PCA及kmeans介绍见吴恩达机器学习–PCA、吴恩达机器学习–kmeans.
代码：
%% Step1: load data and preprocess X = load(mat_path, 'mean_data'); X = (X.mean_data-mean(X.mean_data,1))./var(X.mean_data); %% Step2: compute covariance matrix for k = 1:size(X,2) number_of_samples = size(X,1); sigma = (1/number_of_samples)*X'*X; %% Step3: compute eigenvectors of matrix sigma [U,S,V] = svd(sigma); U_reduce = U(:,1:k); Z = X*U_reduce; %% Step4: check S_k = 0; S_n = sum(diag(S)); for i = 1:k S_k = S_k + S(i,i); end if S_k / S_n >= 0.99 fprintf("%.2f%% variance retained\n", 100*S_k/S_n); break; else if k==2 Z_to_plot = Z; end if k==3 Z_to_plot3 = Z; end fprintf("%.2f%% variance retained\n", 100*S_k/S_n); continue; end end % save('./mean_data_reduced.mat','Z'); opts = statset('Display','final'); [cidx, ctrs] = kmeans(Z_to_plot3, 2, 'Distance','sqeuclidean', ... 'Replicates',5, 'Options',opts); figure(1) plot(Z_to_plot(cidx==1,1),Z_to_plot(cidx==1,2),'r.', ... Z_to_plot(cidx==2,1),Z_to_plot(cidx==2,2),'b.', ... Z_to_plot(cidx==3,1),Z_to_plot(cidx==3,2),'g.', ... ctrs(:,1),ctrs(:,2),'m*'); figure(2) plot3(Z_to_plot3(cidx==1,1),Z_to_plot3(cidx==1,2),Z_to_plot3(cidx==1,3),'r.', ... Z_to_plot3(cidx==2,1),Z_to_plot3(cidx==2,2),Z_to_plot3(cidx==2,3),'b.', ... Z_to_plot3(cidx==3,1),Z_to_plot3(cidx==3,2),Z_to_plot3(cidx==3,3),'g.', ... ctrs(:,1),ctrs(:,2),ctrs(:,3),'m*');可视化：
