R语言入门和使用技巧.ppt

《R语言入门和使用技巧.ppt》由会员分享，可在线阅读，更多相关《R语言入门和使用技巧.ppt（50页珍藏版）》请在三一办公上搜索。

1、R语言入门和 使用技巧,Lijun Jin,Contents,Chapter 1.Introduction,Introduction,R语言的概述定义：R是用于统计分析、绘图的语言和操作环境。R是属于GNU系统的一个自由、免费、源代码开放的软件，它是一个用于统计计算和统计制图的优秀工具。功能:R是一套完整的数据处理、计算和制图软件系统。R语言的发展1980年（贝尔实验室）R完善（MathSoft 公司的统计科学部）R系 统（Auckland大学的Robert Gentleman 和 Ross Ihaka）R is free！R语言的运用免费，开源，统计模块齐全避免了像商业软件在固定的分析过程中

2、存在的问题用户可以得知其中的计算会暗含着何种漏洞或错误可自由计算任何想计算的统计量（包括图形）,Introduction,资源网站资源：R主页：统计之都：http:/cos.name/The R Graph Gallery：Bioconductor：R Graphical Manua：书籍资料：统计建模与R软件（推荐）颜色卡片：R超级卡片：Notepad+下载：Statistics with RR for Beginners(中文版）Statistics and R Reading Notes(统计学与R读书笔记),R charts,基本运算符号,符号 命令或运算提示符+续行符基本算术运算例子

3、+4+5-5-4*5*4/4/545赋值符例子=x=5 xx-5assignassign(“x”,5)求助符例子?parhelp()help(par)整除%/%5%/%3余数%5%3,向量,数值型&整型&单精度实型&双精度实型逻辑型复值型字符型,向量构建c()没有什么规律seq()seq(from,to,by,length.out)rep()rep(x,.),数值型向量,例子 1:10 1 1 2 3 4 5 6 7 8 9 10 x seq(10)#same as 1:10 1 1 2 3 4 5 6 7 8 9 10 seq(1,10,by=1.5)#步长为1.51 1.0 2.5 4.0

4、 5.5 7.0 8.5 10.0 seq(1,6,by=3)#步长为31 1 4 seq(0,5,length.out=11)#生成向量长度为11 1 0.0 0.5 1.0 1.5 2.0 2.5 3.0 3.5 4.0 4.5 5.0 rep(1:10)1 1 2 3 4 5 6 7 8 9 10 rep(1:10,2)#整个向量重复2次 1 1 2 3 4 5 6 7 8 9 10 1 2 3 4 5 6 7 8 9 10 rep(1:3,each=5)#每个元素重复5次 1 1 1 1 1 1 2 2 2 2 2 3 3 3 3 3 rep(1:3,1:3)#每个元素分别重复1、2、

5、3次1 1 2 2 3 3 3 rep(1:4,each=2,len=10)1 1 1 2 2 3 3 4 4 1 1,数组,x=array(1:24,3)1 1 2 3 x=array(1:24,3,4)1 1 2 3 x=array(1:24,c(3,4),1,2,3,41,1 4 7 102,2 5 8 113,3 6 9 12 t(x),1,2,31,1 2 32,4 5 63,7 8 94,10 11 12,x=array(1:24,c(3,4,2),1,1,2,3,41,1 4 7 102,2 5 8 113,3 6 9 12,2,1,2,3,41,13 16 19 222,14

6、17 20 233,15 18 21 24,矩阵,matrix(1:15,nrow=3,ncol=5,byrow=TRUE),1,2,3,4,51,1 2 3 4 52,6 7 8 9 103,11 12 13 14 15 x is.matrix(x)1 TRUE,x=array(1:24,c(3,4,2)is.matrix(x)1 FALSE y-matrix(x,nrow=3),1,2,3,4,5,6,7,81,1 4 7 10 13 16 19 222,2 5 8 11 14 17 20 233,3 6 9 12 15 18 21 24,数据框与列表,数据框是一种矩阵形式的数据结构。数据

