西瓜书手搓TSVM对UCI数据集的预测以及与SVM的对比

霜木君
于 2023-11-06 21:45:11 发布
阅读量252
点赞数 1
文章标签：支持向量机机器学习算法
本文链接：https://blog.csdn.net/m0_63531247/article/details/134254538
版权
我的微信公众号：不断努力的霜木君
虽然不怎么更新，但有机会就分享点东西上去，探讨一下世界与人生的哲学。
这是大四上学期机器学习基础课程的大作业，挺有意思的。后面如果有同学也选了这门课，可以选这个题。
由于我们在做的过程中也参考了很多大佬的做法，所以完全开源。
特点在于：SMO算法中，针对TSVM做了改动，在KKT条件判定、松弛因子等部分都考虑得比较严密。欢迎大家在评论区与我讨论（在我还记得这个项目期间）。
总得来说，我感觉我们这个项目做的不错，完全结合书上的理论做了改动，并不是直接把网上的东西搬过来用，最后老师给了我94分，还行吧，可能我在汇报的时候讲的不够突出，以后继续努力。
下面展示部分报告内容，具体分析及源码请查看报告
下载链接：
lTSVM报告.pdf - 蓝奏云
源码（部分）：
clc
clear all
close all
%% 数据载入
datas = load("iris.data")
rowrank = randperm(size(datas, 1)); % size获得datas的行数，randperm打乱各行的顺序
data_random = datas(rowrank,:);     % 按照rowrank重新排列各行，注意rowrank的位置
X = data_random(1:10,1:4); %有标记样本
y = data_random(1:10,5)'; %有标记样本的标记（这里以行向量存储，要不下面会报错）
X_unknown = data_random(11:70,1:4);  %无标记样本
X_test = data_random(71:100,1:4);    %测试样本
y_test = data_random(71:100,5)';      %测试样本标记（这里以行向量存储，要不下面会报错）
% y = [1,1,1,1,1,1,1,1,-1,-1,-1,-1,-1,-1,-1,-1,-1];% 标记向量  %采用西瓜来测试
% y = double(y);
% X = [0.697,0.460;0.774,0.376;0.634,0.264;...% 属性向量
%     0.608,0.318;0.556,0.215;0.403,0.237;...
%     0.481,0.149;0.437,0.211;0.666,0.091;...
%     0.243,0.267;0.245,0.057;0.343,0.099;...
%     0.639,0.161;0.657,0.198;0.360,0.370;...
%     0.593,0.042;0.719,0.103];
% X_unknown = [0.7,0.3;0.3,0.7;0.5,0.5;0.6,0.4;0.6,0.6;0.2,0.2;0.5,0.1];
% X = double(X);
%% 采用线性核或高斯核
kernel_type = 1; % 0代表线性核，1代表高斯核
%% 线性核建立
K_L = zeros(size(y,2),size(y,2));
for i=1:size(y,2)
    for j=1:size(y,2)
        K_L(i,j) = X(i,:)*X(j,:)';
    end
end
%% 高斯核建立
K_G = zeros(size(y,2),size(y,2));
sigma = 100;
for i=1:size(y,2)
    for j=1:size(y,2)
        K_G(i,j) = exp(-(norm(X(i,:)-X(j,:))^2)/(2*sigma^2));
    end
end
%% 模型训练
C = 10;
if kernel_type == 0
    [w_L,b_L,alphas_L,SVs_L] = smoSimple(X, y',C, 100, K_L,0,sigma) % 线性核_SMO算法求解alpha和b
else
    [w_L,b_L,alphas_L,SVs_L] = smoSimple(X, y',C, 100, K_G,1,sigma) % 高斯核_SMO算法求解alpha和b
end
w_only = w_L;b_only = b_L; alphas_only = alphas_L;
%% TSVM模型构建
Cl=10;
Cu=0.1;
iter = 0;
[L_res,L_corrects,L_wrongs,accuracy_L,res_origin] = SVM_predict(alphas_L,b_L,X_unknown,y,X,y,kernel_type,sigma);
X_total = [X;X_unknown];
while Cu<Cl
    iter = iter+1
    ok_flag = 0;
    K_L = zeros(size([y';L_res],1),size([y';L_res],1));
    for i=1:size([y';L_res],1)
        for j=1:size([y';L_res],1)
            K_L(i,j) = X_total(i,:)*X_total(j,:)';
            K_G(i,j) = exp(-(norm(X_total(i,:)-X_total(j,:))^2)/(2*sigma^2));
            if kernel_type == 1
                K_L(i,j) = K_G(i,j);
            end
        end
    end
    [w_L,b_L,alphas_L,SVs_L] = TSVMsmoSimple(X_total, [y';L_res],Cl,Cu,10, K_L,size(X,1),size(X_unknown,1),kernel_type,sigma);
    while ok_flag ==0
        for i = 1:size(X_unknown,1)-1
            for j=i+1:size(X_unknown,1)
                if kernel_type == 0
                    ksi_i = max(0,1-L_res(i)*(w_L*X_unknown(i,:)'+b_L)); %P127 (6.24)
