6 Commits

Author	SHA1	Message	Date
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	aff0fe480b	Refactor model and training scripts: remove unused imports and add FactorizedHead class for improved modularity	2026-01-09 12:01:52 +08:00
Jiarui Li	c70c3cd71e	Reorganize import statements for consistency and clarity in model and training scripts	2026-01-09 10:16:03 +08:00
Jiarui Li	01a96d37ea	Enhance DataLoader configuration and improve tensor transfer efficiency in Trainer class	2026-01-08 13:20:32 +08:00
Jiarui Li	8293f7ee24	Enhance TabularEncoder with BatchNorm and AutoDiscretization for continuous features	2026-01-08 00:24:43 +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