K-Means源代码

K-Means源代码

        作者：liangdas

        出处：简单点儿，通俗点儿，机器学习 http://write.blog.csdn.net/postedit/25512617

        下面是我写的K-Means的源代码，分别有三个文件，一个是K-Means.h头文件，一个是K-Means.c文件，另外一个是Main.cpp文件。K-Means.h和K-Means.c文件中引用了系统的stdio.h，stdlib.h文件，是因为里面用到了printf和exit函数，如果去掉这两个函数，也就可以去掉stdio.h，stdlib.h文件的引用，那么这个K-Means.h和K-Means.c文件就都是用C自己写的啦，的可移植性就更强啦！

        后面的main.cpp是介绍怎么使用的，输入是按txt格式存贮的，存贮格式是：

sample number(样本总数)

feature number(特征维数)

intend class number(待分类的类别)

feature list as(特征列表):

feature1 feature2 ...

feature1 feature2 ...

......

        当然可以自己定义数据的格式，并重先写LoadPatterns()函数。

K-Means.h

/************************************Author: liangdas *Time: 20140504*Version: 0_20140504*Contaction: *QQ: 358536026  Email: [e-mail]*Working place: Beijing Samsuang Telecom&Technology Institute************************************/#ifndef __K_MEAN_H__#define __K_MEAN_H__#ifdef __cplusplusextern "C"{#endif#define         SUCCESS         1#define         FAILURE         0#define         TRUE            1#define         FALSE           0#define         MAX_DIM20//特征维数#define         MAX_SAMPLES2000//一个类别包含的样本个数#define         MAX_CLUSTER10//最大类别数目typedef struct stCluster{double Center[MAX_DIM];int Member[MAX_SAMPLES];  int NumMembers;}CLASSCLUSTER, *PCLASSCLUSTER;/**************************************************************** Function: ReClassify()* Description: 重新计算样本所属的类别* Input&Output:* Returns:****************************************************************/void ReClassify(double** Pattern, int NumSamples, PCLASSCLUSTER Cluster, int ClusterNum, int NumDim);/**************************************************************** Function: CalcNewClustCenters()* Description: 重新计算类别中心* Input&Output:* Returns:****************************************************************/int CalcNewClustCenters(double** Pattern, int NumSamples, PCLASSCLUSTER Cluster,  int ClusterNum, int NumDim);/**************************************************************** Function: CalcuDistance()* Description: 样本序号p，到第c个类别的距离* Input&Output:* Returns:****************************************************************/double CalcuDistance(int sampleID, int clusterID, double** Pattern, int NumSamples,    PCLASSCLUSTER Cluster, int ClusterNum, int NumDim);/**************************************************************** Function: FindClosestCluster()* Description: 找到样本序号为sampleID的样本，所属的类别* Input&Output:* Returns:****************************************************************/int FindClosestCluster(int sampleID, double** Pattern, int NumSamples, PCLASSCLUSTER Cluster, int ClusterNum, int NumDim);/**************************************************************** Function: LoadPatterns()* Descrption: 通过问卷名字，加载样本列表* Input&OutPut:* Return:* File format: 样本数 特征维数 待分类类别数目 样本。。。****************************************************************/int  LoadPatterns(char *fname, double** Pattern, int* pNumPatterns,   PCLASSCLUSTER Cluster, int* pClusterNum, int* pNumDim);/**************************************************************** Function: InitClusters()* Description: 指定初始类别中心，这个函数取的事样本序列的前ClusterNum* 个样本作为聚类的初始类别中心* Input&Output:* Returns:****************************************************************/void InitClusters(double** Pattern, int NumSamples, PCLASSCLUSTER Cluster,  int ClusterNum, int NumDim);/**************************************************************** Function: RunKMeans()* Description: 执行K-Means分类* Input&Output:* Returns:****************************************************************/void RunKMeans(double** Pattern, int NumSamples, PCLASSCLUSTER Cluster,   int ClusterNum, int NumDim, int nIterTimes);/**************************************************************** Function: SaveClusters()* Description: 保存聚类中心的结果* Input&Output:* Returns:****************************************************************/void SaveCenters(char* pFilePath, PCLASSCLUSTER Cluster, int ClusterNum, int NumDim);/**************************************************************** Function: SaveClusters()* Description: 保存聚类的样本的结果* Input&Output:* Returns:****************************************************************/void SaveClusters(char* pFilePath, double** Pattern, int NumSamples, PCLASSCLUSTER Cluster,   int ClusterNum, int NumDim);#ifdef __cplusplus}#endif#endif

