产生synthetic DataSet的数据集

Copyright 属于 The Skyline Operator的作者

@inproceedings{DBLP:conf/icde/BorzsonyiKS01, author = {Stephan B{\"o}rzs{\"o}nyi and Donald Kossmann and Konrad Stocker}, title = {The Skyline Operator}, booktitle = {ICDE}, year = {2001}, pages = {421-430}, ee = {http://doi.ieeecomputersociety.org/10.1109/ICDE.2001.914855}, crossref = {DBLP:conf/icde/2001}, bibsource = {DBLP, http://dblp.uni-trier.de} } @proceedings{DBLP:conf/icde/2001, editor = {Dimitrios Georgakopoulos and Alexander Buchmann}, title = {Proceedings of the 17th International Conference on Data Engineering, April 2-6, 2001, Heidelberg, Germany}, publisher = {IEEE Computer Society}, year = {2001}, isbn = {0-7695-1001-9}, bibsource = {DBLP, http://dblp.uni-trier.de} }

需要使用g++编译器进行编译

#define FOR_RELEASE #ifdef HAVE_CONFIG_H #include <config.h> #endif #include <iostream> #include <cstdlib> #include <fstream> #include <assert.h> #include <string.h> static const double UPPER = 0.95; static const double LOWER = 0.05; #ifndef RADIUS_BOUND #define RADIUS_BOUND 0.05 #endif #define DOMAIN 10000 using namespace std; double RandomEqual(double min,double max) { double x = (double)rand()/RAND_MAX; return x*(max-min)+min; } double RandomPeak(double min,double max,int dim) { double sum = 0.0; for (int d=0; d<dim; d++) sum += RandomEqual(0,1); sum /= dim; return sum*(max-min)+min; } double RandomNormal(double med,double var) { return RandomPeak(med-var,med+var,12); } double loc(double v, double s) { double d = v / s; long i = (long)d; if(d > i) { i ++; } return (double)i * s; } // void GenerateDataEqually(ostream& dou_data,int Count,int DupRatio,int Dimensions) void GenerateDataEqually(double** center, int Dimensions, int Count, int DupRatio) { double step = 1.0 / ((double)Count / (double)DupRatio); for (int i=0; i<Count; i++) { double x[Dimensions]; for (int d=0; d<Dimensions; d++) { // x[d] = RandomEqual(0,1); x[d] = RandomEqual(LOWER, UPPER); if(DupRatio == 1) { // dou_data << x[d] << " "; center[i][d] = x[d]; } else { // dou_data << loc(x[d],step) << " "; center[i][d] = loc(x[d],step); } } // dou_data << endl; } } // void GenerateDataCorrelated(ostream& dou_data,int Count,int DupRatio,int Dimensions) void GenerateDataCorrelated(double** center, int Dimensions, int Count, int DupRatio) { double step = 1.0 / ((double)Count / (double)DupRatio); double x[Dimensions]; for (long i=0; i<Count; i++) { again: // double v = RandomPeak(0,1,Dimensions); double v = RandomPeak(LOWER, UPPER, Dimensions); for (int d=0; d<Dimensions; d++) x[d] = v; // double l = v<=0.5 ? v:1.0-v; double l = v<=(LOWER+UPPER)/2 ? v : UPPER-v; for (int d=0; d<Dimensions; d++) { // double h = RandomNormal(0,l); double h = RandomNormal(LOWER, l); x[d] += h; x[(d+1)%Dimensions] -= h; } // for (int d=0; d<Dimensions; d++) if (x[d]<0 || x[d]>=1) goto again; for (int d=0; d<Dimensions; d++) if (x[d]<LOWER || x[d]>=UPPER) goto again; for (int d=0; d<Dimensions; d++) { if(DupRatio == 1) { // dou_data << x[d] << " "; center[i][d] = x[d]; } else { // dou_data << loc(x[d],step) << " "; center[i][d] = loc(x[d],step); } } // dou_data << endl; } } // void GenerateDataAnticorrelated(ostream& dou_data,int Count,int DupRatio,int Dimensions) void