pca_parzen_smooth.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=10;%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
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    %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(1:100),:);%测试样本
    exper_test=experiment_test(:,2:end);%测试样本,不带标签
    experiment_train=dimenReduct_samples(p(101:300),:);%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
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

    %构造一个正态函数，以每个训练样本为中心（均值）                                                    
    SIGMA=eye(k_reduction);
    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
    %对第一类
    Result=zeros(m,1);%记录最后分类结果
    for i=1:m
        for j=1:m1
            R1(i)=R1(i)+mvnpdf(exper_test(i,:),exper_train_class1(j,:),SIGMA);
        end
    end
    R1=R1./m1;
    %对第二类
    for i=1:m
        for j=1:m2
            R2(i)=R2(i)+mvnpdf(exper_test(i,:),exper_train_class2(j,:),SIGMA);
        end
    end
    R2=R2./m2;

    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    %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