K-Means.c

/************************************Author: liangdas *Time: 20140504*Version: 0_20140504*Contaction: *QQ: 358536026  Email: [e-mail]*Working place: Beijing Samsuang Telecom&Technology Institute************************************/#include <stdlib.h>#include <io.h>#include <stdio.h>#include "K_Means.h"#ifdef __cplusplusextern "C"{#endif/********************************************************* Function: LoadPatterns()* Descrption: 通过问卷名字，加载样本列表* Input&OutPut:* Return:* File format: 样本数 特征维数 待分类类别数目 样本。。。*********************************************************/int LoadPatterns(char *fname, double** Pattern, int* pNumPatterns,  PCLASSCLUSTER Cluster, int* pClusterNum, int* pNumDim){FILE* InFilePtr;int    i,j;double x;if((InFilePtr = fopen(fname, "rt")) == NULL){return FAILURE;}fscanf(InFilePtr, "%d", pNumPatterns);  // Read # of patternsfscanf(InFilePtr, "%d", pNumDim);   // Read dimension of vectorfscanf(InFilePtr, "%d", pClusterNum);  // Read # of clusters for K-Meansfor (i=0; i<*pNumPatterns; i++)  // For each vector{         for (j=0; j<*pNumDim; j++) {       // create a patternfscanf(InFilePtr,"%lg",&x);       // consisting of all elementsPattern[i][j]=x;} /* endfor */} /* endfor */return SUCCESS;}/**************************************************************** Function: InitClusters()* Description: 指定初始类别中心，这个函数取的事样本序列的前ClusterNum样本作为聚类的初始类别中心* Input&Output:* Returns:****************************************************************/void InitClusters(double** Pattern, int NumSamples, PCLASSCLUSTER Cluster, int ClusterNum, int NumDim){int i,j;printf("Initial cluster centers:\n");if(ClusterNum > NumSamples){printf("class number exceed to sample number\n");}for (i=0; i<ClusterNum; i++) {Cluster[i].Member[0] = i;for (j=0; j<NumDim; j++) {Cluster[i].Center[j] = Pattern[i][j];} /* endfor */} /* endfor */for (i=0; i<ClusterNum; i++) {printf("ClusterCenter[%d]=(%f,%f)\n", i, Cluster[i].Center[0], Cluster[i].Center[1]);} /* endfor */printf("\n");}/**************************************************************** Function: RunKMeans()* Description: 执行K-Means分类* Input&Output:* Returns:****************************************************************/void RunKMeans(double** Pattern, int NumSamples, PCLASSCLUSTER Cluster, int ClusterNum, int NumDim, int nIterTimes){int nStopTag;int pass;int nCurTimes = 0;nStopTag=FALSE;while (nStopTag == FALSE){printf("iteration time = %d\n", nCurTimes);ReClassify(Pattern, NumSamples, Cluster, ClusterNum, NumDim);nStopTag = CalcNewClustCenters(Pattern, NumSamples, Cluster, ClusterNum, NumDim);nCurTimes++;if(nCurTimes>=nIterTimes){nStopTag = TRUE;}}}/**************************************************************** Function: CalcuDistance()* Description: 样本序号sampleID，到第c个类别的距离* Input&Output:* Returns:****************************************************************/double CalcuDistance(int sampleID, int clusterID, double** Pattern, int NumSamples, PCLASSCLUSTER Cluster, int ClusterNum, int NumDim){   // Calc Euclidean norm of vector differencedouble dist,x;                          // between pattern vector, sampleID, and clusterint i;                                  // center, clusterID.char *pnum;dist = 0;for (i=0; i<NumDim; i++){x = (Cluster[clusterID].Center[i]-Pattern[sampleID][i])*(Cluster[clusterID].Center[i]-Pattern[sampleID][i]);dist += (Cluster[clusterID].Center[i]-Pattern[sampleID][i])*(Cluster[clusterID].Center[i]-Pattern[sampleID][i]);} /* endfor */return dist;}/**************************************************************** Function: FindClosestCluster()* Description: 找到样本序号为sampleID的样本，所属的类别* Input&Output:* Returns:****************************************************************/int FindClosestCluster(int sampleID, double** Pattern, int NumSamples, PCLASSCLUSTER Cluster, int ClusterNum, int NumDim){int i, ClustID;double MinDist, d;MinDist =9.9e+99;ClustID=-1;for (i=0; i<ClusterNum; i++){d=CalcuDistance(sampleID, i, Pattern, NumSamples, Cluster, ClusterNum, NumDim);if (d<MinDist){MinDist=d;ClustID=i;}}if (ClustID<0){//printf("Aaargh");exit(0);} /* endif */return ClustID;}/**************************************************************** Function: ReClassify()* Description: 重新计算样本所属的类别* Input&Output:* Returns:****************************************************************/void ReClassify(double** Pattern, int NumSamples, PCLASSCLUSTER Cluster, int ClusterNum, int NumDim){int i,sampleID,Clustid,MemberIndex;//Clear membership list for all current clustersfor (i=0; i<ClusterNum; i++){Cluster[i].NumMembers = 0;}for (sampleID=0; sampleID<NumSamples; sampleID++){//Find cluster center to which the pattern is closestClustid= FindClosestCluster(sampleID, Pattern, NumSamples, Cluster, ClusterNum, NumDim);MemberIndex=Cluster[Clustid].NumMembers;Cluster[Clustid].Member[MemberIndex]=sampleID;Cluster[Clustid].NumMembers++;} /* endfor */}/**************************************************************** Function: CalcNewClustCenters()* Description: 重新计算类别中心* Input&Output:* Returns:****************************************************************/int  CalcNewClustCenters(double** Pattern, int NumSamples, PCLASSCLUSTER Cluster, int ClusterNum, int NumDim){int ConvFlag,VectID,i,j,k;double tmp[MAX_DIM];ConvFlag=TRUE;//printf("The new cluster centers are now calculated as:\n");for (i=0; i<ClusterNum; i++)   //for each cluster{for(j=0; j<NumDim; j++){            // clear workspacetmp[j]=0.0;} /* endfor */for(j=0; j<Cluster[i].NumMembers; j++){ //traverse member vectorsVectID = Cluster[i].Member[j];for (k=0; k<NumDim; k++){         //traverse elements of vectortmp[k] += Pattern[VectID][k];       // add (member) pattern elmnt into temp} /* endfor */} /* endfor */for (k=0; k<NumDim; k++) {tmp[k] = tmp[k]/Cluster[i].NumMembers;if (tmp[k] != Cluster[i].Center[k]){ConvFlag=FALSE;}Cluster[i].Center[k]=tmp[k];} /* endfor */} /* endfor */return ConvFlag;}/**************************************************************** Function: SaveClusters()* Description: 保存聚类中心的结果* Input&Output:* Returns:****************************************************************/void SaveCenters(char* pFilePath, PCLASSCLUSTER Cluster, int ClusterNum, int NumDim){int i,j;FILE* fpResultFile;fpResultFile = fopen(pFilePath, "wt");if(fpResultFile == 0){printf("open file %s error\n", pFilePath);return;}fprintf(fpResultFile, "x\ty\tlabel\t\n");for (i=0; i<ClusterNum; i++){Cluster[i].Member[0] = i;for(j=0; j<NumDim; j++){fprintf(fpResultFile, "%f\t", Cluster[i].Center[j]);}fprintf(fpResultFile, "%d\n", i);} /* endfor */fclose(fpResultFile);}/**************************************************************** Function: SaveClusters()* Description: 保存聚类的结果* Input&Output:* Returns:****************************************************************/void SaveClusters(char* pFilePath, double** Pattern, int NumSamples, PCLASSCLUSTER Cluster,  int ClusterNum, int NumDim){FILE* fpResultFile = 0;int i = 0, j = 0, k = 0;int nSampleID = 0;fpResultFile = fopen(pFilePath, "wt");if(fpResultFile == 0){printf("open file %s error\n", pFilePath);return;}fprintf(fpResultFile, "x\ty\tlabel\t\n");for (i=0; i<ClusterNum; i++){for(j=0; j<Cluster[i].NumMembers; j++){nSampleID = Cluster[i].Member[j];for(k=0; k<NumDim; k++){fprintf(fpResultFile, "%hg\t", Pattern[nSampleID][k]);}fprintf(fpResultFile, "%d\n", i); //所属的类别}} /* endfor */fclose(fpResultFile);}#ifdef __cplusplus}#endif

