,51:52,101:102),]
test
mutate(test,new = Sepal.Length * Sepal.Width) #新增列
#select 按列篩選
#按列號(hào)篩選
select(test,1)
select(test,c(1,5))
select(test,Sepal.Length)
#按列名篩選
select(test,Petal.Length,Petal.Width)
vars<-c("Petal.Length","Petal.Width")
select(test,one_of(vars))
#filter（）篩選行 ==表示判斷 &表示并逾一，%in%表示包含
filter(test,Species=="setosa")
filter(test,Species=="setosa"&Sepal.Length > 5)
filter(test,Species %in% c("setosa","versicolor"))
#arrange()按某一列或某幾列對(duì)整個(gè)表格進(jìn)行排序
arrange(test,Sepal.Length)##默認(rèn)從小到大排序
arrange(test,desc(Sepal.Length))#用desc從大到小
###summarise():匯總
summarise(test,mean(Sepal.Length),sd(Sepal.Length))
#先按照Species分組诸狭，計(jì)算每組Sepal.Length的平均值和標(biāo)準(zhǔn)差
group_by(test,Species)
summarise(group_by(test,Species),mean(Sepal.Length),sd(Sepal.Length))
##管道操作%>%(cmd/ctr+shift+M)
test %>%
group_by(Species) %>%
summarise(mean(Sepal.Length),sd(Sepal.Length))
###count統(tǒng)計(jì)某列的unique值
count(test,Species)
##dplyrc處理關(guān)系數(shù)據(jù)
#將兩個(gè)表進(jìn)行連接，注意：不要引入factor
option(stringAsFactors = 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(nèi)連inner_join,取交集
inner_join(test1,test2,by = "x")
#左連left_join
left_join(test1,test2,by = 'x')
left_join(test2,test1,by = 'x')
#全連接full_join
full_join(test1,test2,by = 'x')
#半連接：返回能夠與y表匹配的x表所有記錄semi_join
semi_join(x = test1,y = test2,by= 'x')
#反連接：返回?zé)o法與y表匹配的x表的所記錄anti_join
anti_join(x = test2, y = test1,by = 'x')
#簡(jiǎn)單合并
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)
