R学习-2-数据类型和向量

原创

用户10420779

发布于 2023-03-14 20:50:49

43600

代码可运行

文章被收录于专栏：adexsl的生信学习记录

运行总次数：0

代码可运行

数据类型

数值型numeric：1.3 2
字符型character："a" 'nn'
逻辑型logical：TRUE---T FALSE---F NA(缺失值，存在但未知)

判断数据类型的函数：

> class()#将要判断的内容写在括号里
> class("a")
[1] "character"
> class(TRUE)
[1] "logical"
> class(3)
[1] "numeric"

常见报错：引号、拼写错误、大小写

> class(a)
Error: object 'a' not found
> calss("a")
Error in calss("a") : could not find function "calss"
class(true)
Error: object 'true' not found
> class（3）
Error: unexpected input in "class（"

Tips---上下键：

逻辑型数据：

比较运算的结果是逻辑值：

>,<,<=,>=,==,!=

> 3==5
[1] FALSE
> 3<=5
[1] TRUE
> 3!=2   #3不等于2
[1] TRUE

逻辑运算多个逻辑条件的连接：

与：&

或：|

非：！

> 3<5&4>5
[1] FALSE
> 3<5|4>5
[1] TRUE
> !(4>5)
[1] TRUE

is族函数，判断，返回值为TRUE或FALSE

> is.numeric()  #是否为数值型数据
> is.logical()  #是否为逻辑型数据
> is.character()  #是否为字符型数据

as族函数转换数据类型：

as.numeric()  #将其他数据类型转换为数值型
as.logical()  #将其他数据类型转换为逻辑型
as.character()  #将其他数据类型转换为字符型

能转换的可以转换，不能转换的不可以转换：

> as.numeric("jimmy")
[1] NA
Warning message:
NAs introduced by coercion

向量

多个数据如何组织？

数据框不是文件，只是R语言内部的数据

数据框的每一列只能存在一种数据类型，单独拿出来的一列是向量，视为一个整体，可以有重复值

Tips---脚本打开是乱码的解决方案

向量的生成

(1)用 c() 结合到一起
c(2,5,6,2,9)
[1] 2 5 6 2 9
c("a","f","md","b")
[1] "a"  "f"  "md" "b"
#(2)连续的数字用冒号“:” 
1:5
[1] 1 2 3 4 5
#(3)有重复的用rep(),有规律的序列用seq(),随机数用rnorm()
rep("x",times=3)
[1] "x" "x" "x"
seq(from=3,to=21,by=3)
[1]  3  6  9 12 15 18 21
rnorm(n=3)
[1]  0.08516491  0.84425482 -0.32409770  #测试某个函数如何使用时生成数据使用
#(4)通过组合,产生更为复杂的向量。
paste0(rep("x",times=3),1:3)
[1] "x1" "x2" "x3"

对单个向量进行的操作

赋值：

> x <- c(1,3,5,1) #规范的赋值符号 Alt+减号
> x   #查看已赋值变量
[1] 1 3 5 1

> x = c(1,3,5,1) #随意的赋值写法
> x 
[1] 1 3 5 1

#赋值+输出一起实现
> (x <- c(1,3,5,1))
[1] 1 3 5 1
> x <- c(1,3,5,1);x
[1] 1 3 5 1

赋值名称：不要使用函数名称定义变量，不用空格斜杠引号等特殊字符

2. 简单数学计算

> 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

3. 根据某条件进行判断，生成逻辑值向量

> x>3
[1] FALSE FALSE  TRUE FALSE
> x==3
[1] FALSE  TRUE FALSE FALSE
>

4. 初级统计

max(x) #最大值

min(x) #最小值

mean(x) #均值

median(x) #中位数

var(x) #方差

sd(x) #标准差

sum(x) #总和

> length(x) #长度   一个向量里有多少元素
[1] 4
> unique(x) #去重复  重复：从左往右第一次出现的元素不是重复，第二次或多次出现则为重复
[1] 1 3 5
> duplicated(x) #判断对应元素是否重复
[1] FALSE FALSE FALSE  TRUE
> duplicated(!x) #不重复的为TRUE,重复的为FALSE
[1] FALSE  TRUE  TRUE  TRUE
> table(x) #重复值统计
x
1 3 5 
2 1 1

R语言的默认思想：

> sort(x)
[1] 1 1 3 5
> sort(x,decreasing = F)
[1] 1 1 3 5
> sort(x,decreasing = T)
[1] 5 3 1 1

练习

> seq(from=2,to=15,by=2)
[1]  2  4  6  8 10 12 14

> paste0(rep("student",times=7),seq(from=2,to=15,by=2))
[1] "student2"  "student4"  "student6" 
[4] "student8"  "student10" "student12"
[7] "student14"

