R語言學習.doc

#層次聚類Data=iris,-5;Means=sapply(data,mean);SD=sapply(data,sd);dataScale=scale(data,center=means,scale=SD);Dist=dist(dataScale,method=”euclidean”);heatmap(as.matrix(Dist),labRow=FALSE,labCol=FALSE);clusteModel=hclust(Dist,method=”ward”);result=cutree(clusteModel,k=3);table(iris,5,result);plot(clusteModel);library(fastcluster); # kuaisu cengcijuleiclusteModel=hclust(Dist,method=”ward”);library(proxy);res=dist(data,method=”cosine”);x=c(0,0,1,1,1,1);y=c(1,0,1,1,0,1);dist(rbind(x,y),method=”Jaccard”);x=c(0,0,1.2,1,0.5,1,NA);y=c(1,0,2.3,1,0.9,1,1);d=abs(x-y);Dist=sum(d!is.na(d)/6;# k-means聚類clusteModel=kmeans(dataScale,centers=3,nstart=10);class(clusteModel);library(proxy);library(cluster);clustModel=pam(dataScale,k=3,metric=”Mahalanobis”);clustModel$medoidstable(iris$Species,clustModel$clustering);par(mfcol=c(1,2);plot(clustModel,which.plots=2,main=”);Plot(clustModel,which.plots=1,main=”);library(devtools);install_github(“l(fā)ijian13/rinds”);rinds:bestCluster(dataScale,2:6);library(fpc);pka=kmeansruns(iris,1:4,krange=2:6,critout=TRUE,runs=2,criterion=”asw”);#基于密度的聚類x1=seq(0,pi,lenth.out=100);y1=sin(x1)+0.1*rnorm(100);x2=1.5+seq(0,pi,length.out=100);y2=cos(x2)+0.1*rnorm(100);data=data.frame(c(x1,x2),c(y1,y2);names(data)=c(“x”,”y”);model1=kmeans(data,centers=2,nstart=10);library(“fpc”);model2=dbscan(data,eps=0.3,MinPts=4);#自組織映射library(kohonen);data=as.matrix(iris,-5);somModel=som(data,grid=somgrid(15,10,”hexagonal”);plot(somModel,ncolors=10,type=”dist.neighbours”);irisclass=as.numeric(iris,5);plot(somModel,type=”mapping”,labels=irisclass,col=irisclass+3,main=”mapping plot”);#主成分分析library(FactoMineR);data(decathlon);head(decathlon,n=2);pca1=princomp(decathlon,1:10);plot(pca1,type=line);res.pca=PCA(decathlon,quanti.sup=11:12,quali.sup=13);#對應分析library(MASS);data(caith);biplot(corresp(caith,nf=2),xlim=c(-0.6,0.8);#多元分析的可視化library(car);data(mpg,package=ggplot2);scatterplotMatrix(mpg,c(displ,cty,hwy),diagonal=histogram,ellipse=TRUE);library(corrplot);data(mtcars);M=cor(mtcars);corrplot(M,order=hclust);#Logistic回歸set.seed(1);b0=1;b1=2;b2=3;x1=rnorm(1000);x2=rnorm(1000);z=b0+b1*x1+b2*x2;pr=1/(1+exp(-z);y=rbinom(1000,1,pr);plotdata2=data.frame(x1,x2,y=factor(y);library(ggplot2);p2=ggplot(data=plotdata2,aes(x=x1,y=x2,color=y)+geom_point();print(p2);data=data.frame(x1,x2,y);model=glm(y.,data=data,family=binomial);summary(model);w=model$coef;inter=-w1/w3;slope=-w2/w3;plotdata3=data.frame(cbind(x1,x2),y=factor(y);p3=ggplot(data=plotdata3,aes(x=x1,y=x2,color=y)+geom_point()+geom_abline(intercept=inter,slope=slope);print(p3);predict(model,newdata=list(x1=1,x2=3),type=response);#復雜網(wǎng)絡snafile=system.file(examples,sna,lijian001.txt,package=rinds);snadf=read.table(snafile,header=FALSE,stringsAsFactors=FALSE);head(snadf)library(igraph);snaobj=graph.data.frame(snadf,directed=FALSE);class(snaobj)vcount(snaobj);ecount(snaobj);neighbors(snaobj,6,mode=all);degree(snaobj,v=6);betweenness(snaobj,v=6,directed=FALSE);closeness(snaobj,v=6);page.rank(snaobj,vids=6);similarity.dice(snaobj,vids=c(6,7);snaclass=munity(snaobj,steps=5);cl=snaclass$membership;V(snaobj)$color=rainbow(max(cl)cl;V(snaobj)$bte=betweenness(snaobj,directed=FALSE);V(snaobj)$size=5;V(snaobj)bte=1800$size=15;V(snaobj)$label=NA;V(snaobj)bte=1800$label= V(snaobj)bte=1800$name;plot(snaobj,layout=layout.fruchterman.reingold,vertex.size= V(snaobj)$size,vertex.color= V(snaobj)$color,vertex.label= V(snaobj)$label,vertex.label.cex= V(snaobj)$cex,edge.color=grey(0.5),edge.arrow.mode=-);用caret包對數(shù)據(jù)清洗并進行回歸樹預測set.seed(1)data(PimaIndiansDiabetes2,package=mlbench)data=PimaIndiansDiabetes2library(caret)library(caret)preProcValues=preProcess(data,-9,method=c(center,scale)scaleddata=predict(preProcValues,data,-9)preProcbox=preProcess(scaleddata,method=c(YeoJohnson)boxdata=predict(preProcbox,scaleddata)preProcimp=preProcess(boxdata,method=bagImpute)procdata=predict(preProcimp,boxdata)procdata$class=data,9library(rpart)rpartModel=rpart(class.,data=procdata,control=rpart.control(cp=0)cptable=as.data.frame(rpartModel$cptable)cptable$errsd=cptable$xerror+cptable$xstdcpvalue=cptablewhich.min(cptable$errsd),CPpruneModel=prune(rpartModel,cpvalue)library(rpart.plot)rpart.plot(pruneModel)pre=predict(pruneModel,procdata,type=class)preTable=table(pre,procdata$class)accuracy=sum(diag(preTable)/sum(preTable)write.table(iris,file=C:/Program