#数据集来自MASS包的cats数据集
#下面的程序将实现用体重和心脏重量来预测一只猫的性别
library(e1071)
data(cats,package="MASS")
summary(cats)
inputData=data.frame(cats[, c (2,3)], Sex= as.factor(cats$Sex))
train=inputData[1:108,]#训练集
test=inputData[109:144,]#测试集
#初步建模
x=train[,-3]
y=train[,3]
#核函数选择高斯核函数
model1=svm(x,y,kernel='radial',gamma=if(is.vector(x)) 1 else1/ncol(x))
#计算训练误差,结果显示有14个样本类别错误
z=test[,-3]
zy=test[,3]
zy=as.integer(zy)
pred1=predict(model1,x)
table(pred1,y)
#优化模型
attach(train)#将数据集train按列单独确认为向量
type=c("C-classification","nu-classification","one-classification")
kernel=c("linear","polynomial","radial","sigmoid")
pred2=array(0,dim=c(108,3,4))
accuracy=matrix(0,3,4)
yy=as.integer(y)
for(i in 1:3)
{
for(j in 1:4)
{
pred2[,i,j]=predict(svm(x,y,type=type[i],kernel=kernel[j]),x)
if(i>2) accuracy[i,j]=sum(pred2[,i,j]!=1)
else accuracy[i,j]=sum(pred2[,i,j]!=yy)
}
}
#12种组合算法在训练集上的误差
wrong=matrix(0,3,4)
for(i in 1:3)
{
for(j in 1:4)
{
wrong[i,j]=mean(yy != pred2[,i,j])#错误率占比
}
}
#选择训练集上误差最小的三种组合,计算在测试集上的误差,三种组合在训练集上的错误率分别为0.241,0.259,0.278;三种组合分别是nu-classification+radial、C-classification+linear组合和C-classification+radial组合。
pred3=array(0,dim=c(108,3,4))
for(i in 1:3)
{
for(j in 1:4)
{
pred3[,i,j]=predict(svm(x,y,type=type[i],kernel=kernel[j]),z)
if(i>2) accuracy[i,j]=sum(pred3[,i,j]!=1)
else accuracy[i,j]=sum(pred3[,i,j]!=yy)
}
}
mean(zy != pred3[,2,3])
mean(zy != pred3[,1,1])
mean(zy != pred3[,1,3])
#计算结果分别为0.417,0,0
#在测试集上错误率为0的两种算法分别是C-classification+linear组合和C-classification+radial组合。