fix(deploy): download preprocessors in Dockerfile + harden predict/counterfactuals

fix(deploy): download preprocessors in Dockerfile + harden predict/counterfactuals

fix(startup): bake model into Docker image at build time

fix(startup): start uvicorn immediately, download model in background lifespan

fix(docker): change port from 8000 to 7860 for HF Spaces compatibility

chore: bump Dockerfile build version to trigger HF Space rebuild

fix: regenerate standard_scaler with correct params + auto-download model at Docker startup

feat: train production XGBoost model, harden Dockerfile, update dependencies

fix(docker): upgrade to python 3.10 to satisfy anyio dependency

chore(deploy): add Dockerfile and requirements for Hugging Face

feat: add Dockerfile for containerized application setup