数据结构与算法C++之并查集的优化

上篇中实现的union操作中合并两个元素是无序的，一般将第一个元素指向第二个元素，如下图中，是将4的根节点指向9，但是这样造成树总的高度为4，如果将9指向4的话，树的高度为3，树的高度减少后会很节省后面的查找花费的时间，因此需要先判断一下两个节点的根节点的数目，选择根节点数目少的节点指向根节点数目多的节点

下面是程序实现

#include <iostream>
#include <cassert>
#include "UnionFindTestHelper.h"

using namespace std;

int main()
{
    int n = 100000;
    UnionFindTestHelper::testUF1(n);
    UnionFindTestHelper::testUF2(n);
    UnionFindTestHelper::testUF3(n);
    return 0;
}

"UnionFindTestHelper.h"定义为

//UnionFindTestHelper.h
#include <iostream>
#include <ctime>
#include <cstdlib> //rand()º¯Êý
#include "UnionFind1.h"
#include "UnionFind2.h"
#include "UnionFind3.h"

using namespace std;

namespace UnionFindTestHelper{

    void testUF1(int n){
        srand(time(NULL));
        UF1::UnionFind uf = UF1::UnionFind(n);

        time_t startTime = clock();

        for(int i = 0; i < n; i++){
            int a = rand()%n;
            int b = rand()%n;
            uf.unionElements(a, b);
        }
        for(int i = 0; i < n; i++){
            int a = rand()%n;
            int b = rand()%n;
            uf.isConnected(a, b);
        }
        time_t endTime = clock();

        cout<<"UF1, "<<2*n<<" ops, "<<double(endTime-startTime)/CLOCKS_PER_SEC<<" s"<<endl;
    }

    void testUF2(int n){
        srand(time(NULL));
        UF2::UnionFind uf = UF2::UnionFind(n);

        time_t startTime = clock();

        for(int i = 0; i < n; i++){
            int a = rand()%n;
            int b = rand()%n;
            uf.unionElements(a, b);
        }
        for(int i = 0; i < n; i++){
            int a = rand()%n;
            int b = rand()%n;
            uf.isConnected(a, b);
        }
        time_t endTime = clock();

        cout<<"UF2, "<<2*n<<" ops, "<<double(endTime-startTime)/CLOCKS_PER_SEC<<" s"<<endl;
    }
    void testUF3(int n){
        srand(time(NULL));
        UF3::UnionFind uf = UF3::UnionFind(n);

        time_t startTime = clock();

        for(int i = 0; i < n; i++){
            int a = rand()%n;
            int b = rand()%n;
            uf.unionElements(a, b);
        }
        for(int i = 0; i < n; i++){
            int a = rand()%n;
            int b = rand()%n;
            uf.isConnected(a, b);
        }
        time_t endTime = clock();

        cout<<"UF3, "<<2*n<<" ops, "<<double(endTime-startTime)/CLOCKS_PER_SEC<<" s"<<endl;
    }

}

使用本篇博客实现的并查集UnionFind3.h定义为

//UnionFind3.h
#include <iostream>
#include <cassert>

using namespace std;

namespace UF3 {

    class UnionFind {

    private:
        int *parent;
        int *sz;
        int count;

    public:
        UnionFind(int n){
            count = n;
            parent = new int[count];
            sz = new int[count];
            for(int i = 0; i < count; i++){
                parent[i] = i;
                sz[i] = 1;
            }
        }

        ~UnionFind(){
            delete[] parent;
            delete[] sz;
        }

        int find( int p){
            assert( p >= 0 && p < count );
            while(p != parent[p])
                p = parent[p];
            return p;
        }

        bool isConnected(int p, int q){
            return find(p) == find(q);
        }

        void unionElements(int p, int q){
            int pRoot = find(p);
            int qRoot = find(q);

            if ( pRoot == qRoot )
                return;

            if (sz[pRoot] < sz[qRoot]){
                parent[pRoot] = qRoot;
                sz[qRoot] += sz[pRoot];
            }
            else{
                parent[qRoot] = pRoot;
                sz[pRoot] += sz[qRoot];
            }

        }
    };
}

"UnionFind1.h"和"UnionFind2.h"的定义见上篇博客
输出为

可以看出，20万次操作 优化后的并查集值花费了0.014秒