kmeans聚类算法c代码

下面是K-means聚类算法的C语言实现代码：

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

#define K 3 // 聚类数
#define N 10 // 数据点数
#define D 2 // 数据维度

// 随机生成数据集
void generate_data(float data[][D], int n) {
    srand((unsigned int) time(NULL));
    for (int i = 0; i < n; i++) {
        for (int j = 0; j < D; j++) {
            data[i][j] = (float) rand() / RAND_MAX;
        }
    }
}

// 计算两个点之间的距离
float distance(float *a, float *b) {
    float diff[D];
    for (int i = 0; i < D; i++) {
        diff[i] = a[i] - b[i];
    }
    float dist = 0;
    for (int i = 0; i < D; i++) {
        dist += pow(diff[i], 2);
    }
    return sqrt(dist);
}

int main() {
    float data[N][D];
    generate_data(data, N);

    float centroids[K][D];
    for (int i = 0; i < K; i++) {
        for (int j = 0; j < D; j++) {
            centroids[i][j] = data[i][j];
        }
    }

    int assignments[N];
    float distances[N];

    int changed = 1;
    while (changed) {
        changed = 0;

        // 计算每个点到每个聚类中心的距离
        for (int i = 0; i < N; i++) {
            float min_dist = INFINITY;
            int min_idx;
            for (int j = 0; j < K; j++) {
                float dist = distance(data[i], centroids[j]);
                if (dist < min_dist) {
                    min_dist = dist;
                    min_idx = j;
                }
            }
            if (assignments[i] != min_idx) {
                changed = 1;
            }
            assignments[i] = min_idx;
            distances[i] = min_dist;
        }

        // 更新聚类中心
        for (int i = 0; i < K; i++) {
            float sum[D] = {0};
            int count = 0;
            for (int j = 0; j < N; j++) {
                if (assignments[j] == i) {
                    for (int k = 0; k < D; k++) {
                        sum[k] += data[j][k];
                    }
                    count++;
                }
            }
            if (count > 0) {
                for (int k = 0; k < D; k++) {
                    centroids[i][k] = sum[k] / count;
                }
            }
        }
    }

    // 输出结果
    for (int i = 0; i < K; i++) {
        printf("Cluster %d:\n", i);
        for (int j = 0; j < N; j++) {
            if (assignments[j] == i) {
                printf("%f, %f\n", data[j][0], data[j][1]);
            }
        }
        printf("\n");
    }

    return 0;
}

这是一个简单的K-means聚类算法实现，可以通过随机生成数据集进行测试，最终输出聚类结果。