Use Decision Tree Attribute Selection Method to determine the splitting criterion
Use Decision Tree Attribute Selection Method to determine the splitting criterion.
Dataset Information:
Coronary artery disease, also called heart disease, causes roughly 735,000 heart attacks each year in the U.S. and kills more than 630,000 Americans each year. According to the American Heart Association, over 7 million Americans have suffered a heart attack in their lifetime. [High Risk Factors for Heart Disease - https://www.webmd.com/heart-disease/risk-factors-for-heart-disease]
UCI Heart Disease Data Set -- https://archive.ics.uci.edu/ml/datasets/Heart+Disease
Heart Disease Dataset D Information:
The dataset consists of 303 individuals data. This
Attribute Information: [See Dataset website for attribute details]
Three attributes are included:
1. #3 (age)
#4 (sex)
-- Value 0: Female
-- Value 1: Male
#9 (chest pain) cp: chest pain type
-- Value 0: asymptomatic
-- Value 1: atypical angina
-- Value 2: non-anginal pain
-- Value 3: typical angina
#58 (num=0 no heart disease num=1 heart disease) (the predicted attribute)
|
Patient ID |
Age |
Sex |
Chest Pain |
Heart Disease? |
|
1 |
60-70 |
1 |
1 |
0 |
|
2 |
60-70 |
1 |
4 |
1 |
|
3 |
60-70 |
1 |
4 |
1 |
|
4 |
30-40 |
1 |
3 |
0 |
|
5 |
40-50 |
0 |
2 |
0 |
|
6 |
50-60 |
1 |
2 |
0 |
|
7 |
60-70 |
0 |
4 |
1 |
|
8 |
50-60 |
0 |
4 |
0 |
|
9 |
60-70 |
1 |
4 |
1 |
|
10 |
50-60 |
1 |
4 |
1 |
|
11 |
50-60 |
1 |
4 |
0 |
|
12 |
50-60 |
0 |
2 |
0 |
|
13 |
50-60 |
1 |
3 |
1 |
|
14 |
40-50 |
1 |
2 |
0 |
|
15 |
50-60 |
1 |
3 |
0 |
|
16 |
50-60 |
1 |
3 |
0 |
|
17 |
40-50 |
1 |
2 |
1 |
|
18 |
50-60 |
1 |
4 |
0 |
|
19 |
40-50 |
0 |
3 |
0 |
- What is the expected information needed to classify a tuple in the Heart Disease dataset D, Info(D)?
- To classify a tuple in D if the tuples are partitioned according to Age, find out Infoage(D) and the Gainage
- To classify a tuple in D if the tuples are partitioned according to Sex, find out Infosex(D) and the Gainsex
- To classify a tuple in D if the tuples are partitioned according to Chest Pain, find out Infochest pain(D) and the Gainchest pain
- Which attribute has the highest information gain and should be selected as the splitting attribute according to 1.1 - 1.4?
Trending now
This is a popular solution!
Step by step
Solved in 3 steps
