一、R语言数据类型(变量)
1、标量(Scalar) character,integer,logical,double等
2、向量(Vector)
3、因子(Factor)
4、矩阵(Matrix)
5、数组(Array)
6、列表(List)
7、数据框(Data frame)
x "hello world" #变量赋值
二、一些基本的常用函数
1)连接字符串 paste() 函数
a "hello"b "how are"b "you"paste(a,b,c) #输出结果为 "hello how are you"paste(a,b,c,sep = "-") #这里指定连接符为- ,输出结果为 "hello-how are-you"paste(a,b,c,sep ="") #输出结果为 "hellohow areyou"
2)计算字符串的字符数 nchar() 函数
result "A B C D")result #输出结果为 7
3)toupper() 和 tolower() 函数的基本语法是
a " A B c d")a #输出结果为 " A B C D"b " A B c d")b #输出结果为 " a b c d"
4)截取字符串的一部分 substring() 函数
cut "hello world",cut #输出结果为 "hello"
三、变量
a 1,b "one",c #逻辑变量d 1:a 1,a #输出结果为 "1" "2" "3" "4" "one"如果其中一个元素是字符,则非字符值则被强制转换为字符类型rep(1:4,each=2) #输出结果为 1 1 2 2 3 3 4 4seq(from=22,to=50,by=3) #输出结果为 22 25 28 31 34 37 40 43 46 49seq(22,50,3) #输出结果为 22 25 28 31 34 37 40 43 46 49
四、向量的操作
1、索引截取b "one",b[1] #输出结果为 "one"b[1:3] #截取连续的 输出结果为 "one" "two" "three"b[c(1,3)] #输出结果为 "one" "three"2、逻辑筛选a 1,b 3]b #输出结果为 5 6 7letters #输出结果为 "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"letters[1:5] #输出结果为 "a" "b" "c" "d" "e"3、向量运算#可以添加,减去,相乘或相除两个相同长度的向量,将结果作为向量输出v1 1,v2 1,add.result add.result #输出结果为 2 6 8 9 5 7sub.result sub.result #输出结果为 0 0 0 1 1 -3multi.result multi.result #输出结果为 1 9 16 20 6 10divi.result divi.result #输出结果为 1.00 1.00 1.00 1.25 1.50 0.40#向量循环利用#如果我们对不等长的两个向量应用算术运算,则较短向量的元素被循环以完成操作v1 2,v1 1,add.result add.result #输出结果为 2 5 5 6 3 7
五、因子(Factor),因子的用处是给数据分组
diabetes=c("T1","T2","T3","T4")diabetes #输出结果为 "T1" "T2" "T3" "T4"diabetes=factor(diabetes)diabetes #输出结果为 T1 T2 T3 T4 Levels: T1 T2 T3 T4#有序因子status=factor(status,order=TRUE,levels=c("one","three","two"))status #输出结果为 one two three one three Levels: one < three < two nlevels(status) #输出结果为 3levels(status) #输出结果为 "one" "three" "two"
六、矩阵(Matrix),函数matrix()用于创建一个矩阵,矩阵数据类型只能是一种
y = matrix(1:12,nrow=3,ncol=4)y #输出结果为 [,1] [,2] [,3] [,4] [1,] 1 4 7 10 [2,] 2 5 8 11 [3,] 3 6 9 12y = matrix(1:12,nrow=3,ncol=4,byrow=TRUE) y #输出结果为 [,1] [,2] [,3] [,4] [1,] 1 2 3 4 [2,] 5 6 7 8 [3,] 9 10 11 12
七、数组 数组和矩阵类似
z 1:z #输出结果为 , , 1 [,1] [,2] [,3] [,4][1,] 1 4 7 10[2,] 2 5 8 11[3,] 3 6 9 12, , 2 [,1] [,2] [,3] [,4][1,] 13 16 19 22[2,] 14 17 20 23[3,] 15 18 21 24
八、数据框,重点
数据框与矩阵类似,也是二维的,与矩阵不同的是,数据框中各列的数据类型可以不同,但是长度必须相同
