本文给出了下面3种输出分类概率学习器的matlab代码,以及例程。
程序包
链接:https://pan.baidu.com/s/1B6R2B7mzEDahWnDQ0zlepw
提取码:9rbp
%% 机器学习-例程
%% 简单介绍
%
%
% 功能:基于训练数据,利用学习器,构建预测模型。
%
% 输入:训练数据(特征+标签),测试数据(特征+标签)。
%
% 输出:预测的标签
%
% 学习器的选择:稳定学习器优先SVM,不稳定学习器优先ELM。(可以对分类数据做可视化分析,根据分布特点选择对应偏好的分类器)
%
%
% 注意:以下例程中,测试数据是‘特征+标签’,输出是测试精度和预测样本。在实际应用中,可直接将测试样本的标签设置为0,然后进行预测标签。
%% 数据整理
load iris.mat % 加载数据集,特征在前,标签在后,每一行是一个样本,每一列是一个特征
tr=iris(1:100,:); % 取iris数据的前100行作为训练样本
te=iris(101:end,:); % 取后50行作为测试样本
%% 学习器
% 1. SVM:支持向量机
[A_SVM,SVM_label] = SVM1(tr,te);
% 需要安装libsvm
% 原理:https://zhuanlan.zhihu.com/p/77750026
% 2.KNN_ave:基于平均距离改进的k-近邻
k = 1;
[A_kNN_1,label_knn_1,Probability] = knn_ave(tr,te,k); % 改进型kNN
% 3.ELM:极限学习机
NumberofHiddenNeurons = 10;
[TestingAccuracy, elmlabel,pro, TrainingAccuracy, TrainingTime, TestingTime] = f_ELM(tr,te,NumberofHiddenNeurons);
function [TestingAccuracy,predicted_label,Scores,Time]=SVM1(tr,te)
tic
model = svmtrain(tr(:,end), tr(:,1:end-1), '-c 1 -g 0.07 -t 0 -b 1 -q');
[predicted_label, TestingAccuracy,Scores] = svmpredict(te(:,end), te(:,1:end-1), model,'-b 1');
TestingAccuracy=TestingAccuracy(1)./100;
p=[];
zhonglei=size(unique(tr(:,end)),1);
for i=1:size(te,1)
[~,b]=max(Scores(i,1:zhonglei));
p(i,:)=[predicted_label(i),b];
end
s=sortrows(p,1);
A2=[];
ss=unique(predicted_label);
ll=size(ss,1);
for j=1:ll
s1=find(s(:,1)==ss(j,1));
s2=s1(1);
A2(j,1)=ss(j,1);
A2(j,2)=s(s2,2);
end
scores=[];
for k=1:size(A2,1)
scores(:,k)=Scores(:,A2(k,2)); %注意大小写
end
Scores=[scores,predicted_label];
[Scores]=guiyi(Scores);
Time=toc;
end
function [A_1,knnlabel_1,Probability]=knn_ave(tr,te,k)
%knn : 搜寻距离测试样本最近的k的训练样本,k个样本中平均距离最短的标签预测为测试样本的标签。
%Input: tr: 训练数据(标签在最后一列)
% te: 测试数据(标签在最后一列)
% k: 近邻数
%Output: A:测试精度
% knnlabel:预测标签
if ~exist('k', 'var')
k = 3;
end %如果没有输入k值,取k=3
num_label = size(unique(tr(:,end)),1);
data=[tr;te];
n=size(data,2);
m1=size(tr,1);
m2=size(te,1); %m1为训练样本数,m2为测试样本数
trd=tr(:,1:n-1);
trl=tr(:,n);
ted=te(:,1:n-1);
tel=te(:,n); %-d为数据,-l为标签
probability=zeros(size(te,1),num_label);
knnlabel_1=zeros(m2,1);
for j=1:m2
distance=zeros(m1,1);
for i=1:m1
distance(i)=norm(ted(j,:)-trd(i,:)); %计算测试数据与每个训练数据的欧式距离
end
[distance1,index]=sort(distance);
x1=trl(index,end);
distance1(:,2)=x1; %distance1的第一列是距离,第二列是标签
di=zeros(num_label,2);
for w=1:num_label
x2=find(distance1(:,2)==w);
x2=x2(1:k,:);
dis=distance1(x2,1);
dis=sum(dis)/k;
di(w,1)=dis;
di(w,2)=w;
end %把每一种标签都找出距离最近的k的样本,并计算平均距离
c=sum(di(:,1))./di(:,1)';
c=c/max(c,[],2);
probability(j,:)=c; %输出概率:距离的总和除以各个距离,然后除以其中最大值,得类概率
b=sortrows(di,1);
knnlabel_1(j,1)=b(1,2); %平均距离最近的标签为预测标签
end
Probability=[probability,knnlabel_1];
bj=(knnlabel_1==tel);
a=nnz(bj);
A_1=a/m2; %输出识别率
function [TestingAccuracy, elmlabel,pro, TrainingAccuracy, TrainingTime, TestingTime] = f_ELM(tr,te,NumberofHiddenNeurons)
% Input:
% Tr - Filename of training data set
% Te - Filename of testing data set
% Note that: each row represents a instance, last column is label, begins from 1
% Elm_Type - 0 for regression; 1 for (both binary and multi-classes) classification
% NumberofHiddenNeurons - Number of hidden neurons assigned to the ELM
% ActivationFunction - Type of activation function:
% 'sig' for Sigmoidal function
% 'sin' for Sine function
% 'hardlim' for Hardlim function
