1、k-邻近算法

1、首先要搭建环境

这里需要numpy、scipy、matplotlib三个库，下载地址如下，双击安装即可：

（需要注意python的版本号和32/64位）

numpy：http://sourceforge.net/projects/numpy/files/NumPy/1.7.0/
matplotlab：http://sourceforge.net/projects/matplotlib/files/matplotlib/matplotlib-1.1.1/
scipy：http://sourceforge.net/projects/scipy/files/scipy/0.12.0/

然后来个最简单的例子：

import pylab as pl
listOfInt = []
for c in range(10):
    listOfInt.append(c*2)
print listOfInt
pl.plot(listOfInt)
pl.show()

这个程序相当于绘制y=2x的图像

结果如下：

2、k-邻近算法

kNN算法非常简单，不再详述它的思路。这段代码来自《机器学习实战》一书，感觉数据集挺理想化的，分类出来效果还是不错的。

代码中只对classify0做了详细注释，其他部分不太重要，我们可以忽略。

测试代码：

# -*- coding: utf-8 -*- 
from numpy import *
import operator
import matplotlib
import matplotlib.pyplot as plt
from os import listdir

def createDatabase():
    groups=array([[1.0,1,1],[1.0,1.0],[0,0],[0,0.1]])
    labels=['A','A','B','B']
    return groups,labels

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]    #shape[0]就是读取矩阵第一维度的长度
    diffMat = tile(inX, (dataSetSize,1)) - dataSet  #tile：构造dataSetSize*1个copy
    sqDiffMat = diffMat**2     #各个项平方
    sqDistances = sqDiffMat.sum(axis=1)#sum(axis=0),普通相加;axis=1,将一个矩阵的每一行向量相加
    distances = sqDistances**0.5     #开根
    sortedDistIndicies = distances.argsort()   #argsort:返回排序的位次,参考补充1
    classCount={}          
    for i in range(k):       #这是一段计数过程
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    #sorted参考python下相关日志
    sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
    #iteritor是迭代器的意思，一次返回一个数据项，直到没有为止
    #operator模块提供的itemgetter函数用于获取对象的哪些维的数据，参数为一些序号（即需要获取的数据在对象中的序号）
    return sortedClassCount[0][0]

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('\t')
        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):
        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))


if __name__ == "__main__":
    #约会测试
    datingClassTest()
    #手写测试
    handwritingClassTest()
    

测试结果：

约会：the total error rate is: 0.064000

手写数字：the total error rate is: 0.011628

感觉挺准的，有点离谱了

我猜想数据集是线性可分的（或者近似线性可分），才会得到这么好的结果。

如图，分的还是挺开的。