最小哈希签名代码

import numpy as np
N=100

start=[[1,0,0,1],[0,0,1,0],[0,1,0,1],[1,0,1,1],[0,0,1,0]]
list_2 = [[N,N,N,N],[N,N,N,N]]
def h1():
    mid=[0,0,0,0,0]
    for i in range(5):
        mid[i]=(i+1)%5
    return mid

def h2():
    mid = [0,0,0,0,0]
    for i in range(5):
        mid[i]=(3*i+1)%5
    return mid

h_1=h1()
h_2=h2()
list_1 = np.column_stack((start,h_1,h_2))

def dp():
    for i in range(5):
        for j in range(4):
            if list_1[i][j] == 1:
                list_2[0][j]=min(list_2[0][j],list_1[i][4])
                list_2[1][j]=min(list_2[1][j],list_1[i][5])
            
def compare(a,b,list_2):
    dp()
    compare_result=0
    for i in range(2):
        if list_2[i][a-1] == list_2[i][b-1]:
            compare_result = compare_result + 1
    compare_result = compare_result / len(list_2)
    a=str(a)
    b=str(b)
    ans = compare_result
    ans=str(ans)
    print(list_1)
    print(list_2)
    print("S"+a+"和S"+b+"的文本相似度估计是"+ans)
    
compare(1,3,list_2)