[R] Kernel SVM.ipynb

Kernel: R

Kernel SVM

Data preprocessing

# Importing the dataset
dataset = read.csv('Social_Network_Ads.csv')
dataset = dataset[3:5]

# Encoding the target feature as factor
dataset$Purchased = factor(dataset$Purchased, levels = c(0, 1))

# Splitting the dataset into the Training set and Test set
# install.packages('caTools')
library(caTools)
set.seed(1234)
split = sample.split(dataset$Purchased, SplitRatio = 0.80)
training_set = subset(dataset, split == TRUE)
test_set = subset(dataset, split == FALSE)

# Feature Scaling
training_set[-3] = scale(training_set[-3])
test_set[-3] = scale(test_set[-3])

Fitting classifier to the Training set

#  install.package('e1071')
library(e1071)
classifier = svm(formula = Purchased ~ ., 
                 data = training_set, 
                 type = 'C-classification', 
                 kernel = 'radial')

Predicting the Test set results

y_pred = predict(classifier, newdata = test_set[-3])

head(y_pred, 10)

head(test_set[3], 10)

Making the Confusion Matrix

cm = table(test_set[, 3], y_pred)
cm

   y_pred
     0  1
  0 45  6
  1  4 25

---

classifier made 45 + 25 = 75 correct prediction and 6 + 4 = 10 incorect predictions.

---

Visualising the Training set results

library(ElemStatLearn)
set = training_set
X1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.01)
X2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.01)
grid_set = expand.grid(X1, X2)
colnames(grid_set) = c('Age', 'EstimatedSalary')
y_grid = predict(classifier, newdata = grid_set)
plot(set[, -3],
     main = 'Kernel SVM (Training set)',
     xlab = 'Age', ylab = 'Estimated Salary',
     xlim = range(X1), ylim = range(X2))
contour(X1, X2, matrix(as.numeric(y_grid), length(X1), length(X2)), add = TRUE)
points(grid_set, pch = '.', col = ifelse(y_grid == 1, 'springgreen3', 'tomato'))
points(set, pch = 21, bg = ifelse(set[, 3] == 1, 'green4', 'red3'), col='white')
legend("topright", legend = c("0", "1"), pch = 16, col = c('red3', 'green4'))

Visualising the Test set results

set = test_set
X1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.01)
X2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.01)
grid_set = expand.grid(X1, X2)
colnames(grid_set) = c('Age', 'EstimatedSalary')
y_grid = predict(classifier, newdata = grid_set)
plot(set[, -3], main = 'Kernel SVM (Test set)',
     xlab = 'Age', ylab = 'Estimated Salary',
     xlim = range(X1), ylim = range(X2))
contour(X1, X2, matrix(as.numeric(y_grid), length(X1), length(X2)), add = TRUE)
points(grid_set, pch = '.', col = ifelse(y_grid == 1, 'springgreen3', 'tomato'))
points(set, pch = 21, bg = ifelse(set[, 3] == 1, 'green4', 'red3'), col='white')
legend("topright", legend = c("0", "1"), pch = 16, col = c('red3', 'green4'))

---

Looks like it is much better the Linear kernel.

---