jiarui_li/DeepHealth
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit Graph

  • ea4682c35a Enhance summary output in extract_sequence_lengths script to include min, max, and percentile values for better data insights main Jiarui Li 2026-01-19 14:41:40 +08:00
  • 29913106cb Add get_sequence_lengths method to HealthDataset and create extract_sequence_lengths script for per-patient sequence length extraction Jiarui Li 2026-01-19 14:39:13 +08:00
  • 76d3fed76f Enhance compute_disease_capture_at_k_fast to support return counts and update LandmarkEvaluator for backward compatibility with new metrics structure Jiarui Li 2026-01-19 00:01:21 +08:00
  • d13fa430b7 Validate bin edges for Piecewise Exponential CIF Loss to ensure at least two finite edges and correct starting point Jiarui Li 2026-01-18 20:54:47 +08:00
  • 6de2132e84 Add fast vectorized implementation for Disease-Capture@K and enhance LandmarkEvaluator with profiling and correctness check options Jiarui Li 2026-01-18 18:14:45 +08:00
  • 6e76d67a10 Enhance _maybe_torch_compile and add _maybe_cudagraph_mark_step_begin for improved CUDA Graphs handling Jiarui Li 2026-01-18 18:04:54 +08:00
  • a4b19b6e08 Enhance LandmarkEvaluator with model compilation and optimization options Jiarui Li 2026-01-18 17:56:59 +08:00
  • 014393a33f Add support for evaluation indices in LandmarkEvaluator class Jiarui Li 2026-01-18 17:43:47 +08:00
  • 0057bc0dd9 Refactor evaluation scripts for multi-GPU execution Jiarui Li 2026-01-18 17:38:20 +08:00
  • b80d9a4256 Remove evaluate_next_event.py and utils.py files to streamline the codebase. These files contained functions and classes related to evaluation and utility operations that are no longer needed. Jiarui Li 2026-01-18 15:41:07 +08:00
  • 1d682c130d Implement control for implicit parallelism using --max_cpu_cores argument Jiarui Li 2026-01-18 00:06:33 +08:00
  • cfe7f88162 Add --max_cpu_cores argument for parallel processing in evaluation scripts Jiarui Li 2026-01-17 23:53:24 +08:00
  • 248fb09c34 Refactor run_evaluations_multi_gpu.sh to remove --tau-short requirement and add support for next-args and horizon-args files Jiarui Li 2026-01-17 23:39:55 +08:00
  • 4686b56336 Refactor next-event evaluation to use next-token scores and implement clean control AUC metrics Jiarui Li 2026-01-17 23:34:19 +08:00
  • e56068e668 Add compare_models.py for model evaluation with primary metrics and age-bin validation Jiarui Li 2026-01-17 16:12:56 +08:00
  • fcd948818c Enhance next-event evaluation with age-bin metrics and diagnostic AUC outputs Jiarui Li 2026-01-17 15:31:12 +08:00
  • 197842b1a6 Add script for multi-GPU evaluations with flexible options and logging Jiarui Li 2026-01-17 14:56:45 +08:00
  • a90f22a865 Enhance HealthDataset with caching for event tensors and update evaluation scripts to use test subsets Jiarui Li 2026-01-17 14:42:02 +08:00
  • 7840a4c53e Refactor next-event evaluation logic and add age-bin metrics output Jiarui Li 2026-01-17 14:09:50 +08:00
  • 67f92ce6c4 Add tqdm progress bar support and disable option for evaluation scripts Jiarui Li 2026-01-17 14:00:42 +08:00
  • bfab601a77 Add evaluation scripts for next-event prediction and horizon-capture evaluation with detailed metric disclaimers Jiarui Li 2026-01-17 13:49:39 +08:00
