【机器学习实战——第2章】：K-近临算法

K-近邻算法概述

对未知类别属性中的数据集中的每个点依次执行以下操作：
（1）计算已知类别数据集中的点与当前点之间的距离
（2）按照距离递增排序
（3）选取与当前距离最小的K个点
（4）确定前K个点所在类别的出现频率
（5）返回前K个点中出现频率最高的类别作为预测分类

import numpy as np
import operator

def createDataSet():#创建数据集
    group = np.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]# .shape[0]返回的行数
    diffMat = np.tile(inX, (dataSetSize, 1)) - dataSet #在行上重复dataSetSize次，列上重复一次
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)# ，sum(0)表示每一列中的数相加，sum(1)表示每一行中的数相加
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()# 返回distances中元素从小到大排序后的索引值
    classCount = {}# 记录每个类别分别出现多少次
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]# 取出前k个元素的label
        # dict.get(key,default=None)，字典的get()方法，返回指定键的值，如果值不在字段中返回default
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
    # python3 中items()替代了iteritems()
    # key=operator.itemgetter(1)根据字典的值进行排序
    # key=operator.itemgetter(0)根据字典的键进行排序
    #sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
    sortedClassCount = sorted(classCount.items(), key=lambda x:x[1], reverse=True)
    # 返回次数最多的类别，即所要分类的类别
    return sortedClassCount[0][0]

使用K-近邻算法改进约会网站的配对效果

将文本记录转换为Numpy的解析程序

def file2matrix(filename):#将文本记录转换为NumPy的解析程序
    fr=open(filename)
    arrayOLines=fr.readlines()
    numberOfLines=len(arrayOLines)
    returnMat = np.zeros((numberOfLines, 3))
    classLabelVector=[]
    index=0
    for line in arrayOLines:
        line = line.strip()
        listFromLine=line.split('\t')
        returnMat[index, : ]=listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index+=1
    return returnMat,classLabelVector

分析数据：使用Matplotlib创建散点图

>>> import KNN
>>> datingDataMat,datingLabels=KNN.file2matrix('datingTestSet2.txt')
>>> import matplotlib
>>> import matplotlib.pyplot as plt
>>> fig = plt.figure()
>>> ax=fig.add_subplot(111)
>>> ax.scatter(datingDataMat[:,1],datingDataMat[:,2])
<matplotlib.collections.PathCollection object at 0x000001275459D240>
>>> plt.show()

>>> plt.scatter(datingDataMat[:,1],datingDataMat[:,2],15.0*np.array(datingLabels),15.0*np.array(datingLabels))
<matplotlib.collections.PathCollection object at 0x0000012754A37A90>

>>> plt.scatter(datingDataMat[:,0],datingDataMat[:,1],15.0*np.array(datingLabels),15.0*np.array(datingLabels))
<matplotlib.collections.PathCollection object at 0x0000012754D2D5F8>

归一化特征值

def autoNorm(dataSet):#归一化特征值
    minVals=dataSet.min(0)
    maxVals=dataSet.max(0)
    ranges=maxVals-minVals
    normDataSet=np.zeros(np.shape(dataSet))
    m=dataSet.shape[0]
    normDataSet = dataSet-np.tile(minVals,(m,1))
    normDataSet = normDataSet / np.tile(ranges, (m, 1))
    return normDataSet,ranges,minVals

分类器针对约会网站的测试代码

def datingClassTest():#分类器针对约会网站的测试代码
    hoRatio = 0.05
    datingDataMat,datingLabels=file2matrix('datingTestSet2.txt')
    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],10)
        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)))

构建完整可用系统

def classifyPerson():
    resultList=['not at all','in small doses','in large doses']
    percentTats=float(input("percentage of time spent playing video games?"))
    ffMiles=float(input("frequent flier miles earned per year?"))
    iceCream=float(input("liters of ice cream consumed per year?"))
    datingDataMat,datingLabels=file2matrix('datingTestSet2.txt')
    normMat,ranges,minVals=autoNorm(datingDataMat)
    inArr=np.array([ffMiles,percentTats,iceCream])
    classifierResult=classify0((inArr-minVals)/ranges,normMat,datingLabels,3)
    print("You will probably like this person: ",resultList[classifierResult-1])

