nndd.m

数据挖掘的工具箱,最新版的,希望对做这方面研究的人有用

%NNDD Nearest neighbour data description method.
% 
%       W = nndd(A,fracrej)
% 
% Calculates the Nearest neighbour data description. Training only
% consists of the computation of the resemblance of all training
% objects to the training data using Leave-one-out.
% 
% See also datasets, mappings, dd_roc

% Copyright: D. Tax, R.P.W. Duin, [e-mail]
% Faculty of Applied Physics, Delft University of Technology
% P.O. Box 5046, 2600 GA Delft, The Netherlands
  
function [W,out] = nndd(a,fracrej)

if nargin < 2 | isempty(fracrej), fracrej = 0.05; end
if nargin < 1 | isempty(a) % empty nndd
	W = mapping(mfilename,{fracrej});
	W = setname(W,'Nearest neighbour data description');
	return
end

if ~ismapping(fracrej)           %training

	a = +target_class(a);      % make sure we have a OneClass dataset
	[m,k] = size(a);

	% Compute distance matrix and remove zero distances:
	distmat = sqeucldistm(a,a);
	large_D = max(distmat(:));
	small_D = 1.0e-10;           % almost zero distance
	distmat = distmat + large_D*(distmat<small_D); %surpress 0 dist.

	% Apply leave-one-out on the training set:
	fit = zeros(m,1);
	for i=1:m
		D = distmat;
		[minD minI] = min(D(i,:));  % dist. from z to 1NN in A
		D(i,minI) = large_D;
		intdist = min(D(:,minI));   % dist. from 1NN to NN(1NN)
		fit(i) = minD./intdist;
	end
	% Now we can obtain the threshold:
	thresh = dd_threshold(fit,1-fracrej);
	% and save all useful data:
	out = fit;
	W.x = +a;
	W.threshold = thresh;
	W.fit = fit;
	W.D = min(distmat,[],2);
	W.scale = mean(fit);
	W = mapping(mfilename,'trained',W,str2mat('target','outlier'),k,2);
	W = setname(W,'Nearest neighbour data description');

else                               %testing

	W = getdata(fracrej);  % unpack
	m = size(a,1);

	%compute:
	distmat = sqeucldistm(+a,W.x);    %dist between train and test
	[mindist I] = min(distmat,[],2); % find the closest dist.
	out = log([mindist./(W.D(I)) repmat(W.threshold,m,1)]);

	% map to probability
	newout = dist2dens(out,W.scale);
           
	W = setdat(a,newout,fracrej);
end
return