机器学习实战ch02: 使用K-近邻算法改进约会网站的匹配效果&识别手写数字

示例01：约会网站匹配

S

将海伦的约会对象分个类为三种类型的人：

1. 不喜欢的人
2. 魅力一般的人
3. 极具魅力的人

海伦手机的样本（datingTestSet2.txt)主要包含以下3种特征

• 每年获得的飞行常客里程数
• 玩视频游戏所耗时间百分比
• 每周消费的冰淇淋公升数

T

使用K-近邻算法将匹配对象分到确切的分类中

A

1.收集数据
2.准备数据：使用python解析文本文件
3.分析数据：使用Matplotlib画图
4.训练算法：不适合KNN
5.测试算法：将海伦提供的部分数据作为测试样本（测试样本是已经完成分类的数据）
6.使用算法

• KNN.py

import numpy as np
import operator

from distlib.compat import raw_input


def createDataSet():
    group = np.array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 0.1]])
    labels = ['A', 'A', 'B', 'B']
    return group, labels


# 程序清单2-1: K-近邻算法
"""
step1.计算已知类别数据集中的点与当前点之间的距离
step2.按照距离递增次序排序
step3.选取与当前距离最小的K个点
step4.确定前K个点所在类别的出现频率
step5.返回前K个点出现频率最高的类别作为当前点的预测分类

inx:分类的输入向量
dataSet:训练样本集
labels:标签向量
K:选择最近邻居的数目
"""


def classify0(inx, dataSet, labels, k): #原始KNN分类器函数
    """计算欧式距离"""
    dataSetSize = dataSet.shape[0]  # shape(0):读取矩阵第一维度的长度
    difMat = np.tile(inx, (dataSetSize, 1)) - dataSet  # title()
    sqDiffMax = difMat ** 2
    sqDistances = sqDiffMax.sum(axis=1)  # sum(axis=1):将矩阵的每一行相加
    distances = sqDistances ** 0.5
    """从小到达排序"""
    sortedDistIndices = distances.argsort()  # argsort():数值从小到大的索引值
    """确定前K个距离最小元素所在的主要分类"""
    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistIndices[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1  # classCount.get(voteIlabel,0)返回字典中votrIlabel元素对应的值
    sortedClassCount = sorted(classCount.items(),
                              key=operator.itemgetter(1), reverse=True)  # operator.itrmgettrt(1)：获取对象指定区域中的值
    return sortedClassCount[0][0]


# 程序清单2-2: 将文本记录准换位NumPy的解析程序
"""
函数的输入为文件名字符串，输出为训练样本矩阵和类标签向量
"""
def file2matrix(filename):
    fr = open(filename)  # 打开i一个文件
    arrayOLines = fr.readlines()  # 读取文件的行数
    numberOfLines = len(arrayOLines)  # len：计算对象的长度
    returnMat = np.zeros((numberOfLines, 3))  # 创建一个numberOfLines行3列的0填充的数组
    classLabelVector = []
    index = 0
    for line in arrayOLines:  # 循环处理文件中的每行数据
        line = line.strip()  # strip():截取掉所有的回车字符
        listFromLine = line.split('\t')  # split('\t'):使用'\t'将整行数据分割成一个元素列表
        returnMat[index, :] = listFromLine[0:3]  # 选取前三个元素
        classLabelVector.append(int(listFromLine[-1]))  # 将最后一列存储到向量classLabrlVextor
        index += 1
    return returnMat, classLabelVector

#程序清单2-3 归一化特征值
"""
归一化公式： newValue = (oldValue-min)/(max-min)

"""
def autoNorm(dataSet):
    minVals = dataSet.min(0) #从列中选取最小值
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals #函数计算可能选取的取值范围
    normDataSet = np.zeros(np.shape(dataSet))  #创建新的返回矩阵
    m = dataSet.shape[0]
    normDataSet = dataSet - np.tile(minVals, (m,1)) #minVal和ranges都为1*3 而特征矩阵为1000*3
    normDataSet = normDataSet/np.tile(ranges,(m,1)) #title()将变量内容赋值成输入矩阵同样大小的矩阵
    return normDataSet, ranges, minVals

