naivebayes.m

这是一个matlab 开发的naive Bayes 分类器算法。可以供大家共享

function [predict, accuracy] = NaiveBayes(Train, Test)
%Input: Training set and testing set, each row represents a instance, last column is label( begins from zero)
%Output:predict label by NaiveBayes as well as its accuracy
Train_sample = Train(:,1:end-1);
Train_label = Train(:,end);
Test_sample = Test(:,1:end-1);
Test_label = Test(:,end);
Class_num = length(unique(Train_label));
Feature_num = size(Train_sample,2);
Para_mean =   cell(1,Class_num);%Mean for each feature and class
Para_dev = cell(1,Class_num);%Dev for each feature and class
Sample_byclass = cell(1,Class_num);%Reorder the data set by class
Prior_prob = zeros(1,Class_num);%Prior probability of each class
for i=1:1:length(Train_sample) 
    Sample_byclass{1,Train_label(i,1)+1} = [Sample_byclass{1,Train_label(i,1)+1}; Train_sample(i,:)];
    Prior_prob(1,Train_label(i,1)+1) = Prior_prob(1,Train_label(i,1)+1) + 1;
end
Prior_prob = Prior_prob/size(Train_sample,1); % Prior probability
for i=1:1:Class_num  %model parameter
     miu = mean(Sample_byclass{1,i});
     delta = std(Sample_byclass{1,i});   
     Para_mean{1,i} = miu;
     Para_dev{1,i} = delta;
end
predict = [];
for i=1:size(Test_sample)   %length(Test_sample)
     prob = log(Prior_prob);
     hei=0;
     for j=1:Class_num
         for k=1:1:Feature_num  %如果方差为0，调整
             if Para_dev{1,j}(1,k) == 0
                 Para_dev{1,j}(1,k) = 0.1667;
             end
             %利用正态分布的密度函数，求概率。为方便计算，对概率求对数,在此我们假设各个属性间是相互独立的
             hei=hei-(Test_sample(i,k)-Para_mean{1,j}(1,k))^2/(2*Para_dev{1,j}(1,k)^2)   - log(Para_dev{1,j}(1,k));
             
         end  %对每一个属性结束
         prob(1,j) = prob(1,j)+hei;
     end %对每个类结束
     [value index] = max(prob);
     predict = [predict ; index-1];
end
accuracy = length(find(predict - Test_label ==0))/length(Test_label);