[R] Principal Component Analysis.ipynb

Kernel: R

Principal Component Analysis

Data preprocessing

# Import the dataset
dataset = read.csv('Wine.csv')

head(dataset, 10)

# Splitting the dataset into the Training set and Test set
library(caTools)
set.seed(42)
split = sample.split(dataset$Customer_Segment, 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[-14] = scale(training_set[-14])
test_set[-14] = scale(test_set[-14])

head(training_set, 10)

head(test_set, 10)

Applying Principal Component Analysis

library(caret)
library(e1071)

Loading required package: lattice
Loading required package: ggplot2

pca  = preProcess(x = training_set[-14], 
                  method = 'pca', 
                  pcaComp = 2)

training_set = predict(pca, training_set)

head(training_set, 10)

training_set = training_set[c(2, 3, 1)] # Reordering the columns

head(training_set, 10)

test_set = predict(pca, test_set)
test_set = test_set[c(2, 3, 1)] # Reordering the columns

head(test_set, 10)

Fitting classifier to the Training set

classifier = svm(formula = Customer_Segment ~ ., 
                 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
     1  2  3
  1 11  1  0
  2  0 14  0
  3  0  0 10

---

classifier made 11 + 14 + 10 = 35 correct prediction and 1 incoreect prediction.

---

Visualizing the Training set results

# install.packages('ElemStatLearn')
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('PC1', 'PC2')
y_grid = predict(classifier, newdata = grid_set)
plot(set[, -3],
     main = 'Kernel SVM (Training set)',
     xlab = '1st Principal Component', ylab = '2nd Principal Component',
     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 == 2, 'lightblue', ifelse(y_grid == 1, 'springgreen3', 'tomato')))
points(set, pch = 21, bg = ifelse(set[, 3] == 2, 'blue3', ifelse(set[, 3] == 1, 'green4', 'red3')), col='white')
legend("topright", legend = c("0", "1", "2"), pch = 16, col = c('red3', 'green4', 'blue3'))

Visualizing 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('PC1', 'PC2')
y_grid = predict(classifier, newdata = grid_set)
plot(set[, -3],
     main = 'Kernel SVM (Test set)',
     xlab = '1st Principal Component', ylab = '2nd Principal Component',
     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 == 2, 'lightblue', ifelse(y_grid == 1, 'springgreen3', 'tomato')))
points(set, pch = 21, bg = ifelse(set[, 3] == 2, 'blue3', ifelse(set[, 3] == 1, 'green4', 'red3')), col='white')
legend("topright", legend = c("0", "1", "2"), pch = 16, col = c('red3', 'green4', 'blue3'))