7、框内含的数据可以是不同类型的数据。每一列的数据必须是同一类型，且每一列的长度必须相同。数据框可以由data.frame()构建。数据框的构建：方法1:读文件read.table()表格式文件read.csv()逗号分隔的文件read.delim()tab键分隔的文件方法2：读变量 x=c(42,7,64,9)y=1:4 z.df=data.frame(INDEX=y,VALUE=x)INDEX VALUE1 1 422 2 73 3 644 9(z.df)INDEX VALUE1 1 422 2 73 3 644 4 9,Xming usage,Step 1:install Xming in

8、WindowStep 2:clink Xming in LinuxStep 3:display picture,Xming usage,Chapter 2.Parameters,Draw element,par()函数的参数详解plot()及相关函数的参数说明,Par charts,Par charts,Col:图中符号（点、线等）的颜色,col.axis 坐标轴刻度标记的颜色col.lab 坐标轴标题的颜色col.main 图主标题的颜色col.sub 图副标题的颜色,Par charts,mfrow,mfcolmar,oma,x-c(1:5)par(ann=F,mar=c(4,4,4,6)

9、plot(x,pch=10,col=4,cex=3,axes=F)mtext(side=1,line=0,side=1,line=0,cex=2)mtext(side=2,line=1,side=2,line=1,cex=2)mtext(side=3,line=2,side=3,line=2,cex=2)mtext(side=4,line=3,side=4,line=3,cex=2)box(),plot charts,plot(c(10,20),c(1,13),col=white,xlab=,ylab=,main=type=,xaxt=n,yaxt=n,cex.main=2.5)ltypes=

10、c(l,p,b,c,o,s,S,h)lpos=c(seq(0,10,2),13,15)for(i in seq_along(ltypes)lines(lposi+1:20,1:20,type=ltypesi,lwd=3)text(9.5+1:8,12-1:8,c(l,p,b,c,o,s,S,h),cex=2,col=red),plot(c(10,20),c(0,10),col=white,xlab=,ylab=,main=lty=,xaxt=n,ylim=c(0,9.6),cex.main=2.5)lnames=c(blank,solid,dashed,dotted,dotdash,longd

11、ash,twodash,51,9396,848481)for(i in 1:10)abline(h=i-1,lty=lnamesi,lwd=3)text(15,i-0.5,lnamesi,cex=2),plot charts,plot(c(0.5,1.5),c(0,3),col=white,xlab=,ylab=,main=cex=,xaxt=n,yaxt=n,cex.main=2.5)for(i in seq(0,3,0.2)points(0,i,pch=16,cex=i)text(1,i,paste(i),cex=i),plot(c(10,20),c(23,25.5),col=white,

12、xlab=,ylab=,main=lwd=,xaxt=n,log=y,cex.main=2.5,yaxp=c(0.1,50,2)for(i in 1:9)lines(c(11,19),c(2(i-4),2(i-4),lwd=2(i-4)text(15,2(i-4+0.5),2(i-4),cex=2),Cex:图上元素（文本和符号等）的缩放倍数；取值为一个相对于1的数值cex.axis 坐标轴刻度标记的缩放倍数cex.lab 坐标轴标题的缩放倍数cex.main 图主标题的缩放倍数cex.sub 图副标题的缩放倍数,plot charts,plot(c(0,4.5),c(0,4),col=whi

13、te,xlab=,ylab=,main=pch=,xaxt=n,yaxt=n,cex.main=2.5)for(i in 0:24)points(i%5,i%/%5,pch=i,cex=2)text(0.3+i%5,i%/%5,i,cex=2),Text,titletitle(main=NULL,sub=NULL,xlab=NULL,ylab=NULL,line=NA,outer=FALSE,.)texttext(x,y=NULL,labels=seq_along(x),adj=NULL,pos=NULL,offset=0.5,vfont=NULL,cex=1,col=NULL,font=NU

14、LL,.)mtextmtext(text,side=3,line=0,outer=FALSE,at=NA,adj=NA,padj=NA,cex=NA,col=NA,font=NA,.),Text,plot(1:10,(-4:5)2,main=Parabola Points,xlab=xlab)mtext(10 of them)for(s in 1:4)+mtext(paste(mtext(.,line=-1,side,col,font=,s,+,cex=,(1+s)/2,),line=-1,+side=s,col=s,font=s,cex=(1+s)/2)mtext(mtext(.,line=

