Interface Evaluation<T extends Output<T>>

Type Parameters:
T - The output type.
All Superinterfaces:
com.oracle.labs.mlrg.olcut.provenance.Provenancable<EvaluationProvenance>
All Known Subinterfaces:
AnomalyEvaluation, ClassifierEvaluation<T>, ClusteringEvaluation, LabelEvaluation, MultiLabelEvaluation, RegressionEvaluation
All Known Implementing Classes:
MultiLabelEvaluationImpl

public interface Evaluation<T extends Output<T>> extends com.oracle.labs.mlrg.olcut.provenance.Provenancable<EvaluationProvenance>
An immutable evaluation of a specific model and dataset.
  • Method Summary

    Modifier and Type
    Method
    Description
    Get a map of all the metrics stored in this evaluation.
    default double
    get(MetricID<T> key)
    Gets the value associated with the specific metric.
    Gets the predictions stored in this evaluation.

    Methods inherited from interface com.oracle.labs.mlrg.olcut.provenance.Provenancable

    getProvenance
  • Method Details

    • asMap

      Map<MetricID<T>,Double> asMap()
      Get a map of all the metrics stored in this evaluation. The keys are metric id's and the values are their corresponding computed results.
      Returns:
      a map of all stored results
    • get

      default double get(MetricID<T> key)
      Gets the value associated with the specific metric. Throws IllegalArgumentException if the metric is unknown.
      Parameters:
      key - The metric to lookup.
      Returns:
      The value for that metric.
    • getPredictions

      List<Prediction<T>> getPredictions()
      Gets the predictions stored in this evaluation.
      Returns:
      The predictions.