KNN(k邻近)

给定一个训练数据集，对新的输入实例，在训练数据集中找到与该实例最邻近的 k 个实例，这 k 个实例的多数属于某个类，就把该输入实例分为这个类。

优点: 精度高、对异常值不敏感、无数据输入假定
缺点: 计算复杂度高、空间复杂度高
适用数据范围: 数值型和标称型

算法比较简单

下面写两个例子：

文本型训练集：

import math
from  numpy import *
from __future__ import print_function
import operator
from os import listdir
from collections import Counter
import matplotlib
import matplotlib.pyplot as plt
def file2matrix(filename):
   fr = open(filename)
   numberOfLines = len(fr.readlines())
   returnMat = zeros((numberOfLines, 3))  # prepare matrix to return
   classLabelVector = []  # prepare labels return
   fr = open(filename)
   index = 0
   for line in fr.readlines():
       line = line.strip()
       listFromLine = line.split('\t')
       returnMat[index, :] = listFromLine[0:3]
       classLabelVector.append(int(listFromLine[-1]))
       index += 1
   return returnMat, classLabelVector
def autoNorm(dataSet):
    minVals=dataSet.min(0)
    maxVals=dataSet.max(0)
    ranges=maxVals-minVals
    normDataSet=zeros(shape(dataSet))
    m=dataSet.shape[0]
    normDataSet=dataSet-tile(minVals,(m,1))
    normDataSet=normDataSet/tile(ranges,(m,1))
    return normDataSet,ranges,minVals
def classify0(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]
def datingClassTest():
    hoRatio=0.1
    datingDataMat,datingLabels=file2matrix('2.KNN/2.KNN/datingTestSet2.txt')
    normMat,ranges,minVals=autoNorm(datingDataMat)
    m=normMat.shape[0]
    numTestVecs=int(m*hoRatio)
    print ('numTestVecs=',numTestVecs)
    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 rate is : %f"%(errorCount/float(numTestVecs)))
    print (errorCount)
datingClassTest()
a1=array([[1,1,1],[0,0,0],[1,1,1]])
a2=a1.shape[0]
print(a2)
a3=tile([1,1,1],(a2,1))-a1
print(a3)
a4=a3.sum(axis=1)
print(a4)

图像类型训练集：

import math
from  numpy import *
from __future__ import print_function
import operator
from os import listdir
from collections import Counter
import matplotlib
import matplotlib.pyplot as plt
def img2vector(filename):
    returnVect=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

def classify0(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]
def handwritingClassTest():
    hwLabels=[]
    trainingFileList=listdir('2.KNN/2.KNN/trainingDigits')
    m=len(trainingFileList)
    trainingMat=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('2.KNN/2.KNN/trainingDigits/%s'% fileNameStr)
    testFileList=listdir('2.KNN/2.KNN/testDigits')
    errorCount=0.0
    mTest=len(testFileList)
    for i in range(mTest):
        fileNameStr=testFileList[i]
        fileStr=fileNameStr.split('.')[0]
        classNumStr=int(fileStr.split('_')[0])
        vectorUnderTest=img2vector('2.KNN/2.KNN/testDigits/%s'% fileNameStr)
        classifierResult=classify0(vectorUnderTest,trainingMat,hwLabels,3)
        print("the classifier came 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("\nthe total error rate is : %f"%(errorCount/float(mTest)))
handwritingClassTest()