这篇博客使用了libsvm中提供的 svm.h svm.c，然后自己编写了一个SVMclassification类，里面有数据读取，训练，预测三个主要的函数，实现了libsvm函数库的函数接口调用。而不是仅仅使用libsvm包中的提供的svm-train.exe文件，svm-train.exe文件也是编写svm-train.cpp经过编译生成的。
double svm_predict(const struct svm_model *model, const struct svm_node *x); 预测函数
int svm_save_model(const char *model_file_name, const struct svm_model *model); 模型的保存和载入struct svm_model *svm_load_model(const char *model_file_name);
当然还要选择合适的核函数和参数.
We propose that beginners try the following procedure : 1、Transform data to the format of an SVM package（读入训练数据并保存为合适的格式） 2、Conduct simple scaling on the data（归一化） 3、Consider the RBF kernel （径向基函数） 4、Use cross-validation to nd the best parameter C and gama（交叉验证选取最佳参数）5、 Use the best parameter C and to train the whole training set。 Test（使用最佳参数训练整个数据集）
libSVM是一个非常有名的SVM开源库，最近我在做分类任务，最后需要用到SVM进行分类，可是网上对于libSVM的介绍大多是matlab的，还有就是使用DOS命令调用的，直接使用libSVM的函数进行编程的介绍非常少，我来大体介绍一下我使用的情况吧。
struct svm_problem { int n; //记录样本总数 double *y; //记录样本所属类别 struct svm_node **x; //存储所有样本的特征，二维数组，一行存一个样本的所有特征};其中svm_node类型的定义如下：[cpp] view plain copyprint?
struct svm_node //用来存储输入空间中的单个特征 { int index; //该特征在特征空间中的维度编号 double value; //该特征的值 }; struct svm_node //用来存储输入空间中的单个特征{ int index; //该特征在特征空间中的维度编号 double value; //该特征的值};借用网上的一张图进行表示：
好了，知道在libsvm中特征是如何存储以后，就可以编写读取文件的函数了。以我使用svm举例，我的特征文件如下图所示：
我的读取文件的函数如下所示：[cpp] view plain copyprint?void ClassificationSVM::readTrainData(const string& featureFileName) { FILE *fp = fopen(featureFileName.c_str(), "r"); if (fp == NULL) { cout << "open feature file error!" << endl; return; } fseek(fp, 0L, SEEK_END); long end = ftell(fp); fseek(fp, 0L, SEEK_SET); long start = ftell(fp); //读取文件，直到文件末尾 while (start != end) { //FEATUREDIM是自定义变量，表示特征的维度 svm_node* features = new svm_node[FEATUREDIM + 1];//因为需要结束标记，因此申请空间时特征维度+1 for (int k = 0; k < FEATUREDIM; k++) { double value = 0; fscanf(fp, "%lf", &value); features[k].index = k + 1;//特征标号，从1开始 features[k].value = value;//特征值 } features[FEATUREDIM].index = -1;//结束标记 char c; fscanf(fp, "/n", &c); char name[100]; fgets(name, 100, fp); name[strlen(name) - 1] = '/0'; //negative sample type is 0 int type = 0; //positive sample type is 1 if (featureFileName == "PositiveFeatures.txt") type = 1; dataList.push_back(features); typeList.push_back(type); sampleNum++; start = ftell(fp); } fclose(fp); } void ClassificationSVM::readTrainData(const string& featureFileName){ FILE *fp = fopen(featureFileName.c_str(), "r"); if (fp == NULL) { cout << "open feature file error!" << endl; return; } fseek(fp, 0L, SEEK_END); long end = ftell(fp); fseek(fp, 0L, SEEK_SET); long start = ftell(fp); //读取文件，直到文件末尾 while (start != end) { //FEATUREDIM是自定义变量，表示特征的维度 svm_node* features = new svm_node[FEATUREDIM + 1];//因为需要结束标记，因此申请空间时特征维度+1 for (int k = 0; k < FEATUREDIM; k++) { double value = 0; fscanf(fp, "%lf", &value); features[k].index = k + 1;//特征标号，从1开始 features[k].value = value;//特征值 } features[FEATUREDIM].index = -1;//结束标记 char c; fscanf(fp, "/n", &c); char name[100]; fgets(name, 100, fp); name[strlen(name) - 1] = '/0'; //negative sample type is 0 int type = 0; //positive sample type is 1 if (featureFileName == "PositiveFeatures.txt") type = 1; dataList.push_back(features); typeList.push_back(type); sampleNum++; start = ftell(fp); } fclose(fp);}其中dataList和typeList分别存放特征值和该特征样本对应的标号（正或负）。三、svm训练和识别
训练时的代码如下图所示：[cpp] view plain copyprint?void ClassificationSVM::train(const string& modelFileName) { cout << "reading positivie features..." << endl; readTrainData("PositiveFeatures.txt"); cout << "reading negative features..." << endl; readTrainData("NegativeFeatures.txt"); cout << sampleNum << endl; prob.l = sampleNum;//number of training samples prob.x = new svm_node *[prob.l];//features of all the training samples prob.y = new double[prob.l];//type of all the training samples int index = 0; while (!dataList.empty()) { prob.x[index] = dataList.front(); prob.y[index] = typeList.front(); dataList.pop_front(); typeList.pop_front(); index++; } cout << "start