python knn算法数据_Python实现KNN算法

#coding:utf-8

importrequests, json, time, re, os, sys, timeimporturllib2importrandomimportnumpy as np#设置为utf-8模式

reload(sys)

sys.setdefaultencoding("utf-8")#读取文本文件,构建二维数组

defreadDataFile(filename,format):ifformat:pass

else:

format= ','list=[]#去除首位空格

filename =filename.strip()#判断数据文件是否存在

ifos.path.isfile(filename):passfile_object= open(filename,'rb')

lines=file_object.readlines()for line inlines:

tmp=[]

line=line.strip()for value in line.split(format)[:-1]:

tmp.append(float(value))

tmp.append(line.split(format)[-1])

list.append(tmp)else:print "%s is not exists" %(filename)returnlist#读取文本数据,拆分原始数据为特征和标签,返回特征值和标签值

def createData(filename,format=','):

data_label=readDataFile(filename,format)if len(data_label) >0:

label=[]

data=[]#data_label = [[1,100,123,'A'],[2,99,123,'A'],[100,1,12,'B'],[99,2,23,'B']]

for each indata_label:

label.append(each[-1])

data.append(each[:-1])returndata,label#根据输入数据和测试数据,进行分类

defcalculateDistance(input,data,label,k):

classes= 'Error'

if len(data[0])==0 or len(label) ==0:print 'data or label is null'

pass

elif k >len(data) :print "k : %s is out of bounds" %(k)pass

elif len(input) <>len(data[0]):print "特征变量值不够,输入变量特征个数为：%s,训练特征变量个数为：%s" %(len(input),len(data[0]))pass

else:

result=[]

length=len(input)for i inrange(len(data)):

sum=0for j inrange(length):#pow(5,2) 标识5的平方为25,取两点之间的距离的平方并累加

sum = sum + pow(input[j] - data[i][j],2)#取平方根

sum = pow(sum,0.5)

result.append(sum)#print result

result =np.array(result)#argsort()根据元素的值从小到大对元素进行排序，返回下标

sortedDistIndex =np.argsort(result)#统计前k个数中各个标签的个数

classCount={}for i inrange(k):

voteLabel=label[sortedDistIndex[i]]###对选取的K个样本所属的类别个数进行统计

#dict.get(key, default=None) 返回指定键的值，如果值不在字典中返回默认值None。

classCount[voteLabel] = classCount.get(voteLabel,0) + 1

###选取出现的类别次数最多的类别

maxCount =0for key,value inclassCount.items():if value >maxCount:

maxCount=value

classes=keyreturnclasses

filename= '/home/shutong/jim/crawl/data.csv'data,label=createData(filename)

input= [1,20]

k= 4result=calculateDistance(input,data,label,k)print input,result