Data science capstone using the 1988 Cleveland, Long Beach, Budapest, and Zurich heart disease dataset, as found on Kaggle: https://www.kaggle.com/johnsmith88/heart-disease-dataset.
Future tasks include the following: removing age as variable; exploring relationship between high cholesterol levels and heart defect types; and finding which ML algorithm is robust for this heart disease dataset.
Using a whole bunch of ML algorithms in an ensemble method blindly and including all variables, like here, is a silly idea and an example of over-fitting.