- Annemieke Schönthaler (s1086735)
- Yaris van Thiel (s1082931)
In this project, we try to predict whether a person is more likely to suffer a stroke based on a dataset with possible risk factors. To predict stroke, we create five decision trees and train a Keras model on the previously mentioned dataset. This dataset is oversampled due to a lack of stroke patients in the dataset. For the best performing decision tree, we get an accuracy of 0.86. For the model, we get an accuracy of 0.76.
- Install packages:
pip install -r requirements.txt - Run both notebooks