libsvm3.21在MATLAB2014a的安装应用之二：LibSVM基本应用

转自http://www.matlabsky.com/thread-12379-1-1.html

一 基本示例

代码（属性：身高，体重；标签：男 / 女）

data = [17670;180 80; 161 45; 163 47];
label = [1;1;-1;-1];
model = svmtrain(label,data);
test = [190 85];
testlabel = 1;
[predicted_label] = svmpredict(testlabel,test,model);

运行结果

optimizationfinished, #iter = 3
nu = 0.990884
obj = -1.981851, rho = -0.009074
nSV = 4, nBSV = 0
Total nSV = 4
Accuracy = 100% (1/1) (classification)

ps：accuracy = 100%，因为此处testlabel =1，而预测值也为1；若testlabel = -1，则accuracy = 0%

ps：[predicted_label,accuracy] =svmpredict(testlabel,test,model)，MATLAB提示：

Usage:

[predicted_label,accuracy, decision_values/prob_estimates] = svmpredict(testing_label_vector,testing_instance_matrix, model, 'libsvm_options')
[predicted_label] = svmpredict(testing_label_vector, testing_instance_matrix,model, 'libsvm_options')

Parameters:
  model: SVM model structure from svmtrain.
  libsvm_options:
  -b probability_estimates: whether to predict probability         estimates, 0 or 1 (default 0); one-classSVM not supported yet
  -q : quiet mode (no outputs)

故预测函数亦可为：

[predicted_label,accuracy, decision_values]= svmpredict(testlabel,test,model, model);

[predicted_label,accuracy, prob_estimates] = svmpredict(testlabel,test,model, model);

 

二 验证数据集breast_cancer

Ps：切记把数据集所在文件夹设置为当前文件夹，否则无法打开数据文件

[label_vector, instance_matrix] = libsvmread('breast_cancer.txt');

%以前500个数据为训练集，其余数据为测试集

ind = 500;

trainlabel = label_vector(1:ind,:);

traindata = instance_matrix(1:ind,:);

testlabel = label_vector(ind+1:end,:);

testdata = instance_matrix(ind+1:end,:);

model = svmtrain(trainlabel,traindata);

%检测训练模型在训练集上的分类效果

[ptrain] = svmpredict(trainlabel,traindata,model);

%检测训练模型在测试集上的分类效果

[ptest] = svmpredict(testlabel,testdata,model);

训练结果

optimization finished, #iter = 94

nu = 0.114641

obj = -48.983625, rho = 0.438680

nSV = 71, nBSV = 53

Total nSV = 71

Accuracy = 96.6% (483/500) (classification)

Accuracy = 99.4536% (182/183) (classification)

 

Ps：svmtrain函数（model = svmtrain（））

Usage: model = svmtrain(training_label_vector,training_instance_matrix, 'libsvm_options');

libsvm_options:

-s svm_type : set type of SVM (default 0)

         0 -- C-SVC          (multi-class classification)

         1 -- nu-SVC                 (multi-class classification)

         2 -- one-class SVM

         3 -- epsilon-SVR        (regression)

         4 -- nu-SVR                 (regression)

-t kernel_type : set type of kernel function (default 2)

         0 -- linear: u'*v

         1 -- polynomial:(gamma*u'*v + coef0)^degree

         2 -- radial basisfunction: exp(-gamma*|u-v|^2)

         3 -- sigmoid:tanh(gamma*u'*v + coef0)

         4 -- precomputedkernel (kernel values in training_instance_matrix)

-d degree : set degree in kernel function (default 3)

-g gamma : set gamma in kernel function (default 1/num_features)  核参数

-r coef0 : set coef0 in kernel function (default 0)

-c cost : set the parameter C of C-SVC, epsilon-SVR, and nu-SVR(default 1)

-n nu : set the parameter nu of nu-SVC, one-class SVM, and nu-SVR(default 0.5)

-p epsilon : set the epsilon in loss function of epsilon-SVR(default 0.1)

-m cachesize : set cache memory size in MB (default 100)

-e epsilon : set tolerance of termination criterion (default 0.001)

-h shrinking : whether to use the shrinking heuristics, 0 or 1(default 1)

-b probability_estimates : whether to train a SVC or SVR model forprobability estimates, 0 or 1 (default 0)

-wi weight : set the parameter C of class i to weight*C, for C-SVC(default 1)

-v n : n-fold cross validation mode

-q : quiet mode (no outputs)