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

Enhance DeepHealth model to incorporate CHECKUP state tokens in next-step training and evaluation, update dataset cache versioning, and improve handling of observed event histories.

Browse Source
This commit is contained in:
Jiarui Li
2026-06-15 14:10:09 +08:00
parent 593ecd2e71
commit c3e49db859
8 changed files with 111 additions and 86 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
train_next_step.py
View File

@@ -1,9 +1,9 @@
"""
Train DeepHealth with next-token / next-time-point supervision.
The dataset remains the current next-step construction: pure disease events plus
optional gap <NO_EVENT> imputation are shifted into autoregressive inputs and
targets. UTS training reads out only same-time group ends.
The next-step dataset uses observed event histories, including CHECKUP state
tokens, plus optional gap <NO_EVENT> imputation. UTS training reads out only
same-time group ends.
"""
from __future__ import annotations