Case Study: Breast Cancer Diagnosis

From Ensemble Methods for Machine Learning by Gautam Kunapuli

Our first case study explores a medical decision-making task: breast cancer diagnosis. We will see how to use scikit-learn’s homogeneous parallel ensemble modules in practice. Specifically, we will train and evaluate the performance of three homogeneous parallel algorithms, each characterized by increasing randomness: bagging with decision trees, random forests and ExtraTrees.

© 2023 Manning — Design Credits