KNN算法

from numpy import *
import operator
from os import listdir
import os
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 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]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    # 按classCount字典的第2个元素（即类别出现的次数）从大到小排序
    sortedClassCount = sorted(classCount.items(),key=operator.itemgetter(1), reverse = True)
    return sortedClassCount[0][0]
def file2matrix(filename):
    fr = open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)
    returnMat = zeros((numberOfLines, 3))
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index, :] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        """
        if listFromLine[-1] == 'largeDoses':
            classLabelVector.append(3)
        elif listFromLine[-1] == 'smallDoses':
            classLabelVector.append(2)
        elif listFromLine[-1] == 'didntLike':
            classLabelVector.append(1)
        """
        index += 1
    return returnMat,classLabelVector
#归一化函数
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))
    return normDataSet, ranges, minVals
#分类器针对约会网站的测试代码
def datingClassTest():
    hoRatio = 0.1
    datingDataMat, datingLabels = file2matrix('E:\machine learning\machinelearninginaction\Ch02\datingTestSet2.txt')
    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)
#约会网站预测函数
def classifyPerson():
    resultList = ['not at all', 'in small doses', 'in large doses']
    percentTats = float(input("玩游戏时长?"))
    ffMiles = float(input("每年坐飞机飞多远?"))
    iceCream = float(input("每年消耗多少汽油?"))
    datingDataMat,datingLabels = file2matrix('E:\machine learning\machinelearninginaction\Ch02\datingTestSet2.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)
    inArr = array([ffMiles,percentTats,iceCream])
    classifierResult = classify0((inArr - minVals)/ranges,normMat,datingLabels,3)
    print("You will probably like this person:",resultList[classifierResult - 1])
#手写板数字识别数据处理
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
#手写板数字识别函数测试
def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('E:/machine learning/machinelearninginaction/Ch02/digits/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('E:/machine learning/machinelearninginaction/Ch02/digits/TrainingDigits/%s' % fileNameStr)
    testFileList = listdir('E:/machine learning/machinelearninginaction/Ch02/digits/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('E:/machine learning/machinelearninginaction/Ch02/digits/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)))