【机器学习实战】k-近邻算法2.2约会网站预测函数

《机器学习实战》学习

书中使用Python2进行代码演示，我这里将其转换为Python3，并做了一些注释。要学会使用断点调试，方便很多

下面的代码是书中2.2节使用k-近邻算法改进约会网站的配对效果的完整测试代码：

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


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


def classify0(inX, dataSet, labels, k):
    '''
    k-近邻算法
    :param inX:用于分类的输入向量
    :param dataSet: 输入的训练样本集
    :param labels: 标签向量
    :param k: 用于选择最近邻居的数目
    :return:　返回k个邻居中距离最近且数量最多的类别作为预测类别
    '''
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX, (dataSetSize, 1)) - dataSet
    sqDiffMat = diffMat ** 2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances ** 0.5
    # 以上为计算输入向量与已有标签样本的欧式距离
    sortedDistIndicies = distances.argsort()  # argsort函数返回的是数组值从小到大的索引值，距离需要从小到大排序
    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
        # Python 字典(Dictionary) get() 函数返回指定键的值，如果值不在字典中返回默认值。
        # get(voteIlabel,0)表示当能查询到相匹配的字典时，就会显示相应key对应的value，如果不能的话，就会显示后面的这个参数。
    sortedClassCount = sorted(classCount.items(),key=operator.itemgetter(1),reverse=True)
    # 按照元祖中第２个值的大小降序排序
    # python2中的iteritems()方法需改为items()
    return sortedClassCount[0][0]


def file2matrix(filename):
    # 将文本记录转换为NumPy的解析程序
    fr = open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)
    print(numberOfLines)
    returnMat = zeros((numberOfLines,3))  # 存放３种特征
    classLabelVector = []  # 存放标签
    index = 0
    for line in arrayOLines:
        line = line.strip()  # strip() 方法用于移除字符串头尾指定的字符（默认为空格或换行符）或字符序列。
        listFromLine = line.split('	')  # split() 通过指定分隔符对字符串进行切片，组成列表
        returnMat[index, :] = listFromLine[0:3]  # 将当前列表的前３个值赋予returnMat的当前行
        classLabelVector.append(int(listFromLine[-1]))  # 将标签添加到classLabelVector中
        index += 1
    return returnMat, classLabelVector


def autoNum(dataSet):
    minVals = dataSet.min(0)  # A.min(0) : 返回A每一列最小值组成的一维数组；
    maxVals = dataSet.max(0)  # A.max(0)：返回A每一列最大值组成的一维数组；
    # https://blog.csdn.net/qq_41800366/article/details/86313052
    ranges = maxVals - minVals
    normDataSet = zeros(shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - tile(minVals, (m,1))
    # tile将minVals的行数乘以m次重复，列数乘以１次重复，每一行都减掉minVals
    normDataSet = normDataSet/tile(ranges,(m,1))
    # 每一行都除以ranges以是实现数据归一化
    return normDataSet,ranges, minVals


def datingClassTest():
    hoRatio = 0.10  # 测试集比重
    m = normMat.shape[0]
    numTestVecs = int(m*hoRatio)  # 测试集数量
    errorCount = 0.0
    for i in range(numTestVecs):
        classfierResult = classify0(normMat[i,:],normMat[numTestVecs:m,:],datingLabels[numTestVecs:m],3)
        print("the classifierResult came back with: %d,the real answer is: %d"%(classfierResult,datingLabels[i]))
        if(classfierResult != datingLabels[i]):errorCount += 1.0
        print("the total error rate is: %f"%(errorCount/float(numTestVecs)))

def classifyPerson():
    resultList = ['not at all', 'in small doses', 'in large doses']
    percentTats = float(input("percentage of time spent playing video games?"))
    # 在 Python3.x 中 raw_input( ) 和 input( ) 进行了整合，去除了 raw_input( )，仅保留了 input( ) 函数，
    # 其接收任意任性输入，将所有输入默认为字符串处理，并返回字符串类型。
    ffMiles = float(input("frequent flier miles earned per year?"))
    iceCream = float(input("liters of ice cream consumed per year?"))
    inArr = array([ffMiles, percentTats, iceCream])  # 输入测试向量
    classifierResult = classify0((inArr-minVals)/ranges,normMat,datingLabels,3)  # 得到分类结果
    print("You will probably like this person:",resultList[classifierResult-1])


if __name__ == "__main__":
    '''
    group,labels = createDataSet()
    result = classify0([0,0],group,labels,3)
    print(result)
    '''
    datingDataMat, datingLabels = file2matrix("./datingTestSet2.txt")  # 数据转换
    # print(datingDataMat)
    # print(datingLabels)
    fig = plt.figure()
    ax = fig.add_subplot()
    ax.scatter(datingDataMat[:,0],datingDataMat[:,1],15.0*array(datingLabels),15.0*array(datingLabels))
    plt.show()
    normMat, ranges, minVals = autoNum(datingDataMat)  # 输入数据归一化
    # print(normMat)
    # print(ranges)
    # print(minVals)
    # datingClassTest()
    classifyPerson()  # 分类

运行结果：
1 percentage of time spent playing video games?10
frequent flier miles earned per year?4000
liters of ice cream consumed per year?1
You will probably like this person: in small doses

# python2中的iteritems()方法需改为items()