Getting Started¶

This project uses pixi for environment management — don't use a bare venv/pip install.

pixi install        # create/sync the environment from pixi.toml/pixi.lock
pixi run test        # run the test suite (pytest tests)
pixi run mlflow-ui    # browse logged experiment runs (sqlite:///mlflow.db)

To work in a notebook or script interactively:

pixi shell
jupyter lab notebooks/

Data files (data/*.csv) are already provided; data/README.md documents how they were extracted from the ground-test database, if you need to regenerate them.

Next¶

• Using the Calibrated Models — load a frozen fit and a pre-trained residual model, and predict where a spectrum lands.
• Notebooks — every stage's prototyping notebook, rendered in full with its own outputs.