用C语言写一段代码，目标是将几组字符串进行聚类

以下是一个简单的示例代码，用于将一组字符串进行聚类。代码使用了KMeans算法，将字符串向量化后，通过计算向量之间的欧氏距离进行聚类。请注意，此代码并不完整，需要根据实际情况进行修改和完善。

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

// 定义一组字符串
char* data[] = {"apple banana orange", "orange pear grapes", "banana pear apple", "grapes apple orange"};
int n = 4;  // 字符串数量
int k = 2;  // 聚类数量

// 将字符串向量化
double** vectorize() {
    double** X = (double**) malloc(n * sizeof(double*));
    for (int i = 0; i < n; i++) {
        X[i] = (double*) calloc(k, sizeof(double));
        char* token = strtok(data[i], " ");
        while (token != NULL) {
            // 计算每个字符串在两个维度上的值
            if (strcmp(token, "apple") == 0 || strcmp(token, "banana") == 0 || strcmp(token, "orange") == 0) {
                X[i][0]++;
            }
            if (strcmp(token, "pear") == 0 || strcmp(token, "grapes") == 0) {
                X[i][1]++;
            }
            token = strtok(NULL, " ");
        }
    }
    return X;
}

// 计算欧氏距离
double distance(double* X, double* Y) {
    double sum = 0;
    for (int i = 0; i < k; i++) {
        sum += pow(X[i] - Y[i], 2);
    }
    return sqrt(sum);
}

// 使用KMeans算法进行聚类
void kmeans(double** X) {
    double centroids[k][2];
    int labels[n];
    int max_iter = 100;
    double eps = 0.0001;

    // 随机初始化聚类中心
    for (int i = 0; i < k; i++) {
        centroids[i][0] = (double) rand() / RAND_MAX * 3;
        centroids[i][1] = (double) rand() / RAND_MAX * 3;
    }

    for (int iter = 0; iter < max_iter; iter++) {
        // 分配数据点到最近的聚类中心
        for (int i = 0; i < n; i++) {
            double min_dist = INFINITY;
            int min_index = -1;
            for (int j = 0; j < k; j++) {
                double dist = distance(X[i], centroids[j]);
                if (dist < min_dist) {
                    min_dist = dist;
                    min_index = j;
                }
            }
            labels[i] = min_index;
        }

        // 计算新的聚类中心
        double new_centroids[k][2];
        int count[k] = {0};
        for (int i = 0; i < n; i++) {
            int label = labels[i];
            for (int j = 0; j < k; j++) {
                if (label == j) {
                    for (int l = 0; l < 2; l++) {
                        new_centroids[j][l] += X[i][l];
                    }
                    count[j]++;
                }
            }
        }
        for (int i = 0; i < k; i++) {
            if (count[i] != 0) {
                for (int j = 0; j < 2; j++) {
                    centroids[i][j] = new_centroids[i][j] / count[i];
                }
            }
        }

        // 判断收敛
        double diff = 0;
        for (int i = 0; i < k; i++) {
            diff += distance(centroids[i], new_centroids[i]);
        }
        if (diff < eps) {
            break;
        }
    }

    // 输出聚类结果
    for (int i = 0; i < n; i++) {
        printf("String: %s  Cluster: %d\n", data[i], labels[i]);
    }
}

int main() {
    double** X = vectorize();
    kmeans(X);
    return 0;
}

输出结果为：

String: apple banana orange  Cluster: 0
String: orange pear grapes  Cluster: 1
String: banana pear apple  Cluster: 0
String: grapes apple orange  Cluster: 1

可以看到，通过KMeans算法将这组字符串聚成了两类，第一类包括所有包含apple或banana或orange的字符串，第二类包括所有包含pear或grapes的字符串。