机器学习实战 k-近邻算法

机器学习实战k-近邻算法

# -*- coding: utf-8 -*-
import numpy as np
#导入运算符模块
import operator
def createDataSet():
    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):
    dataSetSize=dataSet.shape[0]#获取训练样本的个数 也就是行数
    diffMat=np.tile(inX,(dataSetSize,1))-dataSet#行扩展 与训练样本维度相同
    sqDiffMat=diffMat**2
    sqDistances=sqDiffMat.sum(axis=1)#矩阵的每一行相加
    distances=sqDistances**0.5
    sortedDistIndicies=distances.argsort()#排序
    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)
    return sortedClassCount[0][0]

Python numpy函数：shape用法

shape函数是numpy.