Median Maintenance

本文介绍了一种名为“中位数维护”的算法,该算法能够处理从1到10000的整数流,并实时计算每个到达元素时的中位数。通过使用最大堆和最小堆来平衡数据并找出中位数,可以有效地解决这个问题。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

The goal of this problem is to implement the "Median Maintenance" algorithm (covered in the Week 5 lecture on heap applications). The text file contains a list of the integers from 1 to 10000 in unsorted order; you should treat this as a stream of numbers, arriving one by one. Letting xi denote the ith number of the file, the kth median mk is defined as the median of the numbers x1,,xk. (So, if k is odd, then mk is ((k+1)/2)th smallest number among x1,,xk; if k is even, then mk is the (k/2)th smallest number among x1,,xk.)

In the box below you should type the sum of these 10000 medians, modulo 10000 (i.e., only the last 4 digits). That is, you should compute (m1+m2+m3++m10000)mod10000.

OPTIONAL EXERCISE: Compare the performance achieved by heap-based and search-tree-based implementations of the algorithm.

Reference: http://stackoverflow.com/questions/10657503/find-running-median-from-a-stream-of-integers

Step 1: Add next item to one of the heaps


       if next item is smaller than maxHeap root add it to maxHeap,
       else add it to minHeap

Step 2: Balance the heaps (after this step heaps will be either balanced or
        one of them will contain 1 more item)


       if number of elements in one of the heaps is greater than the other by
       more than 1, remove the root element from the one containing more elements and
       add to the other one

Then at any given time you can calculate median like this:

   If the heaps contain equal elements;
     median = (root of maxHeap + root of minHeap)/2
   Else
     median = root of the heap with more elements

#include <iostream>
#include <fstream>
#include <math.h>
#include <vector>
#include <sstream>
#include <map>

using namespace std;

class MaxMinHeap
{
public:
	MaxMinHeap(int _capacity, bool _bmin);
	~MaxMinHeap();

	void Insert(int num);
	void Pop();
	int Top() {return h[0];};
	int Size() {return size;};
private:
	int size;
	int *h;
	bool bmin;
};

MaxMinHeap::MaxMinHeap(int _capacity, bool _bmin = true)
{
	size =0;
	h = (int *)malloc(sizeof(int)*_capacity);
	bmin = _bmin;
}

MaxMinHeap::~MaxMinHeap()
{
	free(h);
}

void MaxMinHeap::Insert(int num)
{
	h[size++] = num;
	int pos = size-1;

	int temp;
	if (bmin) // Min heap
	{
		while(pos >0)
		{
			int parent = pos-1>>1;
			if (h[pos] >= h[parent])
			{
				break;
			} 

			temp = h[parent];
			h[parent] = h[pos];
			h[pos] = temp;

			pos = parent;

		}
	} 
	else
	{
		while(pos >0) // Max heap
		{
			int parent = pos-1>>1;
			if (h[pos] <= h[parent])
			{
				break;
			} 

			temp = h[parent];
			h[parent] = h[pos];
			h[pos] = temp;

			pos = parent;

		}
	}
}


void MaxMinHeap::Pop()
{
	h[0] = h[--size];
	int pos = 0;

	int temp;
	if (bmin) // min heap
	{
		while (pos < (size >> 1))
		{
			int child = 2*pos+1;
			if (child+1< size && h[child+1]< h[child])
			{
				child++;
			}

			if (h[pos] < h[child])
			{
				break;
			}

			temp = h[child];
			h[child] = h[pos];
			h[pos] = temp;
			pos = child;
		}
	}else
	{
		while (pos < (size >> 1)) // max heap
		{
			int child = 2*pos+1;
			if (child+1< size && h[child+1]> h[child])
			{
				child++;
			}

			if (h[pos] >= h[child])
			{
				break;
			}

			temp = h[child];
			h[child] = h[pos];
			h[pos] = temp;
			pos = child;
		}
	}
}


int main()
{
	ifstream infile;
	infile.open("Median.txt");

	MaxMinHeap minHeap(5010, true);
	MaxMinHeap maxHeap(5010, false);
	minHeap.Insert(numeric_limits<int>::max());
	maxHeap.Insert(numeric_limits<int>::min());
	int input;

	int minTop;
	int maxTop;
	int num = 0;
	int sum = 0;
	while(!infile.eof())
	{
		infile>>input;
		/*cout << "Input" << input << endl;*/
		
		minTop = minHeap.Top();
		maxTop = maxHeap.Top();
		if (input < maxTop)
		{
			maxHeap.Insert(input);
		}else
		{
			minHeap.Insert(input);
		}

		// Balance
		if (maxHeap.Size() > minHeap.Size()+1)
		{
			maxTop = maxHeap.Top();
			maxHeap.Pop();

			minHeap.Insert(maxTop);
		}
		if (minHeap.Size() > maxHeap.Size()+1)
		{
			minTop = minHeap.Top();
			minHeap.Pop();

			maxHeap.Insert(minTop);
		}

		// Compute the median
		if (minHeap.Size() == maxHeap.Size()+1)
		{
			sum += minHeap.Top();

			/*cout << "median : " << minHeap.Top() << endl;*/
		}else{
			sum += maxHeap.Top();

			/*cout << "median : " << maxHeap.Top() << endl;*/
		}

		num++;
	}

	cout << "The total number is " << num << endl;
	
	cout << "The sum is " << sum%10000 << endl;

	infile.close();
	return 0;
}


评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值