Predicting heart disease – a case study
You have been asked by a hospital to use machine learning to predict heart disease. Your job is to develop a model and highlight two to three important features that doctors and nurses can focus on to improve patient health.
You decide to use a decision tree classifier with fine-tuned hyperparameters. After the model has been built, you will interpret results using
feature_importances_, an attribute that determines the most important features in predicting heart disease.
Heart Disease dataset
The Heart Disease dataset has been uploaded to GitHub as
heart_disease.csv. This is a slight modification to the original Heart Disease dataset (https://archive.ics.uci.edu/ml/datasets/Heart+Disease) provided by the UCI Machine Learning Repository (https://archive.ics.uci.edu/ml/index.php) with null values cleaned up for your convenience.
Upload the file and display the first five rows as follows: