Package uk.ac.ed.inf.enzml.mulan.learn

Class Summary
EvaluationParameters Contains the evaluation parameters (micro-macro precision, micro-macro accuracy etc.) of a Multi label Mulan experiment.
EvaluatorNoAUC Prepares the evaluation measures taking into consideration the dataset size.
ExperimentTable Gives the names and table field names for multi-label specific evaluation measures (such as micro-accuracy, macro-accuracy, hamming loss etc.)
MulanCrossEvaluator Class created to execute cross-evaluations and extract individual evaluation results (not possible from the Mulan class Evaluator, because only averaged results are returned).
MulanCrossExperimenter Using Mulan (multi-label machine learning), this class initialises and executes either Train-Test evaluation (if two different arff records are given) (calling MulanTrainTestEvaluator) or cross-evaluations (calling MulanCrossEvaluator) if only one arff record is given.
MulanLearner Containing a Mulan learner and its name, that is: the name of the MultiLabelLearnerBase plus the name of the algorithm within
MulanLearners Class
MulanSerializer Takes an arff file and an algorithm.
ResultsFormatter Class
ResultsSaver Outputs cross-evaluation results to screen, file and database.