层次聚类算法之single-linkage和complete-linkage（C语言实现）

2023-10-11 04:48
文章标签 算法 语言 实现 层次 聚类 single complete linkage

本文主要是介绍层次聚类算法之single-linkage和complete-linkage（C语言实现），希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

层次聚类试图在不同层次上对数据集合进行划分， 从而形成树形的聚类结构。数据集的划分可采用“自底向上”的聚合策略，也可以采用“自顶向下”的分拆策略。

AGNES是一种采用自底向上的聚合策略的层次聚合算法，它先将数据集中的每个样本看作是一个初始的聚类簇，然后在算法进行的每一步中找出距离最近的两个聚类来进行合并，该过程不断的重复，直到到达预设的聚类簇的个数。

改算法的关键是如何计算聚类之间的距离， 实际上，每一个聚类是一个样本的集合，因此，只需要采用关于集合的某种距离即可。

最近距离由两个簇的最近的样本来决定， 最大距离由两个簇的最远的样本来决定，由此分别产生的AGNES算法又分别称为single-linkage和complete-linkage算法。


single-linkage算法

#include<stdio.h>
#include<stdlib.h>
#include<math.h>
#include<string.h>
#include<io.h>int sample_size;
int sample_dimension;
char filename[200];double** data;
double** distance;
int cluster_count;void initialization();
void readDataFromFile();
double calculateDistance_BetweenTwoObject(int, int);
void initializationDistanceMatrix();
void AGNES();
void findMinDistance_BetweenClsuter_MIN(int*, int*);
void combineCluster(int, int);
void writeToFile(int);int main(int argc, char* argv[])
{if( argc != 4 ){printf("This algorithm requires 4 user-specified parameter""\n\t\tthe number of sample""\n\t\tthe dimension of sample""\n\t\tthe filename contain the sample""\n\n");exit(0);}sample_size = atoi(argv[1]);sample_dimension = atoi(argv[2]);strcat(filename, argv[3]);initialization();readDataFromFile();initializationDistanceMatrix();AGNES();return 0;
}/** initialize the dynamic array for storing sample* */
void initialization()
{//initializaion the sample dataint i, j;data = (double**)malloc(sizeof(double*) * (sample_size + 1));if( !data ){printf("data malloc error: 0");exit(0);}for( i = 1; i <= sample_size; i++ ){data[i] = (double*)malloc(sizeof(double) * (sample_dimension + 1));if( !data[i] ){printf("data malloc error: %d", i);exit(0);}}//initialiation the distance datadistance = (double**)malloc(sizeof(double*) * (sample_size + 1));if( !distance ){printf("distance malloc error: 0");exit(0);}for( i = 1; i <= sample_size; i++ ){distance[i] = (double*)malloc(sizeof(double) * (sample_size + 1));if( !distance[i] ){printf("distance malloc error: %d", i);exit(0);}}//the 0th element of all row indicate the clauterID of the objectfor( i = 1; i <= sample_size; i++ ){distance[i][0] = i;}
}/** read the sample data from file* */
void readDataFromFile()
{FILE* fread;int i;int j;if( NULL == (fread = fopen(filename, "r"))){printf("open file(%s) error: ", filename);exit(0);}for( i = 1; i <= sample_size; i++ ){for( j = 1; j <= sample_dimension; j++ ){if( 1 != fscanf(fread, "%lf ", &data[i][j])){printf("fscanf error: (%d, %d)", i, j);exit(0);}}}//testprintf("print the origin data:\n");for( i = 1; i <= sample_size; i++ ){for( j = 1; j <= sample_dimension; j++ ){printf("%f\t", data[i][j]);}printf("\n");}//test END
}/** calculate distance between two objects* */
double calculateDistance_BetweenTwoObject(int firstID, int secondID)
{double distance = 0.0;int i;for( i = 1; i <= sample_dimension; i++ ){distance = distance + pow(data[firstID][i] - data[secondID][i], 2);}return sqrt(distance);
}/** calculate initialization distance matrix* */
void initializationDistanceMatrix()
{int i, j;for( i = 1; i <= sample_size; i++ ){for( j = i; j <= sample_size; j++ ){distance[i][j] = calculateDistance_BetweenTwoObject(i, j);distance[j][i] = distance[i][j];}}//testprintf("print the origin distance matrix\n");for( i = 1; i <= sample_size; i++ ){for( j = 0; j <= sample_size; j++ ){printf("%f ", distance[i][j]);}printf("\n");}//test END