                    ksi_j = max(0,1-L_res(j)*(w_L*X_unknown(j,:)'+b_L));
                elseif kernel_type == 1
                    m = size(alphas_L,1);
                    temp1=0;temp2=0;
                    temp3 = [y';L_res];
                    for k=1:m
                        temp1 = temp1 + alphas_L(k)*temp3(k)*exp(-(norm(X_total(k,:)-X_unknown(i,:))^2)/(2*sigma^2));
                        temp2 = temp2 + alphas_L(k)*temp3(k)*exp(-(norm(X_total(k,:)-X_unknown(j,:))^2)/(2*sigma^2));
                    end
                    ksi_i = max(0,1-L_res(i)*(temp1+b_L)); %P127 (6.24)
                    ksi_j = max(0,1-L_res(j)*(temp2+b_L));
                end
                ok_flag = 1;
                if ((L_res(i)*L_res(j))<0) && (ksi_i>0)&&(ksi_j>0)&&((ksi_i+ksi_j)>2)
                    L_res(i) = L_res(i)*(-1);
                    L_res(j) = L_res(j)*(-1);
                    ok_flag = 0;
                    break
                end
            end
            if ok_flag == 0
                break
            end
        end
        if ok_flag == 0
            [w_L,b_L,alphas_L,SVs_L] = TSVMsmoSimple(X_total, [y';L_res],Cl,Cu,10, K_L,size(X,1),size(X_unknown,1),kernel_type,sigma);
        end
    end
    Cu = min(2*Cu,Cl)
end
result = [y';L_res];
%% 测试集检验
[test_res,test_corrects,test_wrongs,accuracy_test,~] = SVM_predict(alphas_L,b_L,X_test,y_test,X_total,result,kernel_type,sigma);
[testonly_res,testonly_corrects,testonly_wrongs,accuracy_testonly,~] = SVM_predict(alphas_only,b_only,X_test,y_test,X_total,result,kernel_type,sigma);
%% 结果绘制
accBound = 0.001; % 决定分类线的精度。值越小，分类线越精确，同时绘制速度越慢
L_idx = SVs_L';
figure(1);
title("训练集（10%+60%） 菱形为“1”样本，圆形为“-1”样本，实心为支持向量")
hold on
for i=1:size(result,1)
    if result(i)==1
        plot(X_total(i,1),X_total(i,2),'diamond r');
    else
        plot(X_total(i,1),X_total(i,2),'ob');    
    end
end
for i=1:size(L_idx,1)
    j = L_idx(i);
    if result(j)==1
        plot(X_total(j,1),X_total(j,2),'diamond r','MarkerFaceColor','r');% 绘制"1"样本支持向量
    else
        plot(X_total(j,1),X_total(j,2),'ob','MarkerFaceColor','b');% 绘制"-1"样本支持向量
    end
end
if kernel_type ==  0
    plotSVM(0, size(X_total,2), X_total, result, b_L, alphas_L, X_total(SVs_L,:), SVs_L, accBound,sigma,1)
else
    plotSVM(1, size(X_total,2), X_total, result, b_L, alphas_L, X_total(SVs_L,:), SVs_L, accBound,sigma,1)
end
figure(2)
title("测试集分类结果（30%）  TSVM")
hold on
for i=1:size(test_res,1)
    if test_res(i)==1
        plot(X_test(i,1),X_test(i,2),'diamond r');
    else
        plot(X_test(i,1),X_test(i,2),'ob');    
    end
    if test_res(i) ~= y_test(i)
        scatter(X_test(i,1),X_test(i,2),1,'MarkerEdgeColor','k','Marker','x','LineWidth',10);
    end
end
figure(3)
title("测试集分类结果（30%）  SVM")
hold on
for i=1:size(test_res,1)
    if testonly_res(i)==1
        plot(X_test(i,1),X_test(i,2),'diamond r');
    else
        plot(X_test(i,1),X_test(i,2),'ob');    
    end
    if testonly_res(i) ~= y_test(i)
