A simple classification task prediction whether a patient would have a heart disease based on their age, height, blood pressure etc. The dataset is from mlbootcamp competition webpage.
The code uses XGBoost (https://xgboost.readthedocs.io/en/latest/) for machine learning task, as well as some features from scikit-learn library. The code is written in Jupyter notebook.
The goal is to predict whether or not the patients from the test set will have a heart disease condition (cardio).
The task is divided in three parts: examining and visualizing data, dealing with missing values and outliers and finally training the boosted tree model.