KNN

# Python-Project
#K均值算法的应用
from numpy import *
import matplotlib.pyplot as plt
import matplotlib
import operator

def classify0(inx,dataset,labels,k):
    dataSetSize=dataset.shape[0]
    diffMat=tile(inx,(dataSetSize,1))-dataset
    sqdiffMat=square(diffMat)
    sqDistances=sqdiffMat.sum(axis=1)
    distances=sqrt(sqDistances)
    index=distances.argsort(0)
    classcount={}
    for i in range(k):
        voteIlabel=labels[int(index[i])]
        classcount[voteIlabel]=classcount.get(voteIlabel,0)+1
    sortedClasscount=sorted(classcount.items(),key=operator.itemgetter(1),reverse=True)
    return sortedClasscount[0][0]
"""
group=mat([[1,1.1],[1,1],[0,0],[0,0.1]])
label=['A','A','B','B']
print(classify0([0,0],group,label,3))
"""
#收集数据
def filetomatrix(filename):
    fr=open(filename)
    arraylines=fr.readlines()
    numbersoflines=len(arraylines)
    returnmat=zeros((numbersoflines,3))
    classlabervector=[]
    index=0
    for line in arraylines:
        line=line.strip()
        listfromline=line.split('\t')
        returnmat[index,:]=list(map(float,listfromline[0:3]))
        classlabervector.append(int(listfromline[-1]))
        index+=1
    return returnmat,classlabervector

#画图
"""
fig=plt.figure()
ax=fig.add_subplot(111)
ax.scatter(s1[:,1],s1[:,2],15.0*array(s2),15.0*array(s2))
plt.show()
"""
#归一化特性
def autonormal(dataset):
    minvals=dataset.min(0)
    maxvals=dataset.max(0)
    ranges=maxvals-minvals
    normdateset=zeros(shape(dataset))
    m=dataset.shape[0]
    normdateset=dataset-tile(minvals,(m,1))
    normdateset=normdateset/tile(ranges,(m,1))
    return normdateset,ranges,minvals

def datingclasstest():
    horatio=0.1
    error=0.0
    datingdatamat,datinglabels=filetomatrix('shuju1.txt')
    normat,ranges,minvals=autonormal(datingdatamat)
    m=normat.shape[0]
    numtestvecs=int(m*horatio)
    for i in range(numtestvecs):
        classifierresult=classify0(normat[i,:],normat[numtestvecs:m,:]
                                   ,datinglabels[numtestvecs:m],4)
        print ("测试结果：%d,真实结果：%d" % (classifierresult,datinglabels[i]))
        if classifierresult!=datinglabels[i]:error+=1.0
    print ("误差率为：%f"%(error/float(numtestvecs)))

def classifyperson():
    leixing=["没有魅力","一般魅力","很有魅力"]
    #input("请输入此人信息：")
    datingdatamat, datinglabels = filetomatrix('shuju1.txt')
    normat, ranges, minvals = autonormal(datingdatamat)
    licheng =10000
    bingjiliang=0.5
    youxibizhong=10
    l=[licheng,bingjiliang,youxibizhong]
    print(l)
    print(minvals)
    #l.astype(float32)
    s=classify0((l-minvals)/ranges,normat,datinglabels,3)
    print("此人特点：%s"%(leixing[s-1]))
      #  i+=1
classifyperson()