Metadata-Version: 2.1
Name: TimeSub
Version: 1.0.1
Summary: A Python package for survival analysis with competing risks
Home-page: https://github.com/sjtu1znj/TimeSub
Author: Nengjie Zhu
Author-email: sjtu_znj@sjtu.edu.cn
License: MIT Licence
Keywords: survival analysis,competing risks,neural networks,hypothesis testing,time-to-event prediction
Platform: any
License-File: LICENSE.txt
Requires-Dist: lifelines==0.30.0
Requires-Dist: numpy==2.2.5
Requires-Dist: scipy==1.15.2
Requires-Dist: torch==2.5.1


    A Python package for survival analysis with competing risks, integrating neural networks and statistical inference. 
    Provides tools for time-to-event prediction, model training with PyTorch backend, and comprehensive hypothesis testing.

    Key Features:
    - Neural network models for time-varying and non-time-varying survival analysis
    - Prediction metrics including time-dependent AUC and C-index calculation
    - Bootstrap-based hypothesis testing (structure & significance tests) for model validation
    
