bool load_fddb(std::vector< std::unique_ptr<NeuralNet::Image> >& images,
size_t num_image, bool uses_first)
{
const size_t patch_size = 32;
size_t loaded_image = 0;
std::ifstream ellipse_list;
if (uses_first)
{
ellipse_list.open("data-fddb/ellipse-1to5.txt");
}
else
{
ellipse_list.open("data-fddb/ellipse-6to10.txt");
}
while (loaded_image < num_image)
{
std::string file_line;
if (!std::getline(ellipse_list, file_line))
{
std::cout << "end-of-file of ellipse file" << std::endl;
return false;
}
file_line.insert(file_line.size(), ".ppm");
file_line.insert(0, "data-fddb/");
auto img_ptr = NeuralNet::loadPPMImage(file_line.c_str());
if (!img_ptr)
{
std::cout << "missing file " << file_line << std::endl;
return false;
}
std::string line_str;
if (!std::getline(ellipse_list, line_str))
{
std::cout << "end-of-file of ellipse file" << std::endl;
return false;
}
std::istringstream iss(line_str);
size_t face_count;
iss >> face_count;
size_t actual_count = 0;
for (size_t i = 0; i < face_count && actual_count+loaded_image < num_image; i++)
{
if (!std::getline(ellipse_list, line_str))
{
std::cout << "end-of-file of ellipse file" << std::endl;
return false;
}
std::istringstream iss2(line_str);
float majsize, minsize, tilt, centx, centy;
iss2 >> majsize >> minsize >> tilt >> centx >> centy;
if (majsize < patch_size)
continue;
auto crop_ptr = NeuralNet::cropImage(img_ptr,
centx - majsize/2,
centy - minsize/2,
majsize,
majsize);
auto fit_ptr = NeuralNet::fitImageTo(crop_ptr, patch_size, patch_size);
images.push_back(preprocessImage(fit_ptr));
actual_count++;
}
loaded_image += actual_count;
}
return true;
}
//NOTE: The file index starts at 1, but we'll subtract one
// to match vector index.
void readInFromFile( vector<Node> &g, string fileName )
{
//clear g
g = {};
Node emptyNode;
ifstream inFile( fileName, ios::in );
if ( !inFile )
{
cerr << endl << "File could not be opened." << endl << endl;
exit(1);
}
string line;
while( getline(inFile, line) )
{
istringstream iss1(line);
string tab;
string sindex;
long index;
getline(iss1, sindex, '\t');
istringstream issIndex(sindex);
issIndex >> index;
//Make index match array index
--index;
//cout << "Index: " << index << endl;
//Add a node
g.push_back(emptyNode);
while( getline(iss1, tab, '\t') )
{
//extra crap (like space or newline) in last iteration
if( tab.length() >= 3 )
{
istringstream iss2(tab);
string comma;
int counter = 0;
long iVert = -1000;
long edgeDist = -1000;
while( getline(iss2, comma, ',') )
{
istringstream iss3(comma);
if( counter == 0 )
{
iss3 >> iVert;
//Make vertex match array index
--iVert;
counter++;
}
else if( counter == 1 )
{
iss3 >> edgeDist;
counter++;
}
else
// Test program
int main(int argc, char *argv[])
{
clock_t s,e;
s = clock();
/**** get inputs ****/
// argv[1] = "T10I4D100K.dat";
// argv[2] = "1";
// argv[3] = "outss.txt";
string input_filename = argv[1];
string output_filename = argv[3];
int min_st = atoi(argv[2]);
/*** check if the input file exist***/
ifstream input(input_filename);
if ( !input.is_open() ) {
// handle error.
cout << "input file not found!"<< endl;
}
/***** read input file and count one-item frequecies *****/
item_freq_map one_item_candidate;
Itemset is;
is.freq(input, one_item_candidate);
/****** find one-item sets ******/
for (auto it = one_item_candidate.begin(); it != one_item_candidate.end(); ){
if (it->second < min_st){
one_item_candidate.erase(it++);
}
else{
++it;
}
}
ofstream output;
output.open(output_filename);
vector <int> one_item;
/****** write one-item sets into the output file ****/
for (item_freq_map::iterator it = one_item_candidate.begin(); it != one_item_candidate.end(); ++it) {
output << it->first << " ("<< it->second << ")\n";
one_item.push_back(stoi(it->first));
}
sort(one_item.begin(), one_item.end());
Trie trie;
map <string ,int> two_item_candidate;
for(int i = 0; i < one_item.size(); i++){
for(int j = i + 1; j < one_item.size(); j++){
string candidate = to_string(one_item[i])+" "+to_string(one_item[j]);
trie.addWord(candidate);
two_item_candidate[candidate] = 0;
}
}
ifstream in(input_filename);
if (!in.is_open() ) {
// handle error.
