第一章 R语言介绍
读取，设置当前工作区
setwd("E:\\Desktop\\R Language\\R")
getwd()
特殊显示格式
> options(digits=3) #显示小数点后三位
> x<-runif(20) ？
> x
[1] 0.329 0.499 0.360 0.922 0.733 0.969 0.840 0.484 0.386 0.964 0.150 0.421
[13] 0.130 0.809 0.483 0.427 0.880 0.221 0.632 0.866
文件操作
ls() #列出当前目录
rm() #删除目录
dir.create("folder") #创建目录
安装包
install.packages("vcd")
> help(package="vcd")
> library(vcd) #加载包
保存工作区
save.image("E:\\Desktop\\R Language\\R\\chapter01\\.RData")
第二章 数据结构和数据录入
向量 - 元素的类型必须一致
> a <- c("k","j","h","a","c","m")
> a[3]
[1] "h"
> a[2:6]
[1] "j" "h" "a" "c" "m"
> a[c(1,2)]
[1] "k" "j"
矩阵 - 元素的类型必须一致，只有二维
> y <- matrix(1:20,nrow=5,ncol=4)
> y
[,1] [,2] [,3] [,4]
[1,] 1 6 11 16
[2,] 2 7 12 17
[3,] 3 8 13 18
[4,] 4 9 14 19
[5,] 5 10 15 20
> cells <- c(1,26,24,68)
> rnames <- c("R1","R2")
> cnames <- c("C1","C2")
> mymatrix <- matrix(cells, nrow=2,ncol=2,byrow=TRUE,dimnames=list(rnames,cnames)) #为行列加别名
> mymatrix
C1 C2
R1 1 26
R2 24 68
> mymatrix <- matrix(cells, nrow=2,ncol=2,byrow=FALSE,dimnames=list(rnames,cnames))
> mymatrix
C1 C2
R1 1 24
R2 26 68
> x <- matrix(1:10,nrow=2)
> x
[,1] [,2] [,3] [,4] [,5]
[1,] 1 3 5 7 9
[2,] 2 4 6 8 10
>
> x(2,)
数组 - 元素类型必须一致，有多维
> #Array
> dim1 <- c("A1","A2")
> dim2 <- c("B1","B2","B3")
> dim3 <- c("C1","C2","C3","C4")
> z <- array(1:24, c(2,3,4),dimnames=list(dim1,dim2,dim3))
> z
, , C1
B1 B2 B3
A1 1 3 5
A2 2 4 6
, , C2
B1 B2 B3
A1 7 9 11
A2 8 10 12
, , C3
B1 B2 B3
A1 13 15 17
A2 14 16 18
, , C4
B1 B2 B3
A1 19 21 23
A2 20 22 24
数据框 - 元素类型可以不同，和表格类似
patientID <- c(1,2,3,4)
> age <- c(25,34,28,52)
> diabetes <- c("Type1","Type2","Type1","Type1")
> status <- c("Poor","Improved","Excellent","Poor")
> patientdata <- data.frame(patientID,age,diabetes,status)
> patientdata
patientID age diabetes status
1 1 25 Type1 Poor
2 2 34 Type2 Improved
3 3 28 Type1 Excellent
4 4 52 Type1 Poor
>
> patientdata[1:2]
patientID age
1 1 25
2 2 34
3 3 28
4 4 52
> patientdata[c("diabetes","status")]
diabetes status
1 Type1 Poor
2 Type2 Improved
3 Type1 Excellent
4 Type1 Poor
> patientdata$age
[1] 25 34 28 52
>
>
> table(patientdata$diabetes,patientdata$status) #转为表，和Excel Pivot Table类似
Excellent Improved Poor
Type1 1 0 2
Type2 0 1 0
>
Attache，With，Detach - 变量作用域，推荐使用with
> attach(mtcars)
> summary(mpg)
Min. 1st Qu. Median Mean 3rd Qu. Max.
10.4 15.4 19.2 20.1 22.8 33.9
> plot(mpg,disp)
> plot(mpg,wt)
> detach(mtcars)
>
>
>
> #with
> with(mtcars,{
+ nokeepstats <- summary(mpg)
+ keepstats <<- summary(mpg) # 把with里面声明的变量保存在with的作用域之外
+ })
> keepstats
Min. 1st Qu. Median Mean 3rd Qu. Max.
