Class CommitteeRegressor

modAL/models/learners.py:632–714

This class is an abstract model of a committee-based active learning regression. Args: learner_list: A list of ActiveLearners forming the CommitteeRegressor. query_strategy: Query strategy function. on_transformed: Whether to transform samples with the pipeline defin

class CommitteeRegressor(BaseCommittee):
    """
    This class is an abstract model of a committee-based active learning regression.
    Args:
        learner_list: A list of ActiveLearners forming the CommitteeRegressor.
        query_strategy: Query strategy function.
        on_transformed: Whether to transform samples with the pipeline defined by each learner's estimator
            when applying the query strategy.
    Examples:
        >>> import numpy as np
        >>> import matplotlib.pyplot as plt
        >>> from sklearn.gaussian_process import GaussianProcessRegressor
        >>> from sklearn.gaussian_process.kernels import WhiteKernel, RBF
        >>> from modAL.models import ActiveLearner, CommitteeRegressor
        >>>
        >>> # generating the data
        >>> X = np.concatenate((np.random.rand(100)-1, np.random.rand(100)))
        >>> y = np.abs(X) + np.random.normal(scale=0.2, size=X.shape)
        >>>
        >>> # initializing the regressors
        >>> n_initial = 10
        >>> kernel = RBF(length_scale=1.0, length_scale_bounds=(1e-2, 1e3)) + WhiteKernel(noise_level=1, noise_level_bounds=(1e-10, 1e+1))
        >>>
        >>> initial_idx = list()
        >>> initial_idx.append(np.random.choice(range(100), size=n_initial, replace=False))
        >>> initial_idx.append(np.random.choice(range(100, 200), size=n_initial, replace=False))
        >>> learner_list = [ActiveLearner(
        ...                         estimator=GaussianProcessRegressor(kernel),
        ...                         X_training=X[idx].reshape(-1, 1), y_training=y[idx].reshape(-1, 1)
        ...                 )
        ...                 for idx in initial_idx]
        >>>
        >>> # query strategy for regression
        >>> def ensemble_regression_std(regressor, X):
        ...     _, std = regressor.predict(X, return_std=True)
        ...     return np.argmax(std)
        >>>
        >>> # initializing the CommitteeRegressor
        >>> committee = CommitteeRegressor(
        ...     learner_list=learner_list,
        ...     query_strategy=ensemble_regression_std
        ... )
        >>>
        >>> # active regression
        >>> n_queries = 10
        >>> for idx in range(n_queries):
        ...     query_idx, query_instance = committee.query(X.reshape(-1, 1))
        ...     committee.teach(X[query_idx].reshape(-1, 1), y[query_idx].reshape(-1, 1))
    """
    def __init__(self, learner_list: List[ActiveLearner], query_strategy: Callable = max_std_sampling,
                 on_transformed: bool = False) -> None:
        super().__init__(learner_list, query_strategy, on_transformed)

    def predict(self, X: modALinput, return_std: bool = False, **predict_kwargs) -> Any:
        """
        Predicts the values of the samples by averaging the prediction of each regressor.
        Args:
            X: The samples to be predicted.