#coding:UTF-8 ''' Created on 2015年5月12日 @author: zhaozhiyong ''' from __future__ import division import scipy.io as scio from scipy import sparse from scipy.sparse.linalg.eigen import arpack#这里只能这么做,不然始终找不到函数eigs from numpy import * def spectalCluster(data, sigma, num_clusters): print "将邻接矩阵转换成相似矩阵" #先完成sigma != 0 print "Fixed-sigma谱聚类" data = sparse.csc_matrix.multiply(data, data) data = -data / (2 * sigma * sigma) S = sparse.csc_matrix.expm1(data) + sparse.csc_matrix.multiply(sparse.csc_matrix.sign(data), sparse.csc_matrix.sign(data)) #转换成Laplacian矩阵 print "将相似矩阵转换成Laplacian矩阵" D = S.sum(1)#相似矩阵是对称矩阵 D = sqrt(1 / D) n = len(D) D = D.T D = sparse.spdiags(D, 0, n, n) L = D * S * D #求特征值和特征向量 print "求特征值和特征向量" vals, vecs = arpack.eigs(L, k=num_clusters,tol=0,which="LM") # 利用k-Means print "利用K-Means对特征向量聚类" #对vecs做正规化 sq_sum = sqrt(multiply(vecs,vecs).sum(1)) m_1, m_2 = shape(vecs) for i in xrange(m_1): for j in xrange(m_2): vecs[i,j] = vecs[i,j]/sq_sum[i] myCentroids, clustAssing = kMeans(vecs, num_clusters) for i in xrange(shape(clustAssing)[0]): print clustAssing[i,0] def randCent(dataSet, k): n = shape(dataSet)[1] centroids = mat(zeros((k,n)))#create centroid mat for j in range(n):#create random cluster centers, within bounds of each dimension minJ = min(dataSet[:,j]) rangeJ = float(max(dataSet[:,j]) - minJ) centroids[:,j] = mat(minJ + rangeJ * random.rand(k,1)) return centroids def distEclud(vecA, vecB): return sqrt(sum(power(vecA - vecB, 2))) #la.norm(vecA-vecB) def kMeans(dataSet, k): m = shape(dataSet)[0] clusterAssment = mat(zeros((m,2)))#create mat to assign data points to a centroid, also holds SE of each point centroids = randCent(dataSet, k) clusterChanged = True while clusterChanged: clusterChanged = False for i in range(m):#for each data point assign it to the closest centroid minDist = inf; minIndex = -1 for j in range(k): distJI = distEclud(centroids[j,:],dataSet[i,:]) if distJI < minDist: minDist = distJI; minIndex = j if clusterAssment[i,0] != minIndex: clusterChanged = True clusterAssment[i,:] = minIndex,minDist**2 #print centroids for cent in range(k):#recalculate centroids ptsInClust = dataSet[nonzero(clusterAssment[:,0].A==cent)[0]]#get all the point in this cluster centroids[cent,:] = mean(ptsInClust, axis=0) #assign centroid to mean return centroids, clusterAssment if __name__ == '__main__': # 导入数据集 matf = 'E://data_sc//corel_50_NN_sym_distance.mat' dataDic = scio.loadmat(matf) data = dataDic['A'] # 谱聚类的过程 spectalCluster(data, 20, 18)
function [cluster_labels evd_time kmeans_time total_time] = sc(A, sigma, num_clusters) %SC Spectral clustering using a sparse similarity matrix (t-nearest-neighbor). % % Input : A : N-by-N sparse distance matrix, where % N is the number of data % sigma : sigma value used in computing similarity, % if 0, apply self-tunning technique % num_clusters : number of clusters % % Output : cluster_labels : N-by-1 vector containing cluster labels % evd_time : running time for eigendecomposition % kmeans_time : running time for k-means % total_time : total running time % % Convert the sparse distance matrix to a sparse similarity matrix, % where S = exp^(-(A^2 / 2*sigma^2)). % Note: This step can be ignored if A is sparse similarity matrix. % disp('Converting distance matrix to similarity matrix...'); tic; n = size(A, 1); if (sigma == 0) % Selftuning spectral clustering % Find the count of nonzero for each column disp('Selftuning spectral clustering...'); col_count = sum(A~=0, 1)'; col_sum = sum(A, 1)'; col_mean = col_sum ./ col_count; [x y val] = find(A); A = sparse(x, y, -val.*val./col_mean(x)./col_mean(y)./2); clear col_count col_sum col_mean x y val; else % Fixed-sigma spectral clustering disp('Fixed-sigma spectral clustering...'); A = A.*A; A = -A/(2*sigma*sigma); end % Do exp function sequentially because of memory limitation num = 2000; num_iter = ceil(n/num); S = sparse([]); for i = 1:num_iter start_index = 1 + (i-1)*num; end_index = min(i*num, n); S1 = spfun(@exp, A(:,start_index:end_index)); % sparse exponential func S = [S S1]; clear S1; end clear A; toc; % % Do laplacian, L = D^(-1/2) * S * D^(-1/2) % disp('Doing Laplacian...'); D = sum(S, 2) + (1e-10); D = sqrt(1./D); % D^(-1/2) D = spdiags(D, 0, n, n); L = D * S * D; clear D S; time1 = toc; % % Do eigendecomposition, if L = % D^(-1/2) * S * D(-1/2) : set 'LM' (Largest Magnitude), or % I - D^(-1/2) * S * D(-1/2): set 'SM' (Smallest Magnitude). % disp('Performing eigendecomposition...'); OPTS.disp = 0; [V, val] = eigs(L, num_clusters, 'LM', OPTS); time2 = toc; % % Do k-means % disp('Performing kmeans...'); % Normalize each row to be of unit length sq_sum = sqrt(sum(V.*V, 2)) + 1e-20; U = V ./ repmat(sq_sum, 1, num_clusters); clear sq_sum V; cluster_labels = k_means(U, [], num_clusters); total_time = toc; % % Calculate and show time statistics % evd_time = time2 - time1 kmeans_time = total_time - time2 total_time disp('Finished!');
