This project looks into using various Python-based machine learning data science libraries in an attempt to build a machine learning model capable of predicting whether or not someone has heart diesease based on their medical attributes. The Jupyter Notebook of the project can be viewed here

Given clinical parameters about a patient, can we predict whether or not they have a heart disease?

The original data came from the UCI Machine Learning Repository (Cleaveland). There is also a version of it available on Kaggle.

The data available on Kaggle only uses 14 asttributes from the original data

1. Attribute No. 3 (age)
2. Attribute No. 4 (sex)
3. Attribute No. 9 (cp)
4. Attribute No. 10 (trestbps)
5. Attribute No. 12 (chol)
6. Attribute No. 16 (fbs)
7. Attribute No. 19 (restecg)
8. Attribute No. 32 (thalach)
9. Attribute No. 38 (exang)
10. Attribute No. 40 (oldpeak)
11. Attribute No. 41 (slope)
12. Attribute No. 44 (ca)
13. Attribute No. 51 (thal)
14. Attribute No. 58 (num) the predicted attribute AKA target