K均值算法用c语言实现

以下是用 C 语言实现 K 均值算法的示例代码：

#include <stdio.h>
#include <stdlib.h>
#include <math.h>

#define MAX_ITERATIONS 100      // 最大迭代次数
#define NUM_POINTS 10           // 数据点数量
#define NUM_CLUSTERS 2          // 聚类数量

// 定义数据点结构体
typedef struct {
    double x, y;
} Point;

// 计算两个点之间的距离
double distance(Point p1, Point p2) {
    double dx = p1.x - p2.x;
    double dy = p1.y - p2.y;
    return sqrt(dx * dx + dy * dy);
}

// 初始化聚类中心点
void init_clusters(Point* data, Point* clusters) {
    // 将前两个数据点作为初始聚类中心点
    clusters[0] = data[0];
    clusters[1] = data[1];
}

// 将数据点划分到最近的聚类中心点
void classify_points(Point* data, Point* clusters, int* assignments) {
    for (int i = 0; i < NUM_POINTS; i++) {
        double min_distance = INFINITY;
        int min_index = -1;
        for (int j = 0; j < NUM_CLUSTERS; j++) {
            double d = distance(data[i], clusters[j]);
            if (d < min_distance) {
                min_distance = d;
                min_index = j;
            }
        }
        assignments[i] = min_index;
    }
}

// 重新计算聚类中心点
void update_clusters(Point* data, Point* clusters, int* assignments) {
    int counts[NUM_CLUSTERS] = {0};
    double sum_x[NUM_CLUSTERS] = {0.0};
    double sum_y[NUM_CLUSTERS] = {0.0};
    for (int i = 0; i < NUM_POINTS; i++) {
        int cluster = assignments[i];
        counts[cluster]++;
        sum_x[cluster] += data[i].x;
        sum_y[cluster] += data[i].y;
    }
    for (int j = 0; j < NUM_CLUSTERS; j++) {
        if (counts[j] > 0) {
            clusters[j].x = sum_x[j] / counts[j];
            clusters[j].y = sum_y[j] / counts[j];
        }
    }
}

// 打印聚类结果
void print_clusters(Point* clusters) {
    printf("Clusters:\n");
    for (int i = 0; i < NUM_CLUSTERS; i++) {
        printf("(%f, %f)\n", clusters[i].x, clusters[i].y);
    }
}

int main() {
    // 初始化数据点
    Point data[NUM_POINTS] = {{1, 1}, {2, 1}, {4, 3}, {5, 4}, {7, 5},
                              {10, 7}, {11, 5}, {12, 6}, {14, 7}, {15, 5}};
    // 初始化聚类中心点
    Point clusters[NUM_CLUSTERS];
    init_clusters(data, clusters);
    // 迭代计算聚类结果
    int assignments[NUM_POINTS];
    for (int i = 0; i < MAX_ITERATIONS; i++) {
        classify_points(data, clusters, assignments);
        update_clusters(data, clusters, assignments);
    }
    // 打印聚类结果
    print_clusters(clusters);
    return 0;
}

这个示例代码演示了如何使用 K 均值算法将 10 个二维数据点划分为 2 个聚类。