這篇博客使用了libsvm中提供的 svm.h svm.c，然后自己編寫了一個SVMclassification類，里面有數據讀取，訓練，預測三個主要的函數，實現了libsvm函數庫的函數接口調用。而不是僅僅使用libsvm包中的提供的svm-train.exe文件，svm-train.exe文件也是編寫svm-train.cpp經過編譯生成的。
double svm_predict(const struct svm_model *model, const struct svm_node *x); 預測函數
int svm_save_model(const char *model_file_name, const struct svm_model *model); 模型的保存和載入struct svm_model *svm_load_model(const char *model_file_name);
當然還要選擇合適的核函數和參數.
We propose that beginners try the following procedure : 1、Transform data to the format of an SVM package（讀入訓練數據并保存為合適的格式） 2、Conduct simple scaling on the data（歸一化） 3、Consider the RBF kernel （徑向基函數） 4、Use cross-validation to nd the best parameter C and gama（交叉驗證選取最佳參數）5、 Use the best parameter C and to train the whole training set。 Test（使用最佳參數訓練整個數據集）
libSVM是一個非常有名的SVM開源庫，最近我在做分類任務，最后需要用到SVM進行分類，可是網上對于libSVM的介紹大多是matlab的，還有就是使用DOS命令調用的，直接使用libSVM的函數進行編程的介紹非常少，我來大體介紹一下我使用的情況吧。
struct svm_problem { int n; //記錄樣本總數 double *y; //記錄樣本所屬類別 struct svm_node **x; //存儲所有樣本的特征，二維數組，一行存一個樣本的所有特征};其中svm_node類型的定義如下：[cpp] view plain copyprint?
struct svm_node //用來存儲輸入空間中的單個特征 { int index; //該特征在特征空間中的維度編號 double value; //該特征的值 }; struct svm_node //用來存儲輸入空間中的單個特征{ int index; //該特征在特征空間中的維度編號 double value; //該特征的值};借用網上的一張圖進行表示：
好了，知道在libsvm中特征是如何存儲以后，就可以編寫讀取文件的函數了。以我使用svm舉例，我的特征文件如下圖所示：
我的讀取文件的函數如下所示：[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); //讀取文件，直到文件末尾 while (start != end) { //FEATUREDIM是自定義變量，表示特征的維度 svm_node* features = new svm_node[FEATUREDIM + 1];//因為需要結束標記，因此申請空間時特征維度+1 for (int k = 0; k < FEATUREDIM; k++) { double value = 0; fscanf(fp, "%lf", &value); features[k].index = k + 1;//特征標號，從1開始 features[k].value = value;//特征值 } features[FEATUREDIM].index = -1;//結束標記 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); //讀取文件，直到文件末尾 while (start != end) { //FEATUREDIM是自定義變量，表示特征的維度 svm_node* features = new svm_node[FEATUREDIM + 1];//因為需要結束標記，因此申請空間時特征維度+1 for (int k = 0; k < FEATUREDIM; k++) { double value = 0; fscanf(fp, "%lf", &value); features[k].index = k + 1;//特征標號，從1開始 features[k].value = value;//特征值 } features[FEATUREDIM].index = -1;//結束標記 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分別存放特征值和該特征樣本對應的標號（正或負）。三、svm訓練和識別
訓練時的代碼如下圖所示：[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類型的對象，就是把之前讀取的特征全部放入svm_problem的對象中。svm_train和svm_save_model函數都是libsvm中自帶的，在svm.h中定義。分類時的代碼如下所示：[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;}分類時的代碼與之前的代碼非常類似，不多做贅述。最后注意：標準的svm只支持二分類問題，對于多分類問題，需要進行其他的處理操作。
使用VS2013創建一個新的空工程，把上圖目錄中的svm.cpp和svm.h復制到工程目錄下，并通過在工程中右鍵——Add——Exsiting Item把這兩個文件添加到工程中去，如下圖所示。
好了，到目前為止環境就搭建好了，簡單明了~注意：VS2013中使用fopen會出現一個錯誤，原因是VS2013自身兼容性不好，認為fopen不安全，可以通過 工程右鍵——Properties——C++——Preprocesser——Preprocesser Definitions中添加_CRT_SECURE_NO_WARNINGS解決該問題。同時VS2013中編譯會出現strdup函數編譯不過去，同樣根據提示，把該函數改為_strdup即可。
