《机器学习实战》学习笔记（二、k-近邻算法）

# -*- coding: utf-8 -*-
'''
Created on Sep 16, 2010
kNN: k Nearest Neighbors

Input:      inX: vector to compare to existing dataset (1xN)
            dataSet: size m data set of known vectors (NxM)
            labels: data set labels (1xM vector)
            k: number of neighbors to use for comparison (should be an odd number)
            
Output:     the most popular class label

@author: pbharrin
'''
from numpy import *
import operator
from os import listdir
#k-近邻算法
#classify0()函数有4个输入参数：
#用于分类的输入向量是inX，
#输入的训练样本集为dataSet,
#标签向量为labels
#最后的参数表示用于选择最近邻居的数目
#其中标签向量的元素数目和矩阵dataSet的行数相同。
def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    #1计算欧式距离
    diffMat = tile(inX, (dataSetSize,1)) - dataSet
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()##numpy.argsort:Returns the indices that would sort an array     
    classCount={} 
    #2选择距离最小的k个点         
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    #3进行排序
    sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

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

#将文本记录到转换NumPy
def file2matrix(filename):
    fr = open(filename)
    #得到文件行数
    numberOfLines = len(fr.readlines())         #get the number of lines in the file
    #创建返回以0填充的NumPy矩阵    
    #为了简化处理，将矩阵的另一维度设置为固定值3，可以按照自己的实际需求增加相应的代码以适应变化的输入值。
    returnMat = zeros((numberOfLines,3))        #prepare matrix to return
    classLabelVector = []                       #prepare labels return   
    fr = open(filename)
    index = 0
    #解析文件数据到列表，循环处理文件中每行数据。
    for line in fr.readlines():
        #首先使用函数line.strip()截取掉所有的回车字符
        line = line.strip()
        #使用tab字符\t将上一步得到的整行数据分割成一个元素列表listFormLine
        listFromLine = line.split('\t')
        #取出前3个元素存储到特征矩阵中
        returnMat[index,:] = listFromLine[0:3]
        #python可以使用索引值-1得到列表的最后一列元素，将列表的最后一列存储到向量classLabelVecter中。
        #此处明确通知解释器，告诉它列表中存储的元素值为整型，否则Python会将其作为字符串处理
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat,classLabelVector
 
#数据归一化公式，自动将数字特征值转化为0到1区间内的值   
def autoNorm(dataSet):
    #将每一列的最小值放在变量minVals中，最大值放在maxVals中
    #dataSet.min(0)中的参数0使得函数可以从列中选取最小值，而不是选取当前行的最小值
    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))
    #特征值相除
    normDataSet = normDataSet/tile(ranges, (m,1))   #element wise divide
    return normDataSet, ranges, minVals
   
#分类器针对约会网站的测试代码
def datingClassTest():
    hoRatio = 0.50      #hold out 10%
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file
    normMat, ranges, minVals = autoNorm(datingDataMat)
    #首先使用file2matrix和autoNorm（）函数从文件中读取数据并将其转换问归一化特征值
    #接着计算测试向量的数量，此步决定了normMat向量中哪些数据用于测试，哪些用于分类器的训练样本
    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
    #然后将这两部分数据输入到原始kNN分类函数classify0
    #最后，函数计算错误率并输出结果

#将图片 
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))