C0 的簇心为： 1.7962962962962965, 1.7986111111111114

C0 的簇心为： 1.7998971193415638, 1.7999614197530864

#include <iostream>
#include <cstdlib>
#include <ctime>
#include <vector>
#include <cmath>using namespace std;class Cluster//聚类，每个聚类都包含两个属性，一个是簇心的属性（维数），另一个是距离本簇心最近的样本点
{
public:vector <double> centroid;//存放簇心的属性（维数）vector <int> samples;//存放属于相同簇心样本的下标
};double CalculateDistance(vector<double> a, vector<double> b)//计算两个向量之间的距离
{int len1 = a.size();int len2 = b.size();if(len1 != len2)cerr<<"Dimensions of two vectors must be same!!\n";double temp = 0;for(int i = 0; i  < len1; ++i)temp += pow(a[i]-b[i], 2);return sqrt(temp);
}//max_iteration表示最大的迭代次数，min_move_distance
vector<Cluster> KMeans(vector<vector<double> >data_set, int k, int max_iteration, double threshold)
{int row_number = data_set.size();//数据的个数int col_number = data_set[0].size();//每个向量(属性)的维数//初始随机选取k个质心vector<Cluster> cluster(k);//存放k个簇心。vector<T> v(n,i)形式，v包含n 个值为 i 的元素srand((int)time(0));for(int i = 0; i < k; ++i){int c = rand()%row_number;cluster[i].centroid = data_set[c];//把第c个作为簇心，并把它相应的属性赋值给centroid}//iterationint iter = 0;while(iter < max_iteration){iter++;for(int i = 0; i < k; ++i)cluster[i].samples.clear();//找出每个样本点所属的质心for(int i = 0; i < row_number; ++i){double min_distance = INT_MAX;int index = 0;//计算离样本点i最近的质心for(int j = 0; j < k; ++j){double temp_distance = CalculateDistance(data_set[i], cluster[j].centroid);if(min_distance > temp_distance){min_distance = temp_distance;index = j;}}cluster[index].samples.push_back(i);//把第i个样本点放入，距离其最近的质心的samples}double max_move_distance = INT_MIN;//更新簇心for(int i = 0; i < k; ++i){vector<double> temp_value(col_number, 0.0);for(int num = 0; num < cluster[i].samples.size(); ++num)//计算每个样本的属性之和{int temp_same = cluster[i].samples[num];for(int j = 0; j < col_number; ++j)temp_value[j] += data_set[temp_same][j];}vector<double> temp_centroid = cluster[i].centroid;for(int j = 0; j < col_number; ++j)cluster[i].centroid[j] = temp_value[j]/cluster[i].samples.size();//计算从上一个簇心移动到当前新的簇心的距离double temp_distance = CalculateDistance(temp_centroid, cluster[i].centroid);if(max_move_distance < temp_distance)max_move_distance = temp_distance;}if(max_move_distance < threshold)break;}return cluster;
}int main()
{int threshold = 0.001;//当从上一个簇心移动到当前粗心的距离几乎不变时，可以结束。这里用threshold作为阈值vector <vector<double> >data_set(9, vector<double>(2, 0.0));int point_number;cin>>point_number;for(int i = 0; i < point_number; ++i){for(int j = 0; j < 2; ++j)cin>>data_set[i][j];}int col = data_set[0].size();vector<Cluster> cluster_res = KMeans(data_set, 2, 200, threshold);for(int i = 0; i < cluster_res.size(); ++i){cout<<"Cluster "<<i<<" : "<<endl;cout<<"\t"<<"Centroid: ";//<<endl;cout<<"(";for(int j = 0; j < cluster_res[i].centroid.size()-1; ++j)cout<< cluster_res[i].centroid[j]<<",";cout<<cluster_res[i].centroid[cluster_res[i].centroid.size()-1]<<")"<<endl;cout<<"\t"<<"Samples: ";for(int j = 0; j < cluster_res[i].samples.size(); ++j){int c = cluster_res[i].samples[j];cout<<"(";for(int m = 0; m < col-1; ++m)cout<<data_set[c][m]<<",";cout<<data_set[c][col-1]<<")  ";}cout<<endl;}return 0;
}/**1 1
2 1
1 2
2 2
3 3
8 8
8 9
9 8
9 9*/