机器学习实践-Ch02 kNN分类算法

#!/usr/bin/env python
# encoding: utf-8

#========================================================================
#                   MACHINE LEARNING IN ACTION - CH02
#                       kNN classify algorithm
#                     Typed in Feb 14, 2016 by Alex
#========================================================================

from numpy import *
import operator

def classify_0(inX,dataSet,labels,k):
    sizeOfDS=dataSet.shape[0]
    # --> tile()
    # Build a matrix with sizeOfDS rows and 1 column
    # to calculate the differences.
    diffMat=tile(inX,(sizeOfDS,1))-dataSet
    sqDiffMat=diffMat**2
    sqDistances=sqDiffMat.sum(axis=1)
    distances=sqDistances**0.5
    # --> argsort()
    # Sort the members of a matrix and return the sorted index of each.
    sortedDistIndicies=distances.argsort()
    classCount={}
    for i in range(k):
        voteInLabel=labels[sortedDistIndicies[i]]
    # --> dict.get()
    # Append a item to the dict and set default as the second parameter.
        classCount[voteInLabel]=classCount.get(voteInLabel,0)+1
    # --> sorted
    # Sort members of object by key(mutiple dimension)
    # and reverse's default key if False which means return ascenting sequence.
    # --> items()
    # Return the items in a couple.
    sortedClassCount=sorted(classCount.items(),\
    # --> operator.itemgetter()
    # Get and return the indicated dimension members of object.
                            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.strip()
    # Return a copy of the string with the leading
    # and trailing characters removed.
        line=line.strip()
    # -->line.split()
    # Get the contents from file in line seperated by Tab character.
        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))
    row=dataSet.shape[0]
    normDataSet=dataSet-tile(minVals,(row,1))
    normDataSet=normDataSet/tile(ranges,(row,1))
    return normDataSet,ranges,minVals

def datingClassTest():
    hoRatio=0.10
    datingDataMat,datingLabels=file2matrix('datingTestSet2.txt')
    normMat,ranges,minVals=autoNorm(datingDataMat)
    row=normMat.shape[0]
    numTestVecs=int(row*hoRatio)
    errorCount=0.0
    for i in range(numTestVecs):
        classifierResult=classify_0(normMat[i,:],\
                                  normMat[numTestVecs:row,:],\
                                  datingLabels[numTestVecs:row],\
                                  3)
        print("the classifier came back with: %d, the real answer is: %d"\
              % (classifierResult,datingLabels[i]))
        if(classifierResult!=datingLabels[i]):errorCount+=1.0
    print("=============================================================")
    print("the total error rate is: %f" % (errorCount/float(numTestVecs)))

def classifyPerson():
    resultList=['not at all','in small doses','in large doses']
    # input has replaced the raw_input function
    # in python 3.x and they are almost the same.
    print("=============================================================")
    print("-----------DATING CLASSIFICATION BY KNN ALGORITHM------------")
    print("=============================================================")
    percentTats=float(input(\
                    "\tPercentage of time spent playing video games?\t"))
    ffMiles=float(input("\tFrequent flier miles earned per year?\t\t"))
    iceCream=float(input("\tLiters of ice cream consumed per year?\t\t"))
    datingDataMat,datingLabels=file2matrix('datingTestSet2.txt')
    normMat,ranges,minVals=autoNorm(datingDataMat)
    inArr=array([ffMiles,percentTats,iceCream])
    classifierResult=classify_0((inArr-minVals)/ranges,\
                                normMat,datingLabels,\
                                3)
    print("=============================================================")
    print("    You will probably like this person:      ",\
          resultList[classifierResult-1])

#------------------------------------------------------------------------
#   Ch02 handwriting congition system by kNN algorithm
#------------------------------------------------------------------------
def img2vector(filename):
    returnVect=zeros((1,1024))
    fr=open(filename)
    for i in range(32):
        lineStr=fr.readline()#readline() just read one line
        for j in range(32):
            returnVect[0,32*i+j]=int(lineStr[j])
    return returnVect
def handwritingClassTest():
    hwLabels=[]
    trainlingFileList=listdir('trainingDigits')
    m=len(trainlingFileList)
    trainingMat=zeros((m,1024))
    for i in range(m):
        fileNameStr=trainlingFileList[i]
        fileStr=fileNameStr.split('.')[0]
        classNumStr=int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i,:]=img2vector('trainingDigits/%s' % fileNameStr)
    testFileList=listdir('testDigits')
    errorCount=0.0
    mTest=len(testFileList)
    for i in range(mTest):
        fileNameStr=testFileList[i]
        fileStr=fileNameStr.split('.')[0]
        classNumStr=int(fileStr.split('_')[0])
        vectorUnderTest=img2vector('testDigits/%s' % fileNameStr)
        classifierResult=classify_0(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)))