ISmRandomForest.ROCcurve

A ROC curve is a graph that enables the user to assess the quality of binary classification. A ROC curve displays relation between the share of objects from the total number of attribute bearers that are correctly identifier as attribute bearers, and the share of objects from the total number of objects that are not attribute bearers and that are by error identifier as attribute bearers on varying of decision rule threshold.

Thus, a ROC curve is calculated if an explanatory series is binary.

A ROC curve is plotted by laying off the obtained sensitivity values along the Y axis, and (1 - specificity) along the X axis.

Sub UserProc;
Var
 RF: SmRandomForest;
 ROCCurve: IROCcurve;
 y: Array[16] Of Integer;
 x3dbl: array[16] Of Double;
 i, res: Integer;
 OneMinusSpecificity, Sensitivity: Array Of Double;
Begin
 // Create a method
 RF := New SmRandomForest.Create;
 // Set initial data
 // Set values corresponding to age group
 y[0] := 5; y[1] := 5; y[2] := 5; y[3] := 5;
 y[4] := 5; y[5] := 5; y[6] := 5; y[7] := 5;
 y[8] := 1; y[9] := 1; y[10] := 1; y[11] := 1;
 y[12] := 1; y[13] := 1; y[14] := 1; y[15] := 1;
 // Set values of explanatory quantitative series
 x3dbl[0] := 1.1; x3dbl[1] := 2.1; x3dbl[2] := 3; x3dbl[3] := 5;
 x3dbl[4] := 40; x3dbl[5] := 6; x3dbl[6] := 7; x3dbl[7] := 8;
 x3dbl[8] := 9; x3dbl[9] := 9; x3dbl[10] := 10; x3dbl[11] := 10;
 x3dbl[12] := 11; x3dbl[13] := 12; x3dbl[14] := 13; x3dbl[15] := 1.4;
 // Determine method parameters
 RF.ForestSize := 20;
 RF.NumberOfPredictors := 2;
 RF.LearningSamplePortion := 0.67;
 // Determine tree size
 RF.TreeSizeSpecification.MaximumNumberOfLevels := 10;
 RF.TreeSizeSpecification.MinimumNumberOfCases := 2;
 // Set explained series
 RF.Dependent.Value := y;
 // Set explanatory sequence series
 RF.ExplanatoriesContinuous.Add.Value := x3dbl;
 // Execute calculation and display values to the console window
 res := RF.Execute;
 ROCCurve := RF.ROCcurve;
 Debug.WriteLine(RF.Errors);
 Debug.WriteLine(RF.Forest.Count.ToString);
 If res <> 0 Then
 Debug.WriteLine("Failed");
 Else
 If ROCCurve <> Null Then
 Debug.WriteLine("ROC curve data:");
 Debug.Indent;
 Debug.WriteLine("Specifity:");
 Debug.Indent;
 OneMinusSpecificity := ROCcurve.OneMinusSpecificity;
            For i := 0 To OneMinusSpecificity.Length - 1 Do                 Debug.WriteLine(OneMinusSpecificity[i]);             End For;             Debug.Unindent;             Debug.WriteLine("Sensitivity:");             Debug.Indent;             Sensitivity := ROCcurve.Sensitivity;             For i := 0 To Sensitivity.Length - 1 Do                 Debug.WriteLine(Sensitivity[i]);             End For;          End If;         // Display classification quality criteria         Debug.Unindent;         Debug.Unindent;         Debug.WriteLine("Classification quality criteria");         Debug.WriteLine("Overall accuracy: " + RF.RelevanceMeasure.Accuracy.ToString);         Debug.WriteLine("F - estimate: " + RF.RelevanceMeasure.F1.ToString);         Debug.WriteLine("Number of truly positive values: " + RF.RelevanceMeasure.TruePositive.ToString);         Debug.WriteLine("Number of truly negative values: " + RF.RelevanceMeasure.TrueNegative.ToString);         Debug.WriteLine("Number of false positive values: " + RF.RelevanceMeasure.FalsePositive.ToString);         Debug.WriteLine("Number of false negative values: " + RF.RelevanceMeasure.FalseNegative.ToString);     End If; End Sub UserProc;

ISmRandomForest.ROCcurve

Syntax

Description

Comments

Example