K-Nearest Neighbors algorithm

from numpy import *
import operator
import matplotlib
import matplotlib.pyplot as plt
from os import listdir

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

group, labels = createDataSet()
  
def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX, (dataSetSize, 1))-dataSet
    sqDiffMat = diffMat ** 2
    sqlDistances = sqDiffMat.sum(axis=1)
    distances = sqlDistances**0.5
    sortedDistIndicies = distances.argsort()
    classCount = {}
    for i in range(k):
        voteLabel = labels[sortedDistIndicies[i]]
        classCount[voteLabel] = classCount.get(voteLabel, 0)+1
    
    sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
   # print sortedClassCount
    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])
        index += 1
    return returnMat, classLabelVector
    
datingDataMat, datingLabels = file2matrix('datingTestSet.txt')

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('datingTestSet.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    numTestVecs = int(m*hoRatio)
    errCount = 0.0
    
    for i in range(numTestVecs):
        classifierResult = classify0(normMat[i,:], normMat[numTestVecs:m,:], datingLabels[numTestVecs:m], 4)
        print 'the classifier came back with: %s, the real answer is: %s' % (classifierResult, datingLabels[i])
        if(classifierResult != datingLabels[i]):
            errCount += 1.0
    print "the total error rate is: %f" % (errCount/float(numTestVecs))
    

def classifyPerson():
    resultList = ['not at all', 'in small doses', 'in large doses']
    percentTats = float(raw_input("percent of time spent playing video games?"))
    ffMiles = float(raw_input("frequent filter miles earned per year?"))
    iceCream = float(raw_input("liters of ice cream consumed per year?"))
    
    datingDataMat, datingLabels = file2matrix('datingTestSet.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)
    inArr = array([percentTats, ffMiles, 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')
    m=len(trainingFileList)
    #print "m=",m
    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('trainingDigits/%s' % fileNameStr)
        
    testFileList = listdir('testDigits')
    errCount = 0.0
    mTest = len(testFileList)
    
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = fileStr.split('_')[0]
        vectorUnderTest = img2vector('testDigits/%s' % fileNameStr)
        classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
        print "the classifier came back with: %s, the real answer is: %s" % (classifierResult, classNumStr)
        #print 'classifierResult = ', classifierResult,"classNumStr = ", classNumStr
        if (int(classifierResult) != int(classNumStr)):
            errCount += 1.0
    
    print "\n the total number of error is: %d" % (errCount)
    print "\n the total error rate is: %f" % (errCount/float(mTest))