用C语言写一个k_means聚类的代码

以下是一个简单的K-Means聚类的C语言实现示例：

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

#define MAX_ITERATIONS 1000
#define DATA_SIZE 100
#define K 3

// 生成随机数据
void generate_data(float data[][2], int n) {
    int i;
    srand((unsigned int)time(NULL));
    for (i = 0; i < n; i++) {
        data[i][0] = (float)(rand() % 100) / 100;
        data[i][1] = (float)(rand() % 100) / 100;
    }
}

// 计算欧氏距离
float euclidean_distance(float x1, float y1, float x2, float y2) {
    return sqrt(pow((x1 - x2), 2) + pow((y1 - y2), 2));
}

// 初始化聚类中心
void init_centers(float data[][2], int n, float centers[][2], int k) {
    int i, j, index;
    float max_dist, dist, *min_dist;
    min_dist = (float *)malloc(sizeof(float) * n);
    // 随机选择一个点作为第一个聚类中心
    index = rand() % n;
    centers[0][0] = data[index][0];
    centers[0][1] = data[index][1];
    // 选出剩下的k-1个聚类中心
    for (i = 1; i < k; i++) {
        max_dist = 0;
        // 计算每个点到当前所有聚类中心的最小距离
        for (j = 0; j < n; j++) {
            dist = euclidean_distance(data[j][0], data[j][1], centers[i-1][0], centers[i-1][1]);
            min_dist[j] = (i == 1) ? dist : fmin(dist, min_dist[j]);
            if (min_dist[j] > max_dist) {
                max_dist = min_dist[j];
                index = j;
            }
        }
        centers[i][0] = data[index][0];
        centers[i][1] = data[index][1];
    }
    free(min_dist);
}

// 执行K-Means聚类
void k_means(float data[][2], int n, float centers[][2], int k, int *labels, int max_iterations) {
    int i, j, iter, index;
    float dist, min_dist;
    // 分配每个点的标签
    for (i = 0; i < n; i++) {
        labels[i] = -1;
    }
    // 迭代更新聚类中心和标签
    for (iter = 0; iter < max_iterations; iter++) {
        int changed = 0;
        for (i = 0; i < n; i++) {
            min_dist = INFINITY;
            for (j = 0; j < k; j++) {
                dist = euclidean_distance(data[i][0], data[i][1], centers[j][0], centers[j][1]);
                if (dist < min_dist) {
                    min_dist = dist;
                    index = j;
                }
            }
            if (labels[i] != index) {
                labels[i] = index;
                changed = 1;
            }
        }
        if (!changed) {
            break;
        }
        for (j = 0; j < k; j++) {
            float sum_x = 0, sum_y = 0;
            int count = 0;
            for (i = 0; i < n; i++) {
                if (labels[i] == j) {
                    sum_x += data[i][0];
                    sum_y += data[i][1];
                    count++;
                }
            }
            if (count > 0) {
                centers[j][0] = sum_x / count;
                centers[j][1] = sum_y / count;
            }
        }
    }
}

// 输出聚类结果
void print_result(float data[][2], int n, float centers[][2], int k, int *labels) {
    int i, j;
    for (i = 0; i < k; i++) {
        printf("Cluster %d: ", i);
        for (j = 0; j < n; j++) {
            if (labels[j] == i) {
                printf("(%f, %f) ", data[j][0], data[j][1]);
            }
        }
        printf("\nCenter: (%f, %f)\n", centers[i][0], centers[i][1]);
    }
}

int main() {
    float data[DATA_SIZE][2];
    float centers[K][2];
    int labels[DATA_SIZE];
    generate_data(data, DATA_SIZE);
    init_centers(data, DATA_SIZE, centers, K);
    k_means(data, DATA_SIZE, centers, K, labels, MAX_ITERATIONS);
    print_result(data, DATA_SIZE, centers, K, labels);
    return 0;
}

这个例子中首先生成了100个二维随机数据，然后用K-Means算法将其分成3类。在K-Means算法中，首先随机选择一个点作为第一个聚类中心，然后选出剩下的k-1个聚类中心。接下来，迭代更新每个点的标签和每个聚类中心的位置，直到收敛或达到最大迭代次数。最后输出每个聚类的数据点和聚类中心的位置。