数据导入+欧式距离计算+互信息计算

数据导入+欧式距离计算+互信息计算

 

# coding=utf-8
import numpy as np
import math
#import pandas as pd
#from sklearn import preprocessing 

nd = np.genfromtxt('11111111.csv', delimiter=',', skip_header=True)
 
final_list = nd.tolist()#转化为list
#print(type(final_list))
#print(final_list)
a=[]
b=[]
c=[]
num=32
k=0
for one in final_list:
    #print(one)
    a.append(tuple(one))#list转化为tuple
#print(a)

for two in a:
    b.append(np.array(two))#tuple转化为array
#print(b[0:5])
def distEclud(vecA, vecB):
    return np.sqrt(sum(np.square(vecA - vecB)))


def NMI(A,B):
    # len(A) should be equal to len(B)
    total = len(A)
    A_ids = set(A)
    B_ids = set(B)
    #Mutual information
    MI = 0
    eps = 1.4e-45
    for idA in A_ids:
        for idB in B_ids:
            idAOccur = np.where(A==idA)
            idBOccur = np.where(B==idB)
            idABOccur = np.intersect1d(idAOccur,idBOccur)
            px = 1.0*len(idAOccur[0])/total
            py = 1.0*len(idBOccur[0])/total
            pxy = 1.0*len(idABOccur)/total
            MI = MI + pxy*math.log(pxy/(px*py)+eps,2)
    # Normalized Mutual information
    Hx = 0
    for idA in A_ids:
        idAOccurCount = 1.0*len(np.where(A==idA)[0])
        Hx = Hx - (idAOccurCount/total)*math.log(idAOccurCount/total+eps,2)
    Hy = 0
    for idB in B_ids:
        idBOccurCount = 1.0*len(np.where(B==idB)[0])
        Hy = Hy - (idBOccurCount/total)*math.log(idBOccurCount/total+eps,2)
    MIhat = 2.0*MI/(Hx+Hy)
    return MIhat

if __name__ == '__main__':
    for i in range(num):
        for j in range(num-1):
            if i <j+1:
                k=k+1
                #print('第{}个距离'.format(k),distEclud(b[i],b[j+1]))
                #print('第{}个互信息'.format(k),NMI(b[i],b[j+1]))
                c.append(NMI(b[i],b[j+1]))
            else:
                pass
    #n=[]#只有互信息
    dic={}
    q=1  
    for i in c:
        dic['第{}个互信息'.format(q)]='{}'.format(i)
        q=q+1
    #print(dic)
    rankdata=sorted(dic.items(),key=operator.itemgetter(1),reverse=True)
    print(rankdata)