create_ml_model

Note

This page is a reference documentation. It only explains the function signature, and not how to use it. Please refer to the Habitat Guide and Python API guide (v2.0) for usage.

create_ml_model(model_name: str, params: Mapping[str, Any] | None = None) → Any[source]

Build one ML model instance for config validation (habit check-config).

Resolves the v1 classifier registry first, then falls back to the v0.1 ModelFactory through the legacy alias routing in _registry_for_plugin_name().

Parameters:

  • model_name – Registered model or classifier name from the YAML.

  • params – Flat hyperparameter mapping from the config params block.

Returns:

A constructed model wrapper without running training.