1.dplyr五個基礎(chǔ)函數(shù)（數(shù)據(jù)使用內(nèi)置數(shù)據(jù)集iris）
1.mutate(),新增列
mutate(test, new = Sepal.Length * Sepal.Width)
image.png
2.select(),按列篩選
select(test,1)
select(test,c(1,5))
select(test,Sepal.Length)
image.png
(2)按列名篩選
select(test, Petal.Length, Petal.Width)
vars <- c("Petal.Length", "Petal.Width")
select(test, one_of(vars))
image.png
image.png
3.filter()篩選行
filter(test, Species == "setosa")
image.png
filter(test, Species == "setosa"&Sepal.Length > 5 )
image.png
filter(test, Species %in% c("setosa","versicolor"))
image.png
4.arrange(),按某1列或某幾列對整個表格進(jìn)行排序
arrange(test, Sepal.Length)#默認(rèn)從小到大排序
image.png
arrange(test, desc(Sepal.Length))#用desc從大到小
image.png
5.summarise()：匯總
summarise(test, mean(Sepal.Length), sd(Sepal.Length))# 計算Sepal.Length的平均值和標(biāo)準(zhǔn)差
image.png
group_by(test, Species)
image.png
summarise(group_by(test, Species),mean(Sepal.Length), sd(Sepal.Length))
image.png
2.dplyr兩個實用技能
1.管道操作 %>% (cmd/ctr + shift + M)
image.png
2：count統(tǒng)計某列的unique值
image.png
3.dplyr處理關(guān)系數(shù)據(jù)
1.內(nèi)連inner_join,取交集
image.png
image.png
inner_join(test1, test2, by = "x")
image.png
2.左連left_join
left_join(test1, test2, by = 'x')
image.png
left_join(test1, test2, by = 'x')
image.png
3.全連full_join
image.png
4.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')
image.png
5.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')
image.png
6.簡單合并
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)
