Implement automated model calibration and uncertainty estimation

[gelluisaac]

Description

    Build model calibration tools for probability calibration and uncertainty estimation using conformal prediction and Bayesian methods.

    ## Files to modify
    - astroml/training/calibration/platt.py
    - astroml/training/calibration/isotonic.py
    - astroml/training/calibration/conformal.py
    - astroml/training/calibration/bayesian.py
    - astroml/api/routers/calibration.py

    ## Out of scope
    - Refactoring unrelated modules
    - Changing public API contracts
    - Major version bumps or breaking changes
    - Performance optimizations not directly related to the issue

    ## Acceptance criteria
    - [ ] Code changes implemented as as per procedure steps
    - [ ] All new code has complete type hints
    - [ ] Unit tests added/updated with >90% coverage for changed code
    - [ ] All tests pass: pytest tests/
    - [ ] Linting passes: pre-commit run --all-files
    - [ ] Documentation updated if needed
    - [ ] Changes reviewed and approved

    ## Procedure
    1. Implement Platt scaling for probability calibration
    2. Build isotonic regression calibration
    3. Add conformal prediction for prediction sets
    4. Implement Bayesian uncertainty estimation
    5. Create calibration evaluation metrics
    6. Build calibration visualization tools
    7. Add calibration API endpoint
    8. Test with various model types