TrueNegativeRateMetric<T>

Models & Types · AiDotNet.Evaluation.Metrics.Classification

Computes True Negative Rate (TNR): same as Specificity, TN / (TN + FP).

Implements: IClassificationMetric<T>

For Beginners

TNR answers: “Of all actual negatives, what proportion did we correctly identify?” This is the same as Specificity but named from a different perspective.

  • TNR = 1: All negatives correctly identified
  • TNR = 0.9: 90% of negatives correctly identified, 10% false alarms

How It Works

TNR = TN / (TN + FP) = Specificity = 1 - FPR

Constructors

Constructor Summary
TrueNegativeRateMetric()

Properties

Property Summary
MetricDirection Direction { get; }
T MaxValue { get; }
T MinValue { get; }
bool RequiresProbabilities { get; }
bool SupportsMultiClass { get; }
string Category { get; }
string Description { get; }
string Name { get; }

Methods

Method Summary
MetricWithCI<T> ComputeWithCI(ReadOnlySpan<T> predictions, ReadOnlySpan<T> actuals, ConfidenceIntervalMethod ciMethod, double confidenceLevel, int bootstrapSamples, int? randomSeed)
T Compute(ReadOnlySpan<T> predictions, ReadOnlySpan<T> actuals)