knn算法实现鸢尾花分类C语言

以下是基于C语言实现的KNN算法鸢尾花分类代码：

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

#define K 3 // 定义K值

// 定义鸢尾花的数据结构
typedef struct {
    double sepallength; // 花萼长度
    double sepalwidth; // 花萼宽度
    double petallength; // 花瓣长度
    double petalwidth; // 花瓣宽度
    char class[20]; // 类别
} Iris;

// 读取数据集
void read_data(char* filename, Iris* dataset, int* n) {
    FILE* fp = fopen(filename, "r");
    if (fp == NULL) {
        printf("Open file %s failed!\n", filename);
        exit(1);
    }
    char buf[1024];
    int i = 0;
    while (fgets(buf, 1024, fp)) {
        sscanf(buf, "%lf,%lf,%lf,%lf,%s", &dataset[i].sepallength, &dataset[i].sepalwidth, \
            &dataset[i].petallength, &dataset[i].petalwidth, dataset[i].class);
        i++;
    }
    *n = i;
    fclose(fp);
}

// 计算两点之间的距离
double distance(Iris* p, Iris* q) {
    return sqrt(pow(p->sepallength - q->sepallength, 2) + pow(p->sepalwidth - q->sepalwidth, 2) + \
        pow(p->petallength - q->petallength, 2) + pow(p->petalwidth - q->petalwidth, 2));
}

// 查找K个最近邻居
void find_k_neighbors(Iris* dataset, int n, Iris* test, Iris** neighbors) {
    double dist;
    double max_dist = 0.0;
    int max_index = 0;
    for (int i = 0; i < K; i++) {
        neighbors[i] = &dataset[i];
        dist = distance(neighbors[i], test);
        if (dist > max_dist) {
            max_dist = dist;
            max_index = i;
        }
    }
    for (int i = K; i < n; i++) {
        dist = distance(&dataset[i], test);
        if (dist < max_dist) {
            neighbors[max_index] = &dataset[i];
            max_dist = dist;
            for (int j = 0; j < K; j++) {
                if (distance(neighbors[j], test) > max_dist) {
                    max_dist = distance(neighbors[j], test);
                    max_index = j;
                }
            }
        }
    }
}

// 计算类别出现次数
char* get_class(Iris** neighbors) {
    int class_count[3] = {0, 0, 0};
    for (int i = 0; i < K; i++) {
        if (strcmp(neighbors[i]->class, "Iris-setosa") == 0) {
            class_count[0]++;
        } else if (strcmp(neighbors[i]->class, "Iris-versicolor") == 0) {
            class_count[1]++;
        } else {
            class_count[2]++;
        }
    }
    int max_count = 0;
    int max_index = 0;
    for (int i = 0; i < 3; i++) {
        if (class_count[i] > max_count) {
            max_count = class_count[i];
            max_index = i;
        }
    }
    if (max_index == 0) {
        return "Iris-setosa";
    } else if (max_index == 1) {
        return "Iris-versicolor";
    } else {
        return "Iris-virginica";
    }
}

int main() {
    Iris dataset[150]; // 数据集
    Iris test_data; // 测试数据
    Iris* neighbors[K]; // 最近邻居
    int n; // 数据集的大小

    read_data("iris.data", dataset, &n); // 读取数据集

    // 手动输入测试数据
    printf("Please input the test data (sepal length, sepal width, petal length, petal width):\n");
    scanf("%lf%lf%lf%lf", &test_data.sepallength, &test_data.sepalwidth, &test_data.petallength, &test_data.petalwidth);

    find_k_neighbors(dataset, n, &test_data, neighbors); // 查找最近邻居

    printf("The class of the test data is %s.\n", get_class(neighbors)); // 输出分类结果

    return 0;
}

注意：本代码中的数据集文件"iris.data"需要自行下载。