}/****************************************************************************************************************						AGNES***************************************************************************************************************/
void AGNES()
{cluster_count = sample_size;int cluster_1, cluster_2;int count = 1;while( cluster_count > 3 ){printf("-------------------%d--------------------\n", count);findMinDistance_BetweenClsuter_MIN(&cluster_1, &cluster_2);combineCluster(cluster_1, cluster_2);				cluster_count--;writeToFile(count++);}
}/** find two clusters the distance between them is minimun, and store the clusterID in @cluster_1 and @cluster_2, respectively.* */
void findMinDistance_BetweenClsuter_MIN(int* cluster_1, int* cluster_2)
{int i, j;double min_distance;int flag = 1;for( i = 1; i <= sample_size; i++ ){for( j = i + 1; j <= sample_size; j++ ){if( distance[i][0] == distance[j][0] ){printf("same cluster!!!! %d and %d\n\n", i , j);continue;}else if( flag == 1 ){min_distance = distance[i][j];*cluster_1 = i;*cluster_2 = j;flag = 0;printf("----get the initial minimum distance is %f(%d, %d)\n", min_distance, i, j);continue;}if( distance[i][j] < min_distance ){min_distance = distance[i][j];*cluster_1 = i;*cluster_2 = j;}}}printf("the minimum is %f :(%d, %d)\n", min_distance, *cluster_1, *cluster_2);
}/** combine the two clusters to one* */
void combineCluster(int cluster_1, int cluster_2)
{int i;int buffer;buffer = distance[cluster_2][0];for( i = 1; i <= sample_size; i++ ){if( distance[i][0] == buffer ){distance[i][0] = distance[cluster_1][0];}}//testprintf(" the minimum distance is %f, and the object is %d and %d\n", distance[cluster_1][cluster_2], cluster_1, cluster_2);int j;for( i = 1; i <= sample_size; i++ ){for( j = 0; j <= sample_size; j++ ){printf("%f ", distance[i][j]);}printf("\n");}
}/** write the result of clustering information to file* */
void writeToFile(int round)
{int i;int j;int* auxiliary = (int*)malloc(sizeof(int) * (sample_size + 1));if( !auxiliary ){printf("auxiliary malloc error");exit(0);}for( i = 1; i <= sample_size; i++ )auxiliary[i] = 0;for( i = 1; i <= sample_size; i++ ){auxiliary[(int)distance[i][0]]++;}int *clusterID = (int*)malloc(sizeof(int) * (sample_size - round + 1));if( !clusterID ){printf("clusterID malloc error");exit(0);}int counter = 1;for( i = 1; i <= sample_size; i++ ){if( auxiliary[i] != 0 )clusterID[counter++] = i;}//testprintf("cluster ID:");for( i = 1; i <= sample_size - round; i++ ){printf("%d ", clusterID[i]);}printf("\n");//test ENDprintf("writeToFile -----------round: %d\n", round);FILE** fwrite;fwrite = (FILE**)malloc(sizeof(FILE*) * (sample_size + 1));if( !fwrite ){printf("fwrite malloc error\n");exit(0);}char filename[200] = "";char instruction[200] = "";sprintf(instruction, "md  Round_%d", round);system(instruction);for( i = 1; i <= sample_size - round; i++ ){sprintf(filename, ".//Round_%d//cluster_%d.data", round, clusterID[i]);if( NULL == (fwrite[clusterID[i]] = fopen(filename, "w"))){printf("open file(%s) error\n", filename);exit(0);}}for( i = 1; i <= sample_size; i++ ){printf("%d ", (int)distance[i][0]);for( j = 1; j <= sample_dimension; j++ ){fprintf(fwrite[(int)distance[i][0]], "%f\t", data[i][j]);printf("%f ", data[i][j]);}fprintf(fwrite[(int)distance[i][0]], "\n");printf("\n");}for( i = 1; i <= sample_size - round; i++ ){fclose(fwrite[clusterID[i]]);}
}

