《机器学习实战》之kNN-笔记1

2 python k近邻算法

便于阅读，先贴完整代码，有个大致印象。后面再分布讲解

# -*- coding: utf-8 -*-
"""
Created on Sat Sep 17 15:31:01 2016

@author: 打江南走过一阵
"""

from numpy import *
import operator
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

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())         #get the number of lines in the file
    returnMat = zeros((numberOfLines,3))        #prepare matrix to return
    classLabelVector = []                       #prepare labels return   
    fr = open(filename)
    index = 0
    for line in fr.readlines():
        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):
    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))   #element wise divide
    return normDataSet, ranges, minVals
    
def datingClassTest():
    hoRatio = 0.10      #hold out 10%
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file
    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],3)
        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))
    print errorCount
    
    #输入某人的信息，便得出对对方喜欢程度的预测值  
    #python中raw_input允许用户输入文本行命令并返回用户所输入的命令
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[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')           #load the training set
    m = len(trainingFileList)
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr)
    testFileList = listdir('testDigits')        #iterate through the test set
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        classNumStr = int(fileStr.split('_')[0])
        vectorUnderTest = img2vector('testDigits/%s' % fileNameStr)
        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))

2.1算法简单说明

这个算法主要工作是测量不同特征值之间的距离，有个这个距离，就可以进行分类了。

简称kNN。

已知：训练集，以及每个训练集的标签。

接下来：和训练集中的数据对比，计算最相似的k个距离。选择相似数据中最多的那个分类。作为新数据的分类。

 

fromnumpy import *#引入科学计算包
import operator #经典python函数库。运算符模块。
#创建数据集
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
#算法核心
#inX：用于分类的输入向量。即将对其进行分类。
#dataSet：训练样本集
#labels:标签向量
def classfy0(inX,dataSet,labels,k):
    #距离计算
    dataSetSize =dataSet.shape[0]#得到数组的行数。即知道有几个训练数据。.shape[0]读取第一维度长度
    diffMat    =tile(inX,(dataSetSize,1))-dataSet#tile:numpy中的函数。tile将原来的一个数组，扩充成了4个一样的数组。diffMat得到了目标与训练数值之间的差值。
    sqDiffMat   =diffMat**2#各个元素分别平方
    sqDistances =sqDiffMat.sum(axis=1)# sum函数中加入参数。sum（a，axis=0）或者是.sum(axis=1)axis=0 就是普通的相加；加入axis=1以后就是将一个矩阵的每一行向量相加
    distances   =sqDistances**0.5#开方，得到距离。
    sortedDistIndicies=distances.argsort()#升序排列
    #选择距离最小的k个点。
    classCount={}
    for i in range(k):
       voteIlabel=labels[sortedDistIndicies[i]]
       classCount[voteIlabel]=classCount.get(voteIlabel,0)+1
    #排序
   sortedClassCount=sorted(classCount.iteritems(),key=operator.itemgetter(1),reverse=True)
    return sortedClassCount[0][0]

函数再解释：

.shape用于计算array各维度的长度，在python中都是从0开始的。

tile函数是numpy包中的，用于重复array，比如上面代码中的tile(inX,(dataSetSize,1))，表示重复inX，其行重复dataSetSize次，而列不重复

.sum是numpy中用于计算一个array内部行列求和，axis=1表示按列求和，即把每一行的元素加起来

.argsort是numpy中对array进行排序的函数，排序是升序

classCount = {} 其中{}表示生成的是字典，在字典这个类中，有方法get，对classCount元素赋值，其实是个计数器

sorted是内置函数，可以help(sorted)查看用法operator模块下的itemgetter函数，顾名思义就是提取第X个元素的意思

 

 2.2示例：改进约会网站配对效果

2.2.1准备数据：从文本文件共解析数据

def file2matrix(filename):
    fr = open(filename)
    numberOfLines = len(fr.readlines())         #get the number of lines in the file
    returnMat = zeros((numberOfLines,3))        #prepare matrix to return
    classLabelVector = []                       #prepare labels return   
    fr = open(filename)
    index = 0
    for line in fr.readlines():
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat,classLabelVector

>>>reload(kNN)

>>>datingDataMat,datingLabels = kNN.file2matrix('datingTestSet2.txt')#此处为datingTestSet2.txt ，书中datingTestSet.txt错误！！

2.2.2分析数据：使用Matplotlib创建散点图

import matplotlib
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:,1],datingDataMat[:,2])
plt.show()

##不知什么错误，plt.show后没有显示图像，在导入下面两句后，图像显示。
import matplotlib as mpl
mpl.use('Agg')

图2-3 没有样本类别标签的约会数据散点图

利用颜色及尺寸标识数据点的属性类别。代码如下：

>>>ax.scatter(datingDataMat[:,1],datingDataMat[:,2],15.0*array(datingLabels),15.0*array(datingLabels))

图2-4 带样本类别标签的约会数据散点图

图2-3和图2-4中散点图采用datingDataMat矩阵中的第二列、第三列数据。虽然图2-4能够比较容易区分数据点从属类别，但依然很难根据这张图得出结论性信息。

针对上述不足，图2-5采用datingDataMat矩阵中的第一列、第二列数据，可以清晰的标识三个不同的样本分类区域。

ax.scatter(datingDataMat[:,0],datingDataMat[:,1],15.0*array(datingLabels),15.0*array(datingLabels))

图2-5 带样本类别标签的约会数据散点图

2.2.3 准备数据：归一化

为防止距离计算中，大数吃小数现象，在距离计算之前需要将数据归一化。

方法是：newValue = (oldValue - min) / (max - min)

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))   #element wise divide
    return normDataSet, ranges, minVals

重新加载kNN.py，函数归一化后的执行结果如下：

2.2.4 测试算法：作为完整程序验证分类器

定义一个计数器变量，每次分类器错误的分类数据，计数器就加1，程序执行完成后计数器的结果除以数据点总数即是错误率。

def datingClassTest():
    hoRatio = 0.10      #hold out 10%
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file
    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],3)
        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))
    print errorCount

重新加载kNN，输入

>>>kNN.datingClassTest()

结果显示错误率是5%

2.2.5 使用算法：构建完整可用系统

#输入某人的信息，便得出对对方喜欢程度的预测值  
#python中raw_input允许用户输入文本行命令并返回用户所输入的命令
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[classifierResult - 1] 

 现在分类器已经构建好了，用户可以自己输入数据，得到对他的喜好程度。

2.3 示例：手写识别系统

#将图像转换为测试向量
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  

#将 from os import listdir 写在文件起始部分
#测试代码
def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('trainingDigits')           #load the training set
    m = len(trainingFileList)
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr)
    testFileList = listdir('testDigits')        #iterate through the test set
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        classNumStr = int(fileStr.split('_')[0])
        vectorUnderTest = img2vector('testDigits/%s' % fileNameStr)
        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))

重新加载kNN,输入

>>>kNN.handwritingClassTest()

执行结果如下：