#!/usr/bin/env python
# -*- coding: UTF-8 -*-
'''=================================================
@Project -> File   ：KNN -> kNN
@IDE    ：PyCharm
@Author ：zgq
@Date   ：2021/1/7 14:15
@Desc   ：
=================================================='''
from numpy import *
import operator #运算符模块
import matplotlib
import matplotlib.pyplot as plt


def creatDateSet():
    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=creatDateSet()

def classify0(inX,dataSet,labels,k):
    #inx用于分类的输入向量
    #训练样本集dataset
    #lables标签
    #k最近邻数目

    #距离计算
    dataSetSize=dataSet.shape[0] #dataset有几行
    diffMat=tile(inX,(dataSetSize,1))-dataSet  #输入向量重复了已有数据集的行数，一起减掉，出来一个新的矩阵，每个数字都记录当前新样本该维度与每个样本差值
    sqDiffMat=diffMat**2
    sqDistances=sqDiffMat.sum(axis=1) #所有横轴元素加和
    distances=sqDistances**0.5  #到此处时 distance为一个一位列数组，记录每条样本与新样本的距离
    sortedDistIndicies= distances.argsort() #对distance进行升序排序
    classCount={}   #DICT类型
    for i in range(k):  #寻找距离最小的K个点
        voteIlabel = labels[sortedDistIndicies[i]]   #返回距离排序中前K条数据的标签
        classCount[voteIlabel]=classCount.get(voteIlabel,0)+1
        #classCount.get(voteIlabel,0) 字典获取vouteIlabel值，没有的话返回0
        #此处for循环将距离最近的K个数据标签进行统计：每次for循环第一步，将第i个标签记录到voteIlable中，第二部将该标签出现后再dict中次数加一
    sortedClassCount=sorted(classCount.items(),key=operator.itemgetter(1),reverse=True)
    return sortedClassCount[0][0]
#test
test=classify0([0,0],group,labels,3)
print(test)

#将文本记录转换为Numpy的解析程序
def file2matrix(filename):
    fr=open(filename)
    arrayOLines=fr.readlines()
    numberOfLines=len(arrayOLines)  #得到文件行数
    returnMat=zeros((numberOfLines,3))  #将行数和列数为3的矩阵填充为0
    classLabelVector=[] #类标签向量
    index=0
    for line in arrayOLines:    #迭代每行
        line = line.strip()     #去除首位空格
        listFromLine=line.split('\t')   #以空格划分数据
        returnMat[index,:]=listFromLine[0:3]    #将第index行所有行赋值上当前行前三项
        classLabelVector.append(int(listFromLine[-1]))  #该行标签给她
        index +=1
    return returnMat,classLabelVector

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


#对当前数据进行可视化
fig=plt.figure()
ax=fig.add_subplot(111)
ax.scatter(datingDataMat[:,0],datingDataMat[:,1],15.0*array(datingLabels),15.0*array(datingLabels))
plt.show()


#对当前数据进行归一化，防止同样权重大小的不同特征，数值大的特征对算法距离影响特别大，都将其置为-1，1之间
def autoNorm(dataSet):
    minVals=dataSet.min(0)  #将每一列中最小的取出来 构成了一个向量
    maxVals=dataSet.max(0)
    ranges=maxVals-minVals  #每一列数值的取值范围
    normDataSet=zeros(shape(dataSet))       #创建一个新的形状和dataset一样的矩阵用0填上
    m=dataSet.shape[0]      #dataset的行数
    normDataSet=dataSet-tile(minVals,(m,1)) #用dataset-将minVal复制n行与原dataset形状对齐，对所有的矩阵里的原来的数进行减最小值
    normDataSet=normDataSet/tile(ranges,(m,1))
    return normDataSet,ranges,minVals

normMat,ranges,minVals=autoNorm(datingDataMat)
print("输出归一化后测试集")
print(normMat)


#测试分类器效果，返回错误率
def datingClassTest():
    hoRatio=0.10
    datingDataMat,datingLabels=file2matrix('datingTestSet2.txt')    #原始数据转换为numoy数据
    normMat,ranges,minVals=autoNorm(datingDataMat)      #归一化好的数据
    m=normMat.shape[0]  #获取归一化好数据样本总数
    numTestVecs=int(m*hoRatio)  #测试集的总数量
    errorCount=0.0 #测试集错误率置为0
    for i in range(numTestVecs):    #遍历每一个测试样本
        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]))
        if(classifierResult!=datingLabels[i]):
            errorCount=errorCount+1
    print("the total error rate is : %f" % (errorCount/float(numTestVecs)))


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?"))
    iceCream=float(input("liters of ice cream consumed per year?"))
    ffMiles=float(input("frequent flier miles earned per year?"))
    datingDataMat,datingLabels=file2matrix('datingTestSet2.txt')
    norMat,ranges,minVals=autoNorm(datingDataMat)
    inArr=array([ffMiles,percentTats,iceCream])
    classifierResult=classify0((inArr-minVals)/ranges,norMat,datingLabels,3)
    print("you will probably like this person:",resultList[classifierResult-1])

    return

classifyPerson()

运行结果：
数据展示

将原始数据txt转换为numpy

[[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]]

输出归一化后测试集

[[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]]

测试错误率结果`

the classifier came back with: 3,the real answer is : 3
the classifier came back with: 2,the real answer is : 2
the classifier came back with: 1,the real answer is : 1
the classifier came back with: 1,the real answer is : 1
the classifier came back with: 1,the real answer is : 1
the classifier came back with: 1,the real answer is : 1
the classifier came back with: 3,the real answer is : 3
the classifier came back with: 3,the real answer is : 3
the classifier came back with: 1,the real answer is : 1
the classifier came back with: 3,the real answer is : 3
……
the total error rate is : 0.050000

输入新数据测试结果：

percentage of time spent playing video games?>? 10
liters of ice cream consumed per year?>? 10000
frequent flier miles earned per year?>? 0.5
you will probably like this person: in large doses