complete-linkage算法 

#include<stdio.h>
#include<stdlib.h>
#include<math.h>
#include<string.h>
#include<io.h>int sample_size;
int sample_dimension;
char filename[200];double** data;
double** distance;
int cluster_count;void initialization();
void readDataFromFile();
double calculateDistance_BetweenTwoObject(int, int);
void initializationDistanceMatrix();
void findMinDistance_BetweenClsuter_MAX(int*, int*);
void AGNES();
void combineCluster(int, int);
void updateDistance(int);
void writeToFile(int);int main(int argc, char* argv[])
{if( argc != 4 ){printf("This algorithm requires 4 user-specified parameter""\n\t\tthe number of sample""\n\t\tthe dimension of sample""\n\t\tthe filename contain the sample""\n\n");exit(0);}sample_size = atoi(argv[1]);sample_dimension = atoi(argv[2]);strcat(filename, argv[3]);initialization();readDataFromFile();initializationDistanceMatrix();AGNES();return 0;
}/** initialize the dynamic array for storing sample* */
void initialization()
{//initializaion the sample dataint i, j;data = (double**)malloc(sizeof(double*) * (sample_size + 1));if( !data ){printf("data malloc error: 0");exit(0);}for( i = 1; i <= sample_size; i++ ){data[i] = (double*)malloc(sizeof(double) * (sample_dimension + 1));if( !data[i] ){printf("data malloc error: %d", i);exit(0);}}//initialiation the distance datadistance = (double**)malloc(sizeof(double*) * (sample_size + 1));if( !distance ){printf("distance malloc error: 0");exit(0);}for( i = 0; i <= sample_size; i++ ){distance[i] = (double*)malloc(sizeof(double) * (sample_size + 1));if( !distance[i] ){printf("distance malloc error: %d", i);exit(0);}}//the 0th element of all row indicate the clauterID of the objectfor( i = 1; i <= sample_size; i++ ){distance[i][0] = i;}//where reserved if distance[0][i] = 1, for( i = 1; i <= sample_size; i++ ){distance[0][i] = 1;}
}/** read the sample data from file* */
void readDataFromFile()
{FILE* fread;int i;int j;if( NULL == (fread = fopen(filename, "r"))){printf("open file(%s) error: ", filename);exit(0);}for( i = 1; i <= sample_size; i++ ){for( j = 1; j <= sample_dimension; j++ ){if( 1 != fscanf(fread, "%lf ", &data[i][j])){printf("fscanf error: (%d, %d)", i, j);exit(0);}}}
}/** calculate distance between two objects* */
double calculateDistance_BetweenTwoObject(int firstID, int secondID)
{double distance = 0.0;int i;for( i = 1; i <= sample_dimension; i++ ){distance = distance + pow(data[firstID][i] - data[secondID][i], 2);}return sqrt(distance);
}/** calculate initialization distance matrix* */
void initializationDistanceMatrix()
{int i, j;for( i = 1; i <= sample_size; i++ ){for( j = i; j <= sample_size; j++ ){distance[i][j] = calculateDistance_BetweenTwoObject(i, j);distance[j][i] = distance[i][j];}}
}/****************************************************************************************************************						AGNES***************************************************************************************************************/
void AGNES()
