###
###
###  SVM Demo - Simulated Data
###
###
####################################################



###-------------------------------------------------
###--- 1. SVM with linear kernel


##--- Simulate sim.data01
set.seed(1)
size=40
x <- matrix(rnorm(size*2), ncol=2)
y <- c(rep(-1,10) , rep(1,10) )
x[y==1,] <-  x[y==1,] + 1

plot(x, col=ifelse(y>0, "red", "blue"))

sim.data=data.frame(x=x, y=as.factor(y))

sim.data.01 <- sim.data[1:20,  ]     # Training data set
sim.data.TS <- sim.data[21:40, ]     # Testing data set


par(mfrow=c(1,2))
plot(sim.data.01[,1:2], col=ifelse(y>0, "red", "blue"), main="Training Set")
plot(sim.data.TS[,1:2], col=ifelse(y>0, "red", "blue"), main="Testing Set")




##--- a. Analyze Training Set with SVM (cost is 10)
library (e1071)         # install.packages("e1071")
svmfit=svm(y~., data=sim.data.01, kernel="linear",  cost=10, scale =FALSE )

plot(svmfit, sim.data.01)  # gives SVM classification plot

svmfit$index    # gives ix of support vectors

summary(svmfit)




##--- b. Analyze Training Set with SVM (cost is 0.1)
library (e1071)         # install.packages("e1071")
svmfit =svm(y~., data=sim.data.01, kernel="linear", cost=0.1, scale =FALSE )

plot(svmfit, sim.data.01)

svmfit$index    # support vectors are different now




##--- c. Pick best Cost with 10-fold CV
library (e1071)         # install.packages("e1071")
set.seed (1)
tune.out=tune(svm, y~., data=sim.data.01, kernel ="linear",
                ranges=list(cost=c(0.001, 0.01, 0.1, 1, 5, 10, 100) ))
summary(tune.out)

#--- Extract the model with best cost
bestmod <- tune.out$best.model
summary(bestmod)

plot(bestmod, sim.data.01)



##--- d. Apply Best model to Test Set
Y.pred=predict(bestmod, sim.data.TS )   # predict using bestmod



table(predict=Y.pred , truth=sim.data.TS$y )



svmfit=svm(y~., data=dat , kernel =" linear ", cost =.01, scale =FALSE )



ypred=predict(svmfit ,testdat)
table(predict=ypred, truth=testdat$y)






x[y==1 ,]= x[y==1 ,]+0.5
plot(x, col =(y+5) /2, pch =19)



dat=data.frame(x=x, y=as.factor(y))
svmfit=svm(y~., data=dat, kernel="linear", cost=1e5)
summary(svmfit)


plot(svmfit , dat)


svmfit =svm(y∼., data=dat , kernel =" linear ", cost =1)
summary (svmfit )
plot(svmfit ,dat )







###-------------------------------------------------
set.seed (1)
x=matrix (rnorm (200*2) , ncol =2)
x[1:100 ,]=x[1:100 ,]+2
x[101:150 ,]= x[101:150 ,] -2
y=c(rep (1 ,150) ,rep (2 ,50) )
dat=data.frame(x=x,y=as.factor (y))



plot(x, col=y)


train=sample (200 ,100)
svmfit =svm(y~., data=dat[train,], kernel="radial", gamma=1, cost=1)
plot(svmfit , dat[train ,])

summary(svmfit)




svmfit=svm(y∼., data=dat [train ,], kernel =" radial ",gamma =1, cost=1e5)
plot(svmfit ,dat [train ,])


set.seed (1)
tune.out=tune(svm , y∼., data=dat[train ,], kernel =" radial ",
ranges =list(cost=c(0.1 ,1 ,10 ,100 ,1000),
gamma=c(0.5,1,2,3,4) ))
summary (tune.out)


table(true=dat[-train ,"y"], pred=predict (tune.out$best .model ,
                                           newx=dat[-train ,]))


library (ROCR)
rocplot =function (pred , truth , ...){
  predob = prediction (pred , truth )
  perf = performance (predob , "tpr ", "fpr ")
  plot(perf ,...)
}


svmfit .opt=svm(y∼., data=dat[train ,], kernel =" radial ",
gamma =2, cost=1, decision .values =T)
fitted =attributes (predict (svmfit.opt ,dat[train,], decision.
                               values =TRUE))$decision .values


par(mfrow =c(1,2))
rocplot (fitted ,dat [train ,"y"], main=" Training Data")



svmfit.flex=svm (y~., data=dat[train ,], kernel =" radial ", gamma =50, cost=1, decision .values =T)
fitted =attributes (predict (svmfit .flex ,dat[train ,], decision.values =T))$decision .values
rocplot (fitted ,dat [train ,"y"], add =T,col ="red ")


fitted =attributes (predict (svmfit .opt ,dat[-train ,], decision .
values =T))$decision .values
rocplot (fitted ,dat [-train ,"y"], main ="Test Data")
fitted =attributes (predict (svmfit .flex ,dat[-train ,], decision.values =T))$decision .values
rocplot (fitted ,dat [-train ,"y"], add=T,col =" red ")











###-------------------------------------------------




set.seed (1)
x=rbind(x, matrix (rnorm (50*2) , ncol =2))
y=c(y, rep (0 ,50) )
x[y==0 ,2]= x[y==0 ,2]+2
dat=data.frame(x=x, y=as.factor (y))
par(mfrow =c(1,1))
plot(x,col =(y+1))
svmfit =svm(y∼., data=dat , kernel =" radial ", cost =10, gamma =1)
plot(svmfit , dat)












library (ISLR)
names(Khan)
[1] "xtrain " "xtest" "ytrain " "ytest "
dim( Khan$xtrain )
[1] 63 2308
dim( Khan$xtest )
[1] 20 2308
length (Khan$ytrain )
[1] 63
length (Khan$ytest )
[1]

table(Khan$ytrain )
1 2 3 4
8 23 12 20
table(Khan$ytest )
1 2


dat=data.frame(x=Khan$xtrain , y=as.factor ( Khan$ytrain ))
out=svm(y~., data=dat , kernel =" linear ",cost =10)
summary (out)


table(out$fitted , dat$y)
1 2


dat.te=data.frame(x=Khan$xtest , y=as.factor (Khan$ytest ))
pred.te=predict (out , newdata =dat.te)
table(pred.te , dat .te$y)