K相邻算法

 1 def classify0(inX, dataSet, labels, k):
 2     dataSetSize = dataSet.shape[0]
 3     diffMat = tile(inX, (dataSetSize,1)) - dataSet
 4     sqDiffMat = diffMat**2
 5     sqDistances = sqDiffMat.sum(axis=1)
 6     distances = sqDistances**0.5
 7     sortedDistIndicies = distances.argsort()
 8     classCount={}
 9     for i in range(k):
10         voteIlabel = labels[sortedDistIndicies[i]]
11         classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
12     sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
13     return sortedClassCount[0][0]

 1 def file2matrix(filename):
 2     fr = open(filename)
 3     numberOfLines = len(fr.readlines())         #get the number of lines in the file
 4     returnMat = zeros((numberOfLines,3))        #prepare matrix to return
 5     classLabelVector = []                       #prepare labels return
 6     fr = open(filename)
 7     index = 0
 8     for line in fr.readlines():
 9         line = line.strip()
10         listFromLine = line.split(‘\t‘)
11         returnMat[index,:] = listFromLine[0:3]
12         classLabelVector.append(int(listFromLine[-1]))
13         index += 1
14     return returnMat,classLabelVector
15 
16 def autoNorm(dataSet):
17     minVals = dataSet.min(0)
18     maxVals = dataSet.max(0)
19     ranges = maxVals - minVals
20     normDataSet = zeros(shape(dataSet))
21     m = dataSet.shape[0]
22     normDataSet = dataSet - tile(minVals, (m,1))
23     normDataSet = normDataSet/tile(ranges, (m,1))   #element wise divide
24     return normDataSet, ranges, minVals
25 
26 def datingClassTest():
27     hoRatio = 0.50      #hold out 10%
28     datingDataMat,datingLabels = file2matrix(‘datingTestSet2.txt‘)       #load data setfrom file
29     normMat, ranges, minVals = autoNorm(datingDataMat)
30     m = normMat.shape[0]
31     numTestVecs = int(m*hoRatio)
32     errorCount = 0.0
33     for i in range(numTestVecs):
34         classifierResult = classify0(normMat[i,:],normMat[numTestVecs:m,:],datingLabels[numTestVecs:m],3)
35         print "the classifier came back with: %d, the real answer is: %d" % (classifierResult, datingLabels[i])
36         if (classifierResult != datingLabels[i]): errorCount += 1.0
37     print "the total error rate is: %f" % (errorCount/float(numTestVecs))
38     print errorCount

 1 def img2vector(filename):
 2     returnVect = zeros((1,1024))
 3     fr = open(filename)
 4     for i in range(32):
 5         lineStr = fr.readline()
 6         for j in range(32):
 7             returnVect[0,32*i+j] = int(lineStr[j])
 8     return returnVect
 9 
10 def handwritingClassTest():
11     hwLabels = []
12     trainingFileList = listdir(‘digits/trainingDigits‘)           #load the training set
13     m = len(trainingFileList)
14     trainingMat = zeros((m,1024))
15     for i in range(m):
16         fileNameStr = trainingFileList[i]
17         fileStr = fileNameStr.split(‘.‘)[0]     #take off .txt
18         classNumStr = int(fileStr.split(‘_‘)[0])
19         hwLabels.append(classNumStr)
20         trainingMat[i,:] = img2vector(‘digits/trainingDigits/%s‘ % fileNameStr)
21     testFileList = listdir(‘digits/testDigits‘)        #iterate through the test set
22     errorCount = 0.0
23     mTest = len(testFileList)
24     for i in range(mTest):
25         fileNameStr = testFileList[i]
26         fileStr = fileNameStr.split(‘.‘)[0]     #take off .txt
27         classNumStr = int(fileStr.split(‘_‘)[0])
28         vectorUnderTest = img2vector(‘digits/testDigits/%s‘ % fileNameStr)
29         classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
30         print "the classifier came back with: %d, the real answer is: %d" % (classifierResult, classNumStr)
31         if (classifierResult != classNumStr): errorCount += 1.0
32     print "\nthe total number of errors is: %d" % errorCount
33     print "\nthe total error rate is: %f" % (errorCount/float(mTest))