        scatter(X_test(i,1),X_test(i,2),1,'MarkerEdgeColor','k','Marker','x','LineWidth',10);
    end
end
%% SMO算法
function [w,b,alphas,SVs] = smoSimple(dataMat, labelMat, C,maxIter, K,kernel_type,sigma)
b = 0;
num = 0;
[N, D] = size(dataMat);
alphas = zeros(N, 1);
iter = 0;
kernalData = K;
w = zeros(1,size(dataMat,2));
while (iter < maxIter)
    alphaPairsChanged = 0; % 记录alpha已经优化的数量
    for i = 1: N
        fXi = (alphas .* labelMat)' * kernalData(:, i) + b; % fXi为目前对xi的预测结果 （6.24）
        Ei = fXi - labelMat(i); % Ei为使用alpha_i计算时的预测误差
        % 接下来的if语句判断某条数据是否符合KKT条件
        %if ((labelMat(i) * Ei < -toler) && (alphas(i) < C)) || ((labelMat(i) * Ei > toler) && (alphas(i) > 0))
        if kernel_type == 0
           ksi_i = max(0,1-labelMat(i)*(w*dataMat(i,:)'+b)); %P127 (6.24)
        elseif kernel_type == 1
            temp1=0;
            for k=1:N
                temp1 = temp1 + alphas(k)*labelMat(k)*exp(-(norm(dataMat(k,:)-dataMat(i,:))^2)/(2*sigma^2));
            end
            ksi_i = max(0,1-labelMat(i)*(temp1+b)); %P127 (6.24)
        end
        if ( ((alphas(i) >= 0) && (alphas(i) <= C))&& ((labelMat(i) * fXi-1+ksi_i >= 0) && (alphas(i)*(labelMat(i) * fXi-1+ksi_i) == 0)&&(ksi_i>=0)&&((C-alphas(i))*ksi_i==0))==0) %训练选取的alpha是不满足KKT条件的。因为满足KKT条件的alpha不需要被优化p125
            % 若alpha可更改，则执行如下语句
            % 选择与i所对应的样本距离最远的j 课本p125
            distance = 0;
            maxdist = 0;
            for index=1:N
                distance = dist(dataMat(i,:),dataMat(index,:)');
                if distance>maxdist
                    maxdist = distance;
                    j = index;
                end
            end
            % 使用选出来的alpha_j计算预测结果fXj
            fXj = (alphas .* labelMat)' * kernalData(:, j) + b;
            Ej = fXj - labelMat(j); % Ej为使用alpha_j计算时的预测误差
            alphaIold = alphas(i);
            alphaJold = alphas(j);
            % 计算alpha_j的上下界
            if labelMat(i) ~= labelMat(j)
                L = max(0, alphas(j) - alphas(i));
                H = min(C, C + alphas(j) - alphas(i));
            else
                L = max(0, alphas(j) + alphas(i) - C);
                H = min(C, alphas(j) + alphas(i));
            end
            if L == H
                continue;
            end
            eta = 2.0 * kernalData(i, j) - kernalData(i, i) - kernalData(j, j);
            if eta >= 0
                fprintf("eta >= 0\n");
                continue;
            end
            alphas(j) = alphas(j) - labelMat(j) * (Ei - Ej) / eta;
            alphas(j) = clipAlpha(alphas(j), H, L); % 越界的alpha被强制赋值
            if (abs(alphas(j) - alphaJold) < 0.00001)% 迭代求解终止条件
                continue;
            end
            % 至此，alpha_j计算完成
            % 根据alpha_i和alpha_j的关系式，计算alpha_i
            alphas(i) = alphaIold + labelMat(j) * labelMat(i) * (alphaJold - alphas(j));
            % 计算分类超平面的偏置
            b1 = b - Ei - labelMat(i) * (alphas(i) - alphaIold) * kernalData(i, i) - ...
