API

This page lists all the public functions and classes of the hazardous package:

Estimators

SurvivalBoost

Cause-specific Cumulative Incidence Function (CIF) with GBDT [R087b999b2617-Alberge2025].

Metrics

metrics.brier_score_survival	Time-dependent Brier score of a survival function estimate.
metrics.brier_score_incidence	Time-dependent Brier score for the kth cause of event.
metrics.integrated_brier_score_survival	Compute the Brier score integrated over the observed time range.
metrics.integrated_brier_score_incidence	Time-integrated Brier score of a cause-specific cumulative incidence estimate.
metrics.concordance_index_incidence	Time-dependent concordance index for prognostic models with competing risks using inverse probability of censoring weighting.
metrics.accuracy_in_time	Accuracy in time for prognostic models using competing risks.
metrics.km_calibration	KM-Calibration: marginal calibration score for survival models.
metrics.aj_calibration_at_t	Pointwise AJ calibration error at each time point.
metrics.aj_calibration_per_event	AJ calibration score per event, integrated over time.
metrics.aj_calibration	Overall AJ calibration score aggregated across all events.

Datasets

data.make_synthetic_competing_weibull	Generate a synthetic dataset with competing Weibull-distributed events.
data.load_seer	Load the seer dataset and optionally apply the same preprocessing as done in SurvTRACE.