鏡像設(shè)置
- 1 file.edit('~/.Rprofile')
- 2
options("repos" = c(CRAN="https://mirrors.tuna.tsinghua.edu.cn/CRAN/"))
options(BioC_mirror="https://mirrors.ustc.edu.cn/bioc/") - 3查詢
options()$repos 和options()$BioC_mirror
安裝加載
install.packages("dplyr"),library(dplyr)
install.packages(“包”)/BiocManager::install(“包”)壮莹。取決于你要安裝的包存在于CRAN網(wǎng)站還是Biocductor
dplyr的五個基礎(chǔ)函數(shù)
mutate（）新增列
mutate(test, new = Sepal.Length * Sepal.Width)
select（）按列篩選
1按列號篩選
select(test,1)
select(test,c(1,5))
select(test,Sepal.Length)
2按列名篩選
select(test, Petal.Length, Petal.Width)
vars <- c("Petal.Length", "Petal.Width")
select(test, one_of(vars))
3filter篩選行
filter(test, Species == "setosa")
filter(test, Species == "setosa"&Sepal.Length > 5 )
filter(test, Species %in% c("setosa","versicolor"))
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
5summarise()：匯總
summarise(test, mean(Sepal.Length), sd(Sepal.Length))# 計算Sepal.Length的平均值和標準差
group_by(test, Species)
先按照Species分組，計算每組Sepal.Length的平均值和標準差
summarise(group_by(test, Species),mean(Sepal.Length), sd(Sepal.Length))
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))
2count統(tǒng)計某列的unique值
count(test,Species)
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
1.內(nèi)連inner_join,取交集
inner_join(test1, test2, by = "x")
2.左連left_join
left_join(test1, test2, by = 'x')
left_join(test2, test1, by = 'x')
3.全連full_join
full_join( test1, test2, by = 'x')
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')
5.反連接：返回無法與y表匹配的x表的所記錄anti_join
anti_join(x = test2, y = test1, by = 'x')
6.簡單合并
在相當于base包里的cbind()函數(shù)和rbind()函數(shù);注意，bind_rows()函數(shù)需要兩個表格列數(shù)相同，而bind_cols()函數(shù)則需要兩個數(shù)據(jù)框有相同的行數(shù)
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)```