                                  labelMat(j) * (alphas(j) - alphaJold) * kernalData(i, j);
            b2 = b - Ej - labelMat(i) * (alphas(i) - alphaIold) * kernalData(i, j) - ...
                                  labelMat(j) * (alphas(j) - alphaJold) * kernalData(j, j);
            if (0 < alphas(i)) && (C > alphas(i))
                b = b1;
            elseif (0 < alphas(j)) && (C > alphas(j))
                b = b2;
            else
                b = (b1 + b2) / 2;
            end
            alphaPairsChanged = alphaPairsChanged + 1;
        end
    end
    if alphaPairsChanged == 0
        iter = iter + 1;
    else
        iter = 0;
    end
end
    w = zeros(1,size(dataMat,2));
    num = 0;
    SVs=zeros(1,1);
    for i = 1:N
        w = w +alphas(i)*labelMat(i)*dataMat(i,:);
        if alphas(i)>0
            num = num +1;
            SVs(num)=i;
        end
    end
end
%% 第一版SMO算法-KKT约束条件与课本不符，废弃不用
function [w,b,alphas,SVs] = sssssmoSimple(dataMat, labelMat, C,maxIter, K)
b = 0;
num = 0;
[N, D] = size(dataMat);
alphas = zeros(N, 1);
iter = 0;
kernalData = K;
while (iter < maxIter)
    alphaPairsChanged = 0; % 记录alpha已经优化的数量
    for i = 1: N
        fXi = (alphas .* labelMat)' * kernalData(:, i) + b; % fXi为目前对xi的预测结果 （6.24）
        Ei = fXi - labelMat(i); % Ei为使用alpha_i计算时的预测误差
        % 接下来的if语句判断某条数据是否符合KKT条件
        %if ((labelMat(i) * Ei < -toler) && (alphas(i) < C)) || ((labelMat(i) * Ei > toler) && (alphas(i) > 0))
        if ( ((alphas(i) >= 0) && (alphas(i) <= C))&& ((labelMat(i) * fXi-1 >= 0) && (alphas(i)*(labelMat(i) * fXi-1) == 0))==0) %训练选取的alpha是不满足KKT条件的。因为满足KKT条件的alpha不需要被优化p125
            % 若alpha可更改，则执行如下语句
            % 选择与i所对应的样本距离最远的j 课本p125
            distance = 0;
            maxdist = 0;
            for index=1:N
                distance = dist(dataMat(i,:),dataMat(index,:)');
                if distance>maxdist
                    maxdist = distance;
                    j = index;
                end
            end
            % 使用选出来的alpha_j计算预测结果fXj
            fXj = (alphas .* labelMat)' * kernalData(:, j) + b;
            Ej = fXj - labelMat(j); % Ej为使用alpha_j计算时的预测误差
            alphaIold = alphas(i);
            alphaJold = alphas(j);
            % 计算alpha_j的上下界
            if labelMat(i) ~= labelMat(j)
                L = max(0, alphas(j) - alphas(i));
                H = min(C, C + alphas(j) - alphas(i));
            else
                L = max(0, alphas(j) + alphas(i) - C);
                H = min(C, alphas(j) + alphas(i));
            end
            if L == H
