[R] K-Nearest Neighbour.ipynb

Kernel: R

K-Nearest Neighbour

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)

Fitting K-NN to the Training set and Predicting the test set result

library(class)
y_pred = knn(train = training_set[, -3], 
             test = test_set[, -3], 
             cl = training_set[, 3],
             k = 5)

head(y_pred, 10)

head(test_set[, 3], 10)

---

Predictions are almost correct.

---

Making the Confusion Matrix

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

   y_pred
     0  1
  0 47  4
  1  5 24

---

That's awesome. Only 5 + 4 = 9, incorrect prediction and 47 + 24 = 81 correct 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('Age', 'EstimatedSalary')
y_grid = knn(train = training_set[, -3], 
             test = grid_set, 
             cl = training_set[, 3], 
             k = 5)
plot(set[, -3],
     main = 'K-Nearest Neighbour Classifier (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'))

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('Age', 'EstimatedSalary')
prob_set = predict(classifier, type = 'response', newdata = grid_set)
y_grid = knn(train = training_set[, -3], 
             test = grid_set, 
             cl = training_set[, 3], 
             k = 5)
plot(set[, -3],
     main = 'K-Nearest Neighbour Classifier (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'))

---

Gist: K-NN is a non Linear Classifier. That's why it predicts so well in our decision making problem.

---