Hi: I write my own code which passed the standard tests, but take forever to pass the one on website. I'll really appreciate it if you have any suggestion on how to improve the speed. Thanks! Here's my code:

import numpy as np
from copy import copy
from itertools import permutations

def checkio(data):
    square = np.array(data)
    n = len(data)
    s = int(n*(1+n**2)/2)
    templist = []
    coord = np.where(square == 0)

    def check(square):
        temp1 = np.sum(square, axis=1)
        temp2 = np.sum(square.T, axis=1)
        temp3 = np.sum(np.diagonal(square))
        temp4 = np.sum(np.diagonal(square[::-1]))
        if temp3 != s or temp4 != s:
            return False
        if np.any(s != temp1) or np.any(s != temp2):
            return False    
        return True

    for i in range(1,n**2+1):
        if i not in square:
            templist.append(i)

    for i in permutations(templist):
        squarecopy = copy(square)
        count = 0
        for j in zip(coord[0], coord[1]):
            squarecopy[j] = i[count]
            count += 1
        if check(squarecopy):
            return squarecopy.tolist()