                continue;
            end
            eta = 2.0 * kernalData(i, j) - kernalData(i, i) - kernalData(j, j);
            if eta >= 0
                fprintf("eta >= 0\n");
                continue;
            end
            alphas(j) = alphas(j) - labelMat(j) * (Ei - Ej) / eta;
            alphas(j) = clipAlpha(alphas(j), H, L); % 越界的alpha被强制赋值
            if (abs(alphas(j) - alphaJold) < 0.00001)% 迭代求解终止条件
                continue;
            end
            % 至此，alpha_j计算完成
            % 根据alpha_i和alpha_j的关系式，计算alpha_i
            alphas(i) = alphaIold + labelMat(j) * labelMat(i) * (alphaJold - alphas(j));
            % 计算分类超平面的偏置
            b1 = b - Ei - labelMat(i) * (alphas(i) - alphaIold) * kernalData(i, i) - ...
                                  labelMat(j) * (alphas(j) - alphaJold) * kernalData(i, j);
            b2 = b - Ej - labelMat(i) * (alphas(i) - alphaIold) * kernalData(i, j) - ...
                                  labelMat(j) * (alphas(j) - alphaJold) * kernalData(j, j);
            if (0 < alphas(i)) && (C > alphas(i))
                b = b1;
            elseif (0 < alphas(j)) && (C > alphas(j))
                b = b2;
            else
                b = (b1 + b2) / 2;
            end
            alphaPairsChanged = alphaPairsChanged + 1;
        end
    end
    if alphaPairsChanged == 0
        iter = iter + 1;
    else
        iter = 0;
    end
end
w = zeros(1,size(dataMat,2));
    for i = 1:N
        w = w +alphas(i)*labelMat(i)*dataMat(i,:);
        if alphas(i)>0
            num = num +1;
            SVs(num)=i;
        end
    end
end
%% TSVM-SMO算法
function [w,b,alphas,SVs] = TSVMsmoSimple(dataMat, labelMat, Cl,Cu,maxIter, K,num_known,num_unknown,kernel_type,sigma)
b = 0;
num = 0;
[N, D] = size(dataMat);
alphas = zeros(N, 1);
iter = 0;
kernalData = K;
w = zeros(1,size(dataMat,2));
while (iter < maxIter)
    alphaPairsChanged = 0; % 记录alpha已经优化的数量
    for i = 1: N
        if i<=num_known
            Ci = Cl;
        else
            Ci = Cu;
        end
        fXi = (alphas .* labelMat)' * kernalData(:, i) + b; % fXi为目前对xi的预测结果 （6.24）
        Ei = fXi - labelMat(i); % Ei为使用alpha_i计算时的预测误差
        % 接下来的if语句判断某条数据是否符合KKT条件
        %if ((labelMat(i) * Ei < -toler) && (alphas(i) < C)) || ((labelMat(i) * Ei > toler) && (alphas(i) > 0))
        if kernel_type == 0
           ksi_i = max(0,1-labelMat(i)*(w*dataMat(i,:)'+b)); %P127 (6.24)
        elseif kernel_type == 1
            temp1=0;
            for k=1:N