15、-2),line=-2)mtext(mtext(.,line=-2,adj=0),line=-2,adj=0),plot(-1:1,-1:1,type=n,xlab=Re,ylab=Im)K-16;text(exp(1i*2*pi*(1:K)/K),col=2,cex=2)par(ann=F,new=T)plot(1:10,1:10,main=text(.)examplesn,+sub=R is GNU,but not.)mtext(Latin-1 accented chars:,side=3)points(c(6,2),c(2,1),pch=3,cex=5,col=green)text(6,

16、2,the text is CENTERED around(x,y)=(6,2)by default,col=4,cex=.8)text(2,1,or Left/Bottom-JUSTIFIED at(2,1)by adj=c(0,0),+adj=c(0,0)text(4,9,expression(hat(beta)=(Xt*X)-1*Xt*y),col=8)text(4,8.4,expression(hat(beta)=(Xt*X)-1*Xt*y),col=11,cex=2)text(4,7,expression(bar(x)=sum(frac(xi,n),i=1,n),col=12,cex

17、=2)title(text(.)examplesn),legend and grid,legend(x,y=NULL,legend,fill=NULL,col=par(col),lty,lwd,pch,angle=45,density=NULL,bty=o,bg=par(bg),box.lwd=par(lwd),box.lty=par(lty),box.col=par(fg),pt.bg=NA,cex=1,pt.cex=cex,pt.lwd=lwd,xjust=0,yjust=1,x.intersp=1,y.intersp=1,adj=c(0,0.5),text.width=NULL,text

18、.col=par(col),merge=do.lines&has.pch,trace=FALSE,plot=TRUE,ncol=1,horiz=FALSE,title=NULL,inset=0,xpd,title.col=text.col),plot(1:3)grid(NA,5,lwd=4,col=3,lty=6)grid(5,NA,lwd=4,col=3,lty=6),grid(nx=NULL,ny=nx,col=lightgray,lty=dotted,lwd=par(lwd),equilogs=TRUE),axis,plot(1:7,rnorm(7),main=axis()example

19、s,type=s,xaxt=n,frame=FALSE,col=red)axis(1,1:7,LETTERS1:7,col.axis=blue)#unusual options:axis(4,col=violet,col.axis=dark violet,lwd=2)axis(3,col=gold,lty=2,lwd=0.5),plot(1:10,xaxt=n)axis(1,xaxp=c(2,9,7),Chapter 3.Graphic samples,Graphics,Pie charts,pie.sales-c(0.12,0.3,0.26,0.16,0.04,0.12)names(pie.

20、sales)-c(Blueberry,Cherry,Apple,Boston Cream,Other,Vanilla Cream)pie(pie.sales,col=c(purple,violetred1,green3,cornsilk,cyan,white),a-c(58.13,21.64,20.24)ratio-sprintf(%.2f,100*a/sum(a)label=paste(ratio,%,sep=)pie(a,col=c(red,blue,green),labels=label)legend(topright,c(mCG,mCHG,mCHH),col=c(2,4,green),

21、pch=15,bty=n),Pie3D charts,library(plotrix)a-c(58.13,21.64,20.24)c-paste(a,%,sep=)label=paste(c(mCG,mCHG,mCHH),c,sep=n)pie3D(a,labels=label,explode=0.1,radius=0.9,border=black),explodeborderlabelsradiusclockwisecolangledensityinit.angle.,Venn charts,install.packages(plotrix)library(plotrix)par(ann=F

22、)plot(0:10,seq(0,10,length=11),type=n,axes=F)draw.circle(2,5,2)draw.circle(4,5,2)text(1,5,labels=10.12%,col=black,font=2)text(3,5,labels=49.5%,col=black,font=2)text(5,5,labels=40.38%,col=black,font=2)text(2,2,Sample1)text(5,2,Samlpe2)text(3.5,8.5,labels=Venn picture“,font=2,cex=1.5),axis charts,x-c(

23、0.00,0.40,0.86,0.85,0.69,0.48,0.54,1.09,1.11,1.73,2.05,2.02)par(bg=lightgray)plot(x,type=n,axes=FALSE,ann=FALSE)usr-par(usr)rect(usr1,usr3,usr2,usr4,col=cornsilk,border=black)lines(x,col=blue)points(x,pch=21,bg=lightcyan,cex=1.25)axis(2,col.axis=blue,las=1)axis(1,at=1:12,lab=month.abb,col.axis=blue)

