In this project, we will implement the Biased Random Forest (BRAF) influenced by the paper, “Biased Random Forest for Dealing with the Class Imbalance Problem”, Mohammed Bader-El-Den; Eleman Teitei; Todd Perry. This paper describes a technique for combating class imbalance at the algorithm-level rather than the data-level. We will train this model with the publicly available Pima Diabetes dataset.
In order to print the results of accuracy, precision, recall scores and plot the k-fold cross-validation and auc curves, run the python file from the terminal or from any editor that runs python3.x.