Appendix A: Custom Recipes

This appendix describes how to use custom recipes in Driverless AI. You’re welcome to create your own recipes, or you can select from a number of recipes available in the https://github.com/h2oai/driverlessai-recipes/tree/rel-1.8.10 repository.

Notes:

• Recipes only need to be added once. After a recipe is added to an experiment, that recipe will then be available for all future experiments.

• In most cases (especially for complex recipes), MOJOs won’t be available out of the box. But, it is possible to get the MOJO. Contact support@h2o.ai for more information about creating MOJOs for custom recipes. (Note that the Python Scoring Pipeline features full support for custom recipes.)

• To enable Shapley calculations in MLI, custom model recipes must use the has_pred_contribs method. Refer to the model recipe template for more info.

Additional Resources

• Custom Recipes FAQ: For answers to common questions about custom recipes.

• How to Write a Recipe: A guide for writing your own recipes.

• Data Template: A template for creating your own Data recipe.

• Model Template: A template for creating your own Model recipe.

• Scorer Template: A template for creating your own Scorer recipe.

• Transformer Template: A template for creating your own Transformer recipe.

Examples

• Adding a Data Recipe
• Driverless AI with H2O-3 Algorithms
• Using a Custom Scorer
• Using a Custom Transformer