breast_cancer_wisconsin.asv

使用高斯模型对威斯康辛州大学医学院长期乳腺癌数据进行了贝叶斯模式识别。识别率为95以上

Total  = length(data(:,1));
VaribleNumber = length(data(1,:));

TrainNumber = floor(Total/2);
TestNumber = Total - TrainNumber-1;
TestMatrix = data(1:TrainNumber,:);
TrainMatrix = data(TrainNumber+1:end,:);

Answer = strcmp(textdata(1:Total,2),'B');

TrainNumber_B =  sum(Answer(1:TrainNumber));
TrainNumber_M = TrainNumber - TrainNumber_B;
P_B = TrainNumber_B / TrainNumber;
P_M = TrainNumber_M / TrainNumber;

Train_B_Matrix = TrainMatrix(Answer(1:TrainNumber) == 1,:);
Train_M_Matrix = TrainMatrix(Answer(1:TrainNumber) == 0,:);

B_MeanMatrix = mean(Train_B_Matrix);
M_MeanMatrix = mean(Train_M_Matrix);
B_ConvarianceMatrix = cov(Train_B_Matrix);
M_ConvarianceMatrix = cov(Train_M_Matrix);

%zero-one loss function
TestCondition_B = zeros(TestNumber,1);
invB_ConvarianceMatrix = inv(B_ConvarianceMatrix);
detB_ConvarianceMatrix = sqrt(det(B_ConvarianceMatrix));

TestCondition_M = zeros(TestNumber,1);
invM_ConvarianceMatrix = inv(M_ConvarianceMatrix);
detM_ConvarianceMatrix = sqrt(det(M_ConvarianceMatrix));
pi2 = (2*pi)^(VaribleNumber/2);

for i = 1:TestNumber
    TestCondition_B(i,1) = exp(-.5*(TestMatrix(i,:)-B_MeanMatrix)*invB_ConvarianceMatrix*(TestMatrix(i,:)-B_MeanMatrix)')/detB_ConvarianceMatrix/pi2;
end
for i = 1:TestNumber
    TestCondition_M(i,1) = exp(-.5*(TestMatrix(i,:)-M_MeanMatrix)*invM_ConvarianceMatrix*(TestMatrix(i,:)-M_MeanMatrix)')/detM_ConvarianceMatrix/pi2;
end

Result = zeros(TestNumber,1);
Result(find(TestCondition_B > TestCondition_M)) = 1;
performance = sum((Result == Answer(TrainNumber+1:end,1))) / TestNumber;