【机器学习系列】kNN（k近邻算法）的python实现

模型代码

模型文件命名为kNN.py

#coding:utf-8

from numpy import *
import operator

def createDataSet():
    group=array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
    labels=['A','A','B','B']
    return group,labels

def classify(inX,dataSet,labels,k):
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX,(dataSetSize,1))-dataSet
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()
    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0)+1
    sortedClassCount = sorted(classCount.iteritems(),key=operator.itemgetter(1),reverse=True)
    return sortedClassCount[0][0]

测试代码

测试代码命名为kNNTest.py

#coding:utf-8

import kNN
from numpy import *

dataSet, labels = kNN.createDataSet()

print kNN.classify([1.3,0.9],dataSet,labels,3)