自学机器学习笔记（五）

最新推荐文章于 2023-04-28 09:57:25 发布

梦忆师

最新推荐文章于 2023-04-28 09:57:25 发布

阅读量694

点赞数

文章标签：机器学习 matlab 算法

本文链接：https://blog.csdn.net/qq_51963033/article/details/122609567

版权

研究兵王问题matlab程序

总代码：

clear all;
% Read the data.
fid  =  fopen('krkopt.DATA');
c = fread(fid, 3);

vec = zeros(6,1);
xapp = [];
yapp = [];
while ~feof(fid)
    string = [];
    c = fread(fid,1);
    flag = flag+1;
    while c~=13
        string = [string, c];
        c=fread(fid,1);
    end;
    fread(fid,1);  
    if length(string)>10
        vec(1) = string(1) - 96;
        vec(2) = string(3) - 48;
        vec(3) = string(5) - 96;
        vec(4) = string(7) - 48;
        vec(5) = string(9) - 96;
        vec(6) = string(11) - 48;
        xapp = [xapp,vec];
        if string(13) == 100
            yapp = [yapp,1];
        else
            yapp = [yapp,-1];
        end;
    end;
end;
fclose(fid);

[N,M] = size(xapp);
p = randperm(M); %直接打乱了训练样本
numberOfSamplesForTraining = 5000;
xTraining = [];
yTraining = [];
for i=1:numberOfSamplesForTraining
    xTraining  = [xTraining,xapp(:,p(i))];
    yTraining = [yTraining,yapp(p(i))];
end;
xTraining = xTraining';
yTraining = yTraining';

xTesting = [];
yTesting = [];
for i=numberOfSamplesForTraining+1:M
    xTesting  = [xTesting,xapp(:,p(i))];
    yTesting = [yTesting,yapp(p(i))];
end;
xTesting = xTesting';
yTesting = yTesting';

%%%%%%%%%%%%%%%%%%%%%%%%
%Normalization
[numVec,numDim] = size(xTraining);
avgX = mean(xTraining);
stdX = std(xTraining);
for i = 1:numVec
    xTraining(i,:) = (xTraining(i,:)-avgX)./stdX;
end;
[numVec,numDim] = size(xTesting);

for i = 1:numVec
    xTesting(i,:) = (xTesting(i,:)-avgX)./stdX;
end;



%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%SVM Gaussian kernel 
%Search for the optimal C and gamma, K(x1,x2) = exp{-||x1-x2||^2/gamma} to
%make the recognition rate maximum. 

%Firstly, search C and gamma in a crude scale (as recommended in 'A practical Guide to Support Vector Classification'))
CScale = [-5, -3, -1, 1, 3, 5,7,9,11,13,15];
gammaScale = [-15,-13,-11,-9,-7,-5,-3,-1,1,3];
C = 2.^CScale;
gamma = 2.^gammaScale;
maxRecognitionRate = 0;
for i = 1:length(C)
    for j = 1:length(gamma)
        cmd=['-t 2 -c ',num2str(C(i)),' -g ',num2str(gamma(j)),' -v 5'];
        recognitionRate = svmtrain(yTraining,xTraining,cmd);
        if recognitionRate>maxRecognitionRate
            maxRecognitionRate = recognitionRate
            maxCIndex = i;
            maxGammaIndex = j;
        end;
    end;
end;

%Then search for optimal C and gamma in a refined scale. 
n = 10;
minCScale = 0.5*(CScale(max(1,maxCIndex-1))+CScale(maxCIndex));
maxCScale = 0.5*(CScale(min(length(CScale),maxCIndex+1))+CScale(maxCIndex));
newCScale = [minCScale:(maxCScale-minCScale)/n:maxCScale];

