SVM

library(e1071)

data("iris")

summary(iris)

##   Sepal.Length    Sepal.Width     Petal.Length    Petal.Width   
##  Min.   :4.300   Min.   :2.000   Min.   :1.000   Min.   :0.100  
##  1st Qu.:5.100   1st Qu.:2.800   1st Qu.:1.600   1st Qu.:0.300  
##  Median :5.800   Median :3.000   Median :4.350   Median :1.300  
##  Mean   :5.843   Mean   :3.057   Mean   :3.758   Mean   :1.199  
##  3rd Qu.:6.400   3rd Qu.:3.300   3rd Qu.:5.100   3rd Qu.:1.800  
##  Max.   :7.900   Max.   :4.400   Max.   :6.900   Max.   :2.500  
##        Species  
##  setosa    :50  
##  versicolor:50  
##  virginica :50  
##                 
##                 
## 

str(iris)

## 'data.frame':    150 obs. of  5 variables:
##  $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
##  $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
##  $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
##  $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
##  $ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...

#model 
model<-svm(Species~ ., data =iris)

model

## 
## Call:
## svm(formula = Species ~ ., data = iris)
## 
## 
## Parameters:
##    SVM-Type:  C-classification 
##  SVM-Kernel:  radial 
##        cost:  1 
##       gamma:  0.25 
## 
## Number of Support Vectors:  51

# split
library(caTools)
split<-sample.split(iris$Species, SplitRatio = 0.7)
training<-subset(iris,split==TRUE)
testing<-subset(iris, split==FALSE)

#visualize
library(ggplot2)
library(GGally)
ggpairs(training, ggplot2::aes(colour = Species, alpha = 0.4))

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# without species
training[,1:4] = scale(training[,1:4])
testing[,1:4] = scale(testing[,1:4])

classifier1 = svm(formula = Species~., data = training, type = 'C-classification', kernel = 'radial')
classifier2 = svm(formula = Species~ Petal.Width + Petal.Length, data = training, type = 'C-classification', kernel = 'radial')

# prediction 
test_pred1 = predict(classifier1, type = 'response', newdata = testing[-5])
test_pred2 = predict(classifier2, type = 'response', newdata = testing[-5])

head(test_pred1)

##      3      4      5     13     14     16 
## setosa setosa setosa setosa setosa setosa 
## Levels: setosa versicolor virginica

table(test_pred1,test_pred2)

##             test_pred2
## test_pred1   setosa versicolor virginica
##   setosa         15          0         0
##   versicolor      0         15         0
##   virginica       0          1        14

#  again build 
svm.model<-svm(Species~.,data=iris, type='C-classification',kernel='linear', scale=FALSE)

plot(iris$Sepal.Length,iris$Sepal.Width,col=as.integer(iris[,5]),pch=c("o","+")[1:150 %in% svm.model$index+1],cex=2,xlab="sepal length", ylab="sepal width")

svm.model1 <- svm(Species ~ Sepal.Length + Sepal.Width, data = iris, kernel = "linear")
plot(svm.model1, iris, Sepal.Width ~ Sepal.Length, slice=list(sepal.Width=1,sepal.Length=2))

svm.prediction<-predict(svm.model1,iris[,-5])

table(svm.prediction)

## svm.prediction
##     setosa versicolor  virginica 
##         49         54         47

# POLYNOMIAL
svm.model2<-svm(Species ~ Sepal.Length + Sepal.Width, data = iris, kernel ='polynomial' )

plot(svm.model2,iris,Sepal.Width ~ Sepal.Length,slice = list(sepal.width=1,sepal.length=2))

# continue