> c(3,"int")  #数值型转换为字符型
[1] "3"   "int"  
> c(2,TRUE)  #逻辑型会转换为数值型，TRUE---1,FASLE---0
[1] 2 1
> c(2,5,FALSE)
[1] 2 5 0
> c("a",TRUE)  #逻辑型转换为字符型
[1] "a"    "TRUE"

练习题2改良版：

a=seq(from=2,to=15,by=2)
> paste0(rep("student",times=length(a),a)
[1] "student2"  "student4"  "student6" 
[4] "student8"  "student10" "student12"
[7] "student14"

R语言中函数思想：能用函数代替就不要手动去数，除非这个代码只用一次

对两个向量的操作

> 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  #等位运算
[1]  4  5 10  7
##3.连接
> paste(x,y,sep=",")  #一对一连接
[1] "1,3" "3,2" "5,5" "1,6"

> x=c("a","a","a")
> y=c("b","b","b")
###如何将两个向量连接在一起？
> paste(x+y)
Error in x + y : non-numeric argument to binary operator
> paste0(x,y)
[1] "ab" "ab" "ab"
> c(x,y)
[1] "a" "a" "a" "b" "b" "b"

paste与paste0的区别与联系

##Usage：
> ###paste(...,sep=" ",collapse=NULL,recycle0=FALSE)
> ###paste(...,collapse=NULL,recycle0=FALSE)
> paste(x,y)  #两个连接元素之间可以有分隔符
[1] "1 3" "3 2" "5 5" "1 6"
> paste0(x,y)  #无缝连接
[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时

> x = c(1,3,5,6,2)
> y = c(3,2,5)
> x == y
[1] FALSE FALSE  TRUE FALSE  TRUE
Warning message:  ##不是报错！！！
In x == y : longer object length is not a multiple of shorter object length

利用循环补齐简化代码：弃长补短

> paste0(rep("x",times=3),1:3)  ##or
> paste0(rep("x",3),1:3)
[1] "x1" "x2" "x3"
> paste0("x",1:3)
[1] "x1" "x2" "x3"
> paste0("student",seq(2,15,2))
[1] "student2"  "student4"  "student6" 
[4] "student8"  "student10" "student12"
[7] "student14"

交集、并集、差集

x = c(1,3,5,6,2)
y = c(3,2,5)
> intersect(x,y)
[1] 3 5 2
> union(x,y) ##取并集并去重复
[1] 1 3 5 6 2
> setdiff(x,y)  ##返回在向量x里存在但在y里不存在的元素
[1] 1 6
> setdiff(y,x)  ##返回在向量y里存在但在x里不存在的元素
numeric(0)  ##空集

重点：%in%（没有快捷键）

> 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

向量筛选（取子集）

按照逻辑值：中括号里时与x等长且一一对应的逻辑值向量
按照位置：中括号里是由x的下标组成的向量

[ ]：将TRUE对应的值挑选出来，FALSE丢弃

> x=1:15
> x
 [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14
[15] 15
> x==10
 [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE
 [8] FALSE FALSE  TRUE FALSE FALSE FALSE FALSE
[15] FALSE
> x[x==10]  ##逻辑值放在中括号里面
[1] 10
> x>10
 [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE
 [8] FALSE FALSE FALSE  TRUE  TRUE  TRUE  TRUE
[15]  TRUE
> x[x>10]
[1] 11 12 13 14 15
> x[x %in% c(9,13)]  ## %in%：x的每个元素在y中存在吗
[1]  9 13

###FALSE取子集
> x=rep(c("a","b","c"),each=3);x
[1] "a" "a" "a" "b" "b" "b" "c" "c" "c"
> duplicated(x)
[1] FALSE  TRUE  TRUE FALSE  TRUE  TRUE FALSE
[8]  TRUE  TRUE
> x[duplicated(x)]
[1] "a" "a" "b" "b" "c" "c"
> x[!duplicated(x)]
[1] "a" "b" "c"

index（索引/下标）

###x[位置]
> x[4]
[1] 4
> x[2:4]
[1] 2 3 4
> x[1,5]
Error in x[1, 5] : incorrect number of dimensions
> x[c(1,5)]  ##取两个不相连位置的元素需要写c()
[1] 1 5
> x[-4]
 [1]  1  2  3  5  6  7  8  9 10 11 12 13 14 15
> x[-(2:4)]
 [1]  1  5  6  7  8  9 10 11 12 13 14 15
###从向量x中筛选出属于向量y中的值
> x=9:12
> y=8:10
> x[x%in%y]
[1]  9 10