training" << endl; svm_model *svmModel = svm_train(&prob, ¶m); cout << "save model" << endl; svm_save_model(modelFileName.c_str(), svmModel); cout << "done!" << endl; } void ClassificationSVM::train(const string& modelFileName){ cout << "reading positivie features..." << endl; readTrainData("PositiveFeatures.txt"); cout << "reading negative features..." << endl; readTrainData("NegativeFeatures.txt"); cout << sampleNum << endl; prob.l = sampleNum;//number of training samples prob.x = new svm_node *[prob.l];//features of all the training samples prob.y = new double[prob.l];//type of all the training samples int index = 0; while (!dataList.empty()) { prob.x[index] = dataList.front(); prob.y[index] = typeList.front(); dataList.pop_front(); typeList.pop_front(); index++; } cout << "start training" << endl; svm_model *svmModel = svm_train(&prob, ¶m); cout << "save model" << endl; svm_save_model(modelFileName.c_str(), svmModel); cout << "done!" << endl;}prob是svm_problem类型的对象，就是把之前读取的特征全部放入svm_problem的对象中。svm_train和svm_save_model函数都是libsvm中自带的，在svm.h中定义。分类时的代码如下所示：[cpp] view plain copyprint?void ClassificationSVM::predict(const string& featureFileName, const string& modelFileName) { std::vector<bool> judgeRight; svm_model *svmModel = svm_load_model(modelFileName.c_str()); FILE *fp; if ((fp = fopen(featureFileName.c_str(), "rt")) == NULL) return; fseek(fp, 0L, SEEK_END); long end = ftell(fp); fseek(fp, 0L, SEEK_SET); long start = ftell(fp); while (start != end) { svm_node* input = new svm_node[FEATUREDIM + 1]; for (int k = 0; k<FEATUREDIM; k++) { double value = 0; fscanf(fp, "%lf", &value); input[k].index = k + 1; input[k].value = value; } char c; fscanf(fp, "/n", &c); char name[100]; fgets(name, 100, fp); name[strlen(name) - 1] = '/0'; input[FEATUREDIM].index = -1; int predictValue = svm_predict(svmModel, input); if (featureFileName == "positive_test.txt") { if (predictValue == 0) judgeRight.push_back(false); else judgeRight.push_back(true); } else if (featureFileName == "negative_test.txt") { if (predictValue == 1) judgeRight.push_back(false); else judgeRight.push_back(true); } start = ftell(fp); } fclose(fp); int correctNum = 0; int totalNum = judgeRight.size(); for (int i = 0; i < totalNum; i++) { if (judgeRight[i] == true) correctNum++; } double precent = 1.0 * correctNum / totalNum; cout << precent << endl; } void ClassificationSVM::predict(const string& featureFileName, const string& modelFileName){ std::vector<bool> judgeRight; svm_model *svmModel = svm_load_model(modelFileName.c_str()); FILE *fp; if ((fp = fopen(featureFileName.c_str(), "rt")) == NULL) return; fseek(fp, 0L, SEEK_END); long end = ftell(fp); fseek(fp, 0L, SEEK_SET); long start = ftell(fp); while (start != end) { svm_node* input = new svm_node[FEATUREDIM + 1]; for (int k = 0; k<FEATUREDIM; k++) { double value = 0; fscanf(fp, "%lf", &value); input[k].index = k + 1; input[k].value = value; } char c; fscanf(fp, "/n", &c); char name[100]; fgets(name, 100, fp); name[strlen(name) - 1] = '/0'; input[FEATUREDIM].index = -1; int predictValue = svm_predict(svmModel, input); if (featureFileName == "positive_test.txt") { if (predictValue == 0) judgeRight.push_back(false); else judgeRight.push_back(true); } else if (featureFileName == "negative_test.txt") { if (predictValue == 1) judgeRight.push_back(false); else judgeRight.push_back(true); } start = ftell(fp); } fclose(fp); int correctNum = 0; int totalNum = judgeRight.size(); for (int i = 0; i < totalNum; i++) { if (judgeRight[i] == true) correctNum++; } double precent = 1.0 * correctNum / totalNum; cout << precent << endl;}分类时的代码与之前的代码非常类似，不多做赘述。最后注意：标准的svm只支持二分类问题，对于多分类问题，需要进行其他的处理操作。
使用VS2013创建一个新的空工程，把上图目录中的svm.cpp和svm.h复制到工程目录下，并通过在工程中右键——Add——Exsiting Item把这两个文件添加到工程中去，如下图所示。
好了，到目前为止环境就搭建好了，简单明了~注意：VS2013中使用fopen会出现一个错误，原因是VS2013自身兼容性不好，认为fopen不安全，可以通过 工程右键——Properties——C++——Preprocesser——Preprocesser Definitions中添加_CRT_SECURE_NO_WARNINGS解决该问题。同时VS2013中编译会出现strdup函数编译不过去，同样根据提示，把该函数改为_strdup即可。
