用knn算法来预测喜爱程度

能根据对方的一些特征判断他（她）对你的吸引程度，是不喜欢，还是一般喜欢，还是很喜欢。以此改进约会配对效果。

1、有一千组数据，前200作为测试数据，后800个作为样本数据，然后训练模型

2、然后吧特征变量归一化去增加数据的可靠性，同时调整k值的参数来提高预测的准确度

3，准确度达到一定程度后，然后输入用户数据来进行匹配最优的人

#! /usr/bin/env python
# -*- coding=utf-8 -*-
from numpy import *
import operator
from os import listdir
import matplotlib
import matplotlib.pyplot as plt
import time
import pdb
def classify0(inX, dataSet, labels, k=5):# k=3 表示分三类
    # print "class lass -------------------------"
    # print inX
    # print dataSet #表示 后面 801的数据
    # print labels  #表示 最后800数据的标签
    # print "class end---------------------------------"
    # pdb.set_trace()
    dataSetSize = dataSet.shape[0]  #代表的是最后801个数据
    # print "classift0"
    # print dataSetSize
    diffMat = tile(inX, (dataSetSize, 1)) - dataSet #把当前的扩展下，然后减去后面801个
    #用欧氏距离来计算输入的数据和样本数据 801个进行计算距离

    # print "处理前的矩阵"
    # print diffMat
    sqDiffMat = diffMat ** 2

    # print "平方后的数据"
    # print sqDiffMat

    sqDistances = sqDiffMat.sum(axis=1)  #行相加求和
    # print "矩阵预处理"
    # print sqDistances
    distances = sqDistances ** 0.5
    # print "处理后的数据"
    # print distances

    sortedDistIndicies = distances.argsort()  # ascend sorted,

    #排序后返回的是索引值
    # print  "输入排序后的数据"
    # print sortedDistIndicies
    # return the index of unsorted, that is to choose the least 3 item
    classCount = {}
    for i in range(k):#让三个人去投票 然后说 他是谁，多者获胜
        voteIlabel = labels[sortedDistIndicies[i]]   #返回第一个是多少号元素
        print "VOTEVOTE"
        print voteIlabel
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1  # a dict with label as key and occurrence number as value
    print classCount
    sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True) #然后根据 key值排序，求出三者之间投票最多的

    '''descend sorted according to value, '''
    print sortedClassCount[0][0]
    return sortedClassCount[0][0]


def file2matrix(filename):
    print "+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"
    fr = open(filename)
    # pdb.set_trace()
    L = fr.readlines()
    numberOfLines = len(L)  # get the number of lines in the file
    print numberOfLines
    returnMat = zeros((numberOfLines, 3))  # prepare matrix to return
    print "初始化矩阵"
    print returnMat
    classLabelVector = []  # prepare labels return  初始化三维矩阵
    index = 0
    for line in L:
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index, :] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        # classLabelVector.append((listFromLine[-1]))
        index += 1
    fr.close()
    print "生成的 label 列表"
    print  classLabelVector
    print type(returnMat)
    ff = open("file.txt",'a')
    ff.write(returnMat)
    ff.close()
    print "生成的三维数据矩阵"
    print returnMat
    return returnMat, classLabelVector   #前面是矩阵，后面是类别



#特征变量归一化
def autoNorm(dataSet):

    #取出每一列的最小值，即每一个特征值得最小值
    minVals = dataSet.min(0) #分别取三维中的最小的数
    print "minvals"
    print minVals

    #取出每一列的最大值，即每一个特征值的最大值
    maxVals = dataSet.max(0)#分别取三维中最大的数
    print "maxvals"
    print maxVals

    #每一个特征变量的取值范围
    ranges = maxVals - minVals
    print "最大值减去最小值的范围"
    print ranges
    normDataSet = zeros(shape(dataSet))  #显示数组的属性
    m = dataSet.shape[0]                 #显示数组的行数
    print "显示数组的行数"
    print m
    normDataSet = dataSet - tile(minVals, (m, 1))#把minVals，行复制m次，列复制一次
    normDataSet = normDataSet / tile(ranges, (m, 1))  # element wise divide
    return normDataSet, ranges, minVals

#分类器测试
def datingClassTest(hoRatio=0.20):
    # hold out 10%
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')  # load data setfrom file
    normMat, ranges, minVals = autoNorm(datingDataMat)  #特征变量归一化
    m = normMat.shape[0]
    print  "what happend"
    print m
    numTestVecs = int(m * hoRatio)#输入 20%的案例   numTestVecs = 200 即取前200 个数据
    errorCount = 0.0
    print "what it is"
    for i in range(numTestVecs):
        classifierResult = classify0(normMat[i, :], normMat[numTestVecs:m, :], datingLabels[numTestVecs:m], 5)  #第一个表示第 i 个数据，然后第二个表示 （后800个数据）从nomTestVecs到最后的数据，第三个数据表示的当前数据的label
        print "the classifier came back with: %d, the real answer is: %d" % (classifierResult, datingLabels[i])
        if (classifierResult != datingLabels[i]): errorCount += 1.0
    print "the total error rate is: %.2f%%" % (100 * errorCount / float(numTestVecs))
    print 'testcount is %s, errorCount is %s' % (numTestVecs, errorCount)


def classifyPerson():
    '''
    input a person , decide like or not, then update the DB
    '''
    resultlist = ['not at all', 'little doses', 'large doses']
    percentTats = float(raw_input('input the person\' percentage of time playing video games:'))
    ffMiles = float(raw_input('flier miles in a year:'))
    iceCream = float(raw_input('amount of iceCream consumed per year:'))
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)
    normPerson = (array([ffMiles, percentTats, iceCream]) - minVals) / ranges
    result = classify0(normPerson, normMat, datingLabels, 3)
    print 'you will probably like this guy in:', resultlist[result - 1]

    # update the datingTestSet
    print 'update dating DB'
    tmp = '\t'.join([repr(ffMiles), repr(percentTats), repr(iceCream), repr(result)]) + '\n'

    with open('datingTestSet2.txt', 'a') as fr:
        fr.write(tmp)


if __name__ == '__main__':
    datingClassTest()
    classifyPerson()
    #handwritingClassTest()