{cluster_count = sample_size;int cluster_1, cluster_2;int count = 1;while( cluster_count > 3 ){printf("-------------------%d--------------------\n", count);findMinDistance_BetweenClsuter_MAX(&cluster_1, &cluster_2);combineCluster(cluster_1, cluster_2);updateDistance(cluster_1);		cluster_count--;writeToFile(count++);}
}/** find two clusters the distance between them is minimun, and store the clusterID in @cluster_1 and @cluster_2, respectively.* */
void findMinDistance_BetweenClsuter_MAX(int* cluster_1, int* cluster_2)
{int i, j;double min_distance;int flag = 1;int object_1;int object_2;for( i = 1; i <= sample_size; i++ ){for( j = i + 1; j <= sample_size; j++ ){if( distance[i][0] == distance[j][0] || ( distance[0][i] == 0 || distance[0][j] == 0 ) ){continue;}else if( flag == 1 ){min_distance = distance[i][j];object_1 = i;object_2 = j;flag = 0;continue;}if( distance[i][j] < min_distance ){min_distance = distance[i][j];object_1 = i;object_2 = j;}}}*cluster_1 = distance[object_1][0];*cluster_2 = distance[object_2][0];
}/** combine the two clusters to one* */
void combineCluster(int cluster_1, int cluster_2)
{int i;for( i = 1; i <= sample_size; i++ ){if( distance[i][0] == cluster_2 ){distance[i][0] = cluster_1;}}
}/** update distance data* */
void updateDistance(int clusterID)
{int i, j;int flag = 1;int save_i;for( i = 1; i <= sample_size; i++ ){if( distance[i][0] == clusterID && flag == 1 ){flag = 0;save_i = i;continue;}else if( distance[i][0] == clusterID && flag == 0 ){distance[0][i] = 0;for( j = 1; j <= sample_size; j++ ){if( distance[i][j] > distance[save_i][j] ){distance[save_i][j] = distance[i][j];}}}}for( i = 1; i <= sample_size; i++ ){distance[i][save_i] = distance[save_i][i];}
}/** write the result of clustering information to file* */
void writeToFile(int round)
{int i;int j;int* auxiliary = (int*)malloc(sizeof(int) * (sample_size + 1));if( !auxiliary ){printf("auxiliary malloc error");exit(0);}for( i = 1; i <= sample_size; i++ )auxiliary[i] = 0;for( i = 1; i <= sample_size; i++ ){auxiliary[(int)distance[i][0]]++;}int *clusterID = (int*)malloc(sizeof(int) * (sample_size - round + 1));if( !clusterID ){printf("clusterID malloc error");exit(0);}int counter = 1;for( i = 1; i <= sample_size; i++ ){if( auxiliary[i] != 0 )clusterID[counter++] = i;}printf("writeToFile -----------round: %d\n", round);FILE** fwrite;fwrite = (FILE**)malloc(sizeof(FILE*) * (sample_size + 1));if( !fwrite ){printf("fwrite malloc error\n");exit(0);}char filename[200] = "";char instruction[200] = "";sprintf(instruction, "md  Round_%d", round);system(instruction);for( i = 1; i <= sample_size - round; i++ ){sprintf(filename, ".//Round_%d//cluster_%d.data", round, clusterID[i]);if( NULL == (fwrite[clusterID[i]] = fopen(filename, "w"))){printf("open file(%s) error\n", filename);exit(0);}}for( i = 1; i <= sample_size; i++ ){printf("%d ", (int)distance[i][0]);for( j = 1; j <= sample_dimension; j++ ){fprintf(fwrite[(int)distance[i][0]], "%f\t", data[i][j]);}fprintf(fwrite[(int)distance[i][0]], "\n");}for( i = 1; i <= sample_size - round; i++ ){fclose(fwrite[clusterID[i]]);}
}


