search

sebp / scikit-survival

Survival analysis built on top of scikit-learn
GNU General Public License v3.0
1.1k stars 210 forks source link

Randomized Search CV for RSF Hyperparametertuning? #463

Open Bylandt opened 3 weeks ago

Bylandt commented 3 weeks ago

Maybe a stupid question, and let me say i am sorry in advance.:

I am currently trying to establish a script for analysis of a larger dataset and am looking for a way to perform Hyperparametertuning using RandomizedSearchCV() instead of GridSearch, since the computation time gets too high for my purposes.

Is there a way to use any of the as_concordance_index_ipcw_scorer(), as_cumulative_dynamic_auc_scorer(), as_integrated_brier_score_scorer() methods for scoring when performing hyerparametertuning using RandomizedSearchCV?

Many thanks and Kind regards, B.

sebp commented 1 week ago

You should be able to use RandomizedSearchCV() in the same way as s GridSearchCV() described in https://scikit-survival.readthedocs.io/en/latest/user_guide/evaluating-survival-models.html#Using-Metrics-in-Hyper-parameter-Search