% 'tribas' for Triangular basis function
% 'radbas' for Radial basis function (for additive type of SLFNs instead of RBF type of SLFNs)
%
% Output:
% TrainingTime - Time (seconds) spent on training ELM
% TestingTime - Time (seconds) spent on predicting ALL testing data
% TrainingAccuracy - Training accuracy:
% RMSE for regression or correct classification rate for classification
% TestingAccuracy - Testing accuracy:
% RMSE for regression or correct classification rate for classification
%elmlabel - predict label by elm for testingdata
Elm_Type=1;
ActivationFunction='sig';
Tr=tr;
Te=te;
if ~exist('Elm_Type', 'var')
Elm_Type = 1;
end
if ~exist('NumberofHiddenNeurons', 'var')
NumberofHiddenNeurons = 10;
end
if ~exist('ActivationFunction', 'var')
ActivationFunction = 'sig';
end
%%%%%%%%%%% Macro definition
REGRESSION=0;
CLASSIFIER=1;
%%%%%%%%%%% Load training dataset
T=Tr(:,end)';
P=Tr(:,1:end-1)';
clear Tr; % Release raw training data array
%%%%%%%%%%% Load testing dataset
TV.T=Te(:,end)';
TV.P=Te(:,1:end-1)';
clear Te; % Release raw testing data array
NumberofTrainingData=size(P,2);
NumberofTestingData=size(TV.P,2);
NumberofInputNeurons=size(P,1);
if Elm_Type~=REGRESSION
%%%%%%%%%%%% Preprocessing the data of classification
sorted_target=sort(cat(2,T,TV.T),2);
label=zeros(1,1); % Find and save in 'label' class label from training and testing data sets
label(1,1)=sorted_target(1,1);
j=1;
for i = 2:(NumberofTrainingData+NumberofTestingData)
if sorted_target(1,i) ~= label(1,j)
j=j+1;
label(1,j) = sorted_target(1,i);
end
end
number_class=j;
NumberofOutputNeurons=number_class;
%%%%%%%%%% Processing the targets of training
temp_T=zeros(NumberofOutputNeurons, NumberofTrainingData);
for i = 1:NumberofTrainingData
for j = 1:number_class
if label(1,j) == T(1,i)
break;
end
end
temp_T(j,i)=1;
end
T=temp_T*2-1;
%%%%%%%%%% Processing the targets of testing
temp_TV_T=zeros(NumberofOutputNeurons, NumberofTestingData);
for i = 1:NumberofTestingData
for j = 1:number_class
if label(1,j) == TV.T(1,i)
break;
end
end
temp_TV_T(j,i)=1;
end
TV.T=temp_TV_T*2-1;
end % end if of Elm_Type
%%%%%%%%%%% Calculate weights & biases
start_time_train=cputime;
%%%%%%%%%%% Random generate input weights InputWeight (w_i) and biases BiasofHiddenNeurons (b_i) of hidden neurons
InputWeight=rand(NumberofHiddenNeurons,NumberofInputNeurons)*2-1;
BiasofHiddenNeurons=rand(NumberofHiddenNeurons,1);
tempH=InputWeight*P;
clear P; % Release input of training data
ind=ones(1,NumberofTrainingData);
BiasMatrix=BiasofHiddenNeurons(:,ind); % Extend the bias matrix BiasofHiddenNeurons to match the demention of H
tempH=tempH+BiasMatrix;
%%%%%%%%%%% Calculate hidden neuron output matrix H
switch lower(ActivationFunction)
case {'sig','sigmoid'}
%%%%%%%% Sigmoid
H = 1 ./ (1 + exp(-tempH));
case {'sin','sine'}
%%%%%%%% Sine
H = sin(tempH);
case {'hardlim'}
%%%%%%%% Hard Limit
H = double(hardlim(tempH));
case {'tribas'}
%%%%%%%% Triangular basis function
H = tribas(tempH);
case {'radbas'}
%%%%%%%% Radial basis function
H = radbas(tempH);
%%%%%%%% More activation functions can be added here
end
clear tempH; % Release the temparary array for calculation of hidden neuron output matrix H
%%%%%%%%%%% Calculate output weights OutputWeight (beta_i)