cout << "input file not found!"<< endl;
}
Utils utils;
string trans;
int tid = 0;
while (std::getline(in, trans))
{
istringstream iss(trans);
string s;
vector<int> st;
//cout << "tid = " << tid<< endl;
while ( getline( iss,s, ' ' ) )
{
st.push_back(atoi(s.c_str()));
}
sort(st.begin(), st.end());
vector<string> sorted_trans;
int k;
for( k = 0; k < st.size(); k++){
string temp = to_string(st[k]);
sorted_trans.push_back(temp);
}
vector<strset> cursubsets = utils.subsets(2, sorted_trans, tid);
tid++;
//utils.printVecOfStrset(cursubsets);
for(int sub = 0; sub < cursubsets.size(); sub ++)
{
string subsetStr = "";
for (int submem = 0; submem < cursubsets.at(sub).size(); submem++)
{
subsetStr = subsetStr + cursubsets.at(sub).at(submem).c_str() + " ";
}
subsetStr = subsetStr.substr(0, subsetStr.length() - 1);
int support = trie.searchWord(subsetStr);
two_item_candidate[subsetStr] = support;
//cout << "support = " << support << endl;
}
}
in.close();
//count_frequency(two_item_candidate)
/*** check which two-item-candidate are frequent ****/
for (auto it = two_item_candidate.begin(); it != two_item_candidate.end(); ){
if (it->second < min_st){
two_item_candidate.erase(it++);
}
else{
++it;
}
}
/*** get item names ***/
vector <string> two_item;
/****** write two-item sets into the output file ****/
for (item_freq_map::iterator it = two_item_candidate.begin(); it != two_item_candidate.end(); ++it) {
//cout << it->first << " ("<< it->second << ")\n";
output << it->first << " ("<< it->second << ")\n";
two_item.push_back(it->first);
}
vector <string> many_item = two_item;
//cout<<"two_item: "<<two_item.size()<<endl;
//cout<<"many:"<<many_item.size()<<endl;
int count = 0;
int k_item = 3;
while(k_item<=5){
// vector <string> prev_item = many_item;
map <string ,int> many_item_candidate;
//cout<<"AREA 2: "<< many_item.size() <<endl;
for(int i = 0; i < many_item.size(); ++i){
for(int j = i + 1; j < many_item.size(); ++j){
vector<int> st;
int item_size = 0;
/****** split string by space *****/
string s1;
istringstream iss(many_item[i]);
while ( getline( iss, s1, ' ' ) ) {
st.push_back(atoi(s1.c_str()));
item_size ++;
}
istringstream iss2(many_item[j]);
string s2;
while ( getline( iss2, s2, ' ' ) ) {
st.push_back(atoi(s2.c_str()));
}
sort(st.begin(), st.end());
st.erase( unique( st.begin(), st.end() ), st.end() );
if(st.size()> item_size+1) continue;
string candidate;
/*** concatinate string *****/
int k = 0;
for(k = 0; k != st.size()-1; ++k){
string temp = to_string(st[k]) + " " ;
candidate = candidate + temp;
}
candidate = candidate + to_string(st[k]);
many_item_candidate[candidate]++;
}
//cout << "i: "<< i<< endl;
}
Trie trie2;
for(auto it = many_item_candidate.begin(); it != many_item_candidate.end();){
int val = it->second;
if(val<k_item){
many_item_candidate.erase(it++);
}
else{
trie2.addWord(it->first);
//cout<<"candidate: "<<it->first<<"e"<<endl;
++it;
}
}
//count_frequency(many_item_candidate)
ifstream in(input_filename);
if (!in.is_open() ) {
// handle error.
