Python机器学习实战笔记之KNN算法

<pre name="code" class="plain"><pre name="code" class="plain">1、k-近邻算法
测量不同特征值之间的距离方法进行分类
优 点 ：精度高、对异常值不敏感、无数据输入假定。
缺点：计算复杂度高、空间复杂度高。
适用数据范围：数值型和标称型。

(常用欧氏距离)
1收集数据2准备数据3分析数据4训练算法5测试算法6使用算法	

Python中识别中文
文件开头添加
#coding:utf-8

k近邻法与kd树
为了提高k近邻搜索的效率，可以考虑使用特殊的结构存储训练数据，以减少计算距离的次数。具体方法有很多，这里介绍kd树方法
参考
http://blog.youkuaiyun.com/qll125596718/article/details/8426458

Python版实现
http://blog.youkuaiyun.com/q383700092/article/details/51757762
R语言版调用函数
http://blog.youkuaiyun.com/q383700092/article/details/51759313
MapReduce简化实现版
http://blog.youkuaiyun.com/q383700092/article/details/51780865
spark版
后续添加

<span style="font-size: 13.3333px;">from numpy import * # 科学计算包</span>

import operator  # 运算符模块
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
#KNN算法核心 inx需要分类的向量，训练样本dataSet标签向量labels 近邻的数目
#调用格式KNN.classify0([0,0], group, labels, 3)
def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]  #向量大小n
    diffMat = tile(inX, (dataSetSize,1)) - dataSet  #分类向量1重复n次减去训练样本
    sqDiffMat = diffMat**2  #**代表幂计算 2次方
    sqDistances = sqDiffMat.sum(axis=1)  #计算每行的和
    distances = sqDistances**0.5  #每个数开根号
    sortedDistIndicies = distances.argsort()  #升序排序后的数据原来位置的下标
    classCount={}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]] #將排序后的labers輸出(从多到少的标号选出3个)
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1 #get(k,d)如果k不在classCount为d
    #将classCount按照第二字段排序
    sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
    #返回最近3个值的里最近的那个值的标签
    return sortedClassCount[0][0]

#将文本记录到转换NumPy的解析程序
#datingDataMat,datingLabels=KNN.file2matrix('G:/python/pythonwork/datingTestSet2.txt')
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()  #去除首尾空格
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))  #索引值-1表示列表中的最后一列元素
        index += 1
    return returnMat,classLabelVector
#归一化
#normMat, ranges, minVals=KNN.autoNorm(datingDataMat)
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
#分类器结果 KNN.datingClassTest()
def datingClassTest():
    hoRatio = 0.50      #hold out 10%
    datingDataMat,datingLabels = file2matrix('G:/python/pythonwork/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 "error: %f,total:  %d" % (errorCount,numTestVecs)

数字识别

#将图像转换为向量
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
#构建手写识别系统
def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('G:/python/pythonwork/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('G:/python/pythonwork/trainingDigits/%s' % fileNameStr)
    testFileList = listdir('G:/python/pythonwork/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('G:/python/pythonwork/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))

k近邻法与kd树
为了提高k近邻搜索的效率，可以考虑使用特殊的结构存储训练数据，以减少计算距离的次数。具体方法有很多，这里介绍kd树方法
参考
http://blog.youkuaiyun.com/qll125596718/article/details/8426458