算法导论08--优化二叉搜索树、顺序输入和哈希表

一、目的

1．熟悉算法设计的基本思想
2．掌握计数排序（count sort）的方法

二、内容与设计思想

有一个公司想开发一个关于花卉的百科全书，用户只要输入花卉的名称，就能够输出花卉的详细信息。花卉包括：牡丹、芍药、茶花、菊花、梅花、兰花、月季、杜鹃花、郁金香、茉莉花、海棠、荷花、栀子花、莲花、百合、康乃馨、玫瑰、格桑花。公司也在试运行阶段发现这些花的访问频率不一，有些花经常性被访问，有些被访问的次数就少很多了。这18种花中，第1种的访问频率是6，第2-3种的访问频率是5，第4-6种的访问频率是4，第7-10种的访问频率是3，第11-15种的访问频率是2，第16-18种的访问频率是1。
这个公司想提升花卉检索效率，所以对比了三种方法。
1、构建优化的二叉搜索树（optimal BST），进行搜索。

// 0.112*1 0.094*2 0.075*3 0.057*4 0.038*5 0.019*3

#include<bits/stdc++.h>
using namespace std;

#define N 18

int main()
{
	int i,j,l,r;
	double t;
	
	double p[19]={0,0.112,0.094,0.094,0.075,0.075,0.075,0.057,0.057,0.057,0.057,0.038,0.038,0.038,0.038,0.038,0.019,0.019,0.019};
	double q[19]={0};
	double e[N+2][N+1]={0};
	double w[N+2][N+1]={0};
	int root[N+1][N+1]={0};
	
	for (i=1;i<=N+1;i++)
	{
		e[i][i-1]=q[i-1];
		w[i][i-1]=q[i-1];
	}
	
	for (l=1;l<=N;l++)
	{
		for (i=1;i<=N-l+1;i++)
		{
			j=i+l-1;
			e[i][j]=1000;
			w[i][j]=w[i][j-1]+p[j]+q[j];
			for (r=i;r<=j;r++)
			{
				t=e[i][r-1]+e[r+1][j]+w[i][j];
				if (t<e[i][j])
				{
					e[i][j]=t;
					root[i][j]=r;
				}
			}
		}
	}
	
	cout<<endl;
	for (i=1;i<=N+1;i++)
	{
		for (j=0;j<=N;j++)
		{
			cout<<e[i][j]<<"\t";
		}
		cout<<endl;
	}
	
	cout<<endl;
	for (i=1;i<=N+1;i++)
	{
		for (j=0;j<=N;j++)
		{
			cout<<w[i][j]<<"\t";
		}
		cout<<endl;
	}
	
	cout<<endl;
	for (i=1;i<=N;i++)
	{
		for (j=1;j<=N;j++)
		{
			cout<<root[i][j]<<"\t";
		}
		cout<<endl;
	}
	
	return 0;
}

2、将这些花卉按照访问频度从高到低放在一个数组中，并顺序访问来检索

#include<bits/stdc++.h>
using namespace std;

int Num=1000;

int main()
{
	int arr[18]={6,5,5,4,4,4,3,3,3,3,2,2,2,2,2,1,1,1}; 
	
	clock_t startTime,endTime;
	startTime = clock();
	for (int k=1;k<=Num;k++)
	{
		for (int i=0;i<18;i++)
		{
			cout<<arr[i]<<" ";
		}
	}
	cout<<endl;
    endTime = clock();
    cout << "The run time is:" <<(double)(1000*(endTime - startTime) / CLOCKS_PER_SEC) << "ms" << endl;
	
	return 0;
}

3、构建哈希表来存储这些数据，并基于哈希表来检索数据。

#include<bits/stdc++.h>
using namespace std;
 
#define MAXHSIZE 100000001 
#define NULLKEY -32768 

int HASHSIZE;
int Num=1000;

typedef struct
{
	int *elem; 
	int count;  
} HashTable;
 
int m = 0; 
		  
int Init(HashTable *H)
{
	int i;
 
	m = HASHSIZE;
	H->elem = (int *)malloc(m * sizeof(int)); 
	H->count = m;
	for (i = 0; i<m; i++)
	{
		H->elem[i] = NULLKEY;
	}
	return 1;
}
 
 
int Hash(int k)
{
	return k % m;
}
 
 
void Insert(HashTable *H, int k)
{
	int addr = Hash(k); 					 
	while (H->elem[addr] != NULLKEY)
	{
		addr = (addr+1) % m;
	}
	H->elem[addr] = k;
}
 
int Search(HashTable *H, int k)
{
	int addr = Hash(k); 
 
							
	while (H->elem[addr] != k)
	{
		addr = (addr+1) % m;
 
		if (H->elem[addr] == NULLKEY || addr == Hash(k))
			return -1;
	}
	return addr;
}
 
void Result(HashTable *H)
{
	int i;
	for (i = 0; i<H->count; i++)
	{
		cout<< H->elem[i]<<" ";
	}
	cout<<endl;
}
 
int main()
{
	int i, j, addr;
	HashTable H;
//	cin>>HASHSIZE;

	int arr[18]={6,5,5,4,4,4,3,3,3,3,2,2,2,2,2,1,1,1}; 
	HASHSIZE=18;

	clock_t startTime,endTime;
	startTime = clock();
	for (int k=1;k<=Num;k++)
	{
		Init(&H);
		for (i = 0; i<HASHSIZE; i++)
		{
			Insert(&H, arr[i]);
		}
		Result(&H);
	}
	
    endTime = clock();
    cout << "The run time is:" <<(double)(1000*(endTime - startTime) / CLOCKS_PER_SEC) << "ms" << endl;

	
	return 0;
}

请实现这三种方法，并且通过实验来比较这三种方法的优劣。