cout << "input file not found!"<< endl;
}
//Utils utils;
string trans;
int tid = 0;
while (std::getline(in, trans))
{
istringstream iss(trans);
string s;
vector<int> st;
//cout << "tid = " << tid<< endl;
while ( getline( iss,s, ' ' ) )
{
st.push_back(atoi(s.c_str()));
}
sort(st.begin(), st.end());
vector<string> sorted_trans;
int k;
for( k = 0; k < st.size(); k++){
string temp = to_string(st[k]);
sorted_trans.push_back(temp);
}
//cout << "vec: ";
//for(int m = 0; m < sorted_trans.size(); m ++)
//cout << sorted_trans.at(m) << " ";
//cout << endl;
vector<strset> cursubsets = utils.subsets(k_item, sorted_trans, tid);
tid++;
//utils.printVecOfStrset(cursubsets);
for(int sub = 0; sub < cursubsets.size(); sub ++)
{
string subsetStr = "";
for (int submem = 0; submem < cursubsets.at(sub).size(); submem++)
{
subsetStr = subsetStr + cursubsets.at(sub).at(submem).c_str() + " ";
}
subsetStr = subsetStr.substr(0, subsetStr.length() - 1);
//cout << "afterSubStr = " << subsetStr << "e" << endl;
int support = trie2.searchWord(subsetStr);
many_item_candidate[subsetStr] = support;
//cout << "support = " << support << endl;
//cout<< "support: " << many_item_candidate[subsetStr] << endl;
// cout<< "CANDIDATE: " << many_item_candidate["39 120 205"] << endl;
}
}
in.close();
/*** check which many-item-candidate are frequent ****/
for (auto it = many_item_candidate.begin(); it != many_item_candidate.end(); ){
if (it->second < min_st){
many_item_candidate.erase(it++);
}
else{
++it;
}
}
//vector <string> many_item;
many_item.clear();
/****** write many-item sets into the output file ****/
for (item_freq_map::iterator it = many_item_candidate.begin(); it != many_item_candidate.end(); ++it) {
//cout << "$%^" <<it->first << " ("<< it->second << ")\n";
output << it->first << " ("<< it->second << ")\n";
many_item.push_back(it->first);
}
//cout<<"size_many_2: "<<many_item.size()<<endl;
count ++;
k_item ++;
}
output.close();
cout << "Done!\n";
//set <int> items;
//vector <vector<int> > transactions;
//string line;
/***** another way to read input file and save it as 2D vector ****/
//while(getline(input, line)){
//stringstream ss(line);
//istream_iterator<int> begin(ss), end;
//transactions.push_back(vector<int>(begin, end));
//items.insert(transactions.end())
//}
//cout << two_item[0]<<endl;
/**** stop timer *****/
e = clock();
float diff ((float)e-(float)s);
cout << diff << endl;
return 0;
}
/**
* Parse the basis set file and generate a set of reference shells
* from which local and external basis set objects are constructed
*/
void BasisSet::parseGlobal(){
std::string readString;
std::string nameOfAtom;
std::string shSymb;
int contDepth;
int atomicNumber;
int indx;
std::vector<libint2::Shell> tmpShell;
bool readRec = false;
bool newRec = false;
bool firstRec = true;
int nEmpty = 0;
int nComm = 0;
int nRec = 0;
while(!this->basisFile_->eof()){
std::getline(*this->basisFile_,readString);
if(readString.size() == 0) nEmpty++;
else if(readString[0] == '!') nComm++;
else if(!readString.compare("****")){
std::getline(*this->basisFile_,readString);
if(readString.size() == 0) { nEmpty++; readRec = false; continue;}
nRec++;
readRec = true;
newRec = true;
}
if(readRec){
std::istringstream iss(readString);
std::vector<std::string> tokens(std::istream_iterator<std::string>{iss},
std::istream_iterator<std::string>{});
if(newRec){
if(!firstRec) {
this->refShells_.push_back(ReferenceShell{atomicNumber,indx,tmpShell});
}
indx = HashAtom(tokens[0],0);
atomicNumber = elements[indx].atomicNumber;
newRec = false;
firstRec = false;
tmpShell.clear();
} else {
