dividedata2.R-20170905

最新推荐文章于 2021-11-21 13:38:00 发布

原创最新推荐文章于 2021-11-21 13:38:00 发布 · 178 阅读

0 ·

CC 4.0 BY-SA版权

R 专栏收录该内容

14 篇文章

订阅专栏

本文通过构建线性模型、支持向量机(SVM)和径向基核函数(RBF)的核支持向量机(KSVM)，对数据进行训练并预测，比较了三种模型在相同数据集上的预测误差。实验中，每种模型被重复训练和测试1000次，以评估其平均预测精度。

library(caret) 
library("kernlab")
data=as.matrix(oadata)
colnames(data)=c('y','x1','x2','x17',paste("x",3:16,sep=""))

c=1000 #验证c次
set.seed(1000)
r1=matrix(0,c,1)
r2=matrix(0,c,1)
r4=matrix(0,c,1)
p1=matrix(0,14,c)

for (k in 1:c) {
  index <-createDataPartition(data[,1], time=1, p=0.8, list=F)
  train=data[index, ]
  test=data[-index, ]
  colnames(train)=c('y','x1','x2','x17',paste("x",3:16,sep=""))
  colnames(test)=c('y','x1','x2','x17',paste("x",3:16,sep=""))
  
  a.lm = lm(y~0+x1+x2+x17
            +as.factor(x3)
            +as.factor(x4)
            #+as.factor(x5)
            +as.factor(x6)
            +as.factor(x7)
            +as.factor(x8)
            +as.factor(x9)
            #+as.factor(x10)
            +as.factor(x11)
            +as.factor(x12)
            #+as.factor(x13)
            +as.factor(x14)
            #+as.factor(x15)
            +as.factor(x16)
            ,data=data.frame(train)) #train集构造anova模型,删去x5，x15，x10，x15
  #assign(paste("a.lm",k,sep=""),a.lm) #记为ak
  #summary(a.lm)
  #assign(paste("beta",k,sep=""),data.matrix(coef(a.lm))) #系数betak
  ytest=predict(aov(a.lm),data.frame(test[,2:18])) 
  #assign(paste("ytest",k,sep=""),ytest) #test集预测结果ytestk
  resi1=abs(ytest-test[,1])/test[,1]
  r1[k]=mean(resi1) #误差r1(k)
  #print(mean(resi1))
  p1[,k]=Anova(a.lm,singular.ok = TRUE,type="III")$Pr #p-value

m<-svm(train[,2:18],train[,1])
#assign(paste("m",k,sep=""),m)
#summary(m)
ytest2=predict(m,test[,2:18])
#assign(paste("ytest2_",k,sep=""),ytest2)
resi2=abs(ytest2-test[,1])/test[,1]
r2[k]=mean(resi2) #误差
#print(mean(resi2))

#svm,kernel=RBF
s=ksvm(train[,2:18],train[,1],kernel = "rbfdot")
s.ytest=predict(s,test[,2:18],type = "response")
r4[k]=mean(abs(s.ytest-test[,1])/test[,1])
}

mean(r1)
mean(r2)
mean(r4)

#最终模型
af.lm = lm(y~0+x1+x2+x17
          +as.factor(x3)
          +as.factor(x4)
          #+as.factor(x5)
          +as.factor(x6)
          +as.factor(x7)
          +as.factor(x8)
          +as.factor(x9)
          #+as.factor(x10)
          +as.factor(x11)
          +as.factor(x12)
          #+as.factor(x13)
          +as.factor(x14)
          #+as.factor(x15)
          +as.factor(x16)
          ,data=data.frame(data)) 
summary(af.lm)
Anova(af.lm,singular.ok = TRUE,type="III")
#ytest=predict(aov(af.lm),data.frame(test[,2:18])) 
#p1[,k]=Anova(af.lm,singular.ok = TRUE,type="III")$Pr #p-value

mf<-svm(data[,2:18],data[,1])
mf

#svm,kernel=RBF
sf=ksvm(data[,2:18],data[,1],kernel = "rbfdot")
sf