Kaggle-Digit Recognizer kNN解决方案

一、题目

​​3.6

from numpy import *import operatorimport csvimport pdbdef toInt(array): array=mat(array) m,n=shape(array) newArray=zeros((m,n)) for i in range(m): for j in range(n): newArray[i,j]=int(array[i,j]) return newArraydef nomalizing(array): m,n=shape(array) for i in range(m): for j in range(n): if array[i,j]!=0: array[i,j]=1 return arraydef loadTrainData(): l=[] with open('train.csv') as file: lines=csv.reader(file) for line in lines: l.append(line) #42001*785 l.remove(l[0]) # remove row 0, get 42000*785 l=array(l) # transfer list to array label=l[:,0] # 从0行0列取到最后一行0列, 显示为1行42000列，而不是42000行1列 data=l[:,1:] # from row 0 to the last row, from col 1 to the last col, 42000*784 return nomalizing(toInt(data)),toInt(label) #data 42000*784 label 1*42000 def loadTestData(): l=[] with open('test.csv') as file: lines=csv.reader(file) for line in lines: l.append(line) #28001*784 l.remove(l[0]) #28000*784 data=array(l) return nomalizing(toInt(data)) # data 28000*784def loadTestResult(): l=[] with open('knn_benchmark.csv') as file: lines=csv.reader(file) for line in lines: l.append(line) #28001*2 l.remove(l[0]) #28000*2 label=array(l) return toInt(label[:,1]) # label 1*28000#inX:1*n dataSet:m*n labels:m*1 def classify(inX, dataSet, labels, k): inX=mat(inX) dataSet=mat(dataSet) labels=mat(labels) dataSetSize = dataSet.shape[0] diffMat = tile(inX, (dataSetSize,1)) - dataSet sqDiffMat = array(diffMat)**2 sqDistances = sqDiffMat.sum(axis=1) distances = sqDistances**0.5 sortedDistIndicies = distances.argsort() classCount={} for i in range(k): voteIlabel = labels[sortedDistIndicies[i],0] classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1 sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True) return sortedClassCount[0][0]def saveResult(result): with open('result.csv', 'w', newline = '') as myFile: myWriter=csv.writer(myFile) for i in result: tmp=[] tmp.append(i) myWriter.writerow(tmp)def Test(): trainData,trainLabel=loadTrainData() testData=loadTestData() testLabel=loadTestResult() m,n=shape(testData) errorCount=0 resultList=[] for i in range(m): print ("classify: ",i) classifierResult = classify(testData[i], trainData[0:20000], trainLabel.transpose()[0:20000], 5) resultList.append(classifierResult) print ("the classifier came back with: %d, the real answer is: %d" % (classifierResult, testLabel[0,i])) if (classifierResult != testLabel[0,i]): errorCount += 1.0 print ("\nthe total number of errors is: %d" % errorCount) print ("\nthe total error rate is: %f"

运行程序： 打开cmd窗口，进入上述代码knn.py所在的目录，进入python环境 执行命令

import

运行结果：

四、Github代码下载

​​下载地址​​

五、参考

版权声明：本文内容由网络用户投稿，版权归原作者所有，本站不拥有其著作权，亦不承担相应法律责任。如果您发现本站中有涉嫌抄袭或描述失实的内容，请联系我们jiasou666@gmail.com 处理，核实后本网站将在24小时内删除侵权内容。