7 Commits

Author	SHA1	Message	Date
Jiarui Li	1df02d85d7	Add LogNormalBasisHazardLoss implementation and update training configuration	2026-01-13 15:59:20 +08:00
Jiarui Li	739eb326f2	Fix formatting in DiscreteTimeCIFNLLLoss documentation for clarity	2026-01-09 18:34:01 +08:00
Jiarui Li	209dde2299	Refactor loss functions and model architecture: replace PiecewiseExponentialLoss with DiscreteTimeCIFNLLLoss, update Trainer to use SimpleHead, and modify argument parsing for new loss type.	2026-01-09 18:31:38 +08:00
Jiarui Li	1fa6d55d79	Refactor PiecewiseExponentialLoss and WeibullNLLLoss: remove lightweight numerical protections and improve error handling for input validation	2026-01-09 13:06:43 +08:00
Jiarui Li	615e2fe748	Refactor PiecewiseExponentialLoss for clarity and numerical stability improvements	2026-01-08 13:05:53 +08:00
Jiarui Li	06a01d2893	Add PiecewiseExponentialLoss class and update TrainConfig for new loss type	2026-01-08 12:45:31 +08:00
Jiarui Li	6984b254b3	Add loss functions and model architecture for time-to-event prediction ... - Implemented ExponentialNLLLoss and WeibullNLLLoss in losses.py for negative log-likelihood calculations. - Developed TabularEncoder class in model.py for encoding tabular features. - Created DelphiFork and SapDelphi classes in model.py for time-to-event prediction using transformer architecture. - Added data preparation scripts in prepare_data.R and prepare_data.py for processing UK Biobank data, including handling field mappings and event data extraction.	2026-01-07 21:32:00 +08:00