机器学习实战-KNN手写数字识别-python3

通过练习配对和手写数字识别，我感觉KNN算法就是将测试的每个数据与训练集里边的所有数据算其距离，然后排序选出前K个距离最小的值，匹配其标签，选择多的标签作为测试数据的类型。这是我的理解有不对的欢迎大佬指正。

数据集在此处

# 导入程序所需要的模块
import numpy as np
import operator
from os import listdir

def img2vector(filename):
    returnVect = np.zeros((1, 1024))    # 存储图片像素的向量维度是1x1024
    fr = open(filename)
    for i in range(32):
        lineStr = fr.readline()
        for j in range(32):
            returnVect[0, 32*i+j] = int(lineStr[j])    # 图片尺寸是32x32，将其依次放入向量returnVect中
    return returnVect

def classify0(inX, dataSet, labels, k):    # inX是测试集，dataSet是训练集，lebels是训练样本标签，k是取的最近邻个数
    dataSetSize = dataSet.shape[0]    # 训练样本个数
    diffMat = np.tile(inX, (dataSetSize, 1)) - dataSet    # np.tile: 重复n次
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5    # distance是inX与dataSet的欧氏距离
    sortedDistIndicies = distances.argsort()    # 返回排序从小到达的索引位置
    classCount = {}   # 字典存储k近邻不同label出现的次数
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1    # 对应label加1，classCount中若无此key，则默认为0
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)    # operator.itemgetter 获取对象的哪个维度的数据
    return sortedClassCount[0][0]    # 返回k近邻中所属类别最多的哪一类

def handwritingClassTest():
    # 训练样本
    hwLabels = []
    trainingFileList = listdir('./digits/trainingDigits')           #导入训练集
    m = len(trainingFileList)
    trainingMat = np.zeros((m, 1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]     # fileNameStr 得到的是每个文件名称，例如"0_0.txt"
        fileStr = fileNameStr.split('.')[0]     #去掉“.txt”，剩下“0_0”
        classNumStr = int(fileStr.split('_')[0])    # 按下划线‘_' 划分“0_0”,取第一个元素为类别标签
        hwLabels.append(classNumStr)
        trainingMat[i, :] = img2vector('./digits/trainingDigits/%s' % fileNameStr)
    # 测试样本
    testFileList = listdir('./digits/testDigits')        #iterate through the test set
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]    # fileNameStr 得到的是每个文件名称，例如"0_0.txt"
        fileStr = fileNameStr.split('.')[0]     #去掉“.txt”，剩下“0_0”
        classNumStr = int(fileStr.split('_')[0])    # 按下划线‘_' 划分“0_0”,取第一个元素为类别标签
        vectorUnderTest = img2vector('./digits/testDigits/%s' % fileNameStr)
        classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)    # 调用knn函数
        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)))

运行结果如图