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

1 kNN.handwritingClassTest()

'''
Input:      inX: vector to compare to existing dataset (1xN)
            dataSet: size m data set of known vectors (NxM)
            labels: data set labels (1xM vector)
            k: number of neighbors to use for comparison (should be an odd number)
Output:     the most popular class label
'''
from numpy import *
import operator
from os import listdir
def classify0(inX, dataSet, labels, k):
dataSetSize = dataSet.shape[0]
diffMat = tile(inX, (dataSetSize,1)) - dataSet
sqDiffMat = diffMat2
sqDistances = sqDiffMat.sum(axis=1)
distances = sqDistances0.5
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 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 file2matrix(filename):
fr = open(filename)
numberOfLines = len(fr.readlines())         #get the number of lines in the file
returnMat = zeros((numberOfLines,3))        #prepare matrix to return
classLabelVector = []                       #prepare labels return   
fr = open(filename)
index = 0
for line in fr.readlines():
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))   #element wise divide
return normDataSet, ranges, minVals
def datingClassTest():
hoRatio = 0.50      #hold out 10%
datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file
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))
print errorCount
def classifyPerson():
resultList = ['not at all', 'in small doses', 'in large doses']
percentTats = float(raw_input("percentage of time spent playing video games?"))
ffMiles = float(raw_input("frequent flier miles earned per year?"))
iceCream = float(raw_input("liters of ice cream consumed per year?"))
datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = autoNorm(datingDataMat)
inArr = array([ffMiles, percentTats, iceCream])
classifierResult = classify0((inArr-minVals)/ranges, normMat, 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
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))