IClassificationMetric<T>
Interfaces · AiDotNet.Evaluation.Metrics
Interface for classification metrics.
Implements: IMetric<T>
Known implementations: AUCPRMetric<T>, AccuracyMetric<T>, BalancedAccuracyMetric<T>, BalancedErrorRateMetric<T>, CohensKappaMetric<T>, DiagnosticOddsRatioMetric<T>, ErrorRateMetric<T>, F1ScoreMetric<T>, FBetaScoreMetric<T>, FalseDiscoveryRateMetric<T>, FalseNegativeRateMetric<T>, FalseOmissionRateMetric<T>, FalsePositiveRateMetric<T>, FowlkesMallowsMetric<T>, HammingLossMetric<T>, HingeLossMetric<T>, InformednessMetric<T>, JaccardScoreMetric<T>, MarkednessMetric<T>, MatthewsCorrelationCoefficientMetric<T>, NPVMetric<T>, NegativeLikelihoodRatioMetric<T>, OptimizedPrecisionMetric<T>, PositiveLikelihoodRatioMetric<T>, PositivePredictiveValueMetric<T>, PrecisionMetric<T>, PrevalenceMetric<T>, PrevalenceThresholdMetric<T>, RecallMetric<T>, SpecificityMetric<T>, ThreatScoreMetric<T>, TrueNegativeRateMetric<T>, ZeroOneLossMetric<T>
Methods
| Method | Summary |
|---|---|
MetricWithCI<T> ComputeWithCI(ReadOnlySpan<T> predictions, ReadOnlySpan<T> actuals, ConfidenceIntervalMethod ciMethod, double confidenceLevel, int bootstrapSamples, int? randomSeed) |
Computes the metric with full result including confidence interval. |
T Compute(ReadOnlySpan<T> predictions, ReadOnlySpan<T> actuals) |
Computes the metric from predicted and actual class labels. |