相似度(參數調節代碼)

// test1.cpp : Defines the entry point for the console application.
//

#include <vector>
#include <cstring>
#include <fstream>
#include <string>
#include <iostream>
#include <algorithm>
#include <cstdio>
#include <cstdlib>
#include <map>
#include <ctime>
#include <iomanip>
#include <cmath>
#include <queue>

using namespace std;

struct serie
{
	vector<double> vec;
	string label;
	double len;
};
double speed = 1.6;
double INF = 1e10;
serie series[10000];
double dpA[2000][2000];
double dpB[2000][2000];
int num = 637;
double coe=0.2;
int WIN = 0;
double down_ratio;
map<int, string> names;
vector<int> lens(38, 0);
vector<int> num1(38, 0);
vector<int> num2(38, 0);
vector<int> classes(38,0);
vector<double> dev_mean(38, 0);

string to_string(int value)
{
	char help[10];
	sprintf(help,"%d",value);
	return string(help);
}
double DPA(int i, int j, int win)
{
	if ((i == 0 && j == win + 1) || (j == 0 && i == win + 1))
	{
		return dpA[i][j];;
	}
	if (abs(i - j) <= win)
		return dpA[i][j];
	return INF;
}
double DPB(int i, int j, int win)   
{
	if ((i == 0 && j == win + 1) || (j == 0 && i == win + 1))
	{
		return dpB[i][j];;
	}
	if (abs(i - j) <= win)
		return dpB[i][j];
	return INF;
}
double getdis(int one, int two, int i, int j)
{
	vector<double>& vec1 = series[one].vec;
	vector<double>& vec2 = series[two].vec;
	int n = vec1.size();
	double ans = (vec1[i * 2] - vec2[j * 2])*(vec1[i * 2] - vec2[j * 2]) + (vec1[i * 2 + 1] - vec2[j * 2 + 1])*(vec1[i * 2 + 1] - vec2[j * 2 + 1]);
	return sqrt(ans);
}
double getdistance00(int one, int two)
{
	int n = series[two].vec.size() + 1;
	dpA[0][0] = 0;
	dpB[0][0] = 0;
	dpA[1][0] = 0;
	dpB[0][1] = 0;
	n /= 2;
	for (int i = 2; i <= min(n - 1, WIN + 1); i++)
	{
		dpA[i][0] = dpA[i - 1][0] + getdis(one, one, i - 1, i - 1 - 1);// fabs(series[one].vec[i - 1] - series[one].vec[i - 1 - 1]);
		dpB[0][i] = dpB[0][i - 1] + getdis(two, two, i - 1, i - 1 - 1);// fabs(series[two].vec[i - 1] - series[two].vec[i - 1 - 1]);getdis(two, two, i - 1, j - 1-1)
	}
	int win = WIN;
	for (int i = 1; i < n; i++)
		for (int j = max(1, i - win); j < min(n, i + win + 1); j++)
		{
			if (i != 1)
				dpA[i][j] = min(DPA(i - 1, j, win) + getdis(one, one, i - 1, i - 1 - 1), DPB(i - 1, j, win) + coe*getdis(one, two, i - 1, j - 1));
			else
				dpA[i][j] = DPB(i - 1, j, win) + coe*getdis(one, two, i - 1, j - 1);

			if (j != 1)
				dpB[i][j] = min(DPA(i, j - 1, win) + coe*getdis(one, two, i - 1, j - 1), DPB(i, j - 1, win) + getdis(two, two, i - 1, j - 1 - 1));
			else
				dpB[i][j] = DPA(i, j - 1, win) + coe*getdis(one, two, i - 1, j - 1);

		}
	return min(dpA[n - 1][n - 1], dpB[n - 1][n - 1]);
}
double getdistance0t(int one, int two)
{
	int n = series[two].vec.size() + 1;
	dpA[0][0] = 0;
	dpB[0][0] = 0;
	dpA[1][0] = 0;
	dpB[0][1] = 0;
	for (int i = 2; i <= min(n-1,WIN + 1); i++)
	{
		dpA[i][0] = dpA[i - 1][0] + fabs(series[one].vec[i - 1] - series[one].vec[i - 1 - 1]);
		dpB[0][i] = dpB[0][i - 1] + 0*fabs(series[two].vec[i - 1] - series[two].vec[i - 1 - 1]);
	}
	int win = WIN;
	for (int i = 1; i < n; i++)
		for (int j = max(1, i - win); j < min(n, i + win + 1); j++)
		{
			if (i != 1)
				dpA[i][j] = min(DPA(i - 1, j, win) + fabs(series[one].vec[i - 1] - series[one].vec[i - 1 - 1]), DPB(i - 1, j, win) + coe*fabs(series[one].vec[i - 1] - series[two].vec[j - 1]));
			else
				dpA[i][j] = DPB(i - 1, j, win) + coe*fabs(series[one].vec[i - 1] - series[two].vec[j - 1]);

			if (j != 1)
				dpB[i][j] = min(DPA(i, j - 1, win) + coe*fabs(series[one].vec[i - 1] - series[two].vec[j - 1]), DPB(i, j - 1, win) + 0*fabs(series[two].vec[j - 1] - series[two].vec[j - 1 - 1]));
			else
				dpB[i][j] = DPA(i, j - 1, win) + coe*fabs(series[one].vec[i - 1] - series[two].vec[j - 1]);

