jiarui_li/DeepHealth
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
57 Commits 1 Branch 0 Tags
248fb09c348727c8b70b6db5c6b3b573aeb902ae
Commit Graph

8 Commits

Author SHA1 Message Date
Jiarui Li
34d8d8ce9d Add evaluation and utility functions for time-dependent metrics 
- Introduced `evaluate.py` for time-dependent evaluation of models, including data loading and model inference.
- Added `evaluation_time_dependent.py` to compute various evaluation metrics such as AUC, average precision, and precision/recall at specified thresholds.
- Implemented CIF calculation methods in `losses.py` for different loss types, including exponential and piecewise exponential models.
- Created utility functions in `utils.py` for context selection and multi-hot encoding of events within specified horizons.
 2026-01-16 14:55:09 +08:00
Jiarui Li
2f46acf2bd Add Piecewise Exponential CIF Loss and update model evaluation for PWE 2026-01-15 11:36:24 +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