这篇关于层次聚类算法之single-linkage和complete-linkage（C语言实现）的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！


http://www.chinasem.cn/article/185619。

相关文章

基于Python实现一个图片拆分工具

基于Python实现一个图片拆分工具

《基于Python实现一个图片拆分工具》这篇文章主要为大家详细介绍了如何基于Python实现一个图片拆分工具,可以根据需要的行数和列数进行拆分,感兴趣的小伙伴可以跟随小编一起学习一下... 简单介绍先自己选择输入的图片，默认是输出到项目文件夹中，可以自己选择其他的文件夹，选择需要拆分的行数和列数，可以通过
阅读更多...
Python中将嵌套列表扁平化的多种实现方法

Python中将嵌套列表扁平化的多种实现方法

《Python中将嵌套列表扁平化的多种实现方法》在Python编程中,我们常常会遇到需要将嵌套列表（即列表中包含列表）转换为一个一维的扁平列表的需求,本文将给大家介绍了多种实现这一目标的方法,需要的朋... 目录python中将嵌套列表扁平化的方法技术背景实现步骤1. 使用嵌套列表推导式2. 使用itert
阅读更多...
Python使用pip工具实现包自动更新的多种方法

Python使用pip工具实现包自动更新的多种方法

《Python使用pip工具实现包自动更新的多种方法》本文深入探讨了使用Python的pip工具实现包自动更新的各种方法和技术,我们将从基础概念开始,逐步介绍手动更新方法、自动化脚本编写、结合CI/C... 目录1. 背景介绍1.1 目的和范围1.2 预期读者1.3 文档结构概述1.4 术语表1.4.1 核
阅读更多...
在Linux中改变echo输出颜色的实现方法

在Linux中改变echo输出颜色的实现方法

《在Linux中改变echo输出颜色的实现方法》在Linux系统的命令行环境下,为了使输出信息更加清晰、突出,便于用户快速识别和区分不同类型的信息,常常需要改变echo命令的输出颜色,所以本文给大家介... 目python录在linux中改变echo输出颜色的方法技术背景实现步骤使用ANSI转义码使用tpu
阅读更多...
Python使用python-can实现合并BLF文件

Python使用python-can实现合并BLF文件

《Python使用python-can实现合并BLF文件》python-can库是Python生态中专注于CAN总线通信与数据处理的强大工具,本文将使用python-can为BLF文件合并提供高效灵活... 目录一、python-can 库：CAN 数据处理的利器二、BLF 文件合并核心代码解析1. 基础合
阅读更多...
Python使用OpenCV实现获取视频时长的小工具

Python使用OpenCV实现获取视频时长的小工具

《Python使用OpenCV实现获取视频时长的小工具》在处理视频数据时,获取视频的时长是一项常见且基础的需求,本文将详细介绍如何使用Python和OpenCV获取视频时长,并对每一行代码进行深入解析... 目录一、代码实现二、代码解析1. 导入 OpenCV 库2. 定义获取视频时长的函数3. 打开视频文
阅读更多...
golang版本升级如何实现

golang版本升级如何实现

《golang版本升级如何实现》：本文主要介绍golang版本升级如何实现问题,具有很好的参考价值,希望对大家有所帮助,如有错误或未考虑完全的地方,望不吝赐教... 目录golanwww.chinasem.cng版本升级linux上golang版本升级删除golang旧版本安装golang最新版本总结gola
阅读更多...
Go语言中make和new的区别及说明

Go语言中make和new的区别及说明

《Go语言中make和new的区别及说明》：本文主要介绍Go语言中make和new的区别及说明,具有很好的参考价值,希望对大家有所帮助,如有错误或未考虑完全的地方,望不吝赐教... 目录1 概述2 new 函数2.1 功能2.2 语法2.3 初始化案例3 make 函数3.1 功能3.2 语法3.3 初始化
阅读更多...
SpringBoot中SM2公钥加密、私钥解密的实现示例详解

SpringBoot中SM2公钥加密、私钥解密的实现示例详解

《SpringBoot中SM2公钥加密、私钥解密的实现示例详解》本文介绍了如何在SpringBoot项目中实现SM2公钥加密和私钥解密的功能,通过使用Hutool库和BouncyCastle依赖,简化... 目录一、前言1、加密信息(示例)2、加密结果(示例)二、实现代码1、yml文件配置2、创建SM2工具
阅读更多...
Mysql实现范围分区表(新增、删除、重组、查看)

Mysql实现范围分区表(新增、删除、重组、查看)

《Mysql实现范围分区表(新增、删除、重组、查看)》MySQL分区表的四种类型（范围、哈希、列表、键值）,主要介绍了范围分区的创建、查询、添加、删除及重组织操作,具有一定的参考价值,感兴趣的可以了解... 目录一、mysql分区表分类二、范围分区（Range Partitioning1、新建分区表：2、分
阅读更多...

Copyright China编程 23002807@qq.com

沪ICP备2023033072号-2