		}
	return min(dpA[n - 1][n - 1], dpB[n - 1][n - 1]) ;
}
double getdistance0(int one, int two)
{
	int n = series[two].vec.size() + 1;
	dpA[0][0] = 0;
	dpB[0][0] = 0;
	dpA[1][0] = 0;
	dpB[0][1] = 0;
	for (int i = 2; i <= min(n - 1, WIN + 1); i++)
	{
		dpA[i][0] = dpA[i - 1][0] + fabs(series[one].vec[i - 1] - series[one].vec[i - 1 - 1]);
		dpB[0][i] = dpB[0][i - 1] + fabs(series[two].vec[i - 1] - series[two].vec[i - 1 - 1]);
	}
	int win = WIN;
	for (int i = 1; i < n; i++)
		for (int j = max(1, i - win); j < min(n, i + win + 1); j++)
		{
			if (i != 1)
				dpA[i][j] = min(DPA(i - 1, j, win) + fabs(series[one].vec[i - 1] - series[one].vec[i - 1 - 1]), DPB(i - 1, j, win) + coe*fabs(series[one].vec[i - 1] - series[two].vec[j - 1]));
			else
				dpA[i][j] = DPB(i - 1, j, win) + coe*fabs(series[one].vec[i - 1] - series[two].vec[j - 1]);

			if (j != 1)
				dpB[i][j] = min(DPA(i, j - 1, win) + coe*fabs(series[one].vec[i - 1] - series[two].vec[j - 1]), DPB(i, j - 1, win) + fabs(series[two].vec[j - 1] - series[two].vec[j - 1 - 1]));
			else
				dpB[i][j] = DPA(i, j - 1, win) + coe*fabs(series[one].vec[i - 1] - series[two].vec[j - 1]);

		}
	return min(dpA[n - 1][n - 1], dpB[n - 1][n - 1]);
}
double dp[2000][2000];
double getdistance1(int one, int two)
{
	int n = series[two].vec.size();
	dp[0][0] = fabs(series[one].vec[0] - series[two].vec[0]);
	int win = WIN;
	for (int i = 1; i < min(i+win,n); i++)
	{
		dp[i][0] = dp[i-1][0]+fabs(series[one].vec[i]-series[two].vec[0]);
		dp[0][i] = dp[0][i-1]+fabs(series[one].vec[0] - series[two].vec[i]);
	}
	for (int i = 1; i < n; i++)
		for (int j = max(1,i-win); j < min(i+win+1,n); j++)
		{
			if (j==i-win)
				dp[i][j] = fabs(series[one].vec[i] - series[two].vec[j]) +  min(dp[i - 1][j], dp[i - 1][j - 1]);
			else if (j==i+win)
				dp[i][j] = fabs(series[one].vec[i] - series[two].vec[j]) + min(dp[i][j - 1], dp[i - 1][j - 1]);
			else
				dp[i][j] = fabs(series[one].vec[i] - series[two].vec[j]) +min(dp[i - 1][j], min(dp[i][j - 1], dp[i - 1][j - 1]));
		}
	return dp[n - 1][n - 1];
	return 0;
}

