Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
debakarr
GitHub Repository: debakarr/machinelearning
 Path: blob/master/Part 3 - Classification/Naive Bayes/classification_template.R
1009 views
1
# Classification template

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 classifier to the Training set

23
# Create your classifier here

24


25
# Predicting the Test set results

26
y_pred = predict(classifier, newdata = test_set[-3])

27


28
# Making the Confusion Matrix

29
cm = table(test_set[, 3], y_pred)

30


31
# Visualising the Training set results

32
library(ElemStatLearn)

33
set = training_set

34
X1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.01)

35
X2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.01)

36
grid_set = expand.grid(X1, X2)

37
colnames(grid_set) = c('Age', 'EstimatedSalary')

38
y_grid = predict(classifier, newdata = grid_set)

39
plot(set[, -3],

40
     main = 'Classifier (Training set)',

41
     xlab = 'Age', ylab = 'Estimated Salary',

42
     xlim = range(X1), ylim = range(X2))

43
contour(X1, X2, matrix(as.numeric(y_grid), length(X1), length(X2)), add = TRUE)

44
points(grid_set, pch = '.', col = ifelse(y_grid == 1, 'springgreen3', 'tomato'))

45
points(set, pch = 21, bg = ifelse(set[, 3] == 1, 'green4', 'red3'))

46


47
# Visualising the Test set results

48
library(ElemStatLearn)

49
set = test_set

50
X1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.01)

51
X2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.01)

52
grid_set = expand.grid(X1, X2)

53
colnames(grid_set) = c('Age', 'EstimatedSalary')

54
y_grid = predict(classifier, newdata = grid_set)

55
plot(set[, -3], main = 'Classifier (Test set)',

56
     xlab = 'Age', ylab = 'Estimated Salary',

57
     xlim = range(X1), ylim = range(X2))

58
contour(X1, X2, matrix(as.numeric(y_grid), length(X1), length(X2)), add = TRUE)

59
points(grid_set, pch = '.', col = ifelse(y_grid == 1, 'springgreen3', 'tomato'))

60
points(set, pch = 21, bg = ifelse(set[, 3] == 1, 'green4', 'red3'))

61