k-近邻算法

听朋友说machine Learning 很牛，特地买了本《机器学习实战》，了解机器学习，顺便学习python。。

第一个算法是kNN，很容易理解，简单实用，但是存储和计算的复杂度有点高，而且无法给出数据的内在含义。

书中介绍的两个实例，让我感觉机器学习确实很实用，以下是从《机器学习实战》中整理摘抄的python代码

实例1：实用kNN改进约会网站的配对效果

from  numpy import *

import operator
from nt import listdir

#kNN算法实现
def classify0(intx, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffmat = tile(intx, (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]]
#         print(type(classCount))
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

#从文件中获取数据
def fileTomatrix(filename):
    fr = open(filename)
    arrayLines = fr.readlines()
    numberOfLines = len(arrayLines)
    returnMat = zeros((numberOfLines, 3))
    classLabelVector = []
    index = 0
    for line in arrayLines:
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index, :] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat, classLabelVector

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

def classifyPerson():
    result=['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 years?"))
    iceCream=float(input("liters of iceCream consumed per year?"))
    
    inArr = array([ffMiles, percentTats, iceCream])
    
    datingDataMat, datingLabels = fileTomatrix('dataSet.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)
    classifierResult = classify0((inArr - minVals) / ranges, normMat, datingLabels, 3)
    
    print("You will probably like this person:",result[classifierResult - 1])
    

实例2：实用kNN识别手写数字

from  numpy import *

import operator
from nt import listdir

#kNN算法实现
def classify0(intx, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffmat = tile(intx, (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]]
#         print(type(classCount))
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]


def image2vector(filename):
    returnResult = zeros((1,1024))
    fr = open(filename)
    for i in range(32):
        listStr = fr.readline()
        for j in range(32):
            returnResult[0,32*i+j] = int(listStr[j])
    return returnResult


def handwritingClassTest():
    trainingFileList = listdir('trainingDigits')
    m = len(trainingFileList)
  
    #得到训练数据     
    trainingMat = zeros((m,1024))
    hwLabels = []
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr= fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i,:] = image2vector('trainingDigits/%s' % fileNameStr)
    
    testFileList = listdir('testDigits')
    errorCount = 0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr= fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        vectorUnderTest = image2vector('testDigits/%s'%fileNameStr)
        classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 5)
        
        print("the classifier came back with: %d,the real number is: %d"\
              %(classifierResult,classNumStr))
        if classifierResult != classNumStr:
            errorCount +=1
    print("\nthe total number of errors is : %d" %errorCount)
    print("\nthe total error rate is %f" % (errorCount/mTest))