CTO H3R7Tech c072f92794 Fix #1: Ajout job run_ml_cache dans scheduler pour alimenter ml_predictions_cache ...

- run_ml_cache() lit les partants, genere predictions via predict_v2,
  enrichit avec metadonnees course, calcule risque, ecrit dans cache
- Planifie 4x/jour: 09:30, 11:35, 13:30, 17:35
- Installe dependances: optuna, shap, lightgbm

Co-Authored-By: Paperclip <noreply@paperclip.ing>

2026-05-23 22:54:29 +02:00

22 KiB

Executable File

Raw Permalink Blame History

View Raw