修改向量中的某个/某些元素：取子集+赋值

R语言中的修改都要赋值，没有赋值就没有发生过

###改一个元素
> x=9:12
> x[4] <- 40
> x
[1]  9 10 11 40
###改多个元素
> x[c(1,5)] <- c(80,20)
> x
[1] 80 10 11 40 20

练习2-4 向量取子集

> load("gands.Rdata")
> g
  [1] "WNT9B"         "CRAMP1L"      
  [3] "MYL12B"        "PRSS8"        
  [5] "GFM2"          "CRAMP1L"      
  [7] "TUBA4A"        "SLCO1C1"      
  [9] "NYNRIN"        "COMMD1"       
 [11] "COMMD1"        "CCT4"         
 [13] "AC017081.1"    "RAB7A"        
 [15] "CCT4"          "ZDHHC16"      
 [17] "CASKIN2"       "MYL12B"       
 [19] "GGT7"          "SNRPE"        
 [21] "RGPD3"         "ZNF586"       
 [23] "COMMD1"        "GGT7"         
 [25] "URB1"          "RAB7A"        
 [27] "MPP2"          "AFG3L2"       
 [29] "URB1"          "AC104581.1"   
 [31] "IL19"          "MPP2"         
 [33] "SYT6"          "ATP2A2"       
 [35] "IL19"          "SNRPE"        
 [37] "ARHGAP1"       "PRSS8"        
 [39] "PNMT"          "ZNF461"       
 [41] "OR2D3"         "CECR5"        
 [43] "SPDL1"         "CLEC17A"      
 [45] "ZNF461"        "ATG10"        
 [47] "ATG10"         "ATG10"        
 [49] "ZDHHC16"       "SLC25A25"     
 [51] "TCP10"         "KRTAP4-3"     
 [53] "SLC30A9"       "SLCO1C1"      
 [55] "UBAC1"         "GGT7"         
 [57] "CASKIN2"       "GSTP1"        
 [59] "PRY"           "UBAC1"        
 [61] "MPP2"          "NYNRIN"       
 [63] "INTS12"        "MYL12B"       
 [65] "MPP2"          "KCND1"        
 [67] "RGPD3"         "RGPD3"        
 [69] "SLC30A9"       "C10orf128"    
 [71] "HBD"           "SLC30A9"      
 [73] "MYL12B"        "GGT7"         
 [75] "HEPH"          "TUBA4A"       
 [77] "RP5-1021I20.4" "KLHDC8A"      
 [79] "HBD"           "HBP1"         
 [81] "CCT4"          "MARC2"        
 [83] "ZNF586"        "LCP1"         
 [85] "CECR5"         "OR2D3"        
 [87] "CRAMP1L"       "LIPE"         
 [89] "INTS12"        "LIPE"         
 [91] "NETO2"         "CANX"         
 [93] "SPDL1"         "ATP6V1B2"     
 [95] "SLCO1C1"       "MARC2"        
 [97] "GGT7"          "LCP1"         
 [99] "CECR5"         "HOOK2"        
> length(g)
[1] 100
> g[g=seq(2,100,2)]
 [1] "CRAMP1L"    "PRSS8"      "CRAMP1L"   
 [4] "SLCO1C1"    "COMMD1"     "CCT4"      
 [7] "RAB7A"      "ZDHHC16"    "MYL12B"    
[10] "SNRPE"      "ZNF586"     "GGT7"      
[13] "RAB7A"      "AFG3L2"     "AC104581.1"
[16] "MPP2"       "ATP2A2"     "SNRPE"     
[19] "PRSS8"      "ZNF461"     "CECR5"     
[22] "CLEC17A"    "ATG10"      "ATG10"     
[25] "SLC25A25"   "KRTAP4-3"   "SLCO1C1"   
[28] "GGT7"       "GSTP1"      "UBAC1"     
[31] "NYNRIN"     "MYL12B"     "KCND1"     
[34] "RGPD3"      "C10orf128"  "SLC30A9"   
[37] "GGT7"       "TUBA4A"     "KLHDC8A"   
[40] "HBP1"       "MARC2"      "LCP1"      
[43] "OR2D3"      "LIPE"       "LIPE"      
[46] "CANX"       "ATP6V1B2"   "MARC2"     
[49] "LCP1"       "HOOK2"     
> s
 [1] "LIPE"          "SLC30A9"      
 [3] "SLC30A9"       "GSTP1"        
 [5] "LIPE"          "INTS12"       
 [7] "OR2D3"         "GFM2"         
 [9] "SLCO1C1"       "NYNRIN"       
[11] "CECR5"         "RAB7A"        
[13] "FO538757.2"    "COMMD1"       
