Package org.tribuo.multilabel.evaluation

package org.tribuo.multilabel.evaluation

Evaluation classes for multi-label classification using MultiLabel.

The default metrics calculated are found in MultiLabelMetrics.

User specified metrics are not currently supported.

Related Packages

Package	Description
org.tribuo.multilabel	Provides classes and infrastructure for working with multi-label classification problems.
org.tribuo.multilabel.baseline	Provides implementations of binary relevance based multi-label classification algorithms.
org.tribuo.multilabel.ensemble	Provides a multi-label ensemble combiner that performs a (possibly weighted) majority vote among each label independently, along with an implementation of classifier chain ensembles.
org.tribuo.multilabel.example	Provides a multi-label data generator for testing implementations and a configurable data source suitable for demos and tests.
org.tribuo.multilabel.sgd	Provides infrastructure for Stochastic Gradient Descent for multi-label classification problems.

Class	Description
MultiLabelConfusionMatrix	A ConfusionMatrix which accepts MultiLabels.
MultiLabelEvaluation	A MultiLabel specific ClassifierEvaluation.
MultiLabelEvaluationImpl	The implementation of a MultiLabelEvaluation using the default metrics.
MultiLabelEvaluator	An Evaluator for MultiLabel problems.
MultiLabelMetric	A EvaluationMetric for evaluating MultiLabel problems.
MultiLabelMetrics	An enum of the default MultiLabelMetrics supported by the multi-label classification evaluation package.