Main.cpp

#include <stdlib.h>#include <stdio.h>#include <io.h>#include <string.h>#include "K_Means.h"#define MAX_ITER_TIMES  1000int main(int argc, char *argv[]){//main procedure//System kmeans;//double       Pattern[MAX_SAMPLES][MAX_DIM+1];double**Pattern;CLASSCLUSTER Cluster[MAX_CLUSTER];int NumSamples;// Number of patternsint NumDim;// Number of dimensions in vectorint ClusterNum;// Number of clustersint i = 0;Pattern = (double**)malloc(sizeof(double*)*MAX_SAMPLES);for(i=0; i<MAX_SAMPLES; i++){Pattern[i] = (double*)malloc(sizeof(double)*MAX_DIM);}char* pFilePath = argv[1];if (argc<2){printf("usage: intput k_means file\n");exit(0);}if (LoadPatterns(pFilePath, (double**)Pattern, &NumSamples, Cluster, &ClusterNum, &NumDim) == FAILURE){printf("read file %s error\n", pFilePath);exit(0);}//#if 0InitClusters((double**)Pattern, NumSamples, Cluster, ClusterNum, NumDim);#elseCluster[0].Center[0] = 21;Cluster[0].Center[1] = 377;Cluster[1].Center[0] = 20;Cluster[1].Center[1] = 377;Cluster[2].Center[0] = 20;Cluster[2].Center[1] = 376;#endifRunKMeans((double**)Pattern, NumSamples, Cluster, ClusterNum, NumDim, MAX_ITER_TIMES);SaveClusters("cluster.txt", (double**)Pattern, NumSamples, Cluster, ClusterNum, NumDim);SaveCenters("center.txt", Cluster, ClusterNum, NumDim);//ShowClusters();//delete memoryfor(i=0; i<MAX_SAMPLES; i++){free(Pattern[i]);}free(Pattern);}

ps：使用或者转载请标明出处，禁止以商业为目的的使用。

如果有需要word版，或者是pdf版的，请与我联系，QQ：358536026