Package org.tribuo.evaluation

Evaluation base classes, along with code for train/test splits and cross validation.

See: Description

Interface Summary

Interface	Description
Evaluation<T extends Output<T>>	An immutable evaluation of a specific model and dataset.
EvaluationRenderer<T extends Output<T>,E extends Evaluation<T>>	Renders an Evaluation into a String.
Evaluator<T extends Output<T>,E extends Evaluation<T>>	An evaluation factory which produces immutable Evaluations of a given Dataset using the given Model.

Class Summary

Class	Description
AbstractEvaluator<T extends Output<T>,C extends MetricContext<T>,E extends Evaluation<T>,M extends EvaluationMetric<T,C>>	Base class for evaluators.
CrossValidation<T extends Output<T>,E extends Evaluation<T>>	A class that does k-fold cross-validation.
DescriptiveStats	Descriptive statistics calculated across a list of doubles.
EvaluationAggregator	Aggregates metrics from a list of evaluations, or a list of models and datasets.
KFoldSplitter<T extends Output<T>>	A k-fold splitter to be used in cross-validation.
KFoldSplitter.TrainTestFold<T extends Output<T>>	Stores a train/test split for a dataset.
OnlineEvaluator<T extends Output<T>,E extends Evaluation<T>>	An evaluator which aggregates predictions and produces Evaluations covering all the Predictions it has seen or created.
TrainTestSplitter<T extends Output<T>>	Splits data into training and testing sets.
TrainTestSplitter.SplitDataSourceProvenance	Provenance for a split data source.

Package org.tribuo.evaluation Description

Evaluation base classes, along with code for train/test splits and cross validation.