SVM简介
支持向量机（support vector machines, SVM）是一种二分类模型，它的基本模型是定义在特征空间上的间隔最大的线性分类器，间隔最大使它有别于感知机；SVM还包括核技巧，这使它成为实质上的非线性分类器。SVM的的学习策略就是间隔最大化，可形式化为一个求解凸二次规划的问题，也等价于正则化的合页损失函数的最小化问题。SVM的的学习算法就是求解凸二次规划的最优化算法。
% 基于SVM的回归预测分析——上证指数开盘指数预测%% 清空环境变量function chapter_shtic;close all;clear;clc;format compact;%% 数据的提取和预处理% 载入测试数据上证指数(1990.12.19-.08.19)% 数据是一个4579*6的double型的矩阵,每一行表示每一天的上证指数% 6列分别表示当天上证指数的开盘指数,指数最高值,指数最低值,收盘指数,当日交易量,当日交易额.load chapter_sh.mat;% 提取数据[m,n] = size(sh);ts = sh(2:m,1);tsx = sh(1:m-1,:);% 画出原始上证指数的每日开盘数figure;plot(ts,'LineWidth',2);title('上证指数的每日开盘数(1990.12.20-.08.19)','FontSize',12);xlabel('交易日天数(1990.12.19-.08.19)','FontSize',12);ylabel('开盘数','FontSize',12);grid on;% 数据预处理,将原始数据进行归一化ts = ts';tsx = tsx';% mapminmax为matlab自带的映射函数% 对ts进行归一化[TS,TSps] = mapminmax(ts,1,2);% 画出原始上证指数的每日开盘数归一化后的图像figure;plot(TS,'LineWidth',2);title('原始上证指数的每日开盘数归一化后的图像','FontSize',12);xlabel('交易日天数(1990.12.19-.08.19)','FontSize',12);ylabel('归一化后的开盘数','FontSize',12);grid on;% 对TS进行转置,以符合libsvm工具箱的数据格式要求TS = TS';% mapminmax为matlab自带的映射函数% 对tsx进行归一化[TSX,TSXps] = mapminmax(tsx,1,2);% 对TSX进行转置,以符合libsvm工具箱的数据格式要求TSX = TSX';%% 选择回归预测分析最佳的SVM参数c&g% 首先进行粗略选择: [bestmse,bestc,bestg] = SVMcgForRegress(TS,TSX,-8,8,-8,8);% 打印粗略选择结果disp('打印粗略选择结果');str = sprintf( 'Best Cross Validation MSE = %g Best c = %g Best g = %g',bestmse,bestc,bestg);disp(str);% 根据粗略选择的结果图再进行精细选择: [bestmse,bestc,bestg] = SVMcgForRegress(TS,TSX,-4,4,-4,4,3,0.5,0.5,0.05);% 打印精细选择结果disp('打印精细选择结果');str = sprintf( 'Best Cross Validation MSE = %g Best c = %g Best g = %g',bestmse,bestc,bestg);disp(str);%% 利用回归预测分析最佳的参数进行SVM网络训练cmd = ['-c ', num2str(bestc), ' -g ', num2str(bestg) , ' -s 3 -p 0.01'];model = svmtrain(TS,TSX,cmd);%% SVM网络回归预测[predict,mse] = svmpredict(TS,TSX,model);predict = mapminmax('reverse',predict',TSps);predict = predict';% 打印回归结果str = sprintf( '均方误差 MSE = %g 相关系数 R = %g%%',mse(2),mse(3)*100);disp(str);%% 结果分析figure;hold on;plot(ts,'-o');plot(predict,'r-^');legend('原始数据','回归预测数据');hold off;title('原始数据和回归预测数据对比','FontSize',12);xlabel('交易日天数(1990.12.19-.08.19)','FontSize',12);ylabel('开盘数','FontSize',12);grid on;figure;error = predict - ts';plot(error,'rd');title('误差图(predicted data - original data)','FontSize',12);xlabel('交易日天数(1990.12.19-.08.19)','FontSize',12);ylabel('误差量','FontSize',12);grid on;figure;error = (predict - ts')./ts';plot(error,'rd');title('相对误差图(predicted data - original data)/original data','FontSize',12);xlabel('交易日天数(1990.12.19-.08.19)','FontSize',12);ylabel('相对误差量','FontSize',12);grid on;snapnow;toc;%% 子函数 SVMcgForRegress.mfunction [mse,bestc,bestg] = SVMcgForRegress(train_label,train,cmin,cmax,gmin,gmax,v,cstep,gstep,msestep)%SVMcg cross validation by faruto%% by faruto%Email:patrick.lee@ QQ:516667408 /faruto BNU%last modified .01.17%Super Moderator @ % 若转载请注明：% faruto and liyang , LIBSVM-farutoUltimateVersion % a toolbox with implements for support vector machines based on libsvm, . % Software available at % % Chih-Chung Chang and Chih-Jen Lin, LIBSVM : a library for% support vector machines, 2001. Software available at% http://www.csie.ntu.edu.tw/~cjlin/libsvm% about the parameters of SVMcg if nargin < 10msestep = 0.06;endif nargin < 8cstep = 0.8;gstep = 0.8;endif nargin < 7v = 5;endif nargin < 5gmax = 8;gmin = -8;endif nargin < 3cmax = 8;cmin = -8;end% X:c Y:g cg:acc[X,Y] = meshgrid(cmin:cstep:cmax,gmin:gstep:gmax);[m,n] = size(X);cg = zeros(m,n);eps = 10^(-4);bestc = 0;bestg = 0;mse = Inf;basenum = 2;for i = 1:mfor j = 1:ncmd = ['-v ',num2str(v),' -c ',num2str( basenum^X(i,j) ),' -g ',num2str( basenum^Y(i,j) ),' -s 3 -p 0.1'];cg(i,j) = svmtrain(train_label, train, cmd);if cg(i,j) < msemse = cg(i,j);bestc = basenum^X(i,j);bestg = basenum^Y(i,j);endif abs( cg(i,j)-mse )<=eps && bestc > basenum^X(i,j)mse = cg(i,j);bestc = basenum^X(i,j);bestg = basenum^Y(i,j);endendend% to draw the acc with different c & g[cg,ps] = mapminmax(cg,0,1);figure;[C,h] = contour(X,Y,cg,0:msestep:0.5);clabel(C,h,'FontSize',10,'Color','r');xlabel('log2c','FontSize',12);ylabel('log2g','FontSize',12);firstline = 'SVR参数选择结果图(等高线图)[GridSearchMethod]'; secondline = ['Best c=',num2str(bestc),' g=',num2str(bestg), ...' CVmse=',num2str(mse)];title({firstline;secondline},'Fontsize',12);grid on;figure;meshc(X,Y,cg);% mesh(X,Y,cg);% surf(X,Y,cg);axis([cmin,cmax,gmin,gmax,0,1]);xlabel('log2c','FontSize',12);ylabel('log2g','FontSize',12);zlabel('MSE','FontSize',12);firstline = 'SVR参数选择结果图(3D视图)[GridSearchMethod]'; secondline = ['Best c=',num2str(bestc),' g=',num2str(bestg), ...' CVmse=',num2str(mse)];title({firstline;secondline},'Fontsize',12);
