kNN算法的python代码和注释

因为用matalb较多，刚接触pyton很多代码不懂，给出一些注释。只注释部分函数，不解释算法。

对算法的详细注释请参考：k-近邻算法(k-Nearest Neighbor)  http://m.blog.csdn.net/article/details?id=52032520&from=singlemessage&isappinstalled=0

'''
Created on Sep 16, 2010
kNN: k Nearest Neighbors

Input:      inX: vector to compare to existing dataset (1xN)
            dataSet: size m data set of known vectors (NxM)
            labels: data set labels (1xM vector)
            k: number of neighbors to use for comparison (should be an odd number)
            
Output:     the most popular class label

@author: pbharrin
'''
from numpy import *
import operator
from os import listdir

#这个listdir是用来列出文档路径的

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]

#dataSet.shape[0],类似于matalb里的size（dataSet，1）
    diffMat = tile(inX, (dataSetSize,1)) - dataSet

#tile类似于matalb里的repmat tile([1,1],(2,2))就是把【1，1】复制成两行两列的矩阵
    sqDiffMat = diffMat**2

#这的**就是求平方，但***不是求3次方

#程序写到此处相当于求了个欧式距离
    sqDistances = sqDiffMat.sum(axis=1)

#a.sum(),对矩阵a里所有元素求和，a.sum(axis=1),对每一行求和，a.sum(axis=0)对每一列求和
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort() 

#argsort（）是用来排序的函数 ，还有几个sort sorted这个多百度多看看，我试验半天没明白，最后还是得百度   
    classCount={}          
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
    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

#生成了一个numberOfLines*3的矩阵

    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)

#这个0，返回每一列的最值
    ranges = maxVals - minVals
    normDataSet = zeros(shape(dataSet))

#后面的归一化跟matalb里.\一个样子，就是不知道python自带这种功能不
    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)

#这里int是向下取整，比如int（3*0.6）=1
    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

#下面是读入32*32的图，变成1*1024的向量，图像处理不感兴趣，不看    
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

#手写识别
def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('trainingDigits')           #load the training set
    m = len(trainingFileList)
    trainingMat = zeros((m,1024))

%这个listdir跟matalb的dir不一样，matalb从第三个开始，这个直接从第一个开始了
    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))