def mtt(data, user_num, poi_num, zero_adjustment=True):
    print "共有" + str(user_num) + "个用户"
    for key in data.keys():
        print "用户" + str(key) + "序列为" + str(data[key])

    correlation_matrix = get_correlation_matrix(data, user_num)
    nor_cor_matrix = normalize(correlation_matrix)
    print "归一化相关系数矩阵: ", nor_cor_matrix

    transition_tensor = build_six_order_transition_tensor(data, poi_num, nor_cor_matrix, zero_adjustment)
    print "转移张量非零元素占比:", sparsity(transition_tensor)
    print "转移张量是否满足随机性:", check_six_order_transition_tensor(transition_tensor)

    return transition_tensor
def mtt(data, user_num, poi_num, zero_adjustment=True):
    print "共有" + str(user_num) + "个用户"
    for key in data.keys():
        print "用户" + str(key) + "序列为" + str(data[key])

    correlation_matrix = get_correlation_matrix(data, user_num)
    nor_cor_matrix = normalize(correlation_matrix)
    print "归一化相关系数矩阵: ", nor_cor_matrix

    transition_tensor = build_six_order_transition_tensor(
        data, poi_num, nor_cor_matrix, zero_adjustment)
    print "转移张量非零元素占比:", sparsity(transition_tensor)
    print "转移张量是否满足随机性:", check_six_order_transition_tensor(transition_tensor)

    return transition_tensor
示例#3
0
def serialization(data, user_num, poi_num):
    correlation_matrix = get_correlation_matrix(data, user_num)
    nor_cor_matrix = normalize(correlation_matrix)
    print "归一化相关系数矩阵: ", nor_cor_matrix

    for i in range(user_num):
        for j in range(user_num):
            if zero_adjustment:
                temp_tensor = build_fouth_order_influence_tensor(data[i], data[j], poi_num, True)
            else:
                temp_tensor = build_fouth_order_influence_tensor(data[i], data[j], poi_num, False)
            print str(i)+"对"+str(j)+"是否满足随机性条件", check_fourth_order_transition_tensor(temp_tensor)

            fouth_influence_tensor = fouth_tensor_hadarmard(nor_cor_matrix[i][j], temp_tensor)
            file_name = str(i)+"_"+str(j)+".db"
            file_path = "data/step_one/"+file_name
            print file_path
            transition_tensor_db = open(file_path, 'w')
            pickle.dump(fouth_influence_tensor, transition_tensor_db)
            transition_tensor_db.close()