KNN （k近邻算法）代码实现

# 如有问题，欢迎大家批评指正，谢谢。 

import numpy as np
from sklearn import datasets
from sklearn.model_selection import train_test_split
import matplotlib.pylab as plt


class KNN:
    def __init__(self, k):
        self.k = k

    def fit(self, X, y):
        self.X_train = X
        self.y_train = y

    def euclidean_distance(self, x1, x2):
        return np.sqrt(np.sum((x1 - x2) ** 2))

    def predict(self, X):
        y_pred = [self._predict(x) for x in X]
        return np.array(y_pred)

    def _predict(self, x):
        # 计算测试点与所有训练点的距离
        distances = [self.euclidean_distance(x, x_train) for x_train in self.X_train]
        # 获取距离最近的k个点的索引
        k_indices = np.argsort(distances)[:self.k]
        # 获取k个点的标签
        k_nearest_labels = [self.y_train[i] for i in k_indices]
        # 返回k个点中出现最频繁的标签
        most_common = np.bincount(k_nearest_labels).argmax()
        return most_common


if __name__ == "__main__":
    # 加载Iris数据集
    iris = datasets.load_iris()
    X = iris.data
    y = iris.target

    # 将数据集分为训练集和测试集
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

    # 初始化KNN分类器，指定K值
    knn = KNN(k=3)

    # 训练模型
    knn.fit(X_train, y_train)

    # 在测试集上进行预测
    print("ytest", y_test)
    predictions = knn.predict(X_test)
    acc = 0
    acc += (y_test == predictions).sum().item()
    acc = 100 * acc / X_test.data.shape[0]
    print(f"Accuracy: {acc:.2f}%")

    # 利用matplotlib绘制图像
    plt.figure(figsize=(8, 6))
    plt.scatter(X_train[y_train == 0, 2], X_train[y_train == 0, 3], color='g', label='Class 0')
    plt.scatter(X_train[y_train == 1, 2], X_train[y_train == 1, 3], color='y', label='Class 1')
    plt.scatter(X_train[y_train == 2, 2], X_train[y_train == 2, 3], color='b', label='Class 2')
    plt.scatter(X_test[:, 2], X_test[:, 3], color='r', label='Predict')

    plt.title('Iris Data Visualization')
    plt.xlabel('Petal Length')
    plt.ylabel('Petal Width')
    plt.legend()
    plt.show()