24、box()title(main=The Level of Interest in R,font.main=4,col.main=red)title(xlab=1996,col.lab=red),axis(side,at=NULL,labels=TRUE,tick=TRUE,line=NA,pos=NA,outer=FALSE,font=NA,lty=solid,lwd=1,lwd.ticks=lwd,col=NULL,col.ticks=NULL,hadj=NA,padj=NA,.),plot(1:7,rnorm(7),main=axis()examples,type=s,xaxt=n,fra

25、me=FALSE,col=red)axis(1,1:7,LETTERS1:7,col.axis=blue)axis(4,col=violet,col.axis=dark violet,lwd=2)axis(3,col=gold,lty=2,lwd=0.5),Rect charts,plot(c(100,200),c(300,450),type=n,xlab=,ylab=)rect(100,300,125,350)#transparent rect(100,400,125,450,col=green,border=blue“)rect(115,375,150,425,col=par(bg),bo

26、rder=transparent)rect(150,300,175,350,density=10,border=red)rect(150,400,175,450,density=30,col=blue,angle=-30,border=transparent)legend(180,450,legend=1:4,fill=c(NA,green,par(fg),blue),density=c(NA,NA,10,30),angle=c(NA,NA,30,-30),rect(xleft,ybottom,xright,ytopdensityangle col border lty lwd.),point

27、 charts,plot(1,col=white,xlab=,ylab=,main=curve(),abline(),points(),lines(),xaxt=n,yaxt=n,type=n,xlim=c(-pi,pi),ylim=c(-pi,pi),cex.main=2.5)arrows(c(-3,0),c(0,-3),c(3,0),c(0,3),lwd=3)curve(sin,-pi,pi,add=T,lwd=3,col=red)curve(cos,-pi,pi,add=T,lwd=3,col=green)curve(tan,-pi/2,pi/2,add=T,lwd=3,col=blue

28、)abline(0,-1,lwd=3,lty=2,col=grey80)abline(0,1,lwd=3,lty=2,col=grey80)abline(1,0,lwd=3,lty=2,col=grey80)abline(-1,0,lwd=3,lty=2,col=grey80)points(3.2*cos(pi*(1:50)/25),3.2*sin(pi*(1:50)/25),pch=19),line(x,ytype),points(pchcexcollwdbg),abline charts,plot(c(-2,3),c(-1,5),type=n,xlab=x,ylab=y,asp=1)abl

29、ine(h=0,v=0,col=gray60)text(1,0,abline(h=0),col=gray60,adj=c(0,-.1)abline(h=-1:5,v=-2:3,col=lightgray,lty=3)abline(a=1,b=2,col=2)text(1,3,abline(1,2),col=2,adj=c(-.1,-.1),abline(a,b,untf=FALSE,.)abline(h=,untf=FALSE,.)abline(v=,untf=FALSE,.)abline(coef=,untf=FALSE,.)abline(reg=,untf=FALSE,.),hist ch

30、arts,直方图宽度-组距高度-频数，频率，频率/组距注：高度-频率/组距，矩形的面积是数据落入区间的频率，可估计总体的概率密度。hist(x,breaks=Sturges,freq=NULL,probability=!freq,include.lowest=TRUE,right=TRUE,density=NULL,angle=45,col=NULL,border=NULL,main=paste(Histogram of,xname),xlim=range(breaks),ylim=NULL,xlab=xname,ylab,axes=TRUE,plot=TRUE,labels=FALSE,nc

31、lass=NULL,.)breaks-组距freq：TRUE-频率直方图FALSE-密度直方图例子：hist(sqrt(islands),breaks=12,+col=lightblue,border=pink),hist charts,w-c(75.0,64.0,47.4,66.9,62.2,62.2,58.7,63.5,66.6,64.0,57.0,69.0,56.9,50.0,72.0)par(mfrow=c(2,2),ann=F)hist(w,freq=F,col=blue,main=freq=F)hist(w,freq=T,col=green,main=freq=T)hist(w,f

32、req=T,col=red,main=breaks=3,density=10,breaks=3,density=10)hist(w,freq=T,col=red,main=breaks=20,breaks=20),density charts,核密度估计函数已知样本，估计其密度。density(x,bw=nrd0,adjust=1,kernel=c(gaussian,epanechnikov,rectriangular,biweight,cosinwindow=kernel,width,give.Rkern=FALSE,n=512,from,to,cut=3,na.rm=FALSE)例子：(k

