COMP5318/COMP4318 Machine Learning and Data Mining
s1 2025
Week 4 Tutorial exercises
Naïve Bayes
Exercise 1. Naïve Bayes for data with nominal features (to do in class)
Given is the following dataset where loan default is the class. Predict the class of the following new example using Naïve Bayes:
home owner = no, marital status = married, annual income=very high
|
|
home
owner
|
marital status
|
income
|
loan
default
|
|
1
|
yes
|
single
|
very high
|
yes
|
|
2
|
no
|
married
|
high
|
yes
|
|
3
|
no
|
single
|
medium
|
no
|
|
4
|
yes
|
married
|
very high
|
no
|
|
5
|
yes
|
divorced
|
high
|
yes
|
|
6
|
no
|
married
|
low
|
no
|
|
7
|
yes
|
divorced
|
very high
|
no
|
|
8
|
no
|
single
|
high
|
yes
|
|
9
|
no
|
married
|
medium
|
no
|
|
10
|
no
|
single
|
low
|
yes
|
Dataset adapted from, Tan, Steinbach, Karpatne and Kumar, Introduction to Data Mining, Pearson, 2019
Exercise 2. Naïve Bayes for data with numeric features (to do in class)
The same task as in the previous exercise but now annual income is a numeric feature:
|
|
home
owner
|
marital status
|
income
(in K)
|
loan
default
|
|
1
|
yes
|
single
|
125
|
yes
|
|
2
|
no
|
married
|
100
|
yes
|
|
3
|
no
|
single
|
70
|
no
|
|
4
|
yes
|
married
|
120
|
no
|
|
5
|
yes
|
divorced
|
95
|
yes
|
|
6
|
no
|
married
|
60
|
no
|
|
7
|
yes
|
divorced
|
220
|
no
|
|
8
|
no
|
single
|
85
|
yes
|
|
9
|
no
|
married
|
75
|
no
|
|
10
|
no
|
single
|
90
|
yes
|
Use Naïve Bayes to predict the class of the following new example:
home owner = no, marital status = married, annual income=120