                temp1 = temp1 + alphas(k)*labelMat(k)*exp(-(norm(dataMat(k,:)-dataMat(i,:))^2)/(2*sigma^2));
            end
            ksi_i = max(0,1-labelMat(i)*(temp1+b)); %P127 (6.24)
        end
        if ( ((alphas(i) >= 0) && (alphas(i) <= Ci))&& ((labelMat(i) * fXi-1+ksi_i >= 0) && (alphas(i)*(labelMat(i) * fXi-1+ksi_i) == 0)&&(ksi_i>=0)&&((Ci-alphas(i))*ksi_i==0))==0) %训练选取的alpha是不满足KKT条件的。因为满足KKT条件的alpha不需要被优化p125
        %if ( ((alphas(i) >= 0) && (alphas(i) <= Ci))&& ((labelMat(i) * fXi-1 >= 0) && (alphas(i)*(labelMat(i) * fXi-1) == 0))==0) %训练选取的alpha是不满足KKT条件的。因为满足KKT条件的alpha不需要被优化p125
            % 若alpha可更改，则执行如下语句
            % 选择与i所对应的样本距离最远的j 课本p125
            distance = 0;
            maxdist = 0;
            for index=1:N
                distance = dist(dataMat(i,:),dataMat(index,:)');
                if distance>maxdist
                    maxdist = distance;
                    j = index;
                end
            end
            if j<=num_known
                Cj = Cl;
            else
                Cj = Cu;
            end
            % 使用选出来的alpha_j计算预测结果fXj
            fXj = (alphas .* labelMat)' * kernalData(:, j) + b;
            Ej = fXj - labelMat(j); % Ej为使用alpha_j计算时的预测误差
            alphaIold = alphas(i);
            alphaJold = alphas(j);
            % 计算alpha_j的上下界
            if labelMat(i) ~= labelMat(j) %假若Ci和Cj不相等，那么上下限与普通SVM不同
                L = max(0, alphas(j) - alphas(i));
                H = min(Cj, Ci + alphas(j) - alphas(i));
            else
                L = max(0, alphas(j) + alphas(i) - Ci);
                H = min(Cj, alphas(j) + alphas(i));
            end
            if L == H
                continue;
            end
            eta = 2.0 * kernalData(i, j) - kernalData(i, i) - kernalData(j, j);
            if eta >= 0
                %fprintf("eta >= 0\n");
                continue;
            end
            alphas(j) = alphas(j) - labelMat(j) * (Ei - Ej) / eta;
            alphas(j) = clipAlpha(alphas(j), H, L); % 越界的alpha被强制赋值
            if (abs(alphas(j) - alphaJold) < 0.00001)% 迭代求解终止条件
                continue;
            end
            % 至此，alpha_j计算完成
            % 根据alpha_i和alpha_j的关系式，计算alpha_i
            alphas(i) = alphaIold + labelMat(j) * labelMat(i) * (alphaJold - alphas(j));
            % 计算分类超平面的偏置
            b1 = b - Ei - labelMat(i) * (alphas(i) - alphaIold) * kernalData(i, i) - ...
                                  labelMat(j) * (alphas(j) - alphaJold) * kernalData(i, j);
            b2 = b - Ej - labelMat(i) * (alphas(i) - alphaIold) * kernalData(i, j) - ...
