Class BaseCommittee

modAL/models/base.py:210–366

Base class for query-by-committee setup. Args: learner_list: List of ActiveLearner objects to form committee. query_strategy: Function to query labels. on_transformed: Whether to transform samples with the pipeline defined by each learner's estimator when

class BaseCommittee(ABC, BaseEstimator):
    """
    Base class for query-by-committee setup.
    Args:
        learner_list: List of ActiveLearner objects to form committee.
        query_strategy: Function to query labels.
        on_transformed: Whether to transform samples with the pipeline defined by each learner's estimator
            when applying the query strategy.
    """
    def __init__(self, learner_list: List[BaseLearner], query_strategy: Callable, on_transformed: bool = False) -> None:
        assert type(learner_list) == list, 'learners must be supplied in a list'

        self.learner_list = learner_list
        self.query_strategy = query_strategy
        self.on_transformed = on_transformed
        # TODO: update training data when using fit() and teach() methods
        self.X_training = None

    def __iter__(self) -> Iterator[BaseLearner]:
        for learner in self.learner_list:
            yield learner

    def __len__(self) -> int:
        return len(self.learner_list)

    def _add_training_data(self, X: modALinput, y: modALinput) -> None:
        """
        Adds the new data and label to the known data for each learner, but does not retrain the model.
        Args:
            X: The new samples for which the labels are supplied by the expert.
            y: Labels corresponding to the new instances in X.
        Note:
            If the learners have been fitted, the features in X have to agree with the training samples which the
            classifier has seen.
        """
        for learner in self.learner_list:
            learner._add_training_data(X, y)

    def _fit_to_known(self, bootstrap: bool = False, **fit_kwargs) -> None:
        """
        Fits all learners to the training data and labels provided to it so far.
        Args:
            bootstrap: If True, each estimator is trained on a bootstrapped dataset. Useful when
                using bagging to build the ensemble.
            **fit_kwargs: Keyword arguments to be passed to the fit method of the predictor.
        """
        for learner in self.learner_list:
            learner._fit_to_known(bootstrap=bootstrap, **fit_kwargs)

    def _fit_on_new(self, X: modALinput, y: modALinput, bootstrap: bool = False, **fit_kwargs) -> None:
        """
        Fits all learners to the given data and labels.
        Args:
            X: The new samples for which the labels are supplied by the expert.
            y: Labels corresponding to the new instances in X.
            bootstrap: If True, the method trains the model on a set bootstrapped from X.
            **fit_kwargs: Keyword arguments to be passed to the fit method of the predictor.
        """