[R] Kernel PCA.ipynb

Kernel: R

Kernel PCA

Data preprocessing

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

head(dataset, 10)

# Splitting the dataset into the Training set and Test set
library(caTools)
set.seed(42)
split = sample.split(dataset$Purchased, SplitRatio = 0.8)
training_set = subset(dataset, split == TRUE)
test_set = subset(dataset, split == FALSE)

head(training_set, 10)

head(test_set, 10)

# Feature Scaling
training_set[, 1:2] = scale(training_set[, 1:2])
test_set[, 1:2] = scale(test_set[, 1:2])

head(training_set, 10)

head(test_set, 10)

Applying Kernel PCA

library(kernlab)

kpca = kpca(x = ~., data = training_set[-3], kernel = 'rbfdot', features = 2)

training_set_pca = as.data.frame(predict(kpca, training_set))
training_set_pca$Purchased = training_set$Purchased

test_set_pca = as.data.frame(predict(kpca, test_set))
test_set_pca$Purchased = test_set$Purchased

head(training_set_pca, 10)

head(test_set_pca, 10)

Fitting Logistic Regreession to the Training set

classifier = glm(formula = Purchased ~ .,
                family = binomial,
                data = training_set_pca)

Predicting the Test set results

prob_pred = predict(classifier, 
                    type = 'response', 
                    newdata = test_set_pca[-3])

head(prob_pred, 10)

y_pred = ifelse(prob_pred > 0.5, 1, 0)

head(y_pred, 10)

Making the Confusion Matrix

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

cm

   y_pred
     0  1
  0 47  4
  1 10 19

---

classifier made 47 + 19 = 66 correct prediction and 10 + 4 = 14 incoreect predictions.

---

Visualizing the Training set results

# install.packages('ElemStatLearn')
library(ElemStatLearn)

set = training_set_pca

X1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.025)
X2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.025)
grid_set = expand.grid(X1, X2)
colnames(grid_set) = c('V1', 'V2')
prob_set = predict(classifier, type = 'response', newdata = grid_set)
y_grid = ifelse(prob_set > 0.5, 1, 0)
plot(set[, -3],
     main = 'Logistic Regression using Kernel PCA (Training set)',
     xlab = 'PC1', ylab = 'PC2',
     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'))

Visualizing the Test set results

set = test_set_pca

X1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.025)
X2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.025)
grid_set = expand.grid(X1, X2)
colnames(grid_set) = c('V1', 'V2')
prob_set = predict(classifier, type = 'response', newdata = grid_set)
y_grid = ifelse(prob_set > 0.5, 1, 0)
plot(set[, -3],
     main = 'Logistic Regression using Kernel PCA (Test set)',
     xlab = 'PC1', ylab = 'PC2',
     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'))