1. Labs: Dimension Reduction, Multi-dimensional Scaling, SVM
Peter Fox and Greg Hughes
Data Analytics – 4600/6600
Group 3 Lab 1, March 2, 2017

2. On your own…
library(EDR) # effective dimension reduction library(dr) library(clustrd) install.packages("edrGraphicalTools") library(edrGraphicalTools) demo(edr_ex1) demo(edr_ex2) demo(edr_ex3) demo(edr_ex4)

3. Some examples – group3/
lab1_dr1.R
lab1_dr2.R
lab1_dr3.R
lab1_dr4.R

4. MDS – group3/ lab1_mds1.R lab1_mds2.R lab1_mds3.R

5. R – many ways (of course)
library(igraph) g <- graph.full(nrow(dist.au)) V(g)$label <- city.names layout <- layout.mds(g, dist = as.matrix(dist.au)) plot(g, layout = layout, vertex.size = 3)

6. Work through these… lab1_svm1.R –> lab1_svm11.R lab1_svm_rpart1.R
Exercise various parts of SVM, parameters, kernels, etc…
Karatzoglou et al

7. Ozone > library(e1071) > library(rpart)
> data(Ozone, package=“mlbench”)
> # # for field codes
> ## split data into a train and test set
> index <- 1:nrow(Ozone)
> testindex <- sample(index, trunc(length(index)/3))
> testset <- na.omit(Ozone[testindex,-3])
> trainset <- na.omit(Ozone[-testindex,-3])
> svm.model <- svm(V4 ~ ., data = trainset, type=“C-classification”,cost = 1000, gamma = )
> svm.pred <- predict(svm.model, testset[,-3])
> crossprod(svm.pred - testset[,3]) / length(testindex)
See:

8. Glass
library(e1071) library(rpart) data(Glass, package="mlbench") index <- 1:nrow(Glass) testindex <- sample(index, trunc(length(index)/3)) testset <- Glass[testindex,] trainset <- Glass[-testindex,] svm.model <- svm(Type ~ ., data = trainset, cost = 100, gamma = 1) # cost = “C” coefficient (Lagrange multiplier) svm.pred <- predict(svm.model, testset[,-10])

9. > table(pred = svm.pred, true = testset[,10]) true pred

10. Example lab1_svm1.R
n <- 150 # number of data points p <- 2 # dimension sigma <- 1 # variance of the distribution meanpos <- 0 # centre of the distribution of positive examples meanneg <- 3 # centre of the distribution of negative examples npos <- round(n/2) # number of positive examples nneg <- n-npos # number of negative examples # Generate the positive and negative examples xpos <- matrix(rnorm(npos*p,mean=meanpos,sd=sigma),npos,p) xneg <- matrix(rnorm(nneg*p,mean=meanneg,sd=sigma),npos,p) x <- rbind(xpos,xneg) # Generate the labels y <- matrix(c(rep(1,npos),rep(-1,nneg))) # Visualize the data plot(x,col=ifelse(y>0,1,2)) legend("topleft",c('Positive','Negative'),col=seq(2),pch=1,text.col=seq(2))

11. Example 1

12. Train/ test
ntrain <- round(n*0.8) # number of training examples tindex <- sample(n,ntrain) # indices of training samples xtrain <- x[tindex,] xtest <- x[-tindex,] ytrain <- y[tindex] ytest <- y[-tindex] istrain=rep(0,n) istrain[tindex]=1 # Visualize plot(x,col=ifelse(y>0,1,2),pch=ifelse(istrain==1,1,2)) legend("topleft",c('Positive Train','Positive Test','Negative Train','Negative Test'),col=c(1,1,2,2), pch=c(1,2,1,2), text.col=c(1,1,2,2))

13. Comparison of test classifier

14. Example ctd
svp <- ksvm(xtrain,ytrain,type="C-svc", kernel='vanilladot', C=100,scaled=c()) # General summary svp # Attributes that you can access attributes(svp) # did you look? # For example, the support vectors alpha(svp) alphaindex(svp) b(svp) # remember b? # Use the built-in function to pretty-plot the classifier plot(svp,data=xtrain)
> # For example, the support vectors
> alpha(svp)
[[1]]
[1]
> alphaindex(svp)
[1]
> b(svp)
[1]

16. Do SVM for iris

17. SVM for Swiss

18. e.g. Probabilities…
library(kernlab) data(promotergene) ## create test and training set ind <- sample(1:dim(promotergene)[1],20) genetrain <- promotergene[-ind, ] genetest <- promotergene[ind, ] ## train a support vector machine gene <- ksvm(Class~.,data=genetrain,kernel="rbfdot",\ kpar=list(sigma=0.015),C=70,cross=4,prob.model=TRUE) ## predict gene type probabilities on the test set genetype <- predict(gene,genetest,type="probabilities")

19. Result
> genetype + - [1,] [2,] [3,] [4,] [5,] [6,] [7,] [8,] [9,] [10,] [11,] [12,] [13,] [14,] [15,] [16,] [17,] [18,] [19,] [20,]

20. R-SVM http://www.stanford.edu/group/wonglab/RSVMpage/r-svm.tar.gz
Read/ skim the paper
Explore this method on a dataset of your choice, e.g. one of the R built-in datasets

21. kernlab http://aquarius.tw.rpi.edu/html/DA/svmbasic_notes.pdf
Some scripts: lab1_svm12.R, lab1_svm13.R

22. kernlab, svmpath and klaR
Start at page 9 (bottom)