K-近邻算法

机器学习实战第一版电子书

电子书地址

实验数据集

约会网站、手写识别系统数据集地址

实验代码

from numpy import *
import operator
import matplotlib.pyplot as plt
import os as os

#准备数据
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
#实施算法
"""
intX    : 用于分类的输入向量
dataSet : 用于训练的数据集
labels  : 标签向量
k       : 选择的邻居数目
"""
def classify0(intX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0] #二维矩阵的行数作为数据集的大小
    diffMat = tile(intX, (dataSetSize, 1)) - dataSet #平铺输入向量同时与训练样本计算欧氏距离
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1) #axis = 0/1/null 0时行相加 1列相加 null所有数相加
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort() #argsort函数对列表进行升序排序，返回在原列表中的索引
    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
        """
        sorted参数说明
            classCount.iteritems() 将字典classCount转换成二元组
            key 排序时选择的元素
            reverse 排序结果默认位升序，反转为降序排列 
        """
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0] #返回出现次数最多的向量标签
#准备数据
def file2matrix(filename):
    fr = open(filename)
    arrayOfLines = fr.readlines() #按行读取文件
    numberOfLines = len(arrayOfLines) #行数
    returnMat = zeros((numberOfLines, 3)) #创建对应行数列为三的矩阵
    classLabelVector = []
    index = 0
    for line in arrayOfLines:
        line = line.strip() #去掉行首尾空格
        listFromLine = line.split('\t') #根据空格分割字符串
        returnMat[index, :] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat, classLabelVector
#归一化
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
#样本集维度转换
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
#约会网站预测
def datingClassTest():
    hoRatio = 0.10
    datingDataMat, datingLabels = file2matrix('D://Desktop//datingTestSet2.txt')
    normDataMat, ranges, minVals = autoNorm(datingDataMat)
    m = normDataMat.shape[0]
    numTestVecs = int(m * hoRatio)
    errorCount = 0.0
    for i in range(numTestVecs):
        classifierResult = classify0(normDataMat[i, :], normDataMat[numTestVecs : m, :], datingLabels[numTestVecs:m], 100)
        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)))
#手写识别预测
def handWritingClassTest():
    hwLabels = []
    trainingFileList = os.listdir('D://Desktop//源代码以及数据//trainingDigits')
    m = len(trainingFileList)
    trainingMat = zeros((m, 1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i, :] = img2vector('D://Desktop//源代码以及数据//trainingDigits/%s' % fileNameStr)
    testFileList = os.listdir('D://Desktop//源代码以及数据//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('D://Desktop//源代码以及数据//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)))
handWritingClassTest()