Class BaseLearner

modAL/models/base.py:24–207

Core abstraction in modAL. Args: estimator: The estimator to be used in the active learning loop. query_strategy: Function providing the query strategy for the active learning loop, for instance, modAL.uncertainty.uncertainty_sampling. force_all_finite:

class BaseLearner(ABC, BaseEstimator):
    """
    Core abstraction in modAL.

    Args:
        estimator: The estimator to be used in the active learning loop.
        query_strategy: Function providing the query strategy for the active learning loop,
            for instance, modAL.uncertainty.uncertainty_sampling.
        force_all_finite: When True, forces all values of the data finite.
            When False, accepts np.nan and np.inf values.
        on_transformed: Whether to transform samples with the pipeline defined by the estimator
            when applying the query strategy.
        **fit_kwargs: keyword arguments.

    Attributes:
        estimator: The estimator to be used in the active learning loop.
        query_strategy: Function providing the query strategy for the active learning loop.
    """

    def __init__(self,
                 estimator: BaseEstimator,
                 query_strategy: Callable,
                 on_transformed: bool = False,
                 force_all_finite: bool = True,
                 **fit_kwargs
                 ) -> None:
        assert callable(query_strategy), 'query_strategy must be callable'

        self.estimator = estimator
        self.query_strategy = query_strategy
        self.on_transformed = on_transformed

        assert isinstance(force_all_finite,
                          bool), 'force_all_finite must be a bool'
        self.force_all_finite = force_all_finite

    def transform_without_estimating(self, X: modALinput) -> Union[np.ndarray, sp.csr_matrix]:
        """
        Transforms the data as supplied to the estimator.

        * In case the estimator is an skearn pipeline, it applies all pipeline components but the last one.
        * In case the estimator is an ensemble, it concatenates the transformations for each classfier
            (pipeline) in the ensemble.
        * Otherwise returns the non-transformed dataset X
        Args:
            X: dataset to be transformed

        Returns:
            Transformed data set
        """
        Xt = []
        pipes = [self.estimator]

        if isinstance(self.estimator, _BaseHeterogeneousEnsemble):
            pipes = self.estimator.estimators_

        ################################
        # transform data with pipelines used by estimator