機器學習實戰例項之手寫數字識別(KNN、python3)
阿新 • • 發佈:2019-01-03
from numpy import * from os import listdir import operator def img2Vector(filename): returnVecter = zeros((1,1024)) fr = open(filename) for i in range(32): linestr = fr.readline() for j in range(32): returnVecter[0,32*i+j] = int(linestr[j]) return returnVecter 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.items(), key=operator.itemgetter(1), reverse=True) return sortedClassCount[0][0] 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)))