feat: scripts to train ml models and compare performance

[narang-an]

Summary

Closes #26
Scripts to train and evaluate 4 different ml models (bayesian, neural network, time series, gradient boot)

Type of change

• feat — new feature
• fix — bug fix
• docs — documentation only
• refactor — code change that neither fixes a bug nor adds a feature
• perf — performance improvement
• test — adding or updating tests
• chore / build / ci — tooling, deps, or pipeline changes

Changes

• Implemented basic methods to train and test each model
• Comparison script to evaluate model performance
• Generated mock data for tests

Database migrations

• No schema changes
• Includes an Alembic migration (just migrate-create "...")
• Migration runs cleanly (just migrate) and rolls back (just migrate-down)

Checklist

• Commits follow Conventional Commits
• Lint passes (just lint) and code is formatted (just format)
• Pre-commit hooks run clean (just hooks installed)
• Updated docs / README / .env.example where relevant
• Tested locally (just dev) and verified the API at http://localhost:8000/docs

How to test

to run tests

1. cd backend
2. uv run pytest

to run eval script with fake data

1. cd backend
2. python scripts/compare_models.py

Notes for reviewers