SVM lab

set.seed(1)
x <- matrix(rnorm(20 * 2), ncol = 2)
y <- c(rep(-1, 10), rep(1, 10))
x[y == 1, ] <- x[y == 1, ] + 1
plot(x, col = (3 - y))

# Fit the support vector classifier
dat <- data.frame(x = x, y = as.factor(y))
library(e1071)
svmfit <- svm(y ~ ., data = dat, kernel = "linear", cost = 10, scale = FALSE)

# Plot the support vector classifier obtained
plot(svmfit, dat)

# Basic information about the support vector classifier fit
summary(svmfit)

## 
## Call:
## svm(formula = y ~ ., data = dat, kernel = "linear", cost = 10, scale = FALSE)
## 
## 
## Parameters:
##    SVM-Type:  C-classification 
##  SVM-Kernel:  linear 
##        cost:  10 
## 
## Number of Support Vectors:  7
## 
##  ( 4 3 )
## 
## 
## Number of Classes:  2 
## 
## Levels: 
##  -1 1

# Cross-validation to select the best choice of the cost parameter
set.seed(1)
tune.out <- tune(svm, y ~ ., data = dat, kernel = "linear", 
                 ranges = list(cost = c(0.001, 0.01, 0.1, 1, 5, 10, 100)))
summary(tune.out)

## 
## Parameter tuning of 'svm':
## 
## - sampling method: 10-fold cross validation 
## 
## - best parameters:
##  cost
##   0.1
## 
## - best performance: 0.05 
## 
## - Detailed performance results:
##    cost error dispersion
## 1 1e-03  0.55  0.4377975
## 2 1e-02  0.55  0.4377975
## 3 1e-01  0.05  0.1581139
## 4 1e+00  0.15  0.2415229
## 5 5e+00  0.15  0.2415229
## 6 1e+01  0.15  0.2415229
## 7 1e+02  0.15  0.2415229

bestmod <- tune.out$best.model
summary(bestmod)

## 
## Call:
## best.tune(METHOD = svm, train.x = y ~ ., data = dat, ranges = list(cost = c(0.001, 
##     0.01, 0.1, 1, 5, 10, 100)), kernel = "linear")
## 
## 
## Parameters:
##    SVM-Type:  C-classification 
##  SVM-Kernel:  linear 
##        cost:  0.1 
## 
## Number of Support Vectors:  16
## 
##  ( 8 8 )
## 
## 
## Number of Classes:  2 
## 
## Levels: 
##  -1 1

# Predict the class labels of test observations
xtest <- matrix(rnorm(20 * 2), ncol = 2)
ytest <- sample(c(-1, 1), 20, rep = TRUE)
xtest[ytest == 1, ] <- xtest[ytest == 1, ] + 1
testdat <- data.frame(x = xtest, y = as.factor(ytest))
ypred <- predict(bestmod, testdat)
table(predict = ypred, truth = testdat$y)

##        truth
## predict -1 1
##      -1  9 1
##      1   2 8