contDepth = std::stoi(tokens[1]);
shSymb = tokens[0];
std::vector<double> exp;
std::vector<double> contPrimary;
std::vector<double> contSecondary;
for(auto i = 0; i < contDepth; i++) {
std::getline(*this->basisFile_,readString);
std::istringstream iss2(readString);
std::vector<std::string> tokens2(std::istream_iterator<std::string>{iss2},
std::istream_iterator<std::string>{});
exp.push_back(std::stod(tokens2[0]));
contPrimary.push_back(std::stod(tokens2[1]));
if(!shSymb.compare("SP"))
contSecondary.push_back(std::stod(tokens2[2]));
}
if(!shSymb.compare("SP")) {
tmpShell.push_back(
libint2::Shell{ exp, {{0,this->doSph_,contPrimary}}, {{0,0,0}} }
);
tmpShell.push_back(
libint2::Shell{ exp, {{1,this->doSph_,contSecondary}}, {{0,0,0}} }
);
} else {
tmpShell.push_back(
libint2::Shell{ exp, {{HashL(shSymb),this->doSph_,contPrimary}}, {{0,0,0}} }
);
}
}
}
}
// Append the last Rec
this->refShells_.push_back(ReferenceShell{atomicNumber,indx,tmpShell});
}; // BasisSet::parseGlobal
void Correlation::getParameters(string filename, int start, int stop)
{
chainName=filename;
double tmp;
string strtmp;
try {
if (start == -1) {
burnin = stop / 5;
}
else {
burnin=start;
}
nbsample = stop-burnin;
if(nbsample<=0)
{
cerr << "ERROR: in Correlation::getParameters, asking sampling from point " << start << " to point "<< stop <<", exiting\n";
cerr.flush();
throw(0);
}
cerr << filename << '\t' << " burnin : " << burnin << '\t' << "sample size : " << nbsample << '\n';
ifstream *is=new ifstream;
is->open(filename.c_str(), ifstream::in);
char line[100000];
string strline;
is->getline(line,100000);
strline=line;
istringstream iss1(strline);
nbparameter=0;
/*ALL*/
iss1 >> strtmp;
iss1 >> strtmp;
iss1 >> strtmp;
/*ALL*/
strtmp="null";
while(iss1.good())
{
iss1 >> strtmp;
nbparameter++;
}
init();
istringstream iss2(strline);
/*ALL*/
iss2 >> strtmp;
iss2 >> strtmp;
iss2 >> strtmp;
/*ALL*/
for(int j=0;j<nbparameter;j++)
iss2 >> parameterName[j];
createParameterBuffer();
createWeight();
for(int i=0;i<stop;i++)
{
/*ALL*/
*is >> tmp;
*is >> tmp;
*is >> tmp;
/*ALL*/
for(int j=0;j<nbparameter;j++)
{
*is >> tmp;
if(i>=burnin)
{
parameters[j][i-burnin]=tmp;
}
}
}
delete is;
} catch(...) {
cerr << "ERROR while reading " << filename << "\n";
cerr.flush();
exit(0);
}
}
void define_data(IloEnv env) {
string line(" ");
ifstream myfile ("/home/DavidRC/data.txt");
int i=0;
int j=0;
int x=0;
int y=0;
if (myfile.is_open())
{
i=0;
j=0;
getline(myfile,line);
n=atoi(line.c_str());
IloNumArray l(env,n);
NumMatrix w(env,n);
for(i=0; i<n; i++)
{
w[i]=IloNumArray(env,n);
}
getline (myfile,line);
istringstream iss1(line);
while (iss1 && j<n)
{
string subs;
iss1 >> subs;
string temp=subs;
if(temp.compare("")==0)
{
continue;
}
else
{
l[j]=atoi(subs.c_str());
}
j++;
}
exit(1);
i=0;
j=0;
while ( getline (myfile,line) && i<n)
{
istringstream iss2(line);
j=0;
while (iss2 && j<n)
{
string subs;
iss2 >> subs;
string temp=subs;
if(temp.compare("")==0)
{
continue;
j++;
}
else
{
w[i][j]=atoi(subs.c_str());
j++;
}
}
i++;
}
m=atoi( line.c_str() );
IloNumArray c(env,m);
NumMatrix d(env,m);
for(i=0; i<m; i++)
{
d[i]=IloNumArray(env,m);
}
i=0;
j=0;
getline (myfile,line);
istringstream iss3(line);
while (iss3 && j<m)
{
string subs;
iss3 >> subs;
string temp=subs;
if(temp.compare("")==0)
{
continue;
}
else
{
c[j]=atoi(subs.c_str());
}
j++;
}
i=0;
j=0;
while ( getline (myfile,line) && i<m)
{
istringstream iss4(line);
j=0;
while (iss4 && j<m)
{
string subs;
iss4 >> subs;
string temp=subs;
if(temp.compare("")==0)
{
continue;
}
else
{
d[i][j]=atoi(subs.c_str());
}
j++;
}
i++;
}
myfile.close();
}
