机器学习实战-第二章代码+注释-KNN

#-*- coding:utf-8 -*-
#https://blog.csdn.net/fenfenmiao/article/details/52165472
from numpy import * #科学计算包

import operator #运算符模块
import matplotlib
import matplotlib.pyplot as plt
#matplotlib.pyplot是一些命令行风格函数的集合

from os import listdir #列出给定目录的文件名

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]  #查看矩阵或者数组的维数     c.shape[1] 为第一维的长度，c.shape[0] 为第二维的长度 此处为4

    #(dataSetSize, 1)使数组重复完是四行一样的  而不是在1行中。
    diffMat = tile(inX, (dataSetSize, 1)) - dataSet     #numpy.tile(A,reps) tile共有2个参数，A指待输入数组，reps则决定A重复的次数。整个函数用于重复数组A来构建新的数组。
    sqDiffMat = diffMat ** 2    #幂  （x1 - x2）的幂
    sqDistance = sqDiffMat.sum(axis = 1)    #每行相加    横着相加
    distances = sqDistance ** 0.5   #开根号
    sortedDistIndicies = distances.argsort()    #argsort是排序，将元素按照由小到大的顺序返回下标
    classCount = {} #dict字典数据类型，字典是Python中唯一内建的映射类型
    for i in range(k) :
        voteIlabel = labels[sortedDistIndicies[i]]
        #get是取字典里的元素，如果之前这个voteIlabel是有的，那么就返回字典里这个voteIlabel里的值，如果没有就返回0（后面写的），这行代码的意思就是算离目标点距离最近的k个点的类别，这个点是哪个类别哪个类别就加1
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
    #key=operator.itemgetter(1)的意思是按照字典里的第一个排序，{A:1,B:2},要按照第1个（AB是第0个），即‘1’‘2’排序。reverse=True是降序排序
    sortedClassCount = sorted(classCount.iteritems(), key = operator.itemgetter(0), reverse = True)
    return sortedClassCount[0][0]

def file2matrix(filename):
    fr = open(filename)
    # 一次读取整个文本数据，并且自动将文件内容分析成一个行的列表，比readline（）快 ，后面的img2vector就是使用的readline（），因为要逐行逐个读取，可以对比一下
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)
    #返回来一个给定形状和类型的用0填充的数组;
    returnMat = zeros((numberOfLines, 3))   #文件有几行就是几行，设置为3列（可调）
    classLabelVector = []
    index = 0
    for line in  arrayOLines :
        line = line.strip() #去掉回车符
        listFromLine = line.split('\t') #分成了4列数据，得到了4个列表
        #将数据前三列提取出来,存放到returnMat的NumPy矩阵中,也就是特征矩阵
        returnMat[index, :] = listFromLine[0 : 3]    #前3个列表元素是爱伦要的特征，取出来去填充returnMat
        #classLabelVector.append(int(listFromLine[-1]))
        if listFromLine[-1] == 'didntLike':
            classLabelVector.append(1)
        elif listFromLine[-1] == 'smallDoses':
            classLabelVector.append(2)
        elif listFromLine[-1] == 'largeDoses':
            classLabelVector.append(3)
        index += 1
    return returnMat, classLabelVector

#归一化
def autoNorm(dataSet) :
    #min(0)返回该矩阵中每一列的最小值
    #min(1)返回该矩阵中每一行的最小值
    #max(0)返回该矩阵中每一列的最大值
    #max(1)返回该矩阵中每一行的最大值
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    #得到数据集的行数  shape方法用来得到矩阵或数组的维数
    normDataSet = zeros(shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - tile(minVals, (m, 1))
    normDataSet = normDataSet / tile(ranges, (m, 1))
    return normDataSet, ranges, minVals


