Class RegressionEvaluator

java.lang.Object

org.tribuo.evaluation.AbstractEvaluator<Regressor, org.tribuo.regression.evaluation.RegressionMetric.Context, RegressionEvaluation, RegressionMetric>

org.tribuo.regression.evaluation.RegressionEvaluator

All Implemented Interfaces:

Evaluator<Regressor, RegressionEvaluation>

public final class RegressionEvaluator
extends AbstractEvaluator<Regressor, org.tribuo.regression.evaluation.RegressionMetric.Context, RegressionEvaluation, RegressionMetric>

A Evaluator for multi-dimensional regression using Regressors.

If the dataset contains an unknown Regressor (as generated by RegressionFactory.getUnknownOutput()) then the evaluate methods will throw IllegalArgumentException with an appropriate message.

Constructor Summary

Constructors

Constructor	Description
RegressionEvaluator()	By default, don't use example weights.
RegressionEvaluator(boolean useExampleWeights)	Construct an evaluator.

Method Summary

Modifier and Type	Method	Description
protected org.tribuo.regression.evaluation.RegressionMetric.Context	createContext(Model<Regressor> model, List<Prediction<Regressor>> predictions)	Create the context needed for evaluation.
protected RegressionEvaluation	createEvaluation(org.tribuo.regression.evaluation.RegressionMetric.Context context, Map<MetricID<Regressor>, Double> results, EvaluationProvenance provenance)	Create an evaluation for the given results
protected Set<RegressionMetric>	createMetrics(Model<Regressor> model)	Creates the appropriate set of metrics for this model, by querying for it's OutputInfo.

Methods inherited from class org.tribuo.evaluation.AbstractEvaluator

computeResults, evaluate, evaluate, evaluate

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface org.tribuo.evaluation.Evaluator

createOnlineEvaluator, evaluate

Constructor Details

RegressionEvaluator

public RegressionEvaluator()

By default, don't use example weights.

RegressionEvaluator

public RegressionEvaluator(boolean useExampleWeights)

Construct an evaluator.

Will weight the examples if requested.

Parameters:

useExampleWeights - Set to true to use the example weights to adjust the importance of the predictions.

Method Details

createMetrics

protected Set<RegressionMetric> createMetrics(Model<Regressor> model)

Description copied from class: AbstractEvaluator

Creates the appropriate set of metrics for this model, by querying for it's OutputInfo.

Specified by:

createMetrics in class AbstractEvaluator<Regressor, org.tribuo.regression.evaluation.RegressionMetric.Context, RegressionEvaluation, RegressionMetric>

Parameters:

model - The model to inspect.

Returns:

The set of metrics.

createContext

protected org.tribuo.regression.evaluation.RegressionMetric.Context createContext(Model<Regressor> model,
 List<Prediction<Regressor>> predictions)

Description copied from class: AbstractEvaluator

Create the context needed for evaluation. The context might store global properties or cache computation.

Specified by:

createContext in class AbstractEvaluator<Regressor, org.tribuo.regression.evaluation.RegressionMetric.Context, RegressionEvaluation, RegressionMetric>

Parameters:

model - the model that will be evaluated

predictions - the predictions that will be evaluated

Returns:

the context for this model and its predictions

createEvaluation

protected RegressionEvaluation createEvaluation(org.tribuo.regression.evaluation.RegressionMetric.Context context,
 Map<MetricID<Regressor>, Double> results,
 EvaluationProvenance provenance)

Description copied from class: AbstractEvaluator

Create an evaluation for the given results

Specified by:

createEvaluation in class AbstractEvaluator<Regressor, org.tribuo.regression.evaluation.RegressionMetric.Context, RegressionEvaluation, RegressionMetric>

Parameters:

context - the context that was used to compute these results

results - the results

provenance - the provenance of the results (including information about the model and dataset)

Returns:

the evaluation