Python实现KNN

# -*- coding: utf-8 -*-
import numpy as np
import operator


def knnClassify(inX, dataSet, labels, k):
    """
        KNN算法
        :param inX: 待判断样本的特征
        :param dataSet: 数据集各个样本的特征
        :param labels: 样本集的标签
        :param k: 取前k个结果
    """
    dataSetSize = dataSet.shape[0]
    
    # 计算输入的向量inX与所有样本的距离，最小二乘法
    diffMat = np.tile(inX, (dataSetSize, 1)) - dataSet
    sqDiffMat = diffMat ** 2
    sqDistances = sqDiffMat.sum(axis = 1)
    distances = sqDistances ** 0.5
    
    # 对距离大小进行排序
    sortedDistIndices = distances.argsort()
    classCount = {}
    
    # 选择距离最小的 K 个点，以label为键，频数为值
    for i in range(k):
        voteLabel = labels[ sortedDistIndices[i] ]
        classCount[ voteLabel ] = classCount.get(voteLabel, 0) + 1
    
    # 按照类别的数量多少进行排序
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)  
    print(sortedClassCount[0][0])
    return sortedClassCount[0][0]  # 返回类别数最多的类别名称
    

if __name__ == '__main__':
    inX = np.array([2,2.2,1.9])
    dataSet = np.array([
        [1,1,1],
        [0.9,0.9,0.9],
        [1.2,1,1.1],
        [1.1,0.9,1],
        [2,2.1,2.2],
        [2.2,2.1,2],
        [2.1,2.3,1.9],
        [1.8,2.1,2],
        [3,3.2,3.1],
        [2.9,2.9,3],
        [2.8,3,3.1],
        [3.2,3.1,3]
    ])
    labels = np.array([1,1,1,1,2,2,2,2,3,3,3,3])
    k = 3
    knnClassify(inX, dataSet, labels, k)