###《Machine Learning in Action》 - KNN

初学Python；理解机器学习。
算法是需要实现的，纸上得来终觉浅。

// @author:       gr
// @date:         2015-01-16
// @email:        forgerui@gmail.com

一、简单的KNN

from numpy import *
import operator

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):
    # 求输入向量与各个样例的距离
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX, (dataSetSize, 1)) - dataSet
    sqDiffMat = diffMat ** 2
    sqDistances = sqDiffMat.sum(axis = 1)
    distances = sqDistances ** 0.5
    
    # 按距离递增排序
    sortedDistIndicies = distances.argsort()
    classCount = {}
    
    # 对前k个样例的标签进行计数
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
    
    # 按照计数对标签进行递减排序
    sortedClassCount = sorted(classCount.iteritems(),
            key = operator.itemgetter(1), reverse=True)
    
    # 返回最多计数的标签，即为该输入向量的预测标签
    return sortedClassCount[0][0]

二、KNN用于约会网站配对效果

def file2matrix(filename):
    # 读取文件
    fr = open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)
    
    returnMat = zeros((numberOfLines, 3))
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        # 去除换行符
        line = line.strip()
        # 按Tab键分割列
        listFromLine = line.split('\t')
        returnMat[index, :] = listFromLine[0:3]
        # 存储标签
        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))
    # 数据的行数
    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('datingTestSet2.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    # 选取测试集数量
    numTestVecs = int(m * hoRatio)
    errorCount = 0.0
    for i in range(numTestVecs):
        classifierResult = classify0(normMat[i, :], normMat[numTestVecs:m, :], \
                datingLabels[numTestVecs:m], 7)
        print "the classifirer came back with: %d, the real answer is: %d"\
                % (classifierResult, datingLabels[i])
        # 记录错误数
        if (classifierResult != datingLabels[i]) : errorCount += 1.0
    print "numTestVecs: %f" % float(numTestVecs)
    print "the total error rate is: %f" % (errorCount/float(numTestVecs))

def classifyPerson():
    # 针对一个人判断
    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]

三、手写识别系统

def img2vector(filename):
    # 32*32的图片转成一个向量
    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)
    trainingMat = zeros((m, 1024))
    # 把训练的文件图片转换成一个m*1024矩阵
    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
    # 在测试集上测试
    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 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 the total error rate is: %f" % (errorCount/float(mTest))