Performs advanced survival analysis and time-to-event modeling using the scikit-survival Python library.
This skill empowers Claude to assist with complex survival analysis workflows, specifically leveraging the scikit-survival library built on top of scikit-learn. It provides expert guidance on handling censored data, fitting diverse models such as Cox Proportional Hazards, Random Survival Forests, and Survival SVMs, and accurately evaluating predictions using industry-standard metrics like the Concordance Index and Brier score. Whether you are analyzing clinical trials, predicting equipment failure, or modeling customer churn, this skill ensures best practices in data preprocessing, model selection, and the interpretation of time-to-event outcomes.
Key Features
01Integrated workflows for competing risks and non-parametric estimation.
028 GitHub stars
03Seamless integration with the scikit-learn ecosystem for pipelines and CV.
04Robust handling of right, left, and interval-censored data structures.
05Specialized survival modeling including Cox, Random Survival Forests, and Boosting.
06Advanced evaluation metrics like Uno's C-index and time-dependent AUC.
Use Cases
01Clinical research for predicting patient survival times and hazard ratios.
02Predictive maintenance to estimate the remaining useful life of machinery.
03Customer retention analysis to model and prevent user churn over time.
