机器学习实战-knn-文本数据，手写字符识别

机器学习实战-knn-文本数据，手写字符识别

from numpy import *
import operator
from os import listdir


# knn分类函数
def classify0(inX, dataSet, labels, k):
    # inX-输入向量
    # dataset-训练数据
    # labels-标签向量
    # k-表示选择最近邻居的数目

    dataSetSize = dataSet.shape[0]  # 看有多少个数据
    # print("dataSetSize", dataSetSize)
    diffMat = tile(inX, (dataSetSize, 1)) - dataSet  # 把数据inX行重复dataSetSize次，列重复1次形成新列表，再减去训练数据
    # 得到的是差值
    # print(diffMat)

    # 计算欧式距离-两个向量点之间
    sqDiffMat = diffMat ** 2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances ** 0.5
    # print("distances", distances)
    sortedDistIndicies = distances.argsort()  # 将数据降序排列,提取的是各个数据的索引
    # print("sortedDistIndicies",sortedDistIndicies)

    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]  # 获取最近邻的标签
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1  # get函数为在classCount中找voteIlabel，有的话返回其值，没有返回0、
        # print("classcount", classCount)
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)  # 将数据变为内含元组的列表
    return sortedClassCount[0][0]


# 创建数据集，包括数据和标签
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


# 将文件里的数据转换到列表
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
    classLabelVector = []  # prepare labels return
    fr = open(filename)
    index = 0
    for line in fr.readlines():  # 解析文件数据到列表
        line = line.strip()  # 截取掉所有回车字符
        listFromLine = line.split('\t')  # 使用tap将整行数据分割成一个元素列表
        returnMat[index, :] = listFromLine[0:3]  # 记录数据，前三个
        classLabelVector.append(int(listFromLine[-1]))  # 记录标签（-1代表最后一列数据-负索引）
        index += 1
    return returnMat, classLabelVector


# 数据归一化，任何特征值都转化到0-1或-1-1之间
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))  # element wise divide
    return normDataSet, ranges, minVals


# 使用文件中的数据训练和测试
def datingClassTest():
    hoRatio = 0.05  # hold out 10%---测试数据集的比例
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')  # load data setfrom file
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    numTestVecs = int(m * hoRatio)  # 将数据集划分为训练数据集和测试数据集
    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)


# 从文本中读取图片，格式化为向量
def img2vector(filename):
    returnVect = zeros((1, 1024))  # 创建1行，1024列的向量
    fr = open(filename)
    for i in range(32):
        lineStr = fr.readline()
        for j in range(32):
            returnVect[0, 32 * i + j] = int(lineStr[j])
    return returnVect


# knn-手写数字识别，1024个距离计算
def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('digits/trainingDigits')  # 获取训练文件内容---文件夹内所有文件的文件名
    m = len(trainingFileList)
    trainingMat = zeros((m, 1024))  # 创建向量
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]  # 去掉 .txt，split的作用是将fileNameStr根据.分成前后两部分，获取第一部分
        classNumStr = int(fileStr.split('_')[0])  # 继续分，获取到数据的标签
        hwLabels.append(classNumStr)
        trainingMat[i, :] = img2vector('digits/trainingDigits/%s' % fileNameStr)  # 将训练数据转变成变量
    testFileList = listdir('digits/testDigits')  # 获取到所有测试数据的文件名
    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('digits/testDigits/%s' % fileNameStr)  # 获取到所有的测试数据

        classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)  # 对所有的测试数据进行分类
        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 errors is: %d" % errorCount)
    print("\nthe total error rate is: %f" % (errorCount / float(mTest)))


handwritingClassTest()