org.tribuo.sequence

Interface SequenceEvaluator<T extends Output<T>,E extends SequenceEvaluation<T>>

Type Parameters:

T - The output type.

E - The evaluation type.

All Known Implementing Classes:

AbstractSequenceEvaluator, LabelSequenceEvaluator

public interface SequenceEvaluator<T extends Output<T>,E extends SequenceEvaluation<T>>

An evaluation factory which produces immutable SequenceEvaluations of a given SequenceDataset using the given SequenceModel.

Method Summary

Modifier and Type	Method and Description
E	evaluate(SequenceModel<T> model, List<List<Prediction<T>>> predictions, DataProvenance dataProvenance) Evaluates the supplied model and predictions by aggregating the appropriate statistics.
E	evaluate(SequenceModel<T> model, SequenceDataset<T> dataset) Evaluates the dataset using the supplied model, returning an immutable evaluation.
E	evaluate(SequenceModel<T> model, SequenceDataSource<T> datasource) Evaluates the datasource using the supplied model, returning an immutable evaluation.

Method Detail

evaluate

E evaluate(SequenceModel<T> model,
           SequenceDataset<T> dataset)

Evaluates the dataset using the supplied model, returning an immutable evaluation.

Parameters:

model - The model to use.

dataset - The dataset to evaluate.

Returns:

An evaluation.

evaluate

E evaluate(SequenceModel<T> model,
           SequenceDataSource<T> datasource)

Evaluates the datasource using the supplied model, returning an immutable evaluation.

Parameters:

model - The model to use.

datasource - The datasource to evaluate.

Returns:

An evaluation.

evaluate

E evaluate(SequenceModel<T> model,
           List<List<Prediction<T>>> predictions,
           DataProvenance dataProvenance)

Evaluates the supplied model and predictions by aggregating the appropriate statistics.

Warning, this method cannot validate that the predictions were returned by the model in question.

Parameters:

model - The model to use.

predictions - The predictions to use.

dataProvenance - The provenance of the test data.

Returns:

An evaluation of the predictions.