minGammaScale = 0.5*(gammaScale(max(1,maxGammaIndex-1))+gammaScale(maxGammaIndex));
maxGammaScale = 0.5*(gammaScale(min(length(gammaScale),maxGammaIndex+1))+gammaScale(maxGammaIndex));
newGammaScale = [minGammaScale:(maxGammaScale-minGammaScale)/n:maxGammaScale];
newC = 2.^newCScale;
newGamma = 2.^newGammaScale;
maxRecognitionRate = 0;
for i = 1:length(newC)
    for j = 1:length(newGamma)
        cmd=['-t 2 -c ',num2str(newC(i)),' -g ',num2str(newGamma(j)),' -v 5'];
        recognitionRate = svmtrain(yTraining,xTraining,cmd);
        if recognitionRate>maxRecognitionRate
            maxRecognitionRate = recognitionRate
            maxC = newC(i);
            maxGamma = newGamma(j);
        end;
    end;
end;

%Train the SVM model by the optimal C and gamma.
cmd=['-t 2 -c ',num2str(maxC),' -g ',num2str(maxGamma)];
model = svmtrain(yTraining,xTraining,cmd);
save model.mat model;
save xTesting.mat xTesting;
save yTesting.mat yTesting;




    
    
    
plot(falsePositive,truePositive);

首先是数据的预处理部分

fid  =  fopen('krkopt.DATA');
c = fread(fid, 3);

fopen函数是读入krkopt.DATA文件，fid就是此文件的文件标识

接下来依次读入矩阵

vec = zeros(6,1);
xapp = [];
yapp = [];
while ~feof(fid)
    string = [];
    c = fread(fid,1);
    flag = flag+1;
    while c~=13
        string = [string, c];
        c=fread(fid,1);
    end;
    fread(fid,1);  
    if length(string)>10
        vec(1) = string(1) - 96;
        vec(2) = string(3) - 48;
        vec(3) = string(5) - 96;
        vec(4) = string(7) - 48;
        vec(5) = string(9) - 96;
        vec(6) = string(11) - 48;
        xapp = [xapp,vec];
        if string(13) == 100
            yapp = [yapp,1];
        else
            yapp = [yapp,-1];
        end;
    end;
end;
fclose(fid);

B=zeros(m,n)：生成m×n全零阵。

xapp矩阵接受六维的训练数据

yapp矩阵接受每个训练数据的标签

feof(fid)函数：文件指针fid到达文件末尾时返回真值，否则返回假，这里while去判断文件是否读完

~=代表不等于，对照ASCII表13代表回车

在while结束后，文件指针停在了回车处，所以在总代码第17行要再读一个字符

只要string长度大于10代表读入数据正常，进行处理，因为读入是字符形式，要转换成数字，而在给出的数据中，每个数字是以，相隔所以要隔着放，最后将处理好的数据分别放入xapp与yapp中

这样的处理，我们要将这28056个样本分为训练集和测试集

[N,M] = size(xapp);
p = randperm(M); %直接打乱了训练样本
numberOfSamplesForTraining = 5000;
xTraining = [];
yTraining = [];
for i=1:numberOfSamplesForTraining
    xTraining  = [xTraining,xapp(:,p(i))];
    yTraining = [yTraining,yapp(p(i))];
end;
xTraining = xTraining';
yTraining = yTraining';

xTesting = [];
yTesting = [];
for i=numberOfSamplesForTraining+1:M
    xTesting  = [xTesting,xapp(:,p(i))];
    yTesting = [yTesting,yapp(p(i))];
end;
xTesting = xTesting';
yTesting = yTesting';

[N,M] = size(xapp) 得到xapp中是有M个数据，数据是N维的

p = randperm(M) 将M个数据打乱

numberOfSamplesForTraining = 5000 我们用5000个样本进行训练

for i=1:numberOfSamplesForTraining 存入训练矩阵中

接下类进行归一化操作

[numVec,numDim] = size(xTraining);
avgX = mean(xTraining);
stdX = std(xTraining);
for i = 1:numVec
    xTraining(i,:) = (xTraining(i,:)-avgX)./stdX;
end;
[numVec,numDim] = size(xTesting);

for i = 1:numVec
    xTesting(i,:) = (xTesting(i,:)-avgX)./stdX;
end;

