生信技能树 Day2 R语言入门

# 1.生成1到15之间所有偶数
seq(from = 2,to = 15,by = 2)

## [1]  2  4  6  8 10 12 14

##参数可以省略
seq(2,15,2)

## [1]  2  4  6  8 10 12 14

# 2.生成向量，内容为："student2"  "student4"  "student6"  "student8"  "student10" "student12" "student14" 
paste0(rep("student",times = 7),seq(from = 2, to = 15,by = 2))

## [1] "student2"  "student4"  "student6"  "student8"  "student10" "student12" "student14"

paste0(rep("student",times = 3),seq(from = 2, to = 15,by = 2))

## [1] "student2"  "student4"  "student6"  "student8"  "student10" "student12" "student14"

paste0(rep("student",times = 7),seq(from = 2, to = 6,by = 2))

## [1] "student2" "student4" "student6" "student2" "student4" "student6" "student2"

# 3.将两种不同类型的数据用c()组合在一起，看输出结果
c(1,"a")

## [1] "1" "a"

c(TRUE,"a")

## [1] "TRUE" "a"

c(1,TRUE)

## [1] 1 1

x <- c(1,3,5,1) #规范的赋值符号 快捷键Alt+减号
x

## [1] 1 3 5 1

#赋值+输出一起实现
x <- c(1,3,5,1);x

## [1] 1 3 5 1

(x <- c(1,3,5,1))

## [1] 1 3 5 1

x <- c(1,3,5,1)
x+1

## [1] 2 4 6 2

log(x)

## [1] 0.000000 1.098612 1.609438 0.000000

sqrt(x)

## [1] 1.000000 1.732051 2.236068 1.000000

x>3

## [1] FALSE FALSE  TRUE FALSE

x==3

## [1] FALSE  TRUE FALSE FALSE

max(x) #最大值

## [1] 5

min(x) #最小值

## [1] 1

mean(x) #均值

## [1] 2.5

median(x) #中位数

## [1] 2

var(x) #方差

## [1] 3.666667

sd(x) #标准差

## [1] 1.914854

sum(x) #总和

## [1] 10

length(x) #长度 元素个数

## [1] 4

unique(x) #去重复 从左往右第二次及以上出现的元素为重复元素

## [1] 1 3 5

duplicated(x) #对应元素是否重复 返回逻辑值向量

## [1] FALSE FALSE FALSE  TRUE

!duplicated(x) # 第一次出现是TRUE 重复是FALSE

## [1]  TRUE  TRUE  TRUE FALSE

table(x) #重复值统计

## x
## 1 3 5 
## 2 1 1

sort(x) # 默认升序

## [1] 1 1 3 5

sort(x,decreasing = F)

## [1] 1 1 3 5

sort(x,decreasing = T)

## [1] 5 3 1 1

a <- seq(2,15,2)
paste0(rep("student",times = length(a)),a)

## [1] "student2"  "student4"  "student6"  "student8"  "student10" "student12" "student14"

x = c(1,3,5,1)
y = c(3,2,5,6)

#(1)比较运算，生成等长的逻辑向量
x == y 

## [1] FALSE FALSE  TRUE FALSE

y == x

## [1] FALSE FALSE  TRUE FALSE

#(2)数学计算
x + y

## [1]  4  5 10  7

#(3)连接

paste(x,y,sep=",")

## [1] "1,3" "3,2" "5,5" "1,6"

#paste与paste0的区别：都是将元素转化为字符串后拼接，paste可以通过sep定义连接符号，默认为空格，也可以无缝连接。paste0没有sep参数，默认无缝连接，可以看成特殊的paste
paste(x,y)

## [1] "1 3" "3 2" "5 5" "1 6"

paste0(x,y)

## [1] "13" "32" "55" "16"

paste(x,y,sep = "")

## [1] "13" "32" "55" "16"

paste(x,y,sep = ",")

## [1] "1,3" "3,2" "5,5" "1,6"

#当两个向量长度不一致
x = c(1,3,5,6,2)
y = c(3,2,5)
x + y

## Warning in x + y: 长的对象长度不是短的对象长度的整倍数

## [1]  4  5 10  9  4

x == y # 啊！warning！

## Warning in x == y: 长的对象长度不是短的对象长度的整倍数

## [1] FALSE FALSE  TRUE FALSE  TRUE

paste0("student",seq(2,15,2))

## [1] "student2"  "student4"  "student6"  "student8"  "student10" "student12" "student14"

#(4)交集、并集、差集 注意会去重
intersect(x,y)# 交集

## [1] 3 5 2

union(x,y) # 并集

## [1] 1 3 5 6 2

setdiff(x,y) # x里的哪些元素y里没有

## [1] 1 6

setdiff(y,x) # y里的哪些元素x里没有

## numeric(0)

# %in% 返回逻辑值向量，与前面向量个数一致，不会去重，注意与intersect的区别
# 与==的区别是元素是否一一对应比较
x %in% y #x的每个元素在y中存在吗

## [1] FALSE  TRUE  TRUE FALSE  TRUE

y %in% x #y的每个元素在x中存在吗

## [1] TRUE TRUE TRUE

x <- 8:12
#根据逻辑值取子集
x[x == 10]

## [1] 10

x[x < 12]

## [1]  8  9 10 11

x[x %in% c(9,13)]

## [1] 9

#根据位置取子集
x[4]

## [1] 11

x[2:4]

## [1]  9 10 11

x[c(1,5)]

## [1]  8 12

x[-4] # 这里负号是排除，不是倒数的意思！！！与python是不一样的！！！

## [1]  8  9 10 12

x[-(2:4)]

## [1]  8 12

# 也可以给元素命名后根据名字取子集，后面会讲

x

## [1]  8  9 10 11 12

#改一个元素
x[4] <- 40
x

## [1]  8  9 10 40 12

#改多个元素
x[c(1,5)] <- c(80,20)
x

## [1] 80  9 10 40 20

# 注意一定要赋值，不然白改

k1 = rnorm(12);k1

##  [1] -0.5911213  0.1683967  0.5130066 -0.8738898 -0.8950050  0.6982776  0.7872991  0.2893432
##  [9]  1.5340035 -0.4590547  0.1422255  0.5780768

k2 = rep(c("a","b","c","d"),each = 3);k2

##  [1] "a" "a" "a" "b" "b" "b" "c" "c" "c" "d" "d" "d"

## rep加不加each重复模式不同哦
plot(k1)

boxplot(k1~k2) #boxplot画箱线图

tmp = sort(log_rank_p[log_rank_p<0.05])

tmp = sort(log_rank_p)[log_rank_p<0.05]