1.鏡像設(shè)置

options("repos" = c(CRAN="https://mirrors.tuna.tsinghua.edu.cn/CRAN/")) 
options(BioC_mirror="https://mirrors.ustc.edu.cn/bioc/") 

此過程可參考生信星球指南

鏡像設(shè)置

2.dplyr的五個基本函數(shù)

2.1 mutate(),新增列

mutate(test, new = Sepal.Length * Sepal.Width)

2.1 mutate(),新增列

2.2 select(),按列篩選

(1)按列號篩選

select(test,1)
select(test,c(1,5))
select(test,Sepal.Length)

2.2 select(),按列篩選，(1)按列號篩選

(2)按列名篩選

select(test, Petal.Length, Petal.Width)
vars <- c("Petal.Length", "Petal.Width")
select(test, one_of(vars))

2.2 select(),按列篩選，(2)按列名篩選

2.3 filter()篩選行

filter(test, Species == "setosa")
filter(test, Species == "setosa"&Sepal.Length > 5 )
filter(test, Species %in% c("setosa","versicolor"))

2.3 filter()篩選行

2.4 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
arrange(test, desc(Sepal.Length))#用desc從大到小

2.4 arrange(),按某1列或某幾列對整個表格進(jìn)行排序

2.5 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
# 先按照Species分組，計算每組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))

2.5 summarise()：匯總

3.dplyr兩個實(shí)用技能

3.1 管道操作 %>% (cmd/ctr + shift + M)

test %>% 
  group_by(Species) %>% 
  summarise(mean(Sepal.Length), sd(Sepal.Length))

3.2 count統(tǒng)計某列的unique值

count(test,Species)

3.dplyr兩個實(shí)用技能

4.dplyr處理關(guān)系數(shù)據(jù)

options(stringsAsFactors = 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 

4.1 內(nèi)連inner_join,取交集

inner_join(test1, test2, by = "x")

4.2 左連left_join

left_join(test1, test2, by = 'x')
left_join(test2, test1, by = 'x')

4.1和4.2

4.3 全連full_join

full_join( test1, test2, by = 'x')

4.4 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')

4.5 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')

4.3、4.4、4.5

4.6 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)

4.6

學(xué)習(xí)小組Day6筆記--高晨Xmind

以上代碼來源于生信星球