机器学习实战笔记第二章-k近邻算法

PS1: 以下代码使用py3.7执行,原书出版于2013年(大概是),示例代码都是10年和11年写的, 使用的是py2的语法, 有许多不能执行,如:

• dict_keys.keys()[*]
• dict.iteritems()
• 等

PS2:所有代码均在Jupyter Notebook上测试, 所需包及版本如下

• numpy :1.16.5
• matplotlib :3.1.1

第二章 k-近邻算法(kNN)

创建数据,其中group为四组数据点,labels分别为四个数据点对应的标签

from numpy import *
# import operator

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)

group,labels = createDataSet()

group

array([[1. , 1.1],
       [1. , 1. ],
       [0. , 0. ],
       [0. , 0.1]])

labels

['A', 'A', 'B', 'B']

def classify0(inX, dataSet, labels, k):
# 距离计算
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX, (dataSetSize,1)) - dataSet
# 求距离的平方
    sqDiffMat = diffMat**2
# 求数组每一行的和
    sqDistances = sqDiffMat.sum(axis=1)
# 取平方根 ,即距离
    distances = sqDistances**0.5
# 由小到大排序  argsort()返回每个元素的"名次"
    sortedDistIndicies = distances.argsort()
# 选择距离最小的k个点
    classCount={}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
# 记录出现次数
        classCount[voteIlabel] = classCount.get(voteIlabel,0)+1
# 降序排序
    sortedClassCount = sorted(classCount.items(), reverse = True )
# 返回出现最多次数的标签
    return sortedClassCount[0][0]

print('结果:',classify0([0,0], group, labels, 3))

结果: B

示例1: 使用k-近邻算法改进约会网站配对效果

文件转为矩阵函数

import numpy as np
def file2matrix(filename):
    fr = open(filename)
    arrayOLines = fr.readlines()
# 得到文件的行数
    numberOfLines = len(arrayOLines)
# 初始化矩阵
    returnMat = np.zeros((numberOfLines, 3))
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index+=1
    return returnMat,classLabelVector
    

datingDataMat, datingLabels = file2matrix('I:\迅雷下载\MLiA_SourceCode\machinelearninginaction\Ch02\datingTestSet2.txt')
datingDataMat

array([[4.0920000e+04, 8.3269760e+00, 9.5395200e-01],
       [1.4488000e+04, 7.1534690e+00, 1.6739040e+00],
       [2.6052000e+04, 1.4418710e+00, 8.0512400e-01],
       ...,
       [2.6575000e+04, 1.0650102e+01, 8.6662700e-01],
       [4.8111000e+04, 9.1345280e+00, 7.2804500e-01],
       [4.3757000e+04, 7.8826010e+00, 1.3324460e+00]])

import matplotlib
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.scatter(datingDataMat[:, 0], datingDataMat[:, 1], 15*array(datingLabels),15*array(datingLabels),)
plt.show()

归一化函数

def autoNorm(dataSet):
    minVals = dataSet.min(axis=0)
    maxVals = dataSet.max(axis=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

normMat, ranges, minVals = autoNorm(datingDataMat)
normMat

array([[0.44832535, 0.39805139, 0.56233353],
       [0.15873259, 0.34195467, 0.98724416],
       [0.28542943, 0.06892523, 0.47449629],
       ...,
       [0.29115949, 0.50910294, 0.51079493],
       [0.52711097, 0.43665451, 0.4290048 ],
       [0.47940793, 0.3768091 , 0.78571804]])

测试代码

def datingClassTest():
    hoRatio = 0.1
    datingDataMat, datingLabels = file2matrix('I:\迅雷下载\MLiA_SourceCode\machinelearninginaction\Ch02\datingTestSet2.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    numTestVecs = int(m*hoRatio)
    errorCount = 0.0
    for i in range(numTestVecs):
        classifierResult = classify0(normMat[i,:], normMat[numTestVecs:m,:],datingLabels[numTestVecs:m],3 )
        if(classifierResult != datingLabels[i]):
            errorCount+=1
            print(classifierResult," " ,datingLabels[i]," ","False")
        else:
            print(classifierResult," " ,datingLabels[i]," ","Right")
    print("The Total error rate is: %f" % (errorCount/numTestVecs))

datingClassTest()

3   3   Right
3   2   False
1   1   Right
1   1   Right
1   1   Right
1   1   Right
3   3   Right
3   3   Right
1   1   Right
3   3   Right
......
......
3   3   Right
3   3   Right
3   2   False
2   1   False
3   1   False
The Total error rate is: 0.120000

示例2: 手写识别系统

将图像转换为测试向量函数

def img2vector(filename):
    returnVector = zeros((1,1024))
    fr = open(filename)
    for i in range(32):
        lineStr = fr.readline()
        for j in range(32):
            returnVector[0,32*i+j] = int(lineStr[j])
    return returnVector

testVector = img2vector(r'I:\迅雷下载\MLiA_SourceCode\machinelearninginaction\Ch02\digits\testDigits\0_13.txt')
testVector

array([[0., 0., 0., ..., 0., 0., 0.]])

locate =r'I:/迅雷下载/MLiA_SourceCode/machinelearninginaction/Ch02/digits/'

测试算法

from os import listdir
def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir(locate + "/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(locate + "/trainingDigits/" + fileNameStr)
    testFileList = listdir(locate + "/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(locate+'/testDigits/'+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()

the classifier came back with: 0, the real answer is: 0
the classifier came back with: 0, the real answer is: 0
the classifier came back with: 0, the real answer is: 0
the classifier came back with: 0, the real answer is: 0
the classifier came back with: 0, the real answer is: 0
the classifier came back with: 0, the real answer is: 0
the classifier came back with: 0, the real answer is: 0
the classifier came back with: 0, the real answer is: 0
......
......

the total number of errors is: 23

the total error rate is: 0.024313

–未完待续–