KNN算法(二)------------约会甄别

最新推荐文章于 2021-01-23 18:37:52 发布

weixin_34362790

最新推荐文章于 2021-01-23 18:37:52 发布

阅读量110

点赞数

CC 4.0 BY-SA版权

文章标签： python 人工智能

原文链接：https://my.oschina.net/piginwind/blog/742247

本文介绍了一个使用Python实现的K近邻(KNN)分类算法，并通过一个具体的约会网站匹配案例展示了如何利用该算法进行数据分类。从加载数据到数据预处理，再到算法实现及最后的效果评估，整个过程详细而清晰。

2019独角兽企业重金招聘Python工程师标准>>>

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


def classify0(inX, dataSet, labels, k):#构建分类器,注释见机器学习(一)
    dataSetSize = dataSet.shape[0]#inx为测试样本集,dataset为训练样本集,label为类别标识
    diffMat = tile(inX, (dataSetSize,1)) - dataSet
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()     
    classCount={}          
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

def file2matrix(filename):
    fr = open(filename)
    numberOfLines = len(fr.readlines())         #get the number of lines in the file
    returnMat = zeros((numberOfLines,3))        #prepare matrix to return
    classLabelVector = []                       #prepare labels return   
    fr = open(filename)
    index = 0
    for line in fr.readlines():
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat,classLabelVector
    
def autoNorm(dataSet):#归一化处理 newvalue = (oldvalue - min)/(max - min)
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    normDataSet = zeros(shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - tile(minVals, (m,1))
    normDataSet = normDataSet/tile(ranges, (m,1))   #element wise divide,归一化处理
    return normDataSet, ranges, minVals
   
def datingClassTest():
    hoRatio = 0.1      #hold out 10%
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    numTestVecs = int(m*hoRatio)
    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]))
        if (classifierResult != datingLabels[i]):#样本集类别(已知类别)和测试集类别(通过classfy函数返回得到)进行比较
            errorCount += 1.0
            print("这里错了")
    print ("the total error rate is: %f" % (errorCount/float(numTestVecs)))
    print (errorCount)
    fig= plt.figure()
    ax = fig.add_subplot(111)
    ax.scatter(datingDataMat[:,0],datingDataMat[:,2],15.0*array(datingLabels),15.0*array(datingLabels),marker =(3,1),alpha = 1)
    plt.ylabel("dreamonfly")
    plt.xlabel("fat")
    plt.show()

datingClassTest()

转载于:https://my.oschina.net/piginwind/blog/742247