double getdistance2(int one, int two)
{
	int n = series[two].vec.size();
	double ans = 0;
	for (int i = 0; i < series[one].vec.size(); i++)
	{
		ans += fabs(series[one].vec[i] - series[two].vec[i]);
	}
	return ans;
}
double getdistance3(int one, int two)
{
	int n = series[one].vec.size();
	double ans = 0;
	for (int i = 0; i < n - 1; i++)
	{
		ans += abs(series[one].vec[i] - series[two].vec[i]);
		ans += abs(series[two].vec[i] - series[one].vec[i + 1]);
		ans += abs(series[one].vec[i] - series[two].vec[i + 1]);
	}
	ans += abs(series[one].vec[n - 1] - series[two].vec[n - 1]);
	return ans;
}
double getdistance4(int one, int two)
{
	int n = series[two].vec.size();
	double ans = 0;
	dp[0][0] = abs(series[one].vec[0] - series[two].vec[0]);
	for (int i = 1; i < n; i++)
	{
		dp[i][0] = dp[i - 1][0] + abs(series[one].vec[i - 1] - series[one].vec[i]);
		dp[0][i] = dp[0][i - 1] + abs(series[two].vec[i - 1] - series[two].vec[i]);
	}
	int win = WIN;
	for (int i = 1; i < n; i++)
		//for (int j = 1; j < n; j++)
			for (int j = max(1, i - win); j < min(i + win + 1, n); j++)
		{
			dp[i][j] = INF;
			if (j - i + 1 <= win)
			dp[i][j] = min(dp[i][j],dp[i - 1][j] + abs(series[one].vec[i - 1] - series[one].vec[i]));
			if (i - j + 1 <= win)
			dp[i][j] = min(dp[i][j], dp[i][j - 1] + abs(series[two].vec[j - 1] - series[two].vec[j]));
			if (j - i + 1 <= win)
			dp[i][j] = min(dp[i][j], dp[i - 1][j ] + abs(series[one].vec[i] - series[two].vec[j])*coe);
			if (i - j + 1 <= win)
			dp[i][j] = min(dp[i][j], dp[i ][j - 1] + abs(series[one].vec[i] - series[two].vec[j])*coe);
			
		}
	return dp[n - 1][n - 1];
}
double getdistance5(int one, int two)
{
	int n = series[one].vec.size();
	double ans = 0;
	ans += abs(series[one].vec[0] - series[two].vec[0]);
	ans += abs(series[one].vec[n - 1] - series[two].vec[n - 1]);
	for (int i = 1; i < n - 1; i++)
	{
		ans += min(abs(series[one].vec[i] - series[two].vec[i - 1]), min(abs(series[one].vec[i] - series[two].vec[i]), abs(series[one].vec[i] - series[two].vec[i + 1])));
	}

	ans += abs(series[one].vec[n - 1] - series[two].vec[n - 1]);
	return ans;
}

void readInfo()
{
	ifstream file("/home/xiefubao/myproject/experiment/vldb_dataset/numhelp.txt");
	if (!file.is_open())
	{
		cout << "num.txt not open!" << endl;
		exit(0);
	}
	for (int i = 0; i < 38; i++)
	{
		string now;
		int no;
		file >> no;
		file >> now;
		file >> lens[i];
		file >> num1[i];
		file >> num2[i];
		file >> classes[i];
		file >> dev_mean[i];
		names[i] = now;
	}
}
void down_sample(int counter)
{
	int newnum = num*(1 - down_ratio);
	int getout = num - newnum;
	for (int i = 0; i < counter; i++)
	{
		vector<double> down;
		vector<int> help(num, 0);
		vector<bool> rem(num, 1);
		for (int j = 0; j < num; j++)
		{
			help[j] = j;
		}
		for (int j = 0; j < getout; j++)
		{
			int position = rand() % (num - j);
			rem[help[position]] = 0;
			swap(help[position], help[num-j-1]);
		}
		vector<double> now(newnum, 0);
		int add = 0;
		for (int j = 0; j < num; j++)
		{
			if (rem[j])
				now[add++] = series[i].vec[j];
		}
		swap(series[i].vec, now);
	}
	num = newnum;
}
void readFile(int filenum , bool train)
{
	num = lens[filenum - 1];
	string filepath = "/home/xiefubao/myproject/experiment/vldb_dataset/" + to_string(filenum) + "/" + names[filenum - 1] + (train ? "_TRAIN" : "_TEST") + ".txt";
	cout << filepath << endl;
	string now;
	ifstream in(filepath.c_str());
	if (!in.is_open())
	{
		cout << "not open" << endl;
		exit(1);
	}
	int number = train ? num2[filenum - 1] : num1[filenum - 1];
	for(int u = 0;u < number;u++)
	{
		in >> now;
		series[u].label = now;
		double len = 0;
		series[u].vec.clear();
		for (int i = 0; i < num; i++)
		{
			double point;
			in >> point;
			point = point;
			series[u].vec.push_back(point);
			if (i != 0)
				len += fabs(point - series[u].vec[i - 1]);
		}
		series[u].len = len;
	}
	cout<<"done 1"<<endl;
	//down_sample(number);
}
/*bool operator<(pair<double,string> n1,pair<double,string> n2) {
        return n1.first < n2.first;
}*/
int getvalue(int filenum,int wlen,double c,int counter,double(*distance) (int, int))
{
	int ans = 0;
	WIN = wlen;
	coe = c;
	for (int i = 0; i < counter; i++)
		{
			//cout << counter << " " << ans <<endl;
			priority_queue<pair<double,string> > pri;
			int prinum = 3;
			for(int j = 0;j < counter; j++)
			{
				if (i == j) continue;
				if (((i+3737)*(j+4343)) %(max(1,counter/classes[filenum]/5)) != 0) continue;
				double dis = distance(i,j);

