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

如何使用Java实现请求deepseek

如何使用Java实现请求deepseek

《如何使用Java实现请求deepseek》这篇文章主要为大家详细介绍了如何使用Java实现请求deepseek功能,文中的示例代码讲解详细,感兴趣的小伙伴可以跟随小编一起学习一下... 目录1.deepseek的api创建2.Java实现请求deepseek2.1 pom文件2.2 json转化文件2.2
阅读更多...
python使用fastapi实现多语言国际化的操作指南

python使用fastapi实现多语言国际化的操作指南

《python使用fastapi实现多语言国际化的操作指南》本文介绍了使用Python和FastAPI实现多语言国际化的操作指南,包括多语言架构技术栈、翻译管理、前端本地化、语言切换机制以及常见陷阱和... 目录多语言国际化实现指南项目多语言架构技术栈目录结构翻译工作流1. 翻译数据存储2. 翻译生成脚本
阅读更多...
如何通过Python实现一个消息队列

如何通过Python实现一个消息队列

《如何通过Python实现一个消息队列》这篇文章主要为大家详细介绍了如何通过Python实现一个简单的消息队列,文中的示例代码讲解详细,感兴趣的小伙伴可以跟随小编一起学习一下... 目录如何通过 python 实现消息队列如何把 http 请求放在队列中执行1. 使用 queue.Queue 和 reque
阅读更多...
Python如何实现PDF隐私信息检测

Python如何实现PDF隐私信息检测

《Python如何实现PDF隐私信息检测》随着越来越多的个人信息以电子形式存储和传输,确保这些信息的安全至关重要,本文将介绍如何使用Python检测PDF文件中的隐私信息,需要的可以参考下... 目录项目背景技术栈代码解析功能说明运行结php果在当今，数据隐私保护变得尤为重要。随着越来越多的个人信息以电子形
阅读更多...
使用 sql-research-assistant进行 SQL 数据库研究的实战指南(代码实现演示)

使用 sql-research-assistant进行 SQL 数据库研究的实战指南(代码实现演示)

《使用sql-research-assistant进行SQL数据库研究的实战指南(代码实现演示)》本文介绍了sql-research-assistant工具,该工具基于LangChain框架,集... 目录技术背景介绍核心原理解析代码实现演示安装和配置项目集成LangSmith 配置（可选）启动服务应用场景
阅读更多...
使用Python快速实现链接转word文档

使用Python快速实现链接转word文档

《使用Python快速实现链接转word文档》这篇文章主要为大家详细介绍了如何使用Python快速实现链接转word文档功能,文中的示例代码讲解详细,感兴趣的小伙伴可以跟随小编一起学习一下... 演示代码展示from newspaper import Articlefrom docx import
阅读更多...
前端原生js实现拖拽排课效果实例

前端原生js实现拖拽排课效果实例

《前端原生js实现拖拽排课效果实例》：本文主要介绍如何实现一个简单的课程表拖拽功能,通过HTML、CSS和JavaScript的配合,我们实现了课程项的拖拽、放置和显示功能,文中通过实例代码介绍的... 目录1. 效果展示2. 效果分析2.1 关键点2.2 实现方法3. 代码实现3.1 html部分3.2
阅读更多...
Java深度学习库DJL实现Python的NumPy方式

Java深度学习库DJL实现Python的NumPy方式

《Java深度学习库DJL实现Python的NumPy方式》本文介绍了DJL库的背景和基本功能,包括NDArray的创建、数学运算、数据获取和设置等,同时,还展示了如何使用NDArray进行数据预处理... 目录1 NDArray 的背景介绍1.1 架构2 JavaDJL使用2.1 安装DJL2.2 基本操
阅读更多...
最长公共子序列问题的深度分析与Java实现方式

最长公共子序列问题的深度分析与Java实现方式

《最长公共子序列问题的深度分析与Java实现方式》本文详细介绍了最长公共子序列（LCS）问题,包括其概念、暴力解法、动态规划解法,并提供了Java代码实现,暴力解法虽然简单,但在大数据处理中效率较低,... 目录最长公共子序列问题概述问题理解与示例分析暴力解法思路与示例代码动态规划解法DP 表的构建与意义动
阅读更多...
java父子线程之间实现共享传递数据

java父子线程之间实现共享传递数据

《java父子线程之间实现共享传递数据》本文介绍了Java中父子线程间共享传递数据的几种方法,包括ThreadLocal变量、并发集合和内存队列或消息队列,并提醒注意并发安全问题... 目录通过 ThreadLocal 变量共享数据通过并发集合共享数据通过内存队列或消息队列共享数据注意并发安全问题总结在 J
阅读更多...

Copyright China编程 23002807@qq.com

沪ICP备2023033072号-2