rfcm.m

模糊C均值算法的m文件带自己的解释

function [center, U, obj_fcn] = fcm(data, cluster_n, options)
%FCM Data set clustering using fuzzy c-means clustering.
%
%   [CENTER, U, OBJ_FCN] = FCM(DATA, N_CLUSTER) finds N_CLUSTER number of
%   clusters in the data set DATA. DATA is size M-by-N, where M is the number of
%   data points and N is the number of coordinates for each data point. The
%   coordinates for each cluster center are returned in the rows of the matrix
%   CENTER. The membership function matrix U contains the grade of membership of
%   each DATA point in each cluster. The values 0 and 1 indicate no membership
%   and full membership respectively. Grades between 0 and 1 indicate that the
%   data point has partial membership in a cluster. At each iteration, an
%   objective function is minimized to find the best location for the clusters
%   and its values are returned in OBJ_FCN.
%
%   [CENTER, ...] = FCM(DATA,N_CLUSTER,OPTIONS) specifies a vector of options
%   for the clustering process:
%       OPTIONS(1): exponent for the matrix U             (default: 2.0)
%       OPTIONS(2): maximum number of iterations          (default: 100)
%       OPTIONS(3): minimum amount of improvement         (default: 1e-5)
%       OPTIONS(4): info display during iteration         (default: 1)
%   The clustering process stops when the maximum number of iterations
%   is reached, or when the objective function improvement between two
%   consecutive iterations is less than the minimum amount of improvement
%   specified. Use NaN to select the default value.
%
%   Example
%       data = rand(100,2);
%       [center,U,obj_fcn] = fcm(data,2);
%       plot(data(:,1), data(:,2),'o');
%       hold on;
%       maxU = max(U);
%       % Find the data points with highest grade of membership in cluster 1
%       index1 = find(U(1,:) == maxU);
%       % Find the data points with highest grade of membership in cluster 2
%       index2 = find(U(2,:) == maxU);
%       line(data(index1,1),data(index1,2),'marker','*','color','g');
%       line(data(index2,1),data(index2,2),'marker','*','color','r');
%       % Plot the cluster centers
%       plot([center([1 2],1)],[center([1 2],2)],'*','color','k')
%       hold off;
%
%   See also FCMDEMO, INITFCM, IRISFCM, DISTFCM, STEPFCM.

%   Roger Jang, 12-13-94, N. Hickey 04-16-01
%   Copyright 1994-2002 The MathWorks, Inc. 
%   $Revision: 1.13 $  $Date: 2002/04/02 21:25:24 $

if nargin ~= 2 & nargin ~= 3,    %判断输入参数个数只能是2个或3个
	error('Too many or too few input arguments!');
end

data_n = size(data, 1); %求出data的第一维(rows)数
in_n = size(data, 2);   %求出data的第二维(columns)数

% Change the following to set default options
default_options = [2;	% exponent for the partition matrix U
		100;	% max. number of iteration
		1e-5;	% min. amount of improvement
		1];	% info display during iteration 

if nargin == 2,
	options = default_options;
 else       %分析有options做参数时候的情况
	% If "options" is not fully specified, pad it with default;
	% values.如果输入参数个数是二那么就调用默认的option;
	if length(options) < 4,   %如果用户给的opition数少于4个那么就将剩余的默认option加上;
		tmp = default_options;
		tmp(1:length(options)) = options;
		options = tmp;
	end
	% If some entries of "options" are nan's, replace them with defaults.
	nan_index = find(isnan(options)==1);%isnan 返回options中是数的值为0(如NaN),不是数时为1
	options(nan_index) = default_options(nan_index);%将denfault_options中对应位置的参数赋值给options中不是数的位置.
	if options(1) <= 1,
		error('The exponent should be greater than 1!');%如果options中的数不超过1个则报错
	end
end
%将options 中的分量分别赋值给四个变量;
expo = options(1);		% Exponent for U
max_iter = options(2);		% Max. iteration
min_impro = options(3);		% Min. improvement
display = options(4);		% Display info or not迭代过程中是否显示信息;

obj_fcn = zeros(max_iter, 1);	% Array for objective function,出世那化输出参数obj_fcn

U = initfcm(cluster_n, data_n);			% Initial fuzzy partition 初始化模糊分配矩阵,使U满足列上相加为1,
% Main loop  主要循环
for i = 1:max_iter,
	[U, center, obj_fcn(i)] = stepfcm(data, U, cluster_n, expo);%在第k步循环中改变聚类中心ceneter,和分配函数U的隶属度值;
	if display, 
		fprintf('Iteration count = %d, obj. fcn = %f\n', i, obj_fcn(i));
	end
	% check termination condition
	if i > 1,
		if abs(obj_fcn(i) - obj_fcn(i-1)) < min_impro, break; end,
	end
end

iter_n = i;	% Actual number of iterations 
obj_fcn(iter_n+1:max_iter) = [];