Class FMeasure
The FMeasure is an utility class for evaluators which measure precision, recall and the resulting f-measure.
Evaluation results are the arithmetic mean of the precision scores calculated for each reference sample and the arithmetic mean of the recall scores calculated for each reference sample.
public sealed class FMeasure- Inheritance
-
FMeasure
- Inherited Members
Properties
PrecisionScore
Retrieves the arithmetic mean of the precision scores calculated for each evaluated sample.
public double PrecisionScore { get; }Property Value
- double
the arithmetic mean of all precision scores
RecallScore
Retrieves the arithmetic mean of the recall score calculated for each evaluated sample.
public double RecallScore { get; }Property Value
- double
the arithmetic mean of all recall scores
Value
Retrieves the f-measure score.
f-measure = 2 * precision * recall / (precision + recall)
public double Value { get; }Property Value
- double
the f-measure or -1 if precision + recall <= 0
Methods
MergeInto(FMeasure)
Merge results into fmeasure metric.
public void MergeInto(FMeasure measure)Parameters
measureFMeasurethe fmeasure
Precision(object[], object[])
Calculates the precision score for the given reference and predicted spans.
public static double Precision(object[] references, object[] predictions)Parameters
Returns
- double
the precision score or NaN if there are no predicted spans
Recall(object[], object[])
Calculates the recall score for the given reference and predicted spans.
public static double Recall(object[] references, object[] predictions)Parameters
Returns
- double
the recall score or NaN if there are no reference spans
ToString()
Creates a human read-able string representation.
public override string ToString()Returns
- string
the results
UpdateScores(object[], object[])
Updates the score based on the number of true positives and the number of predictions and references.
public void UpdateScores(object[] references, object[] predictions)