pca_parzen_hypercube.m

用mushrooms数据对模式识别课程讲述的各种模式分类方法[线性分类

clc;
clear;

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%读取数据，取16个特征
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
samples = textread('data2000.txt');
samples = samples(:,[1:6,9:15,19:22]);  %17列 第1列标号，16列特征

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%对样本进行归一化处理
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
[ms ns]=size(samples);
TMax=max(samples);
TMin=min(samples);
% 第一列是样本标签，从第二列开始归一化
for i=2:ns
    samples(:,i)=(samples(:,i)-TMin(i))/(TMax(i)-TMin(i));
end

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%对样本进行降维，PCA变换
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
k_reduction=16;%降维后的维数
cov_data=cov(samples(:,2:end));
[pc,latent,explained] = pcacov(cov_data);
pc1=pc(:,1:k_reduction);
pc1=pc1';
y=pc1*samples(:,2:end)';
y = [samples(:,1)';y];
dimenReduct_samples = y';%带标签

for w = 1:5  %进行五次实验
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    %将样本分为测试样本，第一类训练样本，第二类训练样本
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    p = randperm(2000);%对1：2000的整数随机排序
    experiment_test=dimenReduct_samples(p(1:500),:);%测试样本
    exper_test=experiment_test(:,2:end);%测试样本,不带标签
    experiment_train=dimenReduct_samples(p(501:2000),:);%训练样本
    index1=find(experiment_train(:,1)==1);%找到训练样本中第一类的行号
    index2=find(experiment_train(:,1)==2);%找到训练样本中第二类的行号
    exper_train_class1=experiment_train(index1,2:end);%训练样本里属于第一类的样本,不带标签
    exper_train_class2=experiment_train(index2,2:end);%训练样本里属于第二类的样本,不带标签

    [m n]=size(exper_test);
    [m1 n1]=size(exper_train_class1);
    [m2 n2]=size(exper_train_class2);
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    %计算类条件概率密度
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    %计算P(x/wi)=k/(nV)
    %取边长hn=1的d=10维超立方体
    %首先计算落入每个待测样本点的超立方体的点的个数
    hn=1;
    V=hn^n;
    K1=zeros(m,1);%记录第一类训练样本落入待测样本的超立方体的点的个数
    K2=zeros(m,1);%记录第二类训练样本落入待测样本的超立方体的点的个数
    R1=zeros(m,1);%记录待测样本在第一类的测试结果
    R2=zeros(m,1);%记录待测样本在第二类的测试结果
    Result=zeros(m,1);%记录最后分类结果
    %先算第一类
    for i=1:m%对每个待测样本
        for j=1:m1%检测每个训练样本
            flag=0;
            for k=1:n%检查每个分量abs(xi)<(hn/2)，如果都小于则待测样本落入超立方体
                if(abs(exper_test(i,k)-exper_train_class1(j,k))<(hn/2))
                    flag=flag+1;
                end
            end
            if flag==n
                    K1(i,1)=K1(i,1)+1;
            end
        end
        R1(i,1)=K1(i,1)/(n*V);
    end
    %再算第二类
    for i=1:m%对每个待测样本
        for j=1:m2%检测每个训练样本
            flag=0;
            for k=1:n%检查每个分量abs(xi)<(hn/2)，如果都小于则待测样本落入超立方体
                if(abs(exper_test(i,k)-exper_train_class2(j,k))<(hn/2))
                    flag=flag+1;
                end
            end
            if flag==n
                    K2(i,1)=K2(i,1)+1;
            end
        end
        R2(i,1)=K2(i,1)/(n*V);
    end

    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    %画类条件概率密度图，并分类
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    %绘图
    plot(R1,'-r','LineWidth',2);
    hold on;
    plot(R2,'-b','LineWidth',2);
    xlabel ('待测样本'); 
    ylabel ('类条件概率密度 P（x|wi）');
    title ('类条件概率密度图');
    %分类
    for i=1:m
        if R1(i,1)>R2(i,1)
            Result(i,1)=1;
        else
            Result(i,1)=2;
        end
    end
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    %分析结果
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    [correct(w,1),error(w,1),ROC(w,:)] = analyse_result(experiment_test,Result);
end

%将结果放到一个数组中，便于观察数据
correct = correct';
error = error';
ROC = ROC';
result = [correct;error;ROC]
result = result';