Goal: Predicting whether a patient has high risk of having a stroke using supervised machine learning algorithms
Tools: Python, Pandas, Scikit-Learn, Imbalanced-learn
Python files in order: 1) EDA.ipynb, 2) functions.py, 3) main_runmodels.py, 4) main_generate_test_results.py, and 5) FinalOutput.ipynb.
Other file: patient_data.sql
Summary: Please read blog post here.