function cluster_labels = k_means(data, centers, num_clusters) %K_MEANS Euclidean k-means clustering algorithm. % % Input : data : N-by-D data matrix, where N is the number of data, % D is the number of dimensions % centers : K-by-D matrix, where K is num_clusters, or % 'random', random initialization, or % [], empty matrix, orthogonal initialization % num_clusters : Number of clusters % % Output : cluster_labels : N-by-1 vector of cluster assignment % % Reference: Dimitrios Zeimpekis, Efstratios Gallopoulos, 2006. % http://scgroup.hpclab.ceid.upatras.gr/scgroup/Projects/TMG/ % % Parameter setting % iter = 0; qold = inf; threshold = 0.001; % % Check if with initial centers % if strcmp(centers, 'random') disp('Random initialization...'); centers = random_init(data, num_clusters); elseif isempty(centers) disp('Orthogonal initialization...'); centers = orth_init(data, num_clusters); end % % Double type is required for sparse matrix multiply % data = double(data); centers = double(centers); % % Calculate the distance (square) between data and centers % n = size(data, 1); x = sum(data.*data, 2)'; X = x(ones(num_clusters, 1), :); y = sum(centers.*centers, 2); Y = y(:, ones(n, 1)); P = X + Y - 2*centers*data'; % % Main program % while 1 iter = iter + 1; % Find the closest cluster for each data point [val, ind] = min(P, [], 1); % Sum up data points within each cluster P = sparse(ind, 1:n, 1, num_clusters, n); centers = P*data; % Size of each cluster, for cluster whose size is 0 we keep it empty cluster_size = P*ones(n, 1); % For empty clusters, initialize again zero_cluster = find(cluster_size==0); if length(zero_cluster) > 0 disp('Zero centroid. Initialize again...'); centers(zero_cluster, :)= random_init(data, length(zero_cluster)); cluster_size(zero_cluster) = 1; end % Update centers centers = spdiags(1./cluster_size, 0, num_clusters, num_clusters)*centers; % Update distance (square) to new centers y = sum(centers.*centers, 2); Y = y(:, ones(n, 1)); P = X + Y - 2*centers*data'; % Calculate objective function value qnew = sum(sum(sparse(ind, 1:n, 1, size(P, 1), size(P, 2)).*P)); mesg = sprintf('Iteration %d:\n\tQold=%g\t\tQnew=%g', iter, full(qold), full(qnew)); disp(mesg); % Check if objective function value is less than/equal to threshold if threshold >= abs((qnew-qold)/qold) mesg = sprintf('\nkmeans converged!'); disp(mesg); break; end qold = qnew; end cluster_labels = ind'; %----------------------------------------------------------------------------- function init_centers = random_init(data, num_clusters) %RANDOM_INIT Initialize centroids choosing num_clusters rows of data at random % % Input : data : N-by-D data matrix, where N is the number of data, % D is the number of dimensions % num_clusters : Number of clusters % % Output: init_centers : K-by-D matrix, where K is num_clusters rand('twister', sum(100*clock)); init_centers = data(ceil(size(data, 1)*rand(1, num_clusters)), :); function init_centers = orth_init(data, num_clusters) %ORTH_INIT Initialize orthogonal centers for k-means clustering algorithm. % % Input : data : N-by-D data matrix, where N is the number of data, % D is the number of dimensions % num_clusters : Number of clusters % % Output: init_centers : K-by-D matrix, where K is num_clusters % % Find the num_clusters centers which are orthogonal to each other % Uniq = unique(data, 'rows'); % Avoid duplicate centers num = size(Uniq, 1); first = ceil(rand(1)*num); % Randomly select the first center init_centers = zeros(num_clusters, size(data, 2)); % Storage for centers init_centers(1, :) = Uniq(first, :); Uniq(first, :) = []; c = zeros(num-1, 1); % Accumalated orthogonal values to existing centers for non-centers % Find the rest num_clusters-1 centers for j = 2:num_clusters c = c + abs(Uniq*init_centers(j-1, :)'); [minimum, i] = min(c); % Select the most orthogonal one as next center init_centers(j, :) = Uniq(i, :); Uniq(i, :) = []; c(i) = []; end clear c Uniq;
参考
1、从拉普拉斯矩阵说到谱聚类(http://blog.csdn.net/v_july_v/article/details/40738211)
2、谱聚类(spectral clustering)(http://www.cnblogs.com/FengYan/archive/2012/06/21/2553999.html)
3、谱聚类算法(Spectral Clustering)(http://www.cnblogs.com/sparkwen/p/3155850.html)