手写数字识别系统

准备数据：将图像转换为测试向量

def img2vector(filename):
    returnVect=np.zeros((1,1024))
    fr=open(filename)
    for i in range(32):
        lineStr=fr.readline()
        for j in range(32):
            returnVect[0,i*32+j]=int(lineStr[j])
    return returnVect

测试算法：使用k-近邻算法识别手写数字

def handwritingClassTest():
    hwLabels=[]
    trainingFileList=os.listdir('trainingDigits')
    m=len(trainingFileList)
    trainingMat=np.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')
    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=classify0(vectorUnderTest,trainingMat,hwLabels,3)
        print("the classifier came up back with: %d, the real answer is %d" %(classifierResult,classNumStr))
        if(classifierResult!=classNumStr): errorCount+=1.0
    print("\n the total number of errors is: %d" % errorCount)
    print("\n thr total error rate is: %f" % (errorCount/float(mTest)))

本章完整代码

import numpy as np
import operator
from os import listdir

def createDataSet():#创建数据集
    group = np.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]#shape[0]返回的行数
    diffMat = np.tile(inX, (dataSetSize, 1)) - dataSet #在行上重复dataSetSize次，列上重复一次
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)#sum(0)表示每一列中的数相加，sum(1)表示每一行中的数相加
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()# 返回distances中元素从小到大排序后的索引值
    classCount = {}# 记录每个类别分别出现多少次
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]# 取出前k个元素的label
        # dict.get(key,default=None)，字典的get()方法，返回指定键的值，如果值不在字段中返回default
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
    # python3 中items()替代了iteritems()
    # key=operator.itemgetter(1)根据字典的值进行排序
    # key=operator.itemgetter(0)根据字典的键进行排序
    #sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
    sortedClassCount = sorted(classCount.items(), key=lambda x:x[1], reverse=True)
    # 返回次数最多的类别，即所要分类的类别
    return sortedClassCount[0][0]

def file2matrix(filename):#将文本记录转换为NumPy的解析程序
    fr=open(filename)
    arrayOLines=fr.readlines()
    numberOfLines=len(arrayOLines)
    returnMat = np.zeros((numberOfLines, 3))
    classLabelVector=[]
    index=0
    for line in arrayOLines:
        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):#归一化特征值
    minVals=dataSet.min(0)
    maxVals=dataSet.max(0)
    ranges=maxVals-minVals
    normDataSet=np.zeros(np.shape(dataSet))
    m=dataSet.shape[0]
    normDataSet = dataSet-np.tile(minVals,(m,1))
    normDataSet = normDataSet / np.tile(ranges, (m, 1))
    return normDataSet,ranges,minVals

def datingClassTest():#分类器针对约会网站的测试代码
    hoRatio = 0.05
    datingDataMat,datingLabels=file2matrix('datingTestSet2.txt')
    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],10)
        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)))

def classifyPerson():
    resultList=['not at all','in small doses','in large doses']
    percentTats=float(input("percentage of time spent playing video games?"))
    ffMiles=float(input("frequent flier miles earned per year?"))
    iceCream=float(input("liters of ice cream consumed per year?"))
    datingDataMat,datingLabels=file2matrix('datingTestSet2.txt')
    normMat,ranges,minVals=autoNorm(datingDataMat)
    inArr=np.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=np.zeros((1,1024))
    fr=open(filename)
    for i in range(32):
        lineStr=fr.readline()
        for j in range(32):
            returnVect[0,i*32+j]=int(lineStr[j])
    return returnVect

def handwritingClassTest():
    hwLabels=[]
    trainingFileList=listdir('trainingDigits')
    m=len(trainingFileList)
    trainingMat=np.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')
    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=classify0(vectorUnderTest,trainingMat,hwLabels,3)
        print("the classifier came up back with: %d, the real answer is %d" %(classifierResult,classNumStr))
        if(classifierResult!=classNumStr): errorCount+=1.0
    print("\n the total number of errors is: %d" % errorCount)
    print("\n thr total error rate is: %f" % (errorCount/float(mTest)))