1、数据框的创建patientID 1,age 22,diabetes "T1",status = c("poor","excellent","improved","poor")status = factor(status,order=TRUE,levels=c("poor","improved","excellent"))patientData patientData#输出结果patientID age diabetes status1 1 22 T1 poor2 2 33 T2 excellent3 3 44 T3 improved4 4 45 T4 poor 2、数据框常用筛选方法,以mtcars为列,mtcars是R中自带的内置数据框mtcats# mpg cyl disp hp drat wt qsec vs am gear carbMazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2head(mtcars)tail(mtcars)colnames(mtcars)#输出结果 "mpg" "cyl" "disp" "hp" "drat" "wt" "qsec" "vs" "am" "gear" "carb"rownames(mtcars)#输出结果 [1] "Mazda RX4" "Mazda RX4 Wag" "Datsun 710" [4] "Hornet 4 Drive" "Hornet Sportabout" "Valiant" [7] "Duster 360" "Merc 240D" "Merc 230" [10] "Merc 280" "Merc 280C" "Merc 450SE" [13] "Merc 450SL" "Merc 450SLC" "Cadillac Fleetwood" [16] "Lincoln Continental" "Chrysler Imperial" "Fiat 128" [19] "Honda Civic" "Toyota Corolla" "Toyota Corona" [22] "Dodge Challenger" "AMC Javelin" "Camaro Z28" [25] "Pontiac Firebird" "Fiat X1-9" "Porsche 914-2" [28] "Lotus Europa" "Ford Pantera L" "Ferrari Dino" [31] "Maserati Bora" "Volvo 142E" nrow(mtcars) #输出结果为 32ncol(mtcars) #输出结果为 11row.names(mtcars) #[1] "Mazda RX4" "Mazda RX4 Wag" "Datsun 710" [4] "Hornet 4 Drive" "Hornet Sportabout" "Valiant" [7] "Duster 360" "Merc 240D" "Merc 230" [10] "Merc 280" "Merc 280C" "Merc 450SE" [13] "Merc 450SL" "Merc 450SLC" "Cadillac Fleetwood" [16] "Lincoln Continental" "Chrysler Imperial" "Fiat 128" [19] "Honda Civic" "Toyota Corolla" "Toyota Corona" [22] "Dodge Challenger" "AMC Javelin" "Camaro Z28" [25] "Pontiac Firebird" "Fiat X1-9" "Porsche 914-2" [28] "Lotus Europa" "Ford Pantera L" "Ferrari Dino" [31] "Maserati Bora" "Volvo 142E" dim(mtcars) #输出结果为 32 11 #rbind 按行合并数据框#cbind 按列合并数据框 3、行索引提取mtcars[1:2,] #提取第1,2行mtcars[,1:2] #提取第1,2列不连续mtcars[c(2,4),c(3,6,9)] #提取第2,4行的第3,6,9列通过列名称提取matcars[,c("mpg","hp")] mtcars $hp #利用$符来取一列数据,返回的是一个向量mtcars[,c("mpg")] #返回一列是一个向量,但是我们想要返回数据框,通过加上一个drop=FALSE处理mtcars[,c("mpg"),drop=FALSE]4、筛选,产生逻辑向量进行筛选interestcol "hp",#interestcol #输出结果为 FALSE FALSE FALSE TRUE FALSE TRUE FALSE FALSE FALSE FALSE FALSEmtcars[, interestcol] #将interestcol中是TRUE的列筛选出来 mtcars $hp>100mtcars[mtcars$hp>100,] #将hp列大于100的行取出来mtcars$hp>100 & mtcars$cy1>6mtcars[mtcars $hp>100 & mtcars $cyl>6,] subset方法subset(mtcars,hp>100 & cyl>6)数据排序,order产生一个排序后的索引orderIDdex 1]) orderIDdex #输出结果 15 16 24 7 17 31 14 23 22 29 12 13 11 6 5 10 25 30 1 2 4 32 21 3 9 8 27 26 19 28 18 20mtcars[orderIDdex,] #按第一列从小到大输出mtcarsorderIDdex 1],decreasing=TRUE)mtcars[orderIDdex,] #按第一列从大到小输出mtcars
九、list
a 1,b 1:c mylist mylistnames(mylist)mylist[1] #输出结果为 1 4 5 6 8mylist[["a"]]