  • 07916ee529 Remove torch_metrics.py file to streamline evaluation metrics implementation Jiarui Li 2026-01-17 13:14:43 +08:00
  • c1bba30de4 Remove evaluation_age_time_dependent.py and utils.py files Jiarui Li 2026-01-17 09:53:15 +08:00
  • a637beb220 Add function to drop zero-positive rows and update CSV export logic in age-bin evaluation Jiarui Li 2026-01-16 17:51:00 +08:00
  • 4068310a12 Refactor aggregation logic in age-bin results to handle pandas version compatibility Jiarui Li 2026-01-16 17:24:53 +08:00
  • 810c75e6d1 Add binary metrics computation and refactor evaluation logic in age-bin evaluation Jiarui Li 2026-01-16 17:19:27 +08:00
  • b1647d1b74 Refactor tqdm import handling and improve context sampling in utils.py Jiarui Li 2026-01-16 16:57:35 +08:00
  • e47a7ce4d6 Add multi-GPU support for age-bin evaluation and refactor aggregation logic Jiarui Li 2026-01-16 16:27:02 +08:00
  • 7a1210b5b0 Fix tqdm import handling by removing try-except block and ensuring proper import Jiarui Li 2026-01-16 16:14:16 +08:00
  • 90dffc3211 Add evaluation scripts for age-bin time-dependent metrics and remove obsolete evaluation_time_dependent.py Jiarui Li 2026-01-16 16:13:31 +08:00
  • 502ddd153b Refactor context index selection in evaluate_time_dependent to improve horizon-specific eligibility handling Jiarui Li 2026-01-16 15:01:35 +08:00
  • 34d8d8ce9d Add evaluation and utility functions for time-dependent metrics Jiarui Li 2026-01-16 14:55:09 +08:00
  • 660dc969bc Remove models_eval_example.json file containing model evaluation configurations. Jiarui Li 2026-01-16 13:09:38 +08:00
  • 2f46acf2bd Add Piecewise Exponential CIF Loss and update model evaluation for PWE Jiarui Li 2026-01-15 11:36:24 +08:00
  • d8b322cbee Enhance Event Rate@K and Recall@K computations with random ranking baseline and additional metrics Jiarui Li 2026-01-11 00:52:35 +08:00
  • 4d53f52aa1 Refactor AUC computation methods and introduce Event Rate@K for cross-cause prioritization Jiarui Li 2026-01-11 00:47:56 +08:00
  • d87752d1f8 Enhance evaluation metrics and progress visualization in model evaluation Jiarui Li 2026-01-10 23:49:37 +08:00
  • 87baef3ecf Fix device transfer for sexes in predict_cifs_for_model function Jiarui Li 2026-01-10 17:02:28 +08:00
  • 029f147ab5 Implement feature X to enhance user experience and fix bug Y in module Z Jiarui Li 2026-01-10 17:00:16 +08:00
  • b88518a03f Refactor model configurations in models_eval_example.json: update names, add loss_type and full_cov attributes for Delphi and SAP Delphi models. Jiarui Li 2026-01-10 14:29:15 +08:00
  • 320597dcde Fix checkpoint path for sap_delphi_discrete_time_cif_partcov model in evaluation examples Jiarui Li 2026-01-10 12:31:47 +08:00
  • b64ba101c2 Add sap_delphi_discrete_time_cif_partcov model configuration to evaluation examples Jiarui Li 2026-01-10 12:22:14 +08:00
  • f795aa5604 Fix survival calculation in cifs_from_exponential_logits: broadcast mask for compatibility with tensor shapes Jiarui Li 2026-01-10 11:42:03 +08:00
  • f231a2e4e5 Add model evaluation configurations for Delphi and SAP Delphi models Jiarui Li 2026-01-10 11:37:12 +08:00
  • 3f15301f26 Enhance multi-GPU experiment runner: add log directory option, improve logging with sanitized filenames, and capture command output in log files. Jiarui Li 2026-01-09 18:46:59 +08:00
