生信技能树笔记day3

#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))
df1

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

df2 <- read.csv("day3/R_02/gene.csv")
df2

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

#数据框属性
dim(df1)

## [1] 4 3

nrow(df1)

## [1] 4

ncol(df1)

## [1] 3

rownames(df1)

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

colnames(df1)

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

#数据框取子集
df1$gene  #删掉score，按tab键试试

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

mean(df1$score)

## [1] 0.5

# 按坐标
df1[2,2]

## [1] "up"

df1[2,]

##    gene change score
## 2 gene2     up     3

df1[,2]

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

df1[c(1,3),1:2]

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

# 按名字
df1[,"gene"]

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

typeof(df1[,"gene"])

## [1] "character"

df1["gene"]

##    gene
## 1 gene1
## 2 gene2
## 3 gene3
## 4 gene4

typeof(df1["gene"])

## [1] "list"

df1[,c('gene','change')]

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

# 按条件（逻辑值）
df1[df1$score>0,]

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

# 中括号里面的逗号表示维度分割！！！
# 数据框按照逻辑值取子集，TRUE对应的行/列留下，FALSE对应的行/列丢掉

# 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

#改行名和列名
rownames(df1) <- c("r1","r2","r3","r4")
#只修改某一行/列的名
colnames(df1)[2] <- "CHANGE"

#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")

##     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

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

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)

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

class(m)

## [1] "matrix" "array"

m1 <- as.data.frame(m)
m1

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

class(m1)

## [1] "data.frame"

#列表
l <- list(m1 = matrix(1:9, nrow = 3),
          m2 = matrix(2:9, nrow = 2))
l

## $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]]

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

l$m1

##      [,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")
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"