SVM example IRIS data in R

SVM is a useful alternative to neural networks

Two key concepts of SVM:

1. maximize the margin

2. the kernel trick

SVM is related to statistical learning theory

SVM was first introduced in 1992

SVM becomes popular because of its success in handwritten digit recognition 1.1% test error rate for SVM.

library(e1071)
library(caret)

## Loading required package: lattice

## Loading required package: ggplot2

library(NLP)

## 
## Attaching package: 'NLP'

## The following object is masked from 'package:ggplot2':
## 
##     annotate

library(tm)

data(iris)

iris$SpeciesClass[iris$Species=="versicolor"] <- "TRUE"
iris$SpeciesClass[iris$Species!="versicolor"] <- "FALSE"
trainPositive<-subset(iris,SpeciesClass=="TRUE")
testnegative<-subset(iris,SpeciesClass=="FALSE")
inTrain<-createDataPartition(1:nrow(trainPositive),p=0.6,list=FALSE)

trainpredictors<-trainPositive[inTrain,1:4]
trainLabels<-trainPositive[inTrain,6]

testPositive<-trainPositive[-inTrain,]
testPosNeg<-rbind(testPositive,testnegative)

testpredictors<-testPosNeg[,1:4]
testLabels<-testPosNeg[,6]

svm.model<-svm(trainpredictors,y=NULL,
           type='one-classification',
           nu=0.10,
           scale=TRUE,
           kernel="radial")

svm.predtrain<-predict(svm.model,trainpredictors)
svm.predtest<-predict(svm.model,testpredictors)

confTrain<-table(Predicted=svm.predtrain,Reference=trainLabels)
confTest<-table(Predicted=svm.predtest,Reference=testLabels)

confusionMatrix(confTest,positive='TRUE')

## Confusion Matrix and Statistics
## 
##          Reference
## Predicted FALSE TRUE
##     FALSE    99   14
##     TRUE      1    4
##                                          
##                Accuracy : 0.8729         
##                  95% CI : (0.799, 0.9271)
##     No Information Rate : 0.8475         
##     P-Value [Acc > NIR] : 0.266948       
##                                          
##                   Kappa : 0.3015         
##  Mcnemar's Test P-Value : 0.001946       
##                                          
##             Sensitivity : 0.22222        
##             Specificity : 0.99000        
##          Pos Pred Value : 0.80000        
##          Neg Pred Value : 0.87611        
##              Prevalence : 0.15254        
##          Detection Rate : 0.03390        
##    Detection Prevalence : 0.04237        
##       Balanced Accuracy : 0.60611        
##                                          
##        'Positive' Class : TRUE           
## 

print(confTrain)

##          Reference
## Predicted TRUE
##     FALSE    6
##     TRUE    26

print(confTest)

##          Reference
## Predicted FALSE TRUE
##     FALSE    99   14
##     TRUE      1    4