def datingClassTest() :
    hoRatio = 0.10
    datingDataMatm, datingLabels = file2matrix('F:\jxq\Desktop\datingTestSet.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)   #归一化
    m = normMat.shape[0]    #二维数组维度大小
    numTestVecs = int(m * hoRatio)  #训练样本从第m * hoRatio 开始
    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)))


def classifyPerson() :
    resultList = ['not at all', 'in small doses', 'in large doses']
    percentTats = float(raw_input("percentage of time spent playing video games?"))
    ffMiles = float(raw_input("frequent flier miles earned per year?"))
    iceCream = float(raw_input("liters of ice cream consumed per year?"))
    datingDataMat, datingLables = file2matrix('F:\jxq\Desktop\datingTestSet.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)
    inArr = array([ffMiles, percentTats, iceCream])
    classifierResult = classify0((inArr-minVals)/ranges, normMat, datingLables, 3)
    print ("You will probably like this person:", resultList[classifierResult - 1]) #索引从0开始，索引减去1才能索引到对应的resultList

def img2vector(filename) :
    returnVect = zeros((1, 1024))   # 用于保存1x1024的向量
    fr = open(filename)
    for i in range(32) :
        lineStr = fr.readline()
        for j in range(32) :
            returnVect[0, 32*i+j] = int(lineStr[j]) # 字符需要强制类型转换成整数

    return returnVect

def handwritingClassTest() :
    hwLabels = []
    #获取目录内容
    trainingFileList = listdir('F:\\jxq\\Documents\\Tencent Files\\834810071\\FileRecv\\machinelearninginaction-master\\machinelearninginaction-master\\Ch02\\digits\\trainingDigits')
    m = len(trainingFileList)
    trainingMat = zeros((m, 1024))
    for i in range(m) :
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0] #无后缀文件名
        classNumStr = int(fileStr.split('_')[0]) #获取文件内的数字
        hwLabels.append(classNumStr)
        #图片转换为向量
        trainingMat[i, :] = img2vector('F:\\jxq\\Documents\\Tencent Files\\834810071\\FileRecv\\machinelearninginaction-master\\machinelearninginaction-master\\Ch02\\digits\\trainingDigits\\%s' %fileNameStr)
    testFileList = listdir('F:\\jxq\\Documents\\Tencent Files\\834810071\\FileRecv\\machinelearninginaction-master\\machinelearninginaction-master\\Ch02\\digits\\testDigits')
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        vectorUnderTest = img2vector('F:\\jxq\\Documents\\Tencent Files\\834810071\\FileRecv\\machinelearninginaction-master\\machinelearninginaction-master\\Ch02\\digits\\testDigits\\%s' %fileNameStr)
        classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3) #分类
        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 error is: %d" %errorCount)
    print("\nthe total error rate is: %f" %(errorCount/float(mTest)))

if __name__ == '__main__':
    #filename = 'F:\jxq\Desktop\datingTestSet.txt'
    #datingDataMat, datingLabels = file2matrix(filename)
    '''
    print(datingDataMat)
    print(datingLabels)
    fig = plt.figure()  #figure()来创建多个图
    ax = fig.add_subplot(111)   #参数349的意思是：将画布分割成3行4列，图像画在从左到右从上到下的第9块
    #后两个是颜色
    ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2], 15.0*array(datingLabels), 15.0*array(datingLabels))    #绘制散点图  X[:,0]就是取所有行的第0个数据, X[:,1] 就是取所有行的第1个数据
    '''
    '''
    normMat, range, minVals = autoNorm(datingDataMat)
    print(normMat)
    print(range)
    print(minVals)
    '''
    #datingClassTest()
    #plt.show()
    #classifyPerson()
    #testVector = img2vector('F:\\jxq\\Documents\\Tencent Files\\834810071\\FileRecv\\machinelearninginaction-master\\machinelearninginaction-master\\Ch02\\digits\\testDigits\\0_13.txt')
    #print(testVector[0, 0:31])
    #print(testVector[0, 32:63])
    handwritingClassTest()