knncWrtK

Try various values of K in KNN classifier

Contents

Syntax

Description

recogRate = knncWrtK(testSet, trainSet, kMax, plotOpt) return the

recognition rates of KNNC w.r.t. various values of k ranging from

1 to kMax.

Example

[trainSet, testSet]=prData('iris');
designNum=size(trainSet.input, 2);
testNum  =size(testSet.input, 2);
fprintf('Use of KNNC for Iris data:\n');
fprintf('\tSize of design set (odd-indexed data)= %d\n', designNum);
fprintf('\tSize of test set (even-indexed data) = %d\n', testNum);
kMax=15;
plotOpt=1;
knncWrtK(testSet, trainSet, kMax, plotOpt);

Use of KNNC for Iris data:
	Size of design set (odd-indexed data)= 75
	Size of test set (even-indexed data) = 75
	1-NNR ===> 1-3/75 = 96.00%.
	2-NNR ===> 1-4/75 = 94.67%.
	3-NNR ===> 1-3/75 = 96.00%.
	4-NNR ===> 1-3/75 = 96.00%.
	5-NNR ===> 1-2/75 = 97.33%.
	6-NNR ===> 1-2/75 = 97.33%.
	7-NNR ===> 1-2/75 = 97.33%.
	8-NNR ===> 1-1/75 = 98.67%.
	9-NNR ===> 1-4/75 = 94.67%.
	10-NNR ===> 1-2/75 = 97.33%.
	11-NNR ===> 1-2/75 = 97.33%.
	12-NNR ===> 1-3/75 = 96.00%.
	13-NNR ===> 1-3/75 = 96.00%.
	14-NNR ===> 1-2/75 = 97.33%.
	15-NNR ===> 1-2/75 = 97.33%.

Published with MATLAB® R2018a