要将训练样本和测试样本都进行归一化处理

这次分类的核函数为RBF核

其中C和gamma的取值要自己去取

这里

CScale = [-5, -3, -1, 1, 3, 5,7,9,11,13,15];
gammaScale = [-15,-13,-11,-9,-7,-5,-3,-1,1,3];
C = 2.^CScale;
gamma = 2.^gammaScale;

C的取值范围为2^-5~~2^15

gamma的取值范围为 2^-15~~2^3

这里是基于人工经验

交叉验证

我们要找到最适合的C和GAMMA：识别率最大

训练集只有5000个样本，我们要估计识别率

注：我们不能用支持向量机模型的样本去测试识别率

会导致过拟合

测试识别率的样本与训练机器学习模型的样本要不一样

这里我们常采用交叉验证

例如：5000个样本分为5个1000份：ABCDE

每次用4个训练，用另一个测试获得识别率

将得到的所有识别率求平均值得到总识别率：五折交叉验证

maxRecognitionRate = 0;
for i = 1:length(C)
    for j = 1:length(gamma)
        cmd=['-t 2 -c ',num2str(C(i)),' -g ',num2str(gamma(j)),' -v 5'];
        recognitionRate = svmtrain(yTraining,xTraining,cmd);
        if recognitionRate>maxRecognitionRate
            maxRecognitionRate = recognitionRate
            maxCIndex = i;
            maxGammaIndex = j;
        end;
    end;
end;

cmd=['-t 2 -c ',num2str(C(i)),' -g ',num2str(gamma(j)),' -v 5']; 这里-v 5 就是进行五折交叉验证

n = 10;
minCScale = 0.5*(CScale(max(1,maxCIndex-1))+CScale(maxCIndex));
maxCScale = 0.5*(CScale(min(length(CScale),maxCIndex+1))+CScale(maxCIndex));
newCScale = [minCScale:(maxCScale-minCScale)/n:maxCScale];

minGammaScale = 0.5*(gammaScale(max(1,maxGammaIndex-1))+gammaScale(maxGammaIndex));
maxGammaScale = 0.5*(gammaScale(min(length(gammaScale),maxGammaIndex+1))+gammaScale(maxGammaIndex));
newGammaScale = [minGammaScale:(maxGammaScale-minGammaScale)/n:maxGammaScale];
newC = 2.^newCScale;
newGamma = 2.^newGammaScale;
maxRecognitionRate = 0;
for i = 1:length(newC)
    for j = 1:length(newGamma)
        cmd=['-t 2 -c ',num2str(newC(i)),' -g ',num2str(newGamma(j)),' -v 5'];
        recognitionRate = svmtrain(yTraining,xTraining,cmd);
        if recognitionRate>maxRecognitionRate
            maxRecognitionRate = recognitionRate
            maxC = newC(i);
            maxGamma = newGamma(j);
        end;
    end;
end;

再次进行交叉验证，找出精确的C和gamma组合

cmd=['-t 2 -c ',num2str(maxC),' -g ',num2str(maxGamma)];
model = svmtrain(yTraining,xTraining,cmd);
save model.mat model;

当这两个超参数确定后，我们要用这5000个样本重新训练一个支持向量机模型，这就是最终模型

不知道数据类别的先验分布，知道识别率毫无意义

单纯用识别率来判断系统的好坏是没有意义的

梦忆师

关注

0
点赞
踩
4

收藏

觉得还不错? 一键收藏
2
评论
自学机器学习笔记（五）

研究兵王问题matlab程序总代码：clear all;% Read the data.fid = fopen('krkopt.DATA');c = fread(fid, 3);vec = zeros(6,1);xapp = [];yapp = [];while ~feof(fid) string = []; c = fread(fid,1); flag = flag+1; while c~=13 string = [string
复制链接

扫一扫