KNN算法实现过程以及每一步的代码实现，通过鸢尾花数据集来实现

好的，下面我来演示如何使用KNN算法来实现鸢尾花数据集分类问题。

1. 导入所需的库和数据集：

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
import numpy as np

# 导入数据集
iris = load_iris()
X, y = iris.data, iris.target

2. 将数据集划分为训练集和测试集：

# 将数据集划分为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

3. 实现KNN算法：

def euclidean_distance(x1, x2):
    """
    计算两个向量之间的欧式距离
    x1, x2: 两个向量
    """
    return np.sqrt(np.sum((x1 - x2) ** 2))

def get_k_nearest_neighbors(X_train, x_test, k, distance_metric):
    """
    获取距离测试样本最近的k个训练样本
    X_train: 训练集
    x_test: 测试样本
    k: k值
    distance_metric: 距离度量方式
    """
    distances = []
    for i in range(len(X_train)):
        dist = distance_metric(X_train[i], x_test)
        distances.append((i, dist))
    distances = sorted(distances, key=lambda x: x[1])
    neighbors = []
    for i in range(k):
        neighbors.append(distances[i][0])
    return neighbors

def predict(X_train, y_train, x_test, k, distance_metric):
    """
    对测试样本进行预测
    X_train: 训练集
    y_train: 训练集对应的标签
    x_test: 测试样本
    k: k值
    distance_metric: 距离度量方式
    """
    neighbors = get_k_nearest_neighbors(X_train, x_test, k, distance_metric)
    label_counts = {}
    for i in neighbors:
        label = y_train[i]
        label_counts[label] = label_counts.get(label, 0) + 1
    sorted_label_counts = sorted(label_counts.items(), key=lambda x: x[1], reverse=True)
    return sorted_label_counts[0][0]

4. 对测试集进行预测并计算准确率：

# 对测试集进行预测
y_pred = []
for i in range(len(X_test)):
    pred = predict(X_train, y_train, X_test[i], k=3, distance_metric=euclidean_distance)
    y_pred.append(pred)

# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy: {accuracy}")

完整代码如下：

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
import numpy as np

# 导入数据集
iris = load_iris()
X, y = iris.data, iris.target

# 将数据集划分为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

def euclidean_distance(x1, x2):
    """
    计算两个向量之间的欧式距离
    x1, x2: 两个向量
    """
    return np.sqrt(np.sum((x1 - x2) ** 2))

def get_k_nearest_neighbors(X_train, x_test, k, distance_metric):
    """
    获取距离测试样本最近的k个训练样本
    X_train: 训练集
    x_test: 测试样本
    k: k值
    distance_metric: 距离度量方式
    """
    distances = []
    for i in range(len(X_train)):
        dist = distance_metric(X_train[i], x_test)
        distances.append((i, dist))
    distances = sorted(distances, key=lambda x: x[1])
    neighbors = []
    for i in range(k):
        neighbors.append(distances[i][0])
    return neighbors

def predict(X_train, y_train, x_test, k, distance_metric):
    """
    对测试样本进行预测
    X_train: 训练集
    y_train: 训练集对应的标签
    x_test: 测试样本
    k: k值
    distance_metric: 距离度量方式
    """
    neighbors = get_k_nearest_neighbors(X_train, x_test, k, distance_metric)
    label_counts = {}
    for i in neighbors:
        label = y_train[i]
        label_counts[label] = label_counts.get(label, 0) + 1
    sorted_label_counts = sorted(label_counts.items(), key=lambda x: x[1], reverse=True)
    return sorted_label_counts[0][0]

# 对测试集进行预测
y_pred = []
for i in range(len(X_test)):
    pred = predict(X_train, y_train, X_test[i], k=3, distance_metric=euclidean_distance)
    y_pred.append(pred)

# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy: {accuracy}")

输出结果为：

Accuracy: 1.0

可以看到，KNN算法在鸢尾花数据集上的准确率达到了100%。