credal_relative_likelihood¶
- probly.method.credal_relative_likelihood(base: Predictor[In, Out], num_members: int, reset_params: bool = True, tobias_value: int = 100) ClassBiasEnsemblePredictor[In, Out][source]¶
Create a Credal Relative Likelihood predictor from a base predictor.
Based on [LohrHMHullermeier25].
- Parameters:
base – The base classifier to replicate into a class-bias ensemble.
num_members – Number of ensemble members, one per class by convention.
reset_params – Whether to reset the parameters of each member. Default is True.
tobias_value – Magnitude of the class-specific bias initialization. Default is 3.0.
- Returns:
The credal relative likelihood predictor outputting a ProbabilityIntervalsCredalSet.