knn算法python代码

以下是一个简单的knn算法的Python代码：

from math import sqrt

# 计算两个向量之间的欧几里德距离
def euclideanDistance(instance1, instance2, length):
    distance = 0
    for i in range(length):
        distance += pow((instance1[i] - instance2[i]), 2)
    return sqrt(distance)

# 返回训练数据集中与测试实例距离最近的k个实例
def getNeighbors(trainingSet, testInstance, k):
    distances = []
    length = len(testInstance)-1
    for x in range(len(trainingSet)):
        dist = euclideanDistance(testInstance, trainingSet[x], length)
        distances.append((trainingSet[x], dist))
    distances.sort(key=lambda x: x[1])
    neighbors = []
    for x in range(k):
        neighbors.append(distances[x][0])
    return neighbors

# 针对给定测试集knn算法的主要功能
def getResponse(neighbors):
    classVotes = {}
    for x in range(len(neighbors)):
        response = neighbors[x][-1]
        if response in classVotes:
            classVotes[response] += 1
        else:
            classVotes[response] = 1
    sortedVotes = sorted(classVotes.items(), key=lambda x: x[1], reverse=True)
    return sortedVotes[0][0]

# 通过计算准确性来评估模型
def getAccuracy(testSet, predictions):
    correct = 0
    for x in range(len(testSet)):
        if testSet[x][-1] == predictions[x]:
            correct += 1
    return (correct / float(len(testSet))) * 100.0

# 测试knn算法
def main():
    # 模拟训练集
    trainSet = [[2, 2, 2, 'a'], [4, 4, 4, 'b'], [5, 5, 5, 'b'], [3, 3, 3, 'a'], [6, 6, 6, 'b'], [8, 8, 8, 'b'], [7, 7, 7, 'a']]
    # 模拟测试集
    testSet = [[5, 5, 5, 'a'], [2, 2, 2, 'b'], [3, 3, 3, 'a'], [8, 8, 8, 'b']]
    # 设置k值
    k = 3
    predictions = []
    for x in range(len(testSet)):
        neighbors = getNeighbors(trainSet, testSet[x], k)
        result = getResponse(neighbors)
        predictions.append(result)
        print(f"预测值为{result}")
    accuracy = getAccuracy(testSet, predictions)
    print('准确率: ' + repr(accuracy) + '%')

if __name__ == '__main__':
    main()

这是一个基本的knn算法代码，适用于任何数据集。当然，您可以根据需要对其进行修改和扩展。