10.4 15.4 19.2 20.1 22.8 33.9
> nokeepstats
閿欒: 鎵句笉鍒板璞?nokeepstats'
标识列
> #Identifier
> patientdata<-data.frame(patientID,age,diabetes,status,row.names=patientID)
> patientdata
patientID age diabetes status
1 1 25 Type1 Poor
2 2 34 Type2 Improved
3 3 28 Type1 Excellent
4 4 52 Type1 Poor
因子 Factor - 字符类型，但是有统计意义
#factor
> patientID <- c(1,2,3,4)
> age <- c(25,34,28,52)
> diabetes <- c("Type1","Type2","Type1","Type1")
> status <-c("Poor","Improved","Excellent","Poor")
> diabetes <- factor(diabetes)
> satus <-factor(stats,order=TRUE)
Error in factor(stats, order = TRUE) : 鎵句笉鍒板璞?stats'
> status <-factor(stats,order=TRUE)
Error in factor(stats, order = TRUE) : 鎵句笉鍒板璞?stats'
> status <-factor(status,order=TRUE)
> patientdata<-data.frame(patientID,age,diabetes,status)
> str(patientdata)
'data.frame': 4 obs. of 4 variables:
$ patientID: num 1 2 3 4
$ age : num 25 34 28 52
$ diabetes : Factor w/ 2 levels "Type1","Type2": 1 2 1 1
$ status : Ord.factor w/ 3 levels "Excellent"<"Improved"<..: 3 2 1 3
> summary(patientdata
+ )
patientID age diabetes status
Min. :1.00 Min. :25.0 Type1:3 Excellent:1
1st Qu.:1.75 1st Qu.:27.2 Type2:1 Improved :1
Median :2.50 Median :31.0 Poor :2
Mean :2.50 Mean :34.8
3rd Qu.:3.25 3rd Qu.:38.5
Max. :4.00 Max. :52.0
> patientdata
patientID age diabetes status
1 1 25 Type1 Poor
2 2 34 Type2 Improved
3 3 28 Type1 Excellent
4 4 52 Type1 Poor
列表 - 元素可以为不同类型，多维
> g<-"My First List"
> h<-c(25,26,18,39)
> j<-matrix(1:10,nrow=5)
> k<-c("one","two","three")
> mylist<-list(title=g,ages=h,j,k)
> mylist
$title
[1] "My First List"
$ages
[1] 25 26 18 39
[[3]]
[,1] [,2]
[1,] 1 6
[2,] 2 7
[3,] 3 8
[4,] 4 9
[5,] 5 10
[[4]]
[1] "one" "two" "three"
> mylist[1]
$title
[1] "My First List"
> mylist[2]
$ages
[1] 25 26 18 39
> mylist["ages"]
$ages
[1] 25 26 18 39
> mylist[c(1,2)]
$title
[1] "My First List"
$ages
[1] 25 26 18 39
> mylist[c(1,2,3)]
$title
[1] "My First List"
$ages
[1] 25 26 18 39
[[3]]
[,1] [,2]
[1,] 1 6
[2,] 2 7
[3,] 3 8
[4,] 4 9
[5,] 5 10
> mylist[["ages"]]
[1] 25 26 18 39
数据输入
> #data input
> mydata <- data.frame(age=numeric(0),gender=character(0),weight=numeric(0))
> mydata <- edit(mydata) #手工输入
mydata <- read.table("studentgrades.csv",header=TRUE,row.names="StudentID",spe=",") #文本文件
导入excel文件
library(xlsx)
workbook <- "test.xlsx"
mydataframe <- read.xlsx(workbook, 1)
第三章 图形初阶
散点图和辅助线
pdf("chapter03\\mygraph.pdf") #结果输出到pdf
> attach(mtcars)
> plot(wt,mpg)
> abline(li(mpg,wt)) #辅助线
> title("Regression of MPG on Weight") #标题
> detach(mtcars)
> dev.off() #立即输出
画布切换
dev.new() 新建
dev.set() 设置焦点
dev.next()
dev.prev()
画图参数>
> #画图参数,改变绘图样式
> opar <- par(no.readonly=TRUE)
> par(lty=2,pch=17)
> plot(dose,drugA,type="b")
> par(opar)
> plot(dose,drugA,type="b",lty=2,pch=17)
> plot(dose,drugA,type="b",lty=2,pch=18)
> plot(dose,drugA,type="b",lty=2,pch=17)
>
> #pch
> #pcex
> #cex
> #lty
> #lwd
> plot(dose,drugA,type="b",lty=3,lwd=3,pch=15,cex=2)
颜色
install.packages(RColorBrewer)
library(RColorBrewer)
> n <-7
> mycolors <- brewer.pal(n,"Set1")
> barplot(rep(1,n),col=mycolors)
>
>