#程序清单 2-4 分类器针对约会网站的测试代码
def datingClassTest():
    hoRatio = 0.10
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt') #读取数据
    normMat, ranges, minVals = autoNorm(datingDataMat) #将其转换成归一化模式
    m = normMat.shape[0]
    numTestVecs = int(m*hoRatio) #计算测试向量的数量
    errorCount = 0.0
    for i in range(numTestVecs):
        classifierResult = classify0(normMat[i,:],normMat[numTestVecs:m,:],
                                    datingLabels[numTestVecs:m],3 )  #将测试数据和巡礼那样本数据输入到KNN分类器classify0函数
        print ("the classifier came back with: %d, thr real answer is: %d"%(classifierResult,datingLabels[i]))
        if (classifierResult != datingLabels[i]): errorCount += 1.0 #计算错误列表并输出结果
    print ("the total erroe rate is: %f"%(errorCount/float(numTestVecs)))


#程序清单2-5 约会网站预测函数
def classifyPerson():
    resultList = ['not at all','in small doses','in large doses'] #结果类型
    percentTats = float(raw_input("percentage of time spent playing video games?")) #raw_input:允许用户输入文本行命令并返回用户所输入的命令
    ffMiles = float(raw_input("frequent flier miles earned per year?"))
    iceCream = float(raw_input("liters of ice cream consumed per year?"))
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt') #读取文件数据
    normMat, ranges, minVals = autoNorm(datingDataMat) #归一化
    inArr = np.array([ffMiles, percentTats, iceCream]) #创建数组
    classifierResult = classify0((inArr-minVals)/ranges,normMat,datingLabels,3) #使用原始KNN分类器
    print("You will probably like this person:",resultList[classifierResult -1]) #输入结果

• test_KNN.py

import numpy as np
import matplotlib
import matplotlib.pyplot as plt
from importlib import reload
import KNN


#2.1.1
group ,labels = KNN.createDataSet()
print(group)
print(labels)

#2.1.2
print(KNN.classify0([0,0], group, labels, 3))


"""
2.2 示例：使用K-近邻算法改进约会网站

"""
#2.2.1 准备数据：从文本文件中解析数据
reload(KNN) #重新加载

datingDataMat, datingLabels = KNN.file2matrix('datingTestSet2.txt')
print(datingDataMat)
print(datingLabels)

#2.2.2 分析数据：使用Matplotlib创建散点图
"""
使用Matplotlib分析数据
"""
# import matplotlib
# import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(2,2,1)
ax.scatter(datingDataMat[:,1],datingDataMat[:,2],
           15.0*np.array(datingLabels),15.0*np.array(datingLabels))#使用第2列和第3列数据

ax = fig.add_subplot(2,2,2)
ax.scatter(datingDataMat[:,0],datingDataMat[:,1],
           15.0*np.array(datingLabels),15.0*np.array(datingLabels))#使用第1列和第2列数据
plt.show()

#2.2.3 准备数据：归一化数值
reload(KNN)
normMat, ranges, minVals = KNN.autoNorm(datingDataMat)
print (normMat)
print (ranges)
print (minVals)

#2.2.4 测试算法： 作为完成程序验证分类器
reload(KNN)
KNN.datingClassTest()


#2.2.5 使用算法：构建完整可用系统
KNN.classifyPerson()

