2-R语言数据结构

#重点：数据框
#1.数据框来源
# （1）用代码新建
# （2）由已有数据转换或处理得到
# （3）读取表格文件
# （4）R语言内置数据

#2.新建和读取数据框
df1 <- data.frame(gene   = paste0("gene",1:4),
                 change  = rep(c("up","down"),each = 2),
                 score   = c(5,3,-2,-4)) #每一列之间要用,隔开
df1

##    gene change score
## 1 gene1     up     5
## 2 gene2     up     3
## 3 gene3   down    -2
## 4 gene4   down    -4

df2 <- read.csv("gene.csv") #工作目录下
df2

##    gene change score
## 1 gene1     up     5
## 2 gene2     up     3
## 3 gene3   down    -2
## 4 gene4   down    -4

#3.数据框属性
#
dim(df1)

## [1] 4 3

nrow(df1) #行数

## [1] 4

ncol(df1) #列数

## [1] 3

#
rownames(df1) #行名

## [1] "1" "2" "3" "4"

colnames(df1) #列名

## [1] "gene"   "change" "score"

#4.数据框取子集
df1$score  #删掉score，按tab键试试,$后可用tab切换

## [1]  5  3 -2 -4

df1$gene #取列

## [1] "gene1" "gene2" "gene3" "gene4"

mean(df1$score)

## [1] 0.5

## 按坐标
df1[2,2] #坐行右列

## [1] "up"

df1[2,]

##    gene change score
## 2 gene2     up     3

df1[,2]

## [1] "up"   "up"   "down" "down"

class(df1[2,]) #"data.frame"

## [1] "data.frame"

class(df1[,2]) #"character"

## [1] "character"

df1[c(1,3),1:2] #取第1、3行，取1、2列

##    gene change
## 1 gene1     up
## 3 gene3   down

## 按名字
df1[,"gene"]

## [1] "gene1" "gene2" "gene3" "gene4"

df1[,c('gene','change')] #可以同时提多列（把要提出来的列写成向量），$只能提一列

##    gene change
## 1 gene1     up
## 2 gene2     up
## 3 gene3   down
## 4 gene4   down

## 按条件（逻辑值）
df1[df1$score>0,] #留TRUE

##    gene change score
## 1 gene1     up     5
## 2 gene2     up     3

#思考题，筛选score>0的基因
df1[df1$score > 0, 'gene'] #df1[df1$score > 0, 1]

## [1] "gene1" "gene2"

df1$gene[df1$score > 0]

## [1] "gene1" "gene2"

## 代码思维
#如何取数据框的最后一列？
df1[,3]

## [1]  5  3 -2 -4

df1[,ncol(df1)]

## [1]  5  3 -2 -4

#如何取数据框除了最后一列以外的其他列？
df1[,-ncol(df1)]

##    gene change
## 1 gene1     up
## 2 gene2     up
## 3 gene3   down
## 4 gene4   down

#筛选score > 0的基因
df1[df1$score > 0,1]

## [1] "gene1" "gene2"

df1$gene[df1$score > 0]

## [1] "gene1" "gene2"

#5.数据框修改

#改一个格
df1[3,3] <- 5
df1

##    gene change score
## 1 gene1     up     5
## 2 gene2     up     3
## 3 gene3   down     5
## 4 gene4   down    -4

#改一整列
df1$score <- c(12,23,50,2) #存在的列名<- == 修改
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) #不存在的列名<- == 新增
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

#改行名和列名
rownames(df1) <- c("r1","r2","r3","r4") #行列取子集结果为向量，所以修改时也得是向量
#只修改某一行/列的名
colnames(df1)[2] <- "CHANGE"

#6.两个数据框的连接
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") #by='共同一列的名字'

##     name blood_type  group vision
## 1  Damon          O group1    4.2
## 2  jimmy          A group1    4.3
## 3 nicker          B group2    4.9

merge(test1,test3,by.x = "name",by.y = "NAME") 

##     name blood_type weight
## 1  Damon          O    140
## 2  jimmy          A    145
## 3 nicker          B    110

?merge

##### 矩阵和列表
m <- matrix(1:9, nrow = 3)
colnames(m) <- c("a","b","c") #加列名
m

##      a b c
## [1,] 1 4 7
## [2,] 2 5 8
## [3,] 3 6 9

#矩阵取子集，不支持$
m[2,]

## a b c 
## 2 5 8

m[,1]

## [1] 1 2 3

m[2,3]

## c 
## 8

m[2:3,1:2]

##      a b
## [1,] 2 5
## [2,] 3 6

m

##      a b c
## [1,] 1 4 7
## [2,] 2 5 8
## [3,] 3 6 9

t(m) #转置

##   [,1] [,2] [,3]
## a    1    2    3
## b    4    5    6
## c    7    8    9

as.data.frame(m) #转换成数据框

##   a b c
## 1 1 4 7
## 2 2 5 8
## 3 3 6 9

pheatmap::pheatmap(m)
pheatmap::pheatmap(m,cluster_cols = F,cluster_rows = F) #可以在允许范围内修改代码

#列表
l <- list(m1 = matrix(1:9, nrow = 3),
          m2 = matrix(2:9, nrow = 2))
l # m1，m2是l列表里的元素名

## $m1
##      [,1] [,2] [,3]
## [1,]    1    4    7
## [2,]    2    5    8
## [3,]    3    6    9
## 
## $m2
##      [,1] [,2] [,3] [,4]
## [1,]    2    4    6    8
## [2,]    3    5    7    9

l[[2]] #两个中括号

##      [,1] [,2] [,3] [,4]
## [1,]    2    4    6    8
## [2,]    3    5    7    9

l$m1 #名字取子集

##      [,1] [,2] [,3]
## [1,]    1    4    7
## [2,]    2    5    8
## [3,]    3    6    9

# 补充：元素的名字

scores = c(100,59,73,95,45)
names(scores) = c("jimmy","nicker","Damon","Sophie","tony") #有名字的向量,名字为向量属性
scores

##  jimmy nicker  Damon Sophie   tony 
##    100     59     73     95     45

scores["jimmy"]

## jimmy 
##   100

scores[c("jimmy","nicker")]

##  jimmy nicker 
##    100     59

names(scores)[scores>60]

## [1] "jimmy"  "Damon"  "Sophie"

# 删除 
rm(l)
rm(df1,df2)
rm(list = ls()) 
#快捷键 ctrl+l 清空控制台

![unnamed-chunk-1-1.png](https://ask8088-private-1251520898.cos.ap-guangzhou.myqcloud.com/developer-images/article/9199560/a92ta5k982.png?q-sign-algorithm=sha1&q-ak=AKID2uZ1FGBdx1pNgjE3KK4YliPpzyjLZvug&q-sign-time=1675346109;1675353309&q-key-time=1675346109;1675353309&q-header-list=&q-url-param-list=&q-signature=ef9071d2e8fd4981ad5876b3a9856683da7ce3e1)
![unnamed-chunk-1-2.png](https://ask8088-private-1251520898.cos.ap-guangzhou.myqcloud.com/developer-images/article/9199560/i2mdkaw6a1.png?q-sign-algorithm=sha1&q-ak=AKID2uZ1FGBdx1pNgjE3KK4YliPpzyjLZvug&q-sign-time=1675346115;1675353315&q-key-time=1675346115;1675353315&q-header-list=&q-url-param-list=&q-signature=3f6641254eb0d8111e919e410980e8b1ed47bd84)