K-means算法

一、 实验目的：
1、 用k-means算法实现n个对象的数据集的聚类划分
2、 体会k-means算法在聚类划分过程中的优缺点
二、 实验内容：
实验题目：设数据集S={(1,1), (2,1), (1,2), (2,2), (4,3), (5,3), (4,4), (5,4)}，令k=2, 试用k-means算法将X划分为k个簇

过程代码：

#include"stdio.h"
#include"stdlib.h"
#include<math.h>
#include<iostream>
using namespace std;
#define N 8 
#define k 2

typedef struct{ 
	float x;
	float y;
}Point;

Point point[N]={
	{1.0, 1.0}, {2.0, 1.0}, {1.0, 2.0}, {2.0, 2.0}, {4.0,3.0},
	{5.0, 3.0}, {4.0, 4.0}, {5.0, 4.0}
}; 
int center[N];
Point mean[k];


float getdistance(Point pointl, Point point2);
void cluster();
float gete();
void getmean(int center[N]);

int main(){
	mean[0].x =point[0].x;
	mean[0].y=point[0].y;
	
	mean[1].x =point[3].x;
	mean[1].y =point[3].y;
	
	mean[2].x =point[6].x;
	mean[2].y =point[6].y;
	int number=0;
    float temp1, temp2; 
	//第一次聚类
	cluster ();
	number++;//number统计进行了几次聚类
	//对第一次累类的结果进行误差平方和的计算
	temp1 = gete();
	printf ("the error1 is:%f\n", temp1);
	//针矿第一次聚类的结果，重新计算是类中心
	getmean(center);
	//第二次聚类
	cluster ();
	number++;
	temp2= gete();
	printf ("the error2 is:%f\n", temp2);
	//送代循环，直到两沈送代误差的差值在一定阈值范围内，则送代停止
	while (fabs(temp1-temp2)> 0.5){
		temp1 = temp2;
		getmean(center);
		cluster();
		temp2 = gete();
		number++;
		printf ("the error%d is:%f\n", number, temp2);
	}
	printf ("the total number of cluster is:%d\n", number);
    system ("pause");
	return 0;
}

//计算距离 
float getdistance(Point point1, Point point2){ 
	float d;
	d=sqrt((point1.x-point2.x)*(point1.x-point2.x) + (point1.y-point2.y)*(point1.y-point2.y));
	return d;
}

 //聚类函数
void cluster(){
	float distance[N][k];
	for (int i =0; i<N; i++){
		for(int j=0;j<k;j++){
			distance[i][j]= getdistance(point[i], mean[j]);
		}
		float min =9999.0;
		for (int j=0; j<k;j++){
			if (distance[i][j] <min){
				min = distance[i][j];
				center[i] =j;
			}
		}
		printf("(%.0f,%.0f)\t in cluster-%d\n", point[i].x, point[i].y, center[i] +1);
	}
}
float gete(){
	float cnt=0, sum=0;
	for (int i =0;i <N; i++){	
		for (int j=0; j<k; i++){
			if (center[i]== j)
				cnt =getdistance(point[i], mean[j]);
		}
		sum+=cnt;
	}
	return sum;
}

//重新计算簇中心 
void getmean(int center[N]){
	Point sum;
	int count;
	for (int i=0;i<N;i++){
		sum.x = 0.0;
		sum.y = 0.0;
		count = 0;
		for(int j=0;j<N;j++){
			if(center[j]==i){
				sum.x+=point[j].x;
				sum.y+=point[j].y;
				count++;
			}
		}
		mean[i].x = sum.x/count;
		mean[i].y = sum.y/count;
	}
	for(int i=0;i<k;i++){
		printf("the new center point of %d is:\t(%f,%f)\n",i+1,mean[i].x,mean[i].y);
	}
}