[[1.  1.1]
 [1.  1. ]
 [0.  0. ]
 [0.  0.1]]
['A', 'A', 'B', 'B']
B
[[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]]
[3, 2, 1, 1, 1, 1, 3, 3, 1, 3, 1, 1, 2, 1, 1, 1, 1, 1, 2, 3, 2, 1, 2, 3, 2, 3, 2, 3, 2, 1, 3, 1, 3, 1, 2, 1, 1, 2, 3, 3, 1, 2, 3, 3, 3, 1, 1, 1, 1, 2, 2, 1, 3, 2, 2, 2, 2, 3, 1, 2, 1, 2, 2, 2, 2, 2, 3, 2, 3, 1, 2, 3, 2, 2, 1, 3, 1, 1, 3, 3, 1, 2, 3, 1, 3, 1, 2, 2, 1, 1, 3, 3, 1, 2, 1, 3, 3, 2, 1, 1, 3, 1, 2, 3, 3, 2, 3, 3, 1, 2, 3, 2, 1, 3, 1, 2, 1, 1, 2, 3, 2, 3, 2, 3, 2, 1, 3, 3, 3, 1, 3, 2, 2, 3, 1, 3, 3, 3, 1, 3, 1, 1, 3, 3, 2, 3, 3, 1, 2, 3, 2, 2, 3, 3, 3, 1, 2, 2, 1, 1, 3, 2, 3, 3, 1, 2, 1, 3, 1, 2, 3, 2, 3, 1, 1, 1, 3, 2, 3, 1, 3, 2, 1, 3, 2, 2, 3, 2, 3, 2, 1, 1, 3, 1, 3, 2, 2, 2, 3, 2, 2, 1, 2, 2, 3, 1, 3, 3, 2, 1, 1, 1, 2, 1, 3, 3, 3, 3, 2, 1, 1, 1, 2, 3, 2, 1, 3, 1, 3, 2, 2, 3, 1, 3, 1, 1, 2, 1, 2, 2, 1, 3, 1, 3, 2, 3, 1, 2, 3, 1, 1, 1, 1, 2, 3, 2, 2, 3, 1, 2, 1, 1, 1, 3, 3, 2, 1, 1, 1, 2, 2, 3, 1, 1, 1, 2, 1, 1, 2, 1, 1, 1, 2, 2, 3, 2, 3, 3, 3, 3, 1, 2, 3, 1, 1, 1, 3, 1, 3, 2, 2, 1, 3, 1, 3, 2, 2, 1, 2, 2, 3, 1, 3, 2, 1, 1, 3, 3, 2, 3, 3, 2, 3, 1, 3, 1, 3, 3, 1, 3, 2, 1, 3, 1, 3, 2, 1, 2, 2, 1, 3, 1, 1, 3, 3, 2, 2, 3, 1, 2, 3, 3, 2, 2, 1, 1, 1, 1, 3, 2, 1, 1, 3, 2, 1, 1, 3, 3, 3, 2, 3, 2, 1, 1, 1, 1, 1, 3, 2, 2, 1, 2, 1, 3, 2, 1, 3, 2, 1, 3, 1, 1, 3, 3, 3, 3, 2, 1, 1, 2, 1, 3, 3, 2, 1, 2, 3, 2, 1, 2, 2, 2, 1, 1, 3, 1, 1, 2, 3, 1, 1, 2, 3, 1, 3, 1, 1, 2, 2, 1, 2, 2, 2, 3, 1, 1, 1, 3, 1, 3, 1, 3, 3, 1, 1, 1, 3, 2, 3, 3, 2, 2, 1, 1, 1, 2, 1, 2, 2, 3, 3, 3, 1, 1, 3, 3, 2, 3, 3, 2, 3, 3, 3, 2, 3, 3, 1, 2, 3, 2, 1, 1, 1, 1, 3, 3, 3, 3, 2, 1, 1, 1, 1, 3, 1, 1, 2, 1, 1, 2, 3, 2, 1, 2, 2, 2, 3, 2, 1, 3, 2, 3, 2, 3, 2, 1, 1, 2, 3, 1, 3, 3, 3, 1, 2, 1, 2, 2, 1, 2, 2, 2, 2, 2, 3, 2, 1, 3, 3, 2, 2, 2, 3, 1, 2, 1, 1, 3, 2, 3, 2, 3, 2, 3, 3, 2, 2, 1, 3, 1, 2, 1, 3, 1, 1, 1, 3, 1, 1, 3, 3, 2, 2, 1, 3, 1, 1, 3, 2, 3, 1, 1, 3, 1, 3, 3, 1, 2, 3, 1, 3, 1, 1, 2, 1, 3, 1, 1, 1, 1, 2, 1, 3, 1, 2, 1, 3, 1, 3, 1, 1, 2, 2, 2, 3, 2, 2, 1, 2, 3, 3, 2, 3, 3, 3, 2, 3, 3, 1, 3, 2, 3, 2, 1, 2, 1, 1, 1, 2, 3, 2, 2, 1, 2, 2, 1, 3, 1, 3, 3, 3, 2, 2, 3, 3, 1, 2, 2, 2, 3, 1, 2, 1, 3, 1, 2, 3, 1, 1, 1, 2, 2, 3, 1, 3, 1, 1, 3, 1, 2, 3, 1, 2, 3, 1, 2, 3, 2, 2, 2, 3, 1, 3, 1, 2, 3, 2, 2, 3, 1, 2, 3, 2, 3, 1, 2, 2, 3, 1, 1, 1, 2, 2, 1, 1, 2, 1, 2, 1, 2, 3, 2, 1, 3, 3, 3, 1, 1, 3, 1, 2, 3, 3, 2, 2, 2, 1, 2, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 1, 3, 2, 1, 3, 3, 1, 2, 3, 2, 1, 3, 3, 3, 1, 2, 2, 2, 3, 2, 3, 3, 1, 2, 1, 1, 2, 1, 3, 1, 2, 2, 1, 3, 2, 1, 3, 3, 2, 2, 2, 1, 2, 2, 1, 3, 1, 3, 1, 3, 3, 1, 1, 2, 3, 2, 2, 3, 1, 1, 1, 1, 3, 2, 2, 1, 3, 1, 2, 3, 1, 3, 1, 3, 1, 1, 3, 2, 3, 1, 1, 3, 3, 3, 3, 1, 3, 2, 2, 1, 1, 3, 3, 2, 2, 2, 1, 2, 1, 2, 1, 3, 2, 1, 2, 2, 3, 1, 2, 2, 2, 3, 2, 1, 2, 1, 2, 3, 3, 2, 3, 1, 1, 3, 3, 1, 2, 2, 2, 2, 2, 2, 1, 3, 3, 3, 3, 3, 1, 1, 3, 2, 1, 2, 1, 2, 2, 3, 2, 2, 2, 3, 1, 2, 1, 2, 2, 1, 1, 2, 3, 3, 1, 1, 1, 1, 3, 3, 3, 3, 3, 3, 1, 3, 3, 2, 3, 2, 3, 3, 2, 2, 1, 1, 1, 3, 3, 1, 1, 1, 3, 3, 2, 1, 2, 1, 1, 2, 2, 1, 1, 1, 3, 1, 1, 2, 3, 2, 2, 1, 3, 1, 2, 3, 1, 2, 2, 2, 2, 3, 2, 3, 3, 1, 2, 1, 2, 3, 1, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 1, 3, 3, 3]
[[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]]
[9.1273000e+04 2.0919349e+01 1.6943610e+00]
[0.       0.       0.001156]
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 3, thr real answer is: 2
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 3, thr real answer is: 1
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 3, thr real answer is: 1
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 2, thr real answer is: 3
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 3, thr real answer is: 3
the classifier came back with: 2, thr real answer is: 2
the classifier came back with: 1, thr real answer is: 1
the classifier came back with: 3, thr real answer is: 1
the total erroe rate is: 0.050000
percentage of time spent playing video games?10
frequent flier miles earned per year?10000
liters of ice cream consumed per year?0.5
You will probably like this person: in small doses

