KNN约会网站配对

示例：在约会网站上使用k-近邻算法

(1) 收集数据：提供文本文件。
(2) 准备数据：使用Python解析文本文件。
(3) 分析数据：使用Matplotlib画二维扩散图。
(4) 训练算法：此步骤不适用于k-近邻算法。
(5) 测试算法：使用海伦提供的部分数据作为测试样本。

测试样本和非测试样本的区别在于：测试样本是已经完成分类的数据，如果预测分类与实际类别不同，则标记为一个错误。
(6) 使用算法：产生简单的命令行程序，然后海伦可以输入一些特征数据以判断对方是否为自己喜欢的类型。

完整的代码

from numpy import *
import operator
#创建数据
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
#数据分析 KNN
def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    #❶（以下三⾏） 距离计算
    diffMat = tile(inX, (dataSetSize,1)) - dataSet 
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()
    classCount={}
    #❷ （以下两⾏） 选择距离最⼩的k个点
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    sortedClassCount = sorted(classCount.items(),
        #❸ 排序
        key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]
# 将⽂本记录转换为NumPy的解析程序
def file2matrix(filename):
    fr = open(filename)
    arrayOlines=fr.readlines() #readlines() 方法用于读取所有行(直到结束符 EOF)并返回列表
    numberOfLines = len(arrayOlines) #❶ 得到⽂件⾏数
    returnMat = zeros((numberOfLines,3)) #❷ 创建返回的Numpy矩阵
    classLabelVector = []
    index = 0
    #❸ （以下三⾏） 解析⽂件数据到列表
    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('\t') #split() 通过指定分隔符对字符串进行切片
        returnMat[index,:] = listFromLine[0:3] #将数据填充到矩阵,3个特征值
        classLabelVector.append(int(listFromLine[-1])) #添加listFromLine的最后一个元素到列表
        index += 1
    return returnMat,classLabelVector
datingDataMat, datingLabels = file2matrix('D:/Python Project/.vscode/Machine-learning-practical-notes/KNN/datingTestSet2.txt')
# print(datingDataMat)
# [[  4.09200000e+04   8.32697600e+00   9.53952000e-01]
#  [  1.44880000e+04   7.15346900e+00   1.67390400e+00]
#  [  2.60520000e+04   1.44187100e+00   8.05124000e-01]
#  ...,
#  [  2.65750000e+04   1.06501020e+01   8.66627000e-01]
#  [  4.81110000e+04   9.13452800e+00   7.28045000e-01]
#  [  4.37570000e+04   7.88260100e+00   1.33244600e+00]]

# print(datingLabels[0:20])
# [3, 2, 1, 1, 1, 1, 3, 3, 1, 3, 1, 1, 2, 1, 1, 1, 1, 1, 2, 3]

#使用matplotlib
import matplotlib
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
# ax.scatter(datingDataMat[:,1], datingDataMat[:,2]) #单色显示图(x,y轴的点)
ax.scatter(datingDataMat[:,1], datingDataMat[:,2],15.0*array(datingLabels), 15.0*array(datingLabels))#双色显示图
# plt.show()

# 归⼀化特征值
# newValue = (oldValue-min)/(max-min)
def autoNorm(dataSet):
    minVals = dataSet.min(0) #每列的最⼩值,dataSet.min(0)中的参数0使得函数可以从列中选取最⼩值， ⽽不是选取当前⾏的最⼩值
    # print(minVals)
    # [ 0.        0.        0.001156]
    maxVals = dataSet.max(0) #每列的最大值
    # print(maxVals)
    # [  9.12730000e+04   2.09193490e+01   1.69551700e+00]
    ranges = maxVals - minVals
    # print(ranges)
    # [  9.12730000e+04   2.09193490e+01   1.69436100e+00]
    normDataSet = zeros(shape(dataSet)) #0矩阵
    m = dataSet.shape[0] #1000个数据
    # print(m)
    # 1000
    normDataSet = dataSet - tile(minVals, (m,1)) #oldValue-min
    normDataSet = normDataSet/tile(ranges, (m,1)) #❶ 特征值相除,ranges = max-min
    return normDataSet, ranges, minVals

# normMat, ranges, minVals = autoNorm(datingDataMat)

# print(normMat)
# [[ 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]]

# print(ranges)
# [  9.12730000e+04   2.09193490e+01   1.69436100e+00]

# print(minVals)
# [ 0.        0.        0.001156]

#分类器针对约会⽹站的测试代码
def datingClassTest():
    # 数据集的占比
    hoRatio = 0.10
    #打开文件获取数据
    datingDataMat,datingLabels = file2matrix('D:/Python Project/.vscode/Machine-learning-practical-notes/KNN/datingTestSet2.txt') 
    #进行归一化操作
    normMat, ranges, minVals = autoNorm(datingDataMat) 
    #归一化后的矩阵大小 m=1000
    m = normMat.shape[0]
    # 测试集的数量 100
    numTestVecs = int(m*hoRatio)
    # 错误的数量
    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]))
        # 如果不匹配,errorCount++
        if (classifierResult != datingLabels[i]): errorCount += 1.0
    # 输出出错百分比
    print ("the total error rate is: %f" % (errorCount/float(numTestVecs)))
# 运行分类器针对约会⽹站的测试代码
# datingClassTest()

# 约会网站预测函数
def classifyPerson():
    resultList = ['not at all','in small doses','in large doses']
    # percentTats = float(input("percentage of time spent playing video games?"))
    # miles = float(input("frequent flier mies earned per year?"))
    # iceCream = float(input("liters of ice cream consumed per week?"))
    percentTats_str = input("percentage of time spent playing video games?")
    miles_str = input("frequent flier mies earned per year?")
    iceCream_str = input("liters of ice cream consumed per week?")
    percentTats = float(percentTats_str)
    miles = float(miles_str)
    iceCream = float(iceCream_str)
    datingDataMat,datingLabels = file2matrix('D:/Python Project/.vscode/Machine-learning-practical-notes/KNN/datingTestSet2.txt')
    normMat,ranges,minVals = autoNorm(datingDataMat)
    inArr = array([miles,percentTats,iceCream])
    classifierResult = classify0((inArr-minVals)/ranges,normMat,datingLabels,3)
    print("\nyou will probably like this person:",resultList[classifierResult - 1])

classifyPerson()

散点图

image

预测结果

image