> n<-10
> mycolors<-rainbow(n)
> pie(rep(1,n),labels=mycolors,col=mycolors)
> mygrays<-gray(0:n/n)
> pie(rep(1,n),labels=mygrays,col=mycolors)
字体
> par(font.lab=3,cex.lab=1.5, font.main=4, cex.main=2)
> windowsFonts(A=windowsFont("Arial Black"),B=windowsFont("Bookman Old Style"),C=windowsFont("comic Sans MS"))
> par(family="A"）
> par(family="A")
> plot(mpg,wt)
图片尺寸
> opar<- par(no.readonly=TRUE)
> par(pin=c(2,3))
> par(cex.axis=.75, font.axis=3)
> plot(dose,drugA,type="b",pch=19,lty=2,col="red")
> plot(dose,drugA,type="b",pch=23,lty=6,col="blue",bg="green")
添加文本和自定义坐标轴
> plot(dose,drugA,type="b",col="red",lty=2,pch=2,lwd=2,main="Clinical Trials for Drug A",sub="This is hypothetical data",xlab="Dosage",ylab="Drug Response",xlim=c(0,60),ylim=c(0,70))
>
> x<-c(1:10)
> y<-x
> z<-10/x
> opar<-par(no.readonly=TRUE)
> par(mar=c(5,4,4,8)+0.1)
> plot(x,y,type="b",pch=21,col="red",yaxt="n",lty=3,ann=FALSE)
> lines(x,z,type="b",pch=22,col="blue",lty=2)
> axis(2,at=x,labels=x,col.axis="red",las=2)
> axis(4,at=x,labels=round(z,digits=2),col.axis="blue",las=2,cex.axis=0.7,tck=-.01)
> axis(4,at=z,labels=round(z,digits=2),col.axis="blue",las=2,cex.axis=0.7,tck=-.01)
> mtext("y=1/x",side=4,line=3,cex.lab=1,las=2,col="blue")
> mtext("y=1/x",side=3,line=3,cex.lab=1,las=2,col="blue")
> mtext("y=1/x",side=3,line=2,cex.lab=1,las=2,col="blue")
> mtext("y=1/x",side=3,line=0,cex.lab=1,las=2,col="blue")
> title("An example of creative Axes",xlab="X values",ylab="Y=X")
> par(opar)
>
>
> dev.new()
> abline(h=c(1,5,7))
Error in int_abline(a = a, b = b, h = h, v = v, untf = untf, ...) :
plot.new has not been called yet
> dev.set()
windows
3
> abline(h=c(1,5,7))
> abline(v=seq(1,10,2), lty=2, col="blue")
标识符，图表legend
> opar<-par(no.readonly=TRUE)
> par(lwd=2,cex=1.5,font.lab=2)
plot(dose,drugA,type="b",pch=15,lty=1,col="red",ylim=c(0,60),main="Drug A vs. Drug B",xlab="Drug Dosage",ylab="Drug Response")
abline(h=c(30),lwd=1.5,lty=2,col="gray")
> line(dose,drugB,type="b",pch=17,lty=2,col="blue")
install.packages("Hmisc")
> library(Hmisc)
minor.tick(nx=3,ny=3,tick.ratio=0.5)
> legend("topleft",inset=.05,title="Drug Type", c("A","B"),lty=c(1,2),pch=c(15,17),col=c("red","blue"))
> par(opar)
#文本标注
> plot(wt,mpg,main="xXX",xlab="xlab",ylab="ylab",pch=18,col="blue")
> text(wt,mpg,row.names(mtcars),cex=0.6,pos=4,col="red")
图形组合 多幅图表在一个画布中显示
> opar<-par(no.readonly=TRUE)
> par(mfrow=c(2,2))
> plot(wt,mpg,main="wt vs. mpg")
> plot(wt,disp,main="wt vs. disp")
> hist(wt,main="hist.")
> boxplot(wt,main="boxplot of wt")
>
>
> layout(matrix(c(1,1,2,3),2,2,byrow=TRUE),widths=c(3,1),heights=c(1,2))
> hist(wt)
> hist(mpg)
> hist(disp)
>
>
>
> opar<-par(no.readonly=TRUE)
> par(fig=c(0,0.8,0,0.8)
+ )
> plot(mtcars$wt, mtcars$mpg, xlab="xlab", ylab="ylab")
> par(fig=c(0,0.8,0.55,1),new=TRUE)
> boxplot(mtcars$wt,horizontal=TRUE,axes=FALSE)
> par(fig=c(0.65,1,0,0.8),new=TRUE)
> boxplot(mtcars$mpg,axes=FALSE)
> mtext("Enhanced Scatterplot",side=3,outer=TRUE,line=-3)
下图是本章最佳图片：D， 虽然R画出来的图形不是很美观，但是它提供了很多灵活的绘图参数，自由组合这些参数应该能画出非常给力的分析报表。
