Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
debakarr
GitHub Repository: debakarr/machinelearning
 Path: blob/master/Part 3 - Classification/K Nearest Neighbors/knn.R
1009 views
1
# K-Nearest Neighbors (K-NN)

2


3
# Importing the dataset

4
dataset = read.csv('Social_Network_Ads.csv')

5
dataset = dataset[3:5]

6


7
# Encoding the target feature as factor

8
dataset$Purchased = factor(dataset$Purchased, levels = c(0, 1))

9


10
# Splitting the dataset into the Training set and Test set

11
# install.packages('caTools')

12
library(caTools)

13
set.seed(123)

14
split = sample.split(dataset$Purchased, SplitRatio = 0.75)

15
training_set = subset(dataset, split == TRUE)

16
test_set = subset(dataset, split == FALSE)

17


18
# Feature Scaling

19
training_set[-3] = scale(training_set[-3])

20
test_set[-3] = scale(test_set[-3])

21


22
# Fitting K-NN to the Training set and Predicting the Test set results

23
library(class)

24
y_pred = knn(train = training_set[, -3],

25
             test = test_set[, -3],

26
             cl = training_set[, 3],

27
             k = 5,

28
             prob = TRUE)

29


30
# Making the Confusion Matrix

31
cm = table(test_set[, 3], y_pred)

32


33
# Visualising the Training set results

34
library(ElemStatLearn)

35
set = training_set

36
X1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.01)

37
X2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.01)

38
grid_set = expand.grid(X1, X2)

39
colnames(grid_set) = c('Age', 'EstimatedSalary')

40
y_grid = knn(train = training_set[, -3], test = grid_set, cl = training_set[, 3], k = 5)

41
plot(set[, -3],

42
     main = 'K-NN (Training set)',

43
     xlab = 'Age', ylab = 'Estimated Salary',

44
     xlim = range(X1), ylim = range(X2))

45
contour(X1, X2, matrix(as.numeric(y_grid), length(X1), length(X2)), add = TRUE)

46
points(grid_set, pch = '.', col = ifelse(y_grid == 1, 'springgreen3', 'tomato'))

47
points(set, pch = 21, bg = ifelse(set[, 3] == 1, 'green4', 'red3'))

48


49
# Visualising the Test set results

50
library(ElemStatLearn)

51
set = test_set

52
X1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.01)

53
X2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.01)

54
grid_set = expand.grid(X1, X2)

55
colnames(grid_set) = c('Age', 'EstimatedSalary')

56
y_grid = knn(train = training_set[, -3], test = grid_set, cl = training_set[, 3], k = 5)

57
plot(set[, -3],

58
     main = 'K-NN (Test set)',

59
     xlab = 'Age', ylab = 'Estimated Salary',

60
     xlim = range(X1), ylim = range(X2))

61
contour(X1, X2, matrix(as.numeric(y_grid), length(X1), length(X2)), add = TRUE)

62
points(grid_set, pch = '.', col = ifelse(y_grid == 1, 'springgreen3', 'tomato'))

63
points(set, pch = 21, bg = ifelse(set[, 3] == 1, 'green4', 'red3'))

64