示例02：识别手写数字

KNN.py

"""
手写数字识别系统
Input: 32像素*32像素的黑白图像(识别0到9)
"""

#将图像转换成向量，即将32*32的二进制推向矩阵转换为 1*1024 的向量
def img2vector(filename):
    returnVect = np.zeros((1,1024)) #创建一个用于存储的空数组
    fr = open(filename) #打开文件
    for i in range(32):
        lineStr = fr.readline() #读取每一行数据
        for j in range(32):
            returnVect[0,32*i+j] = int(lineStr[j]) #将每行的头32个字符值存储在数据中
    return returnVect

#程序清单2-6 手写数字识别系统的测试代码
def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('digits\\trainingDigits') #训练样本 listdir:返回指定的文件夹包含的文件或文件夹的名字的列表
    m =len(trainingFileList) #目中中的文件数
    trainingMat = np.zeros((m,1024)) #矩阵的每行存储一个图像
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr) #从文件名中解析出分类数字并将类代码存储在hwLabels向量中
        trainingMat[i,:] = img2vector('digits\\trainingDigits/%s'%fileNameStr)  #将图像转换成向量
    testFileList =  listdir('digits\\testDigits') #测试样本
    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('digits\\testDigits/%s' %fileNameStr)
        classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)# 测试
        print("the classifier came back with: %d, the real answer is: %d" , (classifierResult, classNumStr))
        print("\nthe total number of errors is: %d" , errorCount)
        print("\nthe total error rate is: %f" , (errorCount/float(mTest)))

test.py

#2.3.1 准备数据：将图像转换为测试向量
testVector = KNN.img2vector('digits/testDigits/0_13.txt')
print(testVector[0,0:31])

#2.3.2 测试算法：使用KNN算法识别手写数字
KNN.handwritingClassTest()