AlgorithmWrapper#
- class AlgorithmWrapper(name: str, display_name: str, algorithm_class: Type, default_params: Dict[str, Any] | None = None, hyperparam_grid: Dict[str, Any] | None = None)#
A wrapper class for machine learning algorithms.
Provides methods to instantiate models with default or tuned parameters and manages hyperparameter grids for model tuning.
- Parameters:
- namestr
Identifier for the algorithm
- display_namestr
Human-readable name for display purposes
- algorithm_classType
The class of the algorithm to be instantiated
- default_paramsdict, optional
Default parameters for model instantiation, by default None
- hyperparam_griddict, optional
Grid of parameters for hyperparameter tuning, by default None
- Attributes:
- namestr
Algorithm identifier
- display_namestr
Human-readable name
- algorithm_classType
The algorithm class
- default_paramsdict
Current default parameters
- hyperparam_griddict
Current hyperparameter grid
- get_hyperparam_grid() Dict[str, Any]#
Get the hyperparameter grid.
- Returns:
- dict
Current hyperparameter grid
- instantiate() Any#
Instantiate model with default parameters.
- Returns:
- Any
Model instance with default parameters and wrapper name attribute
- instantiate_tuned(best_params: Dict[str, Any]) Any#
Instantiate model with tuned parameters.
- Parameters:
- best_paramsdict
Tuned hyperparameters
- Returns:
- Any
Model instance with tuned parameters and wrapper name attribute
Notes
If max_iter is specified in default_params, it will be preserved in the tuned parameters.
- to_markdown() str#
Create markdown representation of algorithm configuration.
- Returns:
- str
Markdown formatted string containing algorithm name and class, default parameters, and hyperparameter grid.