We tried. statsmodels' GLM is not designed to be extended to multiple linear predictors cleanly, and the formula interface adds overhead that actuaries don't use. Better to build clean from the RS ...
. ├── app/ # FastAPI application ├── train/ # Training scripts ├── assets/images/ # Images, diagrams ├── requirements.txt # Python dependencies ├── Dockerfile ├── .env.dist # Sample environment ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results