liner.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

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%使用随机下采样（random subsampling）的方法对,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=samples(p(1:500),:);%测试样本
exper_test=experiment_test(:,2:ns);%测试样本,不带标签
experiment_train=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:ns);%训练样本里属于第一类的样本,不带标签
exper_train_class2=experiment_train(index2,2:ns);%训练样本里属于第二类的样本,不带标签

[m n]=size(exper_test);
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%计算每个待测样本到每个训练样本类的Mahalanobis 距离
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
R1=mahal(exper_test,exper_train_class1);
R2=mahal(exper_test,exper_train_class2);

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%分类
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%分类,
for j=1:m
    if R1(j,1)<=R2(j,1)
        Result(j,1)=1;
    else
        Result(j,1)=2;
    end
end
    
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%分析结果 ，计算准确率, 错误率, 敏感性, 特异性,误判率,漏判率
%   准确率:（有毒的（1）判断为有毒（1）+可食的（2）判断为可食（2））/测试样本总数（500）
%   错误率：1-准确率
%   敏感性：蘑菇有毒（1），且判为有毒（1） 
%   特异性：蘑菇可食（2），且判为可食（2）
%   误判率：实际可食（2），但判为有毒（1）
%   漏判率：实际有毒（1），但判为可食（2）
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
[correct,error,ROC] = analyse_result(experiment_test,Result);