def classifyPerson():
strLabels = ['not at all', 'small doses', 'large doses']
print ''
ffMiles = float(raw_input('frequent flier miles earned per year: '))
percentTats = float(raw_input('percentage of time spent playing video games: '))
iceCream = float(raw_input('liters of ice cream consumed per year: '))
datingDataMat, datingLabels = fileUtil.file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = normalizer.autoNorm(datingDataMat)
testVec = numpy.array([ffMiles, percentTats, iceCream])
classifierResult = kNN.classify((testVec - minVals) / ranges, normMat, datingLabels, 3)
print ''
print 'You will probably like this person:', strLabels[classifierResult - 1]
def classifyPerson():
strLabels = ['not at all', 'small doses', 'large doses']
print ''
ffMiles = float(raw_input('frequent flier miles earned per year: '))
percentTats = float(
raw_input('percentage of time spent playing video games: '))
iceCream = float(raw_input('liters of ice cream consumed per year: '))
datingDataMat, datingLabels = fileUtil.file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = normalizer.autoNorm(datingDataMat)
testVec = numpy.array([ffMiles, percentTats, iceCream])
classifierResult = kNN.classify((testVec - minVals) / ranges, normMat,
datingLabels, 3)
print ''
print 'You will probably like this person:', strLabels[classifierResult -
1]
def handwritingClassTest():
hwLabels = []
# load the training set
trainingFileList = listdir('trainingDigits')
m = len(trainingFileList)
trainingMat = zeros((m, 1024))
for i in range(m):
fileNameStr = trainingFileList[i]
# take off .txt
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i, :] = fileUtil.img2vector('trainingDigits/%s' %
fileNameStr)
# iterate through the test set
testFileList = listdir('testDigits')
errorCount = 0.0
mTest = len(testFileList)
for i in range(mTest):
fileNameStr = testFileList[i]
# take off .txt
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
vectorUnderTest = fileUtil.img2vector('testDigits/%s' % fileNameStr)
classifierResult = kNN.classify(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 "\ntotal number of errors: %d" % errorCount
print "\ntotal error rate: %f" % (errorCount / float(mTest))
def datingClassTest():
# hold out for test
hoRatio = 0.50
# load data set from file
datingDataMat, datingLabels = fileUtil.file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = normalizer.autoNorm(datingDataMat)
m = normMat.shape[0]
numTestVecs = int(m * hoRatio)
errorCount = 0.0
for i in range(numTestVecs):
classifierResult = kNN.classify(normMat[i, :], normMat[numTestVecs:m, :], datingLabels[numTestVecs:m], 3)
print "classifier result: %d, real answer: %d" % (classifierResult, datingLabels[i])
if (classifierResult != datingLabels[i]):
errorCount += 1.0
print "total count: %s, error count: %s" % (numTestVecs, errorCount)
print "total error rate: %f" % (errorCount / float(numTestVecs))
def handwritingClassTest():
hwLabels = []
# load the training set
trainingFileList = listdir('trainingDigits')
m = len(trainingFileList)
trainingMat = zeros((m,1024))
for i in range(m):
fileNameStr = trainingFileList[i]
# take off .txt
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i,:] = fileUtil.img2vector('trainingDigits/%s' % fileNameStr)
# iterate through the test set
testFileList = listdir('testDigits')
errorCount = 0.0
mTest = len(testFileList)
for i in range(mTest):
fileNameStr = testFileList[i]
# take off .txt
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
vectorUnderTest = fileUtil.img2vector('testDigits/%s' % fileNameStr)
classifierResult = kNN.classify(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 "\ntotal number of errors: %d" % errorCount
print "\ntotal error rate: %f" % (errorCount/float(mTest))
def datingClassTest():
# hold out for test
hoRatio = 0.50
# load data set from file
datingDataMat, datingLabels = fileUtil.file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = normalizer.autoNorm(datingDataMat)
m = normMat.shape[0]
numTestVecs = int(m * hoRatio)
errorCount = 0.0
for i in range(numTestVecs):
classifierResult = kNN.classify(normMat[i, :],
normMat[numTestVecs:m, :],
datingLabels[numTestVecs:m], 3)
print "classifier result: %d, real answer: %d" % (classifierResult,
datingLabels[i])
if (classifierResult != datingLabels[i]):
errorCount += 1.0
print "total count: %s, error count: %s" % (numTestVecs, errorCount)
print "total error rate: %f" % (errorCount / float(numTestVecs))