GenerateDataAnticorrelated(double** center, int Dimensions, int Count, int DupRatio) { double step = 1.0 / ((double)Count / (double)DupRatio); double x[Dimensions]; for (long i=0; i<Count; i++) { again: // double v = RandomNormal(0.5,0.25); double v = RandomNormal((LOWER+UPPER)/2, (LOWER+UPPER)/4); for (int d=0; d<Dimensions; d++) x[d] = v; // double l = v<=0.5 ? v:1.0-v; double l = v<=(LOWER+UPPER)/2 ? v : UPPER-v; for (int d=0; d<Dimensions; d++) { double h = RandomEqual(-l,l); x[d] += h; x[(d+1)%Dimensions] -= h; } for (int d=0; d<Dimensions; d++) if (x[d]<LOWER || x[d]>=UPPER) goto again; for (int d=0; d<Dimensions; d++) { if(DupRatio == 1) { // dou_data << x[d] << " "; center[i][d] = x[d]; } else { // dou_data << loc(x[d],step) << " "; center[i][d] = loc(x[d],step); } } // dou_data << endl; } } // void GenerateData(int Dimensions,char Distribution,int Count,int DupRatio, // ostream& dou_data) void GenerateCenter(double** center, int Dimensions, char Distribution, int Count) { if (Count <= 0) { cout << "Amount should be greater than 0" << endl; return; } if (Dimensions < 2) { cout << "Dimension should be greater than 2" << endl; return; } switch (Distribution) { case 'E': case 'e': Distribution = 'E'; break; case 'C': case 'c': Distribution = 'C'; break; case 'A': case 'a': Distribution = 'A'; break; default: cout << "Unknown data distribution error." << endl; return; } // dou_data << Count << " " << Dimensions << endl; switch (Distribution) { case 'E': srand((unsigned)time(NULL)); GenerateDataEqually(center, Dimensions , Count, 1); break; case 'C': srand((unsigned)time(NULL)); GenerateDataCorrelated(center, Dimensions , Count, 1); break; case 'A': srand((unsigned)time(NULL)); GenerateDataAnticorrelated(center, Dimensions , Count, 1); break; } // cout << "done." << endl; } //argv[1]: MIN_GROUP_SIZE, argv[2]: MAX_GROUP_SIZE, argv[3]: dimension, argv[4]: groupNo, argv[5]: distribution int main(int argc, char *argv[]) { int dimension = 4; long groupNo = 5000; char type='E'; char path[128]="/home/yingz/work/SO/exp/center"; #ifdef FOR_RELEASE if( argc <= 4 ) { cerr << "data generator for pskyline" << endl << "Usage: " << argv[0] << endl << " dimension: " << endl << " the number of centers to be generated: " << endl << " distribution for the centers of groups (E(qually) | C(orrelated) | A(nti-correlated)): " << endl << " path " << endl; } else { dimension = atoi(argv[1]); groupNo = atol(argv[2]); type = argv[3][0]; strcpy( path , argv[4] ); } #endif char filename[128]; sprintf( filename, "%s/%dd_%c_%d.txt" , path , dimension, type, groupNo); ofstream out(filename, ios_base::trunc); assert( out.is_open()); out.setf(ios::fixed, ios::floatfield); out << groupNo << " " << dimension << endl; srand(time(NULL)); double** center; center = new double*[groupNo]; for(long i = 0; i < groupNo; ++i) { center[i] = new double[dimension]; } GenerateCenter(center, dimension, type, groupNo); for ( int i=0; i< groupNo; i++ ) { for ( int d=0; d< dimension; d++ ) out<< center[i][d] * DOMAIN << " "; out << endl; } cout << "generation complete" << endl; for(long i = 0; i < groupNo; ++i) { delete[] center[i]; } delete[] center; return EXIT_SUCCESS; } 编译完成后运行 ./a.out 2 100 E .