from numpy import *import operatorfrom cProfile import labelimport matplotlibimport matplotlib.pyplot as pltfrom os import listdirdef createDataSet(): group = array([1.0,1.1],[1.0,1.0],[0,0],[0,0.1]) labels = ['A','A','B','B'] return group, labelsdef 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 TestClassify0(): group,labels = createDataSet() classify0([0,0], group, labels, 3) def file2matrix(filename): fr = open(filename) arrayOLines = fr.readlines() numberOfLines = len(arrayOLines) returnMat = 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 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, minValsdef Test(): datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')# # print datingDataMat,dataingLabels# display as scatter# datingLabels2 = list(datingLabels)# datingLabels2[:100] = [4]*100# fig = plt.figure()# ax = fig.add_subplot(1,1,1)# ax.scatter(datingDataMat[:,1],datingDataMat[:,2],15.0*array(datingLabels),15.0*array(datingLabels))# plt.show() normMat, ranges, minVals = autoNorm(datingDataMat) print normMat def datingClassTest(): hoRatio = 0.50 datingDataMat, datingLabels = file2matrix('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 print "the total error rate is: %f" % (errorCount/float(numTestVecs)) print errorCountdef 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 returnVectdef testImg(): testVector = img2vector('trainingDigits/0_0.txt') print testVector[0,0:31] def handwriteingClassTest(): hwLabels = [] trainingFileList = listdir('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('trainingDigits/%s' % fileNameStr) testFileList = listdir('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('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 print "\nthe total number of errors is: %d" % errorCount print "\nthe total error rate is: %f" % (errorCount/float(mTest))if __name__ == '__main__': handwriteingClassTest()