  • 5f8360a24a Update experiments configuration: replace PiecewiseExponentialLoss with DiscreteTimeCIFNLLLoss for delphi_fork and sap_delphi models Jiarui Li 2026-01-09 18:44:16 +08:00
  • 739eb326f2 Fix formatting in DiscreteTimeCIFNLLLoss documentation for clarity Jiarui Li 2026-01-09 18:34:01 +08:00
  • 209dde2299 Refactor loss functions and model architecture: replace PiecewiseExponentialLoss with DiscreteTimeCIFNLLLoss, update Trainer to use SimpleHead, and modify argument parsing for new loss type. Jiarui Li 2026-01-09 18:31:38 +08:00
  • 880fd53a4b Enhance Trainer class: add logging for WeibullNLLLoss parameters during training and validation Jiarui Li 2026-01-09 13:48:36 +08:00
  • 8723bf7600 Enhance Trainer class: add delta_scale logging for improved training statistics Jiarui Li 2026-01-09 13:28:11 +08:00
  • dc34d51864 Add rank parameter to TrainConfig and update argument parsing for low-rank parameterization Jiarui Li 2026-01-09 13:18:09 +08:00
  • 1fa6d55d79 Refactor PiecewiseExponentialLoss and WeibullNLLLoss: remove lightweight numerical protections and improve error handling for input validation Jiarui Li 2026-01-09 13:06:43 +08:00
  • b54c54a60b Refactor Trainer class: improve training statistics calculation and logging for NLL and regularization Jiarui Li 2026-01-09 12:49:29 +08:00
  • aff0fe480b Refactor model and training scripts: remove unused imports and add FactorizedHead class for improved modularity Jiarui Li 2026-01-09 12:01:52 +08:00
  • c70c3cd71e Reorganize import statements for consistency and clarity in model and training scripts Jiarui Li 2026-01-09 10:16:03 +08:00
  • d7600514af Update Trainer class to rename parameters for clarity in embedding configuration Jiarui Li 2026-01-08 17:11:19 +08:00
  • d20d32ba22 Add multi-GPU experiment runner script and experiments configuration Jiarui Li 2026-01-08 13:57:34 +08:00
  • 01a96d37ea Enhance DataLoader configuration and improve tensor transfer efficiency in Trainer class Jiarui Li 2026-01-08 13:20:32 +08:00
  • 5382f9f159 Remove EMA model implementation from Trainer class and related parameters from TrainConfig Jiarui Li 2026-01-08 13:14:29 +08:00
  • 615e2fe748 Refactor PiecewiseExponentialLoss for clarity and numerical stability improvements Jiarui Li 2026-01-08 13:05:53 +08:00
  • 06a01d2893 Add PiecewiseExponentialLoss class and update TrainConfig for new loss type Jiarui Li 2026-01-08 12:45:31 +08:00
  • 7c36f7a007 Update age_encoder parameter choices in TrainConfig and argument parser for clarity Jiarui Li 2026-01-08 11:38:45 +08:00
  • 9eda00ea48 Add n_tech_tokens parameter to DelphiFork and SapDelphi model initializations Jiarui Li 2026-01-08 11:36:23 +08:00
  • 1d1f568a3f Rename age_encoder parameter to age_encoder_type for clarity in Trainer class Jiarui Li 2026-01-08 11:34:44 +08:00
  • 8293f7ee24 Enhance TabularEncoder with BatchNorm and AutoDiscretization for continuous features Jiarui Li 2026-01-08 00:24:43 +08:00
  • 33ba7e6c1d Refactor training logic to improve early stopping mechanism and variable naming Jiarui Li 2026-01-08 00:07:15 +08:00
  • 811b2e1a46 Implement training script for Delphi model with configurable parameters Jiarui Li 2026-01-07 23:57:29 +08:00
  • 6984b254b3 Add loss functions and model architecture for time-to-event prediction Jiarui Li 2026-01-07 21:32:00 +08:00
  • 5d1d79b908 Initial commit jiarui_li 2026-01-07 21:27:38 +08:00