gpt4 book ai didi

c++ - 如何根据距离矩阵确定节点?

转载 作者:行者123 更新时间:2023-11-30 04:57:21 25 4
gpt4 key购买 nike

假设我有:

A -> B 10

A -> C 5

A -> D 7.5

B -> C 12

B -> D 17

C -> D 5

然后,我收到一个未排序的输入,如下所示:

    K   L   M   N
K 0 10 12 17
L 10 0 5 7.5
M 12 5 0 5
N 17 7.5 5 0

我必须确定(对于任何类型的输入 - 任何顺序)哪个节点(K、L、M 和 N)实际上是 A、B、C 和 D。

对于上面的例子输入,这里的情况是A是LB是KC是M & D 是 N

所以我已经开始了一些事情,但我仍然不确定如何继续。下面为我​​提供了一个 std::map,输入的哪一行是给定的行。但是,即使我知道存在这种组合,我也不确定如何知道未知数(城市顺序)。有人可以帮我对输入进行排序以匹配给定的吗?

#include <iostream>
#include <vector>
#include <algorithm>
#include <map>

using namespace std;

bool checkForSimilar(vector<double> Vec1, vector<double> Vec2)
{
std::sort(Vec1.begin(), Vec1.end());
std::sort(Vec2.begin(), Vec2.end());

return std::equal(Vec1.begin(), Vec1.end(), Vec1.begin(), Vec2.end());
}

int main()
{
vector<vector<double>> GivenDistances = { // A B C D
/*A*/ {0, 10, 5, 7.5},
/*B*/ {10, 0, 12, 17 },
/*C*/ {5, 12, 0, 5 },
/*D*/ {7.5,17, 5, 0 }};

vector<vector<double>> InputDistances = { // K L M N
/*K*/{ 0, 10, 12, 17 },
/*L*/{ 10, 0, 5, 7.5},
/*M*/{ 12, 5, 0, 5 },
/*N*/{ 17, 7.5,5, 0 }};

std::map<int, int> RowMatches;
for (int i = 0; i < InputDistances.size(); i++)
{
for (int j = 0; j < InputDistances[i].size(); j++)
{
// check if current row is any combination if GivenDistances
if (checkForSimilar(InputDistances[i], GivenDistances[j]))
{
RowMatches[i] = j;
}
}
}

// How to order then them??


int pause;
cin >> pause;
return 0;
}

最佳答案

解决问题的函数:

    /** Solve problem posed in https://stackoverflow.com/q/52046650/16582

Search for a permuted column in the input matrix
which matches each given column

@param[out] assign the first node assignment which creates a match
@param[in] distance the distances between nodes, given and input

Mean time to find match ( milliseconds )

<pre>
Cities Search1 Search2
10 20 0.01
100 ??? 4
</pre2>

*/

void Find(
cNodeAssign& assign,
cNodeDistance& distance )
{
raven::set::cRunWatch R("Search");

assign.Clear();

// loop over rows in given distances
for( int given = 0; given < distance.Size(); given++ )
{
// loop over rows in input distances
for( int input = 0; input < distance.Size(); input++ )
{
// check if the input row has already been assigned
if( assign.Find( input ) )
continue;

// check if row and column are permutations of each other
if( distance.IsPermutation( given, input ))
{
// found a match
assign.Add( input );

// no need to search further for this row
break;
}
}
}
}

演示功能和执行时间分析的主要代码

int main()
{
cout << "Original Problem:\n";
vector<vector<double>> GivenDistances = // A B C D
{
/*A*/ {0, 10, 5, 7.5},
/*B*/ {10, 0, 12, 17 },
/*C*/ {5, 12, 0, 5 },
/*D*/ {7.5,17, 5, 0 }
};

vector<vector<double>> InputDistances = // K L M N
{
/*K*/{ 0, 10, 12, 17 },
/*L*/{ 10, 0, 5, 7.5},
/*M*/{ 12, 5, 0, 5 },
/*N*/{ 17, 7.5,5, 0 }
};

cNodeDistance dop( GivenDistances, InputDistances );
cNodeAssign assign( dop.Size() );

dop.Display();
Find( assign, dop );
assign.Display();

Demo( 4 );

Demo( 10 );

Timer( 10 );

Timer( 100 );
}

构建演示应用程序的代码是 available here .

关于c++ - 如何根据距离矩阵确定节点?,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/52046650/

25 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com