                                  labelMat(j) * (alphas(j) - alphaJold) * kernalData(j, j);
            if (0 < alphas(i)) && (Ci > alphas(i))
                b = b1;
            elseif (0 < alphas(j)) && (Cj > alphas(j))
                b = b2;
            else
                b = (b1 + b2) / 2;
            end
            alphaPairsChanged = alphaPairsChanged + 1;
        end
    end
    if alphaPairsChanged == 0
        iter = iter + 1;
    else
        iter = 0;
    end
end
    w = zeros(1,size(dataMat,2));
    SVs=zeros(1,1);
    for i = 1:N
        w = w +alphas(i)*labelMat(i)*dataMat(i,:);
        if alphas(i)>0
            num = num +1;
            SVs(num)=i;
        end
    end
end
%% 预测函数
function [lists,corrects,wrongs,accuracy,res] = SVM_predict(alphas,b,x_pre,y_pre,X_data,label,Kernel,sigma)
m = size(alphas,1);
n = size(x_pre,1);
res = zeros(n,1);
for j=1:n % 软间隔支持向量机      
    for i=1:m
        if Kernel == 0
            res(j) = res(j) + alphas(i)*label(i)*x_pre(j,:)*X_data(i,:)';
        elseif Kernel == 1
            res(j) = res(j) + alphas(i)*label(i)*exp(-(norm(x_pre(j,:)-X_data(i,:))^2)/(2*sigma^2));
        end
    end
    res(j) = res(j) + b;
end
lists = zeros(n,1);
cn=0;wn=0;
accuracy = 0;
corrects = zeros(n,1);
wrongs = zeros(n,1);
try
    for i = 1:n
        if res(i)>0
            lists(i) = 1;
        else
            lists(i) = -1;
        end
        if lists(i) == y_pre(i)
            cn = cn+1;
            corrects(cn)=i;
        else
            wn = wn + 1;
            wrongs(wn) = i;
        end
    end
catch
end
accuracy = cn/(cn+wn); % 计算准确率
end
%% 绘图函数
function plotSVM(Kernel_Method, D, dataMat, labelMat, b, alphas, supportVectors, supportVectorsIndices, accBound,sigma,index)
if D == 2
    % 分类线位于所有预测值为0的数据点位置上。
    % 1、对屏幕空间的矩形范围（至少包含所有训练数据点）内的所有坐标点进行预测
    %       点与点的间隔越小，分类边界线越精确
    % 2、画出预测值为0的点
    % 3、将所有标出的点连起来，构成高维分类超平面在二维上的投影边界
    % 第2和第3步可以用contour函数直接实现
    % 构建屏幕空间坐标集合screenCorMat，第一页为X坐标，第二页为Y坐标
    screenCorX = min(dataMat(:, 1)): accBound: max(dataMat(:, 1));
    screenCorY = min(dataMat(:, 2)): accBound: max(dataMat(:, 2));
    M = length(screenCorY);
    N = length(screenCorX);
    screenCorX = repmat(screenCorX, [M , 1]);
    screenCorY = repmat(screenCorY',[1, N]);
    screenCorMat = cat(3, screenCorX, screenCorY);
    % 平铺屏幕空间所有点，便于预测
    screenCorMat = reshape(screenCorMat, [M * N, 2]);
    % 对屏幕空间所有点进行预测，得到预测结果矩阵predictCor
    for i = 1: N 
        [~,~,~,~,predictCor(:,i)] = SVM_predict(alphas,b,[screenCorX(:,i),screenCorY(:,1)],dataMat,labelMat,Kernel_Method,sigma);
        %predictCor(i) = kernelCor(:, i)' * (labelMat(supportVectorsIndices) .* alphas(supportVectorsIndices)) + b;
    end
    %predictCor = reshape(predictCor, [M, N]);
    % 绘制预测结果为0的所有点，连起来，构成分类边界线
    figure(index), contour(screenCorX, screenCorY, predictCor, [0, 0], 'k:','ShowText','on'); hold on;
    hold on;
    % 圈出所有支持向量
    %figure(index), scatter(supportVectors(:, 1), supportVectors(:, 2), 100, 'k'); hold on;
    % 绘制出边界点所在曲线
    figure(index), contour(screenCorX, screenCorY, predictCor, [1 1], 'r:','ShowText','on'); hold on;
    figure(index), contour(screenCorX, screenCorY, predictCor, [-1 -1], 'r:','ShowText','on');
else
    fprintf('数据维数高于2维，无法绘图\n');
end
end
%% 在1到m之间随机选取一个整数j
function j = selectJrand(i, m)
j = i;
while (j == i)
    j = randperm(m, 1);
end
end

%% 调整大于H或小于L的alpha，即掐头去尾
function aj = clipAlpha(aj, H, L)
% 令大于H的alpha等于H
if aj > H
    aj = H;
end
% 令小于L的alpha等于L
if aj < L
    aj = L;
end
end
葡萄酒数据集的实现方法就不给出了，在报告里有。
欢迎大家关注我的微信公众号：不断努力的霜木君