Python实现KNN算法及手写程序识别

1.Python实现KNN算法

输入：inX：与现有数据集（1xN）进行比较的向量
   dataSet：已知向量的大小m数据集（NxM）
   个标签：数据集标签（1xM矢量）
   k：用于比较的邻居数（应为奇数）
输出：最受欢迎的类标签(归类问题)

 # -*- coding: utf-8 -*-
 """
 Created on Sun Apr 16 23:01:54 2017
 
 @author: SimonsZhao
 """ kNN: k Nearest Neighbors
 Input:      inX: vector to compare to existing dataset (1xN)
             dataSet: size m data set of known vectors (NxM)
             labels: data set labels (1xM vector)
             k: number of neighbors to use for comparison (should be an odd number)
 Output:     the most popular class label '''
 from numpy import *
 import operator
 from os import listdir
 
 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 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 file2matrix(filename):
     fr = open(filename)
     numberOfLines = len(fr.readlines())         #get the number of lines in the file
     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))   #element wise divide
     return normDataSet, ranges, minVals
 
 def datingClassTest():
     hoRatio = 0.50      #hold out 10%
     datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file
     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 rate is: %f" % (errorCount/float(numTestVecs))
     print errorCount
 
 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 handwritingClassTest():
     hwLabels = []
     trainingFileList = listdir('trainingDigits')           #load the training set
     m = len(trainingFileList)
     trainingMat = zeros((m,1024))
     for i in range(m):
         fileNameStr = trainingFileList[i]
         fileStr = fileNameStr.split('.')[0]     #take off .txt
         classNumStr = int(fileStr.split('_')[0])
         hwLabels.append(classNumStr)
         trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr)
     testFileList = listdir('testDigits')        #iterate through the test set
     errorCount = 0.0
     mTest = len(testFileList)
     for i in range(mTest):
         fileNameStr = testFileList[i]
         fileStr = fileNameStr.split('.')[0]     #take off .txt
         classNumStr = int(fileStr.split('_')[0])
         vectorUnderTest = img2vector('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))

2.数据集(测试集合训练集)

3.KNN测试结果