knnrloo.m

一个关于数据聚类和模式识别的程序,在生物化学,化学中因该都可以用到.希望对大家有用,谢谢支持

function [recogRate, computed, nearestIndex] = knnrLoo(DS, k, plotOpt)
%knnrLoo: Leave-one-out recognition rate of KNNR
%	Usage: [recogRate, computed, nearestIndex] = knnrLoo(DS, k, plotOpt)
%		recogRate: recognition rate
%		computed: Computed output
%		nearestIndex: Nearest sample index of all data points
%		DS: Design set
%			DS.input: Input data (each column is a feature vector)
%			DS.output: Output class (ranging from 1 to N)
%		k: The "k" in k-nearest neighbor rule
%		plotOpt: 1 for ploting data (2D only)
%
%	For example:
%		DS=prData('random2');
%		k=1;
%		plotOpt=1;
%		[recogRate, computed, nearestIndex] = knnrLoo(DS, k, plotOpt);

%	Roger Jang, 19970628, 20040928

if nargin<1, selfdemo; return; end
if nargin<2, k=1; end
if nargin<3, plotOpt=0; end

output=unique(DS.output);
if ~isequal(1:length(output), output)
	error('DS.output has wrong format! (It should have a value from 1 to no. of classes.)\n');
end

[dim, dataNum] = size(DS.input);
nearestIndex = zeros(1, dataNum);
computed = zeros(size(DS.output));
for i=1:dataNum
%	if rem(i, 100)==0, fprintf('%d/%d\n', i, dataNum); end
	looData = DS;
	looData.input(:,i) = [];
	looData.output(:,i) = [];
	TS.input=DS.input(:,i);
	TS.output=DS.output(:,i);
	[computed(i), junk, tmp] = knnr(looData, TS, k);
	nearestIndex(i) = tmp(1);
	if nearestIndex(i)>=i,
		nearestIndex(i)=nearestIndex(i)+1;
	end
end
hitIndex = find(DS.output==computed);
recogRate = length(hitIndex)/dataNum;

if plotOpt & dim==2
	dcprDataPlot(DS);
	axis image; box on
	missIndex=1:dataNum;
	missIndex(hitIndex)=[];
	% display these points
	for i=1:length(missIndex),
		line(DS.input(1,missIndex(i)), DS.input(2,missIndex(i)), 'marker', 'x', 'color', 'k');
	end
	titleString = sprintf('%d leave-one-out error points denoted by "x".', length(missIndex));
	title(titleString);
end

% ====== Self demo ======
function selfdemo
DS=prData('random2');
k=1;
plotOpt=1;
[recogRate, hitIndex, nearestIndex] = feval(mfilename, DS, k, plotOpt);