				if(pri.size() < prinum)
					pri.push(make_pair(dis,series[j].label));
				else if(pri.top().first > dis)
				{
					pri.pop();
					pri.push(make_pair(dis,series[j].label));
				}
			}
			for(int u = 1;u <= prinum && !pri.empty();u++)
			{
				if(pri.top().second == series[i].label)
				{
					ans += u*u;
				}
				pri.pop();
			}
		}
		cout << "ans " << ans <<endl;
	return ans;
}
int   find_win_size(int filenum,double c,int counter,double(*distance) (int, int))
{
	int max_value = -1;
	int len = -1;
	for(int wlen = lens[filenum] / 2; wlen >= 2 ; wlen /= speed)
	{
		cout<<wlen<<endl;
		int value = getvalue(filenum,wlen,c,counter,distance);
		if(value >= max_value)
		{
			max_value = value;
			len = wlen;
		}
	}
	return len;
}
double find_ceo(int filenum,int counter, double(*distance) (int, int))
{
	int max_value = -1;
	double ans = -1;
	for(double rat = 1; rat > 0.001 ; rat /= 1.8)
	{
		int value = getvalue(filenum,WIN,rat,counter,distance);
		if(value >= max_value)
		{
			max_value = value;
			ans = rat;
		}
	}
	return ans;
}
int main()
{
	//cout << "xie" <<  << 123 << "123" << endl; getchar();
	readInfo(); 
	ofstream result;
	result.open("/home/xiefubao/myproject/experiment/vldb_dataset/compare.txt",ios::app);
	//file location
	//int filenum = 31;
	bool train = false;
	for (int filenum = 38; filenum <= 38; filenum++)
	{
		/*down_ratio = 0.2;
		readFile(filenum, false);
		cout << "start find winsize" << endl;
		WIN = find_win_size(filenum - 1,dev_mean[filenum-1]/2,num2[filenum -1],getdistance0);
		cout << "start find coe" << endl;
		coe = find_ceo(filenum - 1,num2[filenum -1],getdistance0);
		cout << "have done" << endl;
		cout << "WIN && coe : " << WIN << " " << coe <<endl;
        */
		clock_t start, finish;
		start = clock();

        WIN = 5;
        coe = dev_mean[filenum - 1];
		vector<int> hitnum(5, 0);
		int counter = num1[filenum - 1];

		cout << "reading" << endl;
		
		readFile(filenum, train);
		cout << "have read" << endl;
		cout << "xiefubao " << WIN << coe <<endl;
		//double(*distance[5]) (int, int) = { getdistance00, getdistance0, getdistance1, getdistance2, getdistance3 };
		double(*distance[5]) (int, int) = { getdistance0,getdistance1, getdistance2 };
		vector<int> computeDis;
		computeDis.push_back(0);
		computeDis.push_back(1);
		computeDis.push_back(2);
		//computeDis.push_back(3);
		//computeDis.push_back(4);
		for (int i = 0; i < counter; i++)
		{
			
			vector<double> mist(5, INF);
			vector<int> bestnum(5, -1);
			//cout << i << endl;  
			for (int j = 0; j < counter; j++)
			{
				if (i == j) continue;
				if (rand() %(max(1,counter/classes[filenum-1]/5)) != 0) continue;
				vector<double> dist(5, 0);
				for (int k = 0; k < computeDis.size(); k++)
				{
					dist[computeDis[k]] = distance[computeDis[k]](i, j);
				}
				for (int k = 0; k < computeDis.size(); k++)
					if (dist[computeDis[k]] < mist[computeDis[k]])
					{
						mist[computeDis[k]] = dist[computeDis[k]];
						bestnum[computeDis[k]] = j;
					}
			}
			if (i == counter - 1)
			{
				result << setw(2) << setfill(' ')  << filenum << " ";
			}
			for (int k = 0; k < computeDis.size(); k++)
			{
				if (series[i].label == series[bestnum[computeDis[k]]].label)
				{
					hitnum[computeDis[k]]++;
				}
				if (i % 100 == 0 || i == counter - 1)
					cout << "distance" << computeDis[k] << " hitsnum:" << hitnum[computeDis[k]] << " / " << i + 1 << " " << counter << endl;
				if (i == counter - 1)
				{
					result << setw(5) << setfill(' ')<< hitnum[computeDis[k]] << " ";
				}
			} 
			if (i % 100 == 0 || i == counter - 1)
				cout << endl;
			if (i == counter - 1)
			{
				result << setw(5) << setfill(' ') << counter <<" ";
				result << setw(4) << setfill(' ')<< WIN << "    " << setw(7) << setfill(' ') << coe << endl;
			}
		}
		finish = clock();
		//cout << "timeofcost: "<< finish - start << endl;
		cout << "series length: " << num << endl << endl;
		
	}
	return 0;
}

發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章