python中knn算法实现

#coding:  utf-8
'''
@author:zhoumeixu
createdate:2015年8月27日
'''

#np.zeros((4,2))
#np.zeros(8).reshape(4,2)
#x=np.array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])    np.zeros_like(x)

# 最值和排序：最值有np.max(),np.min() 他们都有axis和out（输出）参数,
# 而通过np.argmax(), np.argmin()可以得到取得最大或最小值时的 下标。
# 排序通过np.sort(), 而np.argsort()得到的是排序后的数据原来位置的下标

# 简单实现knn算法的基本思路
import numpy as np
import   operator  #运算符操作包
from _ctypes import Array
from statsmodels.sandbox.regression.kernridgeregress_class import plt_closeall
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
group,labels=createDataSet()
def  classify0(inx,dataSet,labels,k):
dataSetSize=dataSet.shape[0]
diffMat=np.tile(inx,(dataSetSize,1))-dataSet
sqDiffMat=diffMat**2
sqDistances=sqDiffMat.sum(axis=1)
distances=sqDistances**0.5            #计算距离 python中会自动广播的形式
sortedDistIndicies=distances.argsort()  #排序，得到原来数据的在原来所在的下标
classCount={}
for  i in range(k):
voteIlabel=labels[sortedDistIndicies[i]]  # 计算距离最近的值所在label标签
classCount[voteIlabel]=classCount.get(voteIlabel,0)+1    # 计算距离最近的值所在label标签，对前k哥最近数据进行累加

sortedClassCount=sorted(classCount.iteritems(),key=operator.itemgetter(1),reverse=True)  #排序得到距离k个最近的数所在的标签
return sortedClassCount[0][0]
if __name__=='__main__':
print(classify0([0,0],group,labels,4))

# 利用knn算法改进约会网站的配对效果
def  file2matrix(filename):
fr=open(filename)
arrayOLines=fr.readlines()
numberOfLines=len(arrayOLines)
returnMat=np.zeros((numberOfLines,3))
classLabelVector=[]
index=0
for line in arrayOLines:
line=line.strip()
listFromLine=line.split('\t')
returnMat[index,:]=listFromLine[0:3]
classLabelVector.append(int(listFromLine[-1]))
index+=1
return returnMat ,classLabelVector   #生成训练数据的array和目标array

path=u'D:\\Users\\zhoumeixu204\\Desktop\\python语言机器学习\\机器学习实战代码   python\\机器学习实战代码\\machinelearninginaction\\Ch02\\'
datingDataMat,datingLabels=file2matrix(path+'datingTestSet2.txt')

import  matplotlib
import  matplotlib.pyplot as plt
fig=plt.figure()
ax=fig.add_subplot(111)
ax.scatter(datingDataMat[:,1],datingDataMat[:,2])
plt.show()
ax.scatter(datingDataMat[:,1],datingDataMat[:,2],15.0*np.array(datingLabels),15*np.array(datingDataMat[:,2]))
plt.show()      #生成训练数据的array和目标array

def  autoNorm(dataset):
minVals=dataset.min(0)
maxVals=dataset.max(0)
ranges=maxVals-minVals
normeDataSet=np.zeros(np.shape(dataset))
m=dataset.shape[0]
normDataSet=dataset-np.tile(minVals,(m,1))
normDataSet=normDataSet/np.tile(ranges,(m,1))
return  normDataSet ,ranges,minVals

normMat,ranges,minVals=autoNorm(datingDataMat)

def   datingClassTest():
hoRatio=0.1
datingDataMat,datingLabels=file2matrix(path+'datingTestSet2.txt')
normMat,ranges,minVals=autoNorm(datingDataMat)
m=normMat.shape[0]
numTestVecs=int(m*hoRatio)
errorCount=0.0
for  i in range(numTestVecs):
classifierResult=classify0(normMat[i,:], normMat[numTestVecs:m,:], datingLabels[numTestVecs:m],3)
print "the classifier came back  with :%d,the  real answer is :%d"\
%(classifierResult,datingLabels[i])
if  classifierResult!=datingLabels[i]:
errorCount+=1.0
print "the  total error rare is :%f"%(errorCount/float(numTestVecs))  #利用knn算法测试错误率

if __name__=='__main__':
datingClassTest()
#利用构建好的模型进行预测
def   classifyPerson():
resultList=['not at all','in same doses','in large d oses']
percentTats=float(raw_input("percentage  if time spent playin cideo  games:"))
ffMiles=float(raw_input("frequnet  fliter  miles earned  per year:"))
iceCream=float(raw_input("liters of ice cream consumed per year:"))
datingDataMat,datingLabels=file2matrix(path+'datingTestSet2.txt')
normMat,ranges,minVals=autoNorm(datingDataMat)
inArr=np.array([ffMiles,percentTats,iceCream])
classifierResult=classify0((inArr-minVals)/ranges,normMat,datingLabels,3)
print("you  will probably  like  the person:",resultList[classifierResult-1])

if  __name__!='__main__':
classifyPerson()

#利用knn算法进行手写识别系统验证

path=u'D:\\Users\\zhoumeixu204\\Desktop\\python语言机器学习\\机器学习实战代码   python\\机器学习实战代码\\machinelearninginaction\\Ch02\\'
def img2vector(filename):
returnVect=np.zeros((1,1024))
fr=open(filename)
for i in range(32):
lineStr=fr.readline()
for j in range(32):
returnVect[0,32*i+j]=int(lineStr[j])
return returnVect

testVector=img2vector(path+'testDigits\\0_13.txt')
print(testVector[0,0:31])
import os
def   handwritingClassTest():
hwLabels=[]
trainingFileList=os.listdir(path+'trainingDigits')
m=len(trainingFileList)
trainingMat=np.zeros((m,1024))
for   i in range(m):
fileNameStr=trainingFileList[i]
fileStr=fileNameStr.split('.')[0]
classNumStr=int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i,:]=img2vector(path+'trainingDigits\\'+fileNameStr)
testFileList=os.listdir(path+'testDigits')
errorCount=0.0
mTest=len(testFileList)
for j in range(mTest):
fileNameStr=testFileList[j]
fileStr=fileNameStr.split('.')[0]
classNumStr=int(fileNameStr.split('_')[0])
classNumStr=int(fileStr.split('_')[0])
vectorUnderTest=img2vector(path+'testDigits\\'+fileNameStr)
classifierResult=classify0(vectorUnderTest,trainingMat,hwLabels,3)
print("the  classifier canme back with:%d,the real answer is :%d"%(classifierResult,classNumStr))
if classifierResult!=classNumStr:
errorCount+=1.0
print("\nthe total  number of  errors is :%d"%errorCount)
print("\n the total error rate is :%f"%(errorCount/float(mTest)))
if  __name__=='__main__':
handwritingClassTest()