Survival analysis with PyTorch
Project description
pycox is a python package for survival analysis and time-to-event prediction with PyTorch. It is built on the torchtuples package for training PyTorch models.
Read the documentation at: https://github.com/havakv/pycox
The package contains
- survival models: (Logistic-Hazard, DeepHit, DeepSurv, Cox-Time, MTLR, etc.)
- evaluation criteria (concordance, Brier score, Binomial log-likelihood, etc.)
- event-time datasets (SUPPORT, METABRIC, KKBox, etc)
- simulation studies
- illustrative examples
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
pycox-0.3.0.tar.gz
(59.3 kB
view hashes)
Built Distribution
pycox-0.3.0-py3-none-any.whl
(73.6 kB
view hashes)