kNN分类算法

import numpy as np
import operator


def createDataSet():
    '''
    创建数据集
    :return: 数据集特征值，数据集标签
    '''
    group = np.array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
    labels = ['A','A','B','B']
    return group,labels


def classify0(inX, dataset, labels, k):
    '''
    :param inX: 输入向量,即待测试数据
    :param dataset: 数据集特征值
    :param labels: 数据集标签
    :param k: 取最近的k个值
    :return: 标定结果
    '''
    datasetSize = dataset.shape[0] #数组行数
    diffMat = np.tile(inX, (datasetSize, 1)) - dataset #输入向量行数乘以datasetSize倍-dataset
    sqDiffMat = diffMat ** 2  #求每一项的平方
    sqDistances = sqDiffMat.sum(axis=1) #每一行的和
    distances = sqDistances ** 0.5  # 对sqDistances开方
    sortedDistIndicies = distances.argsort() #对distances中元素从小到大排序，返回对应原数组中的索引
    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True) #对字典按值从大到小排序
    return sortedClassCount[0][0]

if __name__ == '__main__':
    group,labels = createDataSet()
    print(classify0([1,1], group, labels, 3)) #输入向量为[1,1]
    print(classify0([0,0], group, labels, 3))  # 输入向量为[0,0]

运行结果：

E:\Anaconda3\python.exe E:/kNN.py
A
B

进程已结束，退出代码 0

摘自《机器学习实战》