# modAL.acquisition¶

Acquisition functions for Bayesian optimization.

modAL.acquisition.max_EI(optimizer: modAL.models.base.BaseLearner, X: Union[list, numpy.ndarray, scipy.sparse.csr.csr_matrix], tradeoff: float = 0, n_instances: int = 1) → Tuple[numpy.ndarray, Union[list, numpy.ndarray, scipy.sparse.csr.csr_matrix]][source]

Maximum EI query strategy. Selects the instance with highest expected improvement.

Parameters: optimizer – The BayesianOptimizer object for which the utility is to be calculated. X – The samples for which the expected improvement is to be calculated. tradeoff – Value controlling the tradeoff parameter. n_instances – Number of samples to be queried. The indices of the instances from X chosen to be labelled; the instances from X chosen to be labelled.
modAL.acquisition.max_PI(optimizer: modAL.models.base.BaseLearner, X: Union[list, numpy.ndarray, scipy.sparse.csr.csr_matrix], tradeoff: float = 0, n_instances: int = 1) → Tuple[numpy.ndarray, Union[list, numpy.ndarray, scipy.sparse.csr.csr_matrix]][source]

Maximum PI query strategy. Selects the instance with highest probability of improvement.

Parameters: optimizer – The BayesianOptimizer object for which the utility is to be calculated. X – The samples for which the probability of improvement is to be calculated. tradeoff – Value controlling the tradeoff parameter. n_instances – Number of samples to be queried. The indices of the instances from X chosen to be labelled; the instances from X chosen to be labelled.
modAL.acquisition.max_UCB(optimizer: modAL.models.base.BaseLearner, X: Union[list, numpy.ndarray, scipy.sparse.csr.csr_matrix], beta: float = 1, n_instances: int = 1) → Tuple[numpy.ndarray, Union[list, numpy.ndarray, scipy.sparse.csr.csr_matrix]][source]

Maximum UCB query strategy. Selects the instance with highest upper confidence bound.

Parameters: optimizer – The BayesianOptimizer object for which the utility is to be calculated. X – The samples for which the maximum upper confidence bound is to be calculated. beta – Value controlling the beta parameter. n_instances – Number of samples to be queried. The indices of the instances from X chosen to be labelled; the instances from X chosen to be labelled.
modAL.acquisition.optimizer_EI(optimizer: modAL.models.base.BaseLearner, X: Union[list, numpy.ndarray, scipy.sparse.csr.csr_matrix], tradeoff: float = 0) → numpy.ndarray[source]

Expected improvement acquisition function for Bayesian optimization.

Parameters: optimizer – The BayesianOptimizer object for which the utility is to be calculated. X – The samples for which the expected improvement is to be calculated. tradeoff – Value controlling the tradeoff parameter. Expected improvement utility score.
modAL.acquisition.optimizer_PI(optimizer: modAL.models.base.BaseLearner, X: Union[list, numpy.ndarray, scipy.sparse.csr.csr_matrix], tradeoff: float = 0) → numpy.ndarray[source]

Probability of improvement acquisition function for Bayesian optimization.

Parameters: optimizer – The BayesianOptimizer object for which the utility is to be calculated. X – The samples for which the probability of improvement is to be calculated. tradeoff – Value controlling the tradeoff parameter. Probability of improvement utility score.
modAL.acquisition.optimizer_UCB(optimizer: modAL.models.base.BaseLearner, X: Union[list, numpy.ndarray, scipy.sparse.csr.csr_matrix], beta: float = 1) → numpy.ndarray[source]

Upper confidence bound acquisition function for Bayesian optimization.

Parameters: optimizer – The BayesianOptimizer object for which the utility is to be calculated. X – The samples for which the upper confidence bound is to be calculated. beta – Value controlling the beta parameter. Upper confidence bound utility score.