title: "数据框取子集、修改和连接的方法"
output: html_document
date: "2023-03-18"
df1 <- data.frame(gene = paste0("gene",1:4),
change = rep(c("up","down"),each = 2),
score = c(5,3,-2,-4))
df1
## gene change score
## 1 gene1 up 5
## 2 gene2 up 3
## 3 gene3 down -2
## 4 gene4 down -4
df1$gene #df1后加"$",再按tab键可以直接选择df1的列名
## [1] "gene1" "gene2" "gene3" "gene4"
df1$score
## [1] 5 3 -2 -4
mean(df1$score) #计算scroe这一列的均值
## [1] 0.5
df1[,"gene"]
## [1] "gene1" "gene2" "gene3" "gene4"
df1[,c('gene','change')]
## gene change
## 1 gene1 up
## 2 gene2 up
## 3 gene3 down
## 4 gene4 down
df1[df1$score>0,] #取score>0的行
## gene change score
## 1 gene1 up 5
## 2 gene2 up 3
df1[2,] #取第2行
## gene change score
## 2 gene2 up 3
df1[,2] #取第2列
## [1] "up" "up" "down" "down"
df1[2,2] #取第2行,第2列
## [1] "up"
df1[c(1,3),1:2] #取第1和第3行,第1和第2列
## gene change
## 1 gene1 up
## 3 gene3 down
df1[,ncol(df1)] #最后一列就是列数值
## [1] 5 3 -2 -4
df1[,-ncol(df1)]
## gene change
## 1 gene1 up
## 2 gene2 up
## 3 gene3 down
## 4 gene4 down
df1[df1$score > 0,1] #方法1
## [1] "gene1" "gene2"
df1[df1$score > 0,"gene"] #方法2
## [1] "gene1" "gene2"
df1$gene[df1$score > 0] #方法3
## [1] "gene1" "gene2"
df1[3,3] <- 5
df1
## gene change score
## 1 gene1 up 5
## 2 gene2 up 3
## 3 gene3 down 5
## 4 gene4 down -4
df1$score <- c(12,23,50,2)
df1
## gene change score
## 1 gene1 up 12
## 2 gene2 up 23
## 3 gene3 down 50
## 4 gene4 down 2
df1$p.value <- c(0.01,0.02,0.07,0.05)
df1
## gene change score p.value
## 1 gene1 up 12 0.01
## 2 gene2 up 23 0.02
## 3 gene3 down 50 0.07
## 4 gene4 down 2 0.05
rownames(df1) <- c("r1","r2","r3","r4")
df1
## gene change score p.value
## r1 gene1 up 12 0.01
## r2 gene2 up 23 0.02
## r3 gene3 down 50 0.07
## r4 gene4 down 2 0.05
colnames(df1)[2] <- "CHANGE"
df1
## gene CHANGE score p.value
## r1 gene1 up 12 0.01
## r2 gene2 up 23 0.02
## r3 gene3 down 50 0.07
## r4 gene4 down 2 0.05
df1[!duplicated(df1$CHANGE),]
## gene CHANGE score p.value
## r1 gene1 up 12 0.01
## r3 gene3 down 50 0.07
test1 <- data.frame(name = c('jimmy','nicker','Damon','Sophie'),
blood_type = c("A","B","O","AB"))
test1
## name blood_type
## 1 jimmy A
## 2 nicker B
## 3 Damon O
## 4 Sophie AB
test2 <- data.frame(name = c('Damon','jimmy','nicker','tony'),
group = c("group1","group1","group2","group2"),
vision = c(4.2,4.3,4.9,4.5))
test2
## name group vision
## 1 Damon group1 4.2
## 2 jimmy group1 4.3
## 3 nicker group2 4.9
## 4 tony group2 4.5
test3 <- data.frame(NAME = c('Damon','jimmy','nicker','tony'),
weight = c(140,145,110,138))
test3
## NAME weight
## 1 Damon 140
## 2 jimmy 145
## 3 nicker 110
## 4 tony 138
merge(test1,test2,by="name")
## name blood_type group vision
## 1 Damon O group1 4.2
## 2 jimmy A group1 4.3
## 3 nicker B group2 4.9
merge(x = test1,y = test3,by.x = "name",by.y = "NAME")
## name blood_type weight
## 1 Damon O 140
## 2 jimmy A 145
## 3 nicker B 110
test1 <- data.frame(name = c('jimmy','nicker','Damon','Sophie'),
blood_type = c("A","B","O","AB"))
test1
## name blood_type
## 1 jimmy A
## 2 nicker B
## 3 Damon O
## 4 Sophie AB
test2 <- data.frame(name = c('Damon','jimmy','nicker','tony'),
group = c("group1","group1","group2","group2"),
vision = c(4.2,4.3,4.9,4.5))
test2
## name group vision
## 1 Damon group1 4.2
## 2 jimmy group1 4.3
## 3 nicker group2 4.9
## 4 tony group2 4.5
library(dplyr)
inner_join(test1,test2,by="name") #取交集
## name blood_type group vision
## 1 jimmy A group1 4.3
## 2 nicker B group2 4.9
## 3 Damon O group1 4.2
right_join(test1,test2,by="name") #右连接,保留右边表格的name列,缺失值填充NA
## name blood_type group vision
## 1 jimmy A group1 4.3
## 2 nicker B group2 4.9
## 3 Damon O group1 4.2
## 4 tony <NA> group2 4.5
full_join(test1,test2,by="name") #全连接,两个表的name列都要,缺失值填充NA
## name blood_type group vision
## 1 jimmy A group1 4.3
## 2 nicker B group2 4.9
## 3 Damon O group1 4.2
## 4 Sophie AB <NA> NA
## 5 tony <NA> group2 4.5
semi_join(test1,test2,by="name") #半连接,左边表格中的人名在右边表格中存在的行则保留,否则删去
## name blood_type
## 1 jimmy A
## 2 nicker B
## 3 Damon O
anti_join(test1,test2,by="name") #反连接,左边表格中的人名在右边表格中不存在的行保留,否则删去
## name blood_type
## 1 Sophie AB
引用自生信技能树
原创声明:本文系作者授权腾讯云开发者社区发表,未经许可,不得转载。
如有侵权,请联系 cloudcommunity@tencent.com 删除。
原创声明:本文系作者授权腾讯云开发者社区发表,未经许可,不得转载。
如有侵权,请联系 cloudcommunity@tencent.com 删除。