Files/R/zhangfuchang.csv,sep=,)data=read.table(file=C:/Program Files/R/zhangfuchang.csv,sep=,)write.table(procdata,file=C:/Program Files/R/zhangfuchang.csv,sep=,)procdata=read.table(file=C:/Program Files/R/zhangfuchang.csv,sep=,)回歸樹回歸代碼rpartModel=rpart(class.,data=procdata,control=rpart.control(cp=0.01),parms=list(loss=matrix(c(0,5,1,0),2)pre=predict(rpartModel,procdata,type=class)preTable=table(pre,procdata$class)accuracy=sum(diag(preTable)/sum(preTable)用分類回歸數(shù)分類，并用10重交叉驗證的R代碼procdata=read.table(file=C:/Program Files/R/zhangfuchang.csv,sep=,)num=sample(1:10,nrow(procdata),replace=TRUE)res=array(0,dim=c(2,2,10)n=ncol(procdata)for (i in 1:10)train=procdatanum!=i,test=procdatanum=i,model=rpart(class.,data=train,control=rpart.control(cp=0.1)pre=predict(model,test,-n,type=class)res,i=as.matrix(table(pre,test,n)table=apply(res,MARGIN=c(1,2),sum)sum(diag(table)/sum(table)貝葉斯分類library(MASS)library(klaR)nbModel=NaiveBayes(class.,data=procdata,usekernel=FALSE,fL=1)plot(nbModel,vars=glucose,legendplot=TRUE)plot(nbModel,vars=pressure,legendplot=TRUE)支持向量機分類library(devtools)install_github(lijian13/rinds)library(rinds)data(LMdata,package=rinds)library(kernlab)model=ksvm(y.,data=LMdata$SVM,kernel=rbfdot,C=1)plot(model,data=LMdata$SVM)用caret包中的train函數(shù)分別進行回歸樹、貝葉斯分類、最近鄰分類、神經(jīng)網(wǎng)絡分類、支持向量機分類、隨即森林分類回歸樹：library(caret)library(caret)library(e1071)fitControl=trainControl(method=repeatedcv,number=10,repeats=3)tunedf=data.frame(.cp=seq(0.001,0.1,length=10)treemodel=train(x=procdata,-9,y=procdata,9,method=rpart,trControl=fitControl,tuneGrid=tunedf)plot(treemodel)貝葉斯：library(klaR)library(caret)fitControl=trainControl(method=repeatedcv,number=10,repeats=3)tunedf=data.frame(.fL=1,.usekernel=TRUE)nbmodel=train(x=procdata,-9,y=procdata,9,method=nb,trControl=fitControl,tuneGrid=tunedf)densityplot(nbmodel)最近鄰：library(caret)fitControl=trainControl(method=repeatedcv,number=10,repeats=3)tunedf=data.frame(.k=seq(3,20,by=2)knnmodel=train(x=procdata,-9,y=procdata,9,method=knn,trControl=fitControl,tuneGrid=tunedf)plot(knnmodel)神經(jīng)網(wǎng)絡：library(caret)library(nnet)fitControl=trainControl(method=repeatedcv,number=10,repeats=3)tunedf=expand.grid(.decay=0.1,.size=5:10,.bag=TRUE)nnetmodel=train(class.,data=procdata,method=avNNet,trControl=fitControl,trace=FALSE,linout=FALSE,tuneGrid=tunedf)plot(nnetmodel)支持向量機library(caret)library(kernlab)fitControl=trainControl(method=repeatedcv,number=10,repeats=3)tunedf=data.frame(.C=seq(0,1,length=11)svmmodel=train(class.,data=procdata,method=svmRadialCost,trControl=fitControl,tuneGrid=tunedf)plot(svmmodel)隨即森林：library(caret)library(randomForest)fitControl=trainControl(method=repeatedcv,number=10,repeats=3)rfmodel=train(class.,data=procdata,method=rf,trControl=fitControl,tuneLength=5)plot(rfmodel)varImpPlot(rfmodel$finalModel)partialPlot(rfmodel$finalModel,procdata,-9,mass,which.class=pos)importance(rfmodel$finalModel)rm(list=ls()x=rnorm(1e4)*2+6y=0.5*x+1y=y+rnorm(length(y)smoothScatter(x,y)model=lm(yx)abline(model,lwd=2)text(1,8,R2=0.XXXX)R語言作單樣本的Wilcoxon秩和檢驗：x=c(4.12,5.81,7.63,9.74,10.39,11.92,12.32,12.89,13.54,14.45)wilcox.test(x-8,alt=greater)R語言作成對樣本的Wilcoxon秩和檢驗：algae=read.table(Analysis.txt,header=F,dec=.,s=c(season,size,speed,mxPH,mnO2,Cl,NO3,NH4,oPO4,PO4,Chla,a1,a2,a3,a4,a5,a6,a7),na.strings=c(XXXXXXX)library(DMwR)data(algae)找出那些樣本含有NA algae!complete.cases(algae),求出含有NA的樣本總個數(shù) nrow(algae!complete.cases(algae),)剔除含有NA的所有樣本 algae=na.o