OutputWeight=pinv(H') * T'; % implementation without regularization factor //refer to 2006 Neurocomputing paper
%OutputWeight=inv(eye(size(H,1))/C+H * H') * H * T'; % faster method 1 //refer to 2012 IEEE TSMC-B paper
%implementation; one can set regularizaiton factor C properly in classification applications
%OutputWeight=(eye(size(H,1))/C+H * H') \ H * T'; % faster method 2 //refer to 2012 IEEE TSMC-B paper
%implementation; one can set regularizaiton factor C properly in classification applications
%If you use faster methods or kernel method, PLEASE CITE in your paper properly:
%Guang-Bin Huang, Hongming Zhou, Xiaojian Ding, and Rui Zhang,
%"Extreme Learning Machine for Regression and Multi-Class Classification,"
%submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence, October 2010.
end_time_train=cputime;
TrainingTime=end_time_train-start_time_train; % Calculate CPU time (seconds) spent for training ELM
%%%%%%%%%%% Calculate the training accuracy
Y=(H' * OutputWeight)'; % Y: the actual output of the training data
if Elm_Type == REGRESSION
TrainingAccuracy=sqrt(mse(T - Y)); % Calculate training accuracy (RMSE) for regression case
end
clear H;
%%%%%%%%%%% Calculate the output of testing input
start_time_test=cputime;
tempH_test=InputWeight*TV.P;
clear TV.P; % Release input of testing data
ind=ones(1,NumberofTestingData);
BiasMatrix=BiasofHiddenNeurons(:,ind); % Extend the bias matrix BiasofHiddenNeurons to match the demention of H
tempH_test=tempH_test + BiasMatrix;
switch lower(ActivationFunction)
case {'sig','sigmoid'}
%%%%%%%% Sigmoid
H_test = 1 ./ (1 + exp(-tempH_test));
case {'sin','sine'}
%%%%%%%% Sine
H_test = sin(tempH_test);
case {'hardlim'}
%%%%%%%% Hard Limit
H_test = hardlim(tempH_test);
case {'tribas'}
%%%%%%%% Triangular basis function
H_test = tribas(tempH_test);
case {'radbas'}
%%%%%%%% Radial basis function
H_test = radbas(tempH_test);
%%%%%%%% More activation functions can be added here
end
TY=(H_test' * OutputWeight)'; % TY: the actual output of the testing data
probability=TY';
[TYmax,elmlabel]=max(TY);
elmlabel=elmlabel';
probability=[probability,elmlabel];
end_time_test=cputime;
TestingTime=end_time_test-start_time_test; % Calculate CPU time (seconds) spent by ELM predicting the whole testing data
if Elm_Type == REGRESSION
TestingAccuracy=sqrt(mse(TV.T - TY)); % Calculate testing accuracy (RMSE) for regression case
end
if Elm_Type == CLASSIFIER
%%%%%%%%%% Calculate training & testing classification accuracy
MissClassificationRate_Training=0;
MissClassificationRate_Testing=0;
for i = 1 : size(T, 2)
[x, label_index_expected]=max(T(:,i));
[x, label_index_actual]=max(Y(:,i));
if label_index_actual~=label_index_expected
MissClassificationRate_Training=MissClassificationRate_Training+1;
end
end
TrainingAccuracy=1-MissClassificationRate_Training/size(T,2);
for i = 1 : size(TV.T, 2)
[x, label_index_expected]=max(TV.T(:,i));
[x, label_index_actual]=max(TY(:,i));
if label_index_actual~=label_index_expected
MissClassificationRate_Testing=MissClassificationRate_Testing+1;
end
end
TestingAccuracy=1-MissClassificationRate_Testing/size(TV.T,2);
for i=1:size(te,1)
c=probability(i,1:size(tr,2)-1);
c=c-min(c,[],2);
c=c./max(c,[],2);
c=c+0.00001;
[c]=guiyi(c);
pro(i,:)=[c,probability(i,end)];
end
end