机器学习 naive 贝叶斯分类器实现 （附原始matlab代码和数据集）

function my_NaiveBayes(data,label) %% data shuffle and split re_ind=randperm(size(label,1)); data=data(re_ind,:); label=label(re_ind,:); [vec1,~,~]=pca(data); accuracy=[]; i=1; for t=1:40 disp(['No. ',num2str(i),' starts !']); para={}; % PCA for dimention reduction data_pca=data*vec1(:,1:t); traindata=data_pca(1:floor(size(data,1)*0.8),:); trainlabel=label(1:floor(size(data,1)*0.8),:); trainlabel(trainlabel==0)=10; testdata=data_pca(floor(size(data,1)*0.8)+1:end,:); testlabel=label(floor(size(data,1)*0.8)+1:end,:); testlabel(testlabel==0)=10; fprintf('The number of traindata is %d and the number of testdata is %d \n',size(trainlabel,1),size(testlabel,1)) %% Get the data and label of every class loc={}; for loc1=1:10 loc{loc1}=find(trainlabel==loc1); end X={}; for x1=1:10 X{x1}=traindata(loc{x1},:); end Y={}; for y1=1:10 Y{y1}=trainlabel(loc{y1},:); end %% Calculate the prior probability ratio=zeros(10,1); for class_ratio=1:10 ratio(class_ratio)=length(Y{class_ratio})/length(trainlabel); end for classes=1:10 mat1=[]; x=X{classes}; for feature_dim=1:t tem_mean=mean(x(:,feature_dim)); tem_var=var(x(:,feature_dim)); mat1=[mat1;[tem_mean,tem_var]]; end para{classes}=mat1; end predicted_label=zeros(length(testlabel),1); for test_num=1:size(testlabel,1) prob=zeros(10,1); for test_classes=1:10 test_data=testdata(test_num,:); mm=1; for feature_num=1:t mm=mm*1./(sqrt(2*pi*para{test_classes}(feature_num,2))).*exp(-0.5.*(test_data(feature_num)-para{test_classes}(feature_num,1)).^2./para{test_classes}(feature_num,2)); end prob(test_classes)=mm*ratio(test_classes); end [~,loc_find]=max(prob); predicted_label(test_num)=loc_find; end accuracy1=sum(predicted_label==testlabel)./length(testlabel); accuracy=[accuracy;accuracy1]; disp(['No. ',num2str(i),' completes !']); i=i+1; end figure(2) plot(1:40,accuracy) title('Naive Bayes Classification Accuracy') ylabel('accuracy(%)') xlabel('dimensionality of data') end