-
Notifications
You must be signed in to change notification settings - Fork 40
/
Decision Tree Classification.R
85 lines (59 loc) · 2.52 KB
/
Decision Tree Classification.R
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
# Decision Tree Classification Lecture
### Changing the Working Directory
setwd('./Machine Learning A-Z/Part 3 - Classification/Section 19 - Decision Tree Classification')
## Importing the Dataset
dataset = read.csv('Social_Network_Ads.csv')
dataset = dataset[3:5]
## Encoding the Target Feature as Factor
dataset$Purchased = factor(dataset$Purchased, levels = c(0,1))
## Splitting the Dataset into the Training Set and Test Set
library(caTools)
set.seed(123)
split = sample.split(dataset$Purchased, SplitRatio = 0.75)
training_set = subset(dataset, split == TRUE)
test_set = subset(dataset, split == FALSE)
## Feature Scaling
training_set[-3] = scale(training_set[-3])
test_set[-3] = scale(test_set[-3])
## Fitting Decision Tree to the Training Set
library(rpart)
classifier = rpart(formula = Purchased ~ .,
data=training_set)
## Predicting the Test Set Results
y_pred = predict(classifier, newdata = test_set[-3], type = 'class')
y_pred
## Making the Confusion Matrix
cm = table(test_set[,3], y_pred)
cm
## Visualizing the Training Set Results
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 = predict(classifier, newdata = grid_set, type ='class')
plot(set[, -3],
main = 'Decision Tree (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, 'salmon', 'blue'))
points(set, pch = 21, bg = ifelse(set[, 3] == 1, 'green4', 'red3'))
## 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')
y_grid = predict(classifier, newdata = grid_set, type = 'class')
plot(set[, -3],
main = 'Decision Tree (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, 'red', 'green'))
points(set, pch = 21, bg = ifelse(set[, 3] == 1, 'blue', 'orange'))
## Plotting the Decision Tree
plot(classifier)
text(classifier)