from numpy import *
from os import listdir #used in the handwritting example
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
sqDistances = sqDiffMat.sum(axis=1)
distances = sqDistances**0.5
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 file2matrix(filename):
fr = open(filename)
numberOfLines = len(fr.readlines())
returnMat = zeros((numberOfLines,3))
classLabelVector = []
fr = open(filename)
index = 0
for line in fr.readlines():
line = line.strip()
listFromLine = line.split('\t')
returnMat[index,:] = listFromLine[0:3]
classLabelVector.append((listFromLine[-1])) #int() is not useful
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 = 0.10
datingDataMat, datingLabels = file2matrix('datingTestSet2.txt') #The class value in this file is numeric while it is nominal, which we do not need in datingTestSet(same reason as below).
normMat, rangs, 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)
if (classifierResult !=datingLabels[i]):
errorCount +=1.0
print "the classifier came back with: %d, the real answer is: %d" %(int(classifierResult), int(datingLabels[i]))
print "the total error rate is: %f" %(errorCount/float(numTestVecs))
#in python shell commond line, one is "ax.scatter(datingDataMat[:,1], datingDataMat[:,2],
15.0*array(datingLabels), 15.0*array(datingLabels))"
#which needs to be corrected as "ax.scatter(datingDataMat[:,1], datingDataMat[:,2],
15.0*array(map(int,datingLabels)), 15.0*array(map(int,datingLabels)))"
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[int(classifierResult)-1] #needs to compulsively transfer the data type
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')
trainingFileList1 = trainingFileList[1:len(trainingFileList)]
#to get rid of the first element in list, which is ".DS_Store". It may cause bad effect on the file reading.
#Why? Due to the mechanism of the storage of OS X folder that automatically add ".DS_Store" as a default?
m = len(trainingFileList1)
trainingMat = zeros((m,1024))
for i in range(m):
fileNameStr = trainingFileList1[i]
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr)
testFileList = listdir('testDigits')
testFileList1 = testFileList[1:len(testFileList)]
#The reason is the same as the above instance
errorCount = 0.0
mTest = len(testFileList1)
for i in range(mTest):
fileNameStr = testFileList1[i]
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
vectorUnderTest = img2vector('testDigits/%s' % fileNameStr) # '%'sign is for connecting two component
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))
from os import listdir #used in the handwritting example
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
sqDistances = sqDiffMat.sum(axis=1)
distances = sqDistances**0.5
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 file2matrix(filename):
fr = open(filename)
numberOfLines = len(fr.readlines())
returnMat = zeros((numberOfLines,3))
classLabelVector = []
fr = open(filename)
index = 0
for line in fr.readlines():
line = line.strip()
listFromLine = line.split('\t')
returnMat[index,:] = listFromLine[0:3]
classLabelVector.append((listFromLine[-1])) #int() is not useful
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 = 0.10
datingDataMat, datingLabels = file2matrix('datingTestSet2.txt') #The class value in this file is numeric while it is nominal, which we do not need in datingTestSet(same reason as below).
normMat, rangs, 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)
if (classifierResult !=datingLabels[i]):
errorCount +=1.0
print "the classifier came back with: %d, the real answer is: %d" %(int(classifierResult), int(datingLabels[i]))
print "the total error rate is: %f" %(errorCount/float(numTestVecs))
#in python shell commond line, one is "ax.scatter(datingDataMat[:,1], datingDataMat[:,2],
15.0*array(datingLabels), 15.0*array(datingLabels))"
#which needs to be corrected as "ax.scatter(datingDataMat[:,1], datingDataMat[:,2],
15.0*array(map(int,datingLabels)), 15.0*array(map(int,datingLabels)))"
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[int(classifierResult)-1] #needs to compulsively transfer the data type
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')
trainingFileList1 = trainingFileList[1:len(trainingFileList)]
#to get rid of the first element in list, which is ".DS_Store". It may cause bad effect on the file reading.
#Why? Due to the mechanism of the storage of OS X folder that automatically add ".DS_Store" as a default?
m = len(trainingFileList1)
trainingMat = zeros((m,1024))
for i in range(m):
fileNameStr = trainingFileList1[i]
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr)
testFileList = listdir('testDigits')
testFileList1 = testFileList[1:len(testFileList)]
#The reason is the same as the above instance
errorCount = 0.0
mTest = len(testFileList1)
for i in range(mTest):
fileNameStr = testFileList1[i]
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
vectorUnderTest = img2vector('testDigits/%s' % fileNameStr) # '%'sign is for connecting two component
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))