[15] "C10orf128"     "HEPH"         
[17] "HBD"           "AFG3L2"       
[19] "ZNF586"        "SPDL1"        
[21] "KLHDC8A"       "AC017081.1"   
[23] "SLC30A9"       "CECR5"        
[25] "GGT7"          "COMMD1"       
[27] "CASKIN2"       "MPP2"         
[29] "KLHDC8A"       "PLEKHN1"      
[31] "SLC30A9"       "ATG10"        
[33] "SNRPE"         "FO538757.2"   
[35] "GSTP1"         "ARHGAP1"      
[37] "AC104581.1"    "KLHL17"       
[39] "CLEC17A"       "PERM1"        
[41] "RAB7A"         "GGT7"         
[43] "SLC25A25"      "URB1"         
[45] "OR4F16"        "ZNF461"       
[47] "RGPD3"         "CECR5"        
[49] "RP5-1021I20.4" "OR4F5"        
> g%in%s
  [1] FALSE FALSE FALSE FALSE  TRUE FALSE FALSE
  [8]  TRUE  TRUE  TRUE  TRUE FALSE  TRUE  TRUE
 [15] FALSE FALSE  TRUE FALSE  TRUE  TRUE  TRUE
 [22]  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE
 [29]  TRUE  TRUE FALSE  TRUE FALSE FALSE FALSE
 [36]  TRUE  TRUE FALSE FALSE  TRUE  TRUE  TRUE
 [43]  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE FALSE
 [50]  TRUE FALSE FALSE  TRUE  TRUE FALSE  TRUE
 [57]  TRUE  TRUE FALSE FALSE  TRUE  TRUE  TRUE
 [64] FALSE  TRUE FALSE  TRUE  TRUE  TRUE  TRUE
 [71]  TRUE  TRUE FALSE  TRUE  TRUE FALSE  TRUE
 [78]  TRUE  TRUE FALSE FALSE FALSE  TRUE FALSE
 [85]  TRUE  TRUE FALSE  TRUE  TRUE  TRUE FALSE
 [92] FALSE  TRUE FALSE  TRUE FALSE  TRUE FALSE
 [99]  TRUE FALSE
> g[g%in%s]
 [1] "GFM2"          "SLCO1C1"      
 [3] "NYNRIN"        "COMMD1"       
 [5] "COMMD1"        "AC017081.1"   
 [7] "RAB7A"         "CASKIN2"      
 [9] "GGT7"          "SNRPE"        
[11] "RGPD3"         "ZNF586"       
[13] "COMMD1"        "GGT7"         
[15] "URB1"          "RAB7A"        
[17] "MPP2"          "AFG3L2"       
[19] "URB1"          "AC104581.1"   
[21] "MPP2"          "SNRPE"        
[23] "ARHGAP1"       "ZNF461"       
[25] "OR2D3"         "CECR5"        
[27] "SPDL1"         "CLEC17A"      
[29] "ZNF461"        "ATG10"        
[31] "ATG10"         "ATG10"        
[33] "SLC25A25"      "SLC30A9"      
[35] "SLCO1C1"       "GGT7"         
[37] "CASKIN2"       "GSTP1"        
[39] "MPP2"          "NYNRIN"       
[41] "INTS12"        "MPP2"         
[43] "RGPD3"         "RGPD3"        
[45] "SLC30A9"       "C10orf128"    
[47] "HBD"           "SLC30A9"      
[49] "GGT7"          "HEPH"         
[51] "RP5-1021I20.4" "KLHDC8A"      
[53] "HBD"           "ZNF586"       
[55] "CECR5"         "OR2D3"        
[57] "LIPE"          "INTS12"       
[59] "LIPE"          "SPDL1"        
[61] "SLCO1C1"       "GGT7"         
[63] "CECR5"        
> length(g[g%in%s])
[1] 63
> x=rnorm(10,0,18)
> x
 [1]   5.2828494   3.0746745   0.8475577
 [4] -11.3365565  26.5630396  22.5384872
 [7]  22.8419036   6.9907060 -23.1082285
[10]  -3.8680376
> x[x<(-2)]
[1] -11.336557 -23.108229  -3.868038

简单向量作图

> k1 = rnorm(12);k1
 [1]  0.8622467  0.4796227  1.5102533  0.6260323
 [5]  2.7191662  0.4572955 -1.2713989  0.3595864
 [9] -0.1002634 -1.5966247  2.2007094 -2.5580408
> plot(k1)
> k2 = rep(c("a","b","c","d"),each = 3);k2
 [1] "a" "a" "a" "b" "b" "b" "c" "c" "c" "d" "d"
[12] "d"
> boxplot(k1~k2)  ##箱线图