33、ernels-eval(formals(density.default)$kernel)plot(density(0,bw=1),xlab=,main=Rs density()kernels with bw=1)for(i in 2:length(kernels)lines(density(0,bw=1,kernel=kernelsi),col=i,lwd=2)legend(topright,legend=kernels,col=seq(kernels),lty=1,cex=.8,y.intersp=1,lwd=2),density charts,par(ann=F)m-read.table(

34、Inbred.0.8,head=T)n-read.table(Wild.0.8,head=T)x-m,10m,10 0y-n,10n,10 0plot(density(x,bw=0.02),col=2,axes=F)par(ann=F,new=T)plot(density(y,bw=0.02),col=3)mtext(Methylation level of gene,side=1,line=3,cex=1.3)mtext(Density,side=2,line=3,cex=1.3)legend(topright,lwd=c(2,2),cex=1,col=c(2:3),legend=c(Inb

35、red,Wild)title(Oyster),barplot charts,library(RColorBrewer)par(mfrow=c(2,2),mar=c(3,2.5,0.5,0.1)death=t(VADeaths),5:1barplot(death,col=brewer.pal(4,Set1)barplot(death,col=brewer.pal(4,Set1),beside=TRUE,legend=TRUE)x-c(1,2,-3,4,-9,10,-1,2,0,-8)r-barplot(x,col=rainbow(20)tN-c(6,6,19,16,17,14,8,8,3,3)r

36、-barplot(tN,col=rainbow(20),horiz=T),barplot charts,mtread.table(overlap.CF_ANT.Methylation.level.region.relation,head=F);pdf(overlap.CF_ANT.Methylation.level.region.relation.pdf,height=8,width=12);x=0:10y=4+8*xpar(bty=7,mar=c(9,8,2,0.5),mgp=c(5,1,0);n-data.frame(mt,c(2:8)barplot(t(as.matrix(n),col=

37、c(2:8),axes=F,ylim=c(0,0.12),width=1,beside=T,ylab=Relative methylaion level,cex.lab=2);axis(1,at=y,lab=F)text(y-1,-0.017,labels=mt,1,srt=45,xpd=T,cex=1.7,font.lab=2,cex.lab=2)axis(2,las=1,cex.axis=1.8,font.axis=2)legend(topright,legend=c(CF_Egg,CF_larva,CF_Major,CF_Minor,CF_male,CF_Q,CF_VQ),pch=15,

38、col=c(2:8),cex=1.5);,barplot2 charts,library(gplots)hh-t(VADeaths)1,1mybarcol-gray20ci.l-hh*0.85ci.u-hh*1.15barplot2(hh,ci.l=ci.l,ci.u=ci.u,plot.ci=TRUE,col=3,axes=F),barplot2 charts,library(gplots)hh-t(VADeaths),5:1 mybarcol-gray20 ci.l-hh*0.85 ci.u-hh*1.15 mp-barplot2(hh,beside=TRUE,col=c(lightblu

39、e,mistyrose,lightcyan,lavender),legend=colnames(VADeaths),ylim=c(0,100),main=Death Rates in Virginia,font.main=4,sub=Faked 95 percent error bars,col.sub=mybarcol,cex.names=1.5,plot.ci=TRUE,ci.l=ci.l,ci.u=ci.u,plot.grid=TRUE)mtext(side=1,at=colMeans(mp),line=2,text=paste(Mean,formatC(colMeans(hh),col

40、=red)box(),Rural Male Rural Female Urban Male Urban Female50-54 11.7 8.7 15.4 8.455-59 18.1 11.7 24.3 13.660-64 26.9 20.3 37.0 19.365-69 41.0 30.9 54.6 35.170-74 66.0 54.3 71.1 50.0,boxplot charts,箱线图直接简洁的展示数据分布的特征。boxplot(x,.,range=1.5,width=NULL,varwidth=FALSE,notch=FALSE,outline=TRUE,names,plot=T

