/// <summary>
/// Add a set of evaluation metrics to the set of observations.
/// </summary>
/// <param name="metrics">The observed binary classification evaluation metric</param>
void IMetricsStatistics <BinaryClassificationMetrics> .Add(BinaryClassificationMetrics metrics)
{
AreaUnderRocCurve.Add(metrics.AreaUnderRocCurve);
Accuracy.Add(metrics.Accuracy);
PositivePrecision.Add(metrics.PositivePrecision);
PositiveRecall.Add(metrics.PositiveRecall);
NegativePrecision.Add(metrics.NegativePrecision);
NegativeRecall.Add(metrics.NegativeRecall);
F1Score.Add(metrics.F1Score);
AreaUnderPrecisionRecallCurve.Add(metrics.AreaUnderPrecisionRecallCurve);
}
/// <summary>
/// Add a set of evaluation metrics to the set of observations.
/// </summary>
/// <param name="metrics">The observed binary classification evaluation metric</param>
public override void Add(BinaryClassificationMetrics metrics)
{
Auc.Add(metrics.AreaUnderRocCurve);
Accuracy.Add(metrics.Accuracy);
PositivePrecision.Add(metrics.PositivePrecision);
PositiveRecall.Add(metrics.PositiveRecall);
NegativePrecision.Add(metrics.NegativePrecision);
NegativeRecall.Add(metrics.NegativeRecall);
F1Score.Add(metrics.F1Score);
Auprc.Add(metrics.AreaUnderPrecisionRecallCurve);
}
public void F1ScoreTest()
{
var actual = new Matrix(100, 1);
var expected = new Matrix(100, 1);
actual.InRandomize(0.25, 0.75);
expected.InRandomize(0.25, 0.75);
var metric = new F1Score();
var e = metric.Evaluate(actual, expected);
var val = 0.0;
var div = 0.0;
for (var i = 0; i < actual.Rows; i++)
{
for (var j = 0; j < actual.Columns; j++)
{
if (Math.Abs(actual[i, j]) < 0.5 && Math.Abs(expected[i, j]) < 0.5)
{
val += 0.0;
}
else if (Math.Abs(actual[i, j] - 1.0) < 0.5 && Math.Abs(expected[i, j] - 1.0) < 0.5)
{
val += 2.0;
div += 2.0;
}
div++;
}
}
val /= div;
Assert.IsTrue(Math.Abs(e - val) < 0.01, metric.Type().ToString() + " Evaluate.");
}