KNN近邻算法学习笔记——代码详细注释

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

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]                              # 读取group的第一维度长度(行数)，此处为4
    # tile函数 tile(inX, i);扩展长度  tile(inX, (i,j)) ;i是扩展个数，j是扩展长度
    diffMat = tile(inX, (dataSetSize,1)) - dataSet           # tile将inX重复成一个4*1的矩阵再做减法得到[[-1.  -1.1]，[-1.  -1. ]，[ 0.   0. ]，[ 0.  -0.1]]
    sqDiffMat = diffMat ** 2                                    # 每个元素平方
    sqDistances = sqDiffMat.sum(axis = 1)                       # 没有axis参数表示全部相加，axis＝0表示按列相加，axis＝1表示按照行的方向相加
    distances = sqDistances ** 0.5
    sortedDistIndicies = distances.argsort()                    # 排序，并按顺序返回列表的索引index
    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel , 0) + 1      # 前K个值分类，是哪个类那个类的个数+1
    sortedClassCount = sorted(classCount.items(),                        # .items()将字典classCount中所有键值对以dict_items的形式返回
                              key = operator.itemgetter(1), reverse=True)       # .itemgetter(1)方法按照第二个元素的次序对元祖进行排序
    return sortedClassCount[0][0]

def file2matrix(filename):
    # 将文本记录转换为Numpy的解析程序
    fr = open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)
    returnMat = zeros((numberOfLines,3))                 # 创建以0 填充的矩阵numpy
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        line = line.strip()                                 # line.strip()截取掉所有的回车字符
        listFromLine = line.split('\t')                     # 使用tab字符\t将上一步得到的整行数据分割成一个元素列表
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat,classLabelVector

def autoNorm(dataSet):
    # 归一化特征值
    minVals = dataSet.min(0)                            # 参数0 使得函数可以从列中选取最小值
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    normDataSet = zeros(shape(dataSet))
    m = dataSet.shape[0]                                # 读取dataSet的第一维度长度(行数)，此处为1000
    normDataSet = dataSet - tile(minVals, (m,1))
    newDataSet = normDataSet/tile(ranges, (m,1))
    return newDataSet,ranges,minVals

def datingClassTest():
    hoRatio = 0.1
    datingDataMat, datingLabels =file2matrix('datingTestSet.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    numTestVecs = int(m * hoRatio)    # 取10%做测试数据
    errorCount = 0.0
    for i in range(numTestVecs):
        a = random.randint(1000)               # 取0-999的随机数
        classifierResult = classify0(normMat[a, :], normMat[numTestVecs:m, :],datingLabels[numTestVecs:m], 3)
        print('the classifier came back with: %s,the real answer is: %s' % (classifierResult, datingLabels[i]))
        if (classifierResult != datingLabels[a]):
            errorCount += 1.0
    print('the total error rate is: %f' % (errorCount/float(numTestVecs)))

def classifyPerson():
    resultList = ['not at al', 'in small doses', 'in large doses']
    percentTats = float(input('percentage of time spent playing video games?'))
    ffMiles = float(input('frequent flier miles earned per year?'))
    iceCream = float(input('liters of ice cream consumed per year?'))
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)
    inArr = array([ffMiles, percentTats, iceCream])
    classifierResult = classify0((inArr-minVals)/ranges, normMat, datingLabels, 3)          # 这里要把输入的数据归一化
    print('You will probably like this person: ', resultList[classifierResult - 1])

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 handwrtingClassTest():
    hwLabels = []
    trainingFileList = listdir('trainingDigits')            # listdir函数列出给定目录的文件名
    m = len(trainingFileList)                                 # 1934
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]                    # 返回一个下标从零开始到.字符串
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr)     # 将每个文件的01存储到trainingMat里
    testFileList = listdir('testDigits')
    errorCount = 0.0
    mTest = len(testFileList)                                  # 946
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]
        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__':
    '''
    group,labels = createDataSet()
    G = classify0([0,0],group,labels,3)
    print(G)
    '''
    '''
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    print(datingDataMat)
    fig = plt.figure()
    ax = fig.add_subplot(111)
    # ax.scatter(datingDataMat[:,0],datingDataMat[:,1], 15.0*array(datingLabels), 15.0*array(datingLabels))
    plt.xlabel('每年获取的飞行常客里程数')
    plt.ylabel('玩视频游戏所耗时间百分比')
    datingLabels = array(datingLabels)
    idx_1 = where(datingLabels == '1')
    ax.scatter(datingDataMat[idx_1, 0], datingDataMat[idx_1, 1], marker='*', color='r', label='不喜欢', s=20)
    idx_2 = where(datingLabels == '2')
    ax.scatter(datingDataMat[idx_2, 0], datingDataMat[idx_2, 1], marker='o', color='b', label='魅力一般', s=10)
    idx_3 = where(datingLabels == '3')
    ax.scatter(datingDataMat[idx_3, 0], datingDataMat[idx_3, 1], marker='+', color='g', label='极具魅力', s=30)
    plt.legend(loc='upper left')
    plt.show()
    '''
    # datingClassTest()
    # classifyPerson()
    handwrtingClassTest()