scikit-survival and dev-survivors
Scikit-survival is a mature, production-ready survival analysis framework integrated with scikit-learn's ecosystem, while dev-survivors is an experimental interpretability-focused library—they are **competitors** offering alternative approaches to the same problem domain, though scikit-survival is vastly more established and widely adopted.
About scikit-survival
sebp/scikit-survival
Survival analysis built on top of scikit-learn
This tool helps researchers and analysts predict when an event will occur, like patient recovery or machine failure, even when some subjects haven't experienced the event yet. You input data with observed event times and censored data (where the event hasn't happened or wasn't observed within the study period), and it outputs models that estimate event probabilities over time. This is for data scientists, statisticians, and researchers working with time-to-event data.
About dev-survivors
iuliivasilev/dev-survivors
Stay Alive. A Reliable and Interpretable Survival Analysis Library
This helps scientists and analysts predict when an event will occur, like patient discharge or equipment failure, even with incomplete or messy data. You feed it historical event data, and it outputs reliable predictions about future events and clear explanations of the factors involved. Anyone in healthcare, industrial maintenance, or business analytics who needs to understand 'time-to-event' predictions would use this.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work