1、首先在jupyter中New一个Untitle.ipynb,然后将它重命名为kNN.py,接着在kNN.py中输入一下代码(课本代码):
注:以下代码中,存在我自己的测试数据文件的路径,你们要改为自己测试数据文件的路径
from numpy import *
import operator
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 classify0(inX, dataSet, labels, k):
dataSetSize = dataSet.shape[0]
diffMat = tile(inX, (dataSetSize, 1)) - dataSet
sqdiffMat = diffMat**2
sqdistance = sqdiffMat.sum(axis=1)
#print(sqdistance)
distance = sqdistance**0.5
sortedDistIndex = distance.argsort()
classCount = {}
for i in range(k):
voteIlabel = labels[sortedDistIndex[i]]
classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
return sortedClassCount[0][0]
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, minVals
def datingClassTest():
hoRatio = 0.1
datingDataMat,datingLabels = file2matrix('F:\Softwares\Python\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 += 1.0
print ("the total error rate is: %f" % (errorCount/float(numTestVecs)))
def classifyPerson():
resultList = ["not at all","in small does","in large does"]
percentTats = float(input("percentage of time spent playing video games?"))
ffMiles = float(input("frequent flier miles earned per year?"))
iceCream = float(input("liters of ice cream consumes per year?"))
datingDataMat,datingLabels = file2matrix('F:\Softwares\Python\datingTestSet2.txt')
normMat,ranges,minVals = autoNorm(datingDataMat)
inArr = array([ffMiles,percentTats,iceCream])
classifierResult = classify0(((inArr-minVals)/ranges),datingDataMat,datingLabels,3)
print("You will probably like this person:",resultList[classifierResult - 1])
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
from os import listdir
def handwritingClassTest():
hwLabels = []
trainingFileList = listdir('F:/Softwares/Python/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('F:/Softwares/Python/trainingDigits/%s' % fileNameStr)
testFileList = listdir('F:/Softwares/Python/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('F:/Softwares/Python/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、将测试数据文件放在和kNN.py同一个目录下。或者像我一样,直接在代码中修改成自己的测试文件路径
注:还有几处,自己注意修改
3、现在可以开始测试数据,在jupyter中再创建一个文件,命名为testKNN.ipynb