41、RUE,border=par(fg),col=NULL,log=,pars=list(boxwex=0.8,staplewex=0.5,outwex=0.5),horizontal=FALSE,add=FALSE,at=NULL)例子：,Notch:凹槽所表示的实际上是中位数的一个区间估计.计算式：Q2+/1.58IQR/区间置信水平:95%在比较两组数据中位数差异时，我们只需要观察箱线图的凹槽是否有重叠部分，若两个凹槽互不交叠，那么说明这两组数据的中位数有显著差异（P值小于0.05).,x-c(1,2,3,4,9,10,-1,2,0,-8)boxplot(x,notch=T,col=blue

42、,outline=T),boxplot charts,t=read.table(CF_Egg.sum_len.txt,header=T)par(font=2,cex.axis=1.2,font.lab=2,font.axis=2)boxplot(list(t,1,t,2,t,3,t,4,t,5,t,6,t,7,t,8,t,9,t,10),notch=T,outline=F,names=c(1,2,3,4,5,6,7,8,9,10),col=2:11)mtext(Methylation level,side=1,line=3,cex=1.3)mtext(Gene length,side=2,li

43、ne=3,cex=1.3)title(CF_Egg Distribution)box(),Cluster chart,系统聚类分析法：最短距离法(single):最长距离法(complete)：中间距离法(median)：类平均法(average)：重心法(centroid)：离差平方和(ward”):相似分析法(“Mcquitty”):,x hc1 hc3 opar plot(hc1,hang=-1);plot(hc2,hang=-1)plot(hc3,hang=-1);plot(hc4,hang=-1)par(opar)d-dist(x),Dij表示第i个样本与第j个样本的距离，G1,G2

44、.表示类，DKL表示GK与GL的距离,heatmap chart,library(pheatmap)test=matrix(rnorm(200),20,10)test1:10,seq(1,10,2)=test1:10,seq(1,10,2)+3test11:20,seq(2,10,2)=test11:20,seq(2,10,2)+2colnames(test)=paste(Test,1:10,sep=)rownames(test)=paste(Gene,1:20,sep=)pheatmap(test),heatmap chart,x0.4),col=cm.colors,trace=none,d

45、ensity.info=none,labRow=,labCol=c(FEM,NFEM,SRM,NSRM)heatmap.2(z,xlab=,ylab=,na.rm=T,revC=T,keysize=2,symkey=min(x 0.4),col=terrain.colors,trace=none,density.info=none,Rowv=NA,labRow=,labCol=c(FEM,NFEM,SRM,NSRM)heatmap.2(z,xlab=,ylab=,na.rm=T,revC=T,keysize=2,symkey=min(x 0.4),col=topo.colors,trace=n

46、one,density.info=none,Rowv=NA,labRow=,labCol=c(FEM,NFEM,SRM,NSRM)heatmap.2(z,xlab=,ylab=,na.rm=T,revC=T,keysize=1.8,symkey=min(x 0.4),col=rainbow,trace=none,density.info=none,Rowv=NA,labRow=,labCol=c(FEM,NFEM,SRM,NSRM)heatmap.2(z,xlab=,ylab=,na.rm=T,revC=T,keysize=1.8,symkey=min(x 0.4),col=heat.colo

47、rs,trace=none,density.info=none,Rowv=NA,labRow=,labCol=c(FEM,NFEM,SRM,NSRM)heatmap.2(z,xlab=,ylab=,na.rm=T,revC=T,keysize=1.8,symkey=min(x 0.4),col=gray.colors,trace=none,density.info=none,Rowv=NA,labRow=,labCol=c(FEM,NFEM,SRM,NSRM),练习题,1./ifs5/PC_PA_UN/ANIMAL/USER/GROUP2/jinlijun/Rcourse/barplot.tx

48、t 将这个文件的数据可视化。（barplot）2./ifs5/PC_PA_UN/ANIMAL/USER/GROUP2/jinlijun/Rcourse/pie.txt 将这个文件的数据可视化。（pie）3./ifs5/PC_PA_UN/ANIMAL/USER/GROUP2/jinlijun/Rcourse/join 将这个目录下的5个.stat文件的数据画在一张图上。（plot）要求图形效果跟/ifs5/PC_PA_UN/ANIMAL/USER/GROUP2/jinlijun/Rcourse/join/rpkm_bin.CG.RML.pdf 差不多，颜色可以有差别，其中两条灰色的垂直线分别在坐标21和40的位置上。,