机器学习（K邻近算法）

算法描述

K邻近算法采用测量不同特征值之间的距离方法进行分类

工作原理

存在一个样本数据集合，也称作训练样本集，并且样本集中每个数据都存在标签，即我们知道样本集中每一数据与所属分类的对应关系。输入没有标签的新数据后，将新数据的每个特征与样本集中数据对应的特征进行比较

然后算法提取样本集中最相似的数据（最邻近）的分类标签。一般来说，我们只选择样本数据集中前K个最相似的数据，这就是K-邻近算法中K的出处，通常K是不大于20的整数。最后，选择K个最相似的数据中出现次数最多

的分类，作为新数据的分类

算法的类别

该算法属于监督学习，用于分类，因而其目标变量是分散的

优点

对异常数据值不敏感，精度高，无数据输入设定

缺点

空间计算复杂度高

算法的一般流程

收集数据

准备数据

分析数据

训练算法

测试算法

使用算法

KNN算法实现代码

from numpy import *
import operator
from os import listdir
import matplotlib
import matplotlib.pyplot as plt

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]]
        #对类计数
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
    #选取出现次数最多的
    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




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('	')
        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 = 0.50      #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


 

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):
        #读取图片文件名 0_1.txt
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        classNumStr = int(fileStr.split('_')[0])
        #标记标签
        hwLabels.append(classNumStr)
        trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr)
    #测试模型
    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 "
the total number of errors is: %d" % errorCount
    print "
the total error rate is: %f" % (errorCount/float(mTest))

  
if __name__ == "__main__":
#    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')
#    ranges= autoNorm(datingDataMat)
#    fig = plt.figure()
#    ax = fig.add_subplot(111)
#    ax.scatter(datingDataMat[:,1],datingDataMat[:,2],s = 15.0*array(datingLabels),c = array(datingLabels))
#    ax.scatter(datingDataMat[:,1],datingDataMat[:,2],c = 'r')
#    dataMatX = array([[1,2,3],[4,5,6],[7,8,9]])
#    dataMatY = array([[2,4,6],[8,10,12],[14,16,18]])
#    big = array([11,21,31])
#    ax.scatter(dataMatX[:,1],dataMatY[:,1],s = 15.0*big,c = big)
#    plt.show()
#    print array(datingLabels)
#    print datingDataMat
     handwritingClassTest()