double
Potential::getCondPotValueFor(INTDBLMAP& assignment)
{
if(assignment.find(factorVariables.begin()->first)==assignment.end())
{
cerr <<"Fatal error! No variable assignment for " << factorVariables.begin()->first << endl;
exit(-1);
}
double newmean=0;
for(INTDBLMAP_ITER aIter=mbcondMean_Vect.begin();aIter!=mbcondMean_Vect.end();aIter++)
{
if(assignment.find(aIter->first)==assignment.end())
{
cout <<"Warning! No variable assignment for " << aIter->first << endl;
continue;
}
double aval=assignment[aIter->first];
newmean=newmean+(aval*aIter->second);
}
newmean=newmean+mbcondMean_Part;
double normsq=2*PI*mbcondVar;
double norm=sqrt(2*PI*mbcondVar);
norm=sqrt(normsq);
double x=assignment[factorVariables.begin()->first];
double dev=(x-newmean)*(x-newmean);
dev=dev/(2*mbcondVar);
double eval=exp(-1.0*dev);
double pval=eval/norm;
return pval;
}
double
Potential::predictSample(INTDBLMAP& jointConf, int vId)
{
if(jointConf.find(factorVariables.begin()->first)==jointConf.end())
{
cerr <<"Fatal error! No variable assignment for " << factorVariables.begin()->first << endl;
exit(-1);
}
double newmean=0;
for(INTDBLMAP_ITER aIter=mbcondMean_Vect.begin();aIter!=mbcondMean_Vect.end();aIter++)
{
if(jointConf.find(aIter->first)==jointConf.end())
{
cerr <<"Fatal error! No variable assignment for " << aIter->first << endl;
exit(-1);
}
double aval=jointConf[aIter->first];
newmean=newmean+(aval*aIter->second);
}
newmean=newmean+mbcondMean_Part;
return newmean;
}
double
Potential::generateSample(INTDBLMAP& jointConf, int vId,gsl_rng* r,double gVar)
{
if(jointConf.find(factorVariables.begin()->first)==jointConf.end())
{
cerr <<"Fatal error! No variable assignment for " << factorVariables.begin()->first << endl;
exit(-1);
}
double newmean=0;
for(INTDBLMAP_ITER aIter=mbcondMean_Vect.begin();aIter!=mbcondMean_Vect.end();aIter++)
{
if(jointConf.find(aIter->first)==jointConf.end())
{
cerr <<"Fatal error! No variable assignment for " << aIter->first << endl;
exit(-1);
}
double aval=jointConf[aIter->first];
newmean=newmean+(aval*aIter->second);
}
newmean=newmean+mbcondMean_Part;
double x=gsl_ran_gaussian(r,sqrt(gVar));
x=x+newmean;
return x;
}
int
PotentialManager::estimateAllMeanCov(bool random, INTDBLMAP& gMean, map<int,INTDBLMAP*>& gCovar,INTINTMAP& trainEvidSet)
{
int evidCnt=trainEvidSet.size();
//First get the mean and then the variance
int dId=0;
for(INTINTMAP_ITER eIter=trainEvidSet.begin();eIter!=trainEvidSet.end();eIter++)
{
EMAP* evidMap=NULL;
if(random)
{
evidMap=evMgr->getRandomEvidenceAt(eIter->first);
}
else
{
evidMap=evMgr->getEvidenceAt(eIter->first);
}
for(EMAP_ITER vIter=evidMap->begin();vIter!=evidMap->end(); vIter++)
{
int vId=vIter->first;
Evidence* evid=vIter->second;
double val=evid->getEvidVal();
if(gMean.find(vId)==gMean.end())
{
gMean[vId]=val;
}
else
{
gMean[vId]=gMean[vId]+val;
}
}
dId++;
}
//Now estimate the mean
for(INTDBLMAP_ITER idIter=gMean.begin();idIter!=gMean.end();idIter++)
{
idIter->second=idIter->second/(double) evidCnt;
INTDBLMAP* vcov=new INTDBLMAP;
gCovar[idIter->first]=vcov;
}
return 0;
}
int
PotentialManager::estimateAllMeanCov(bool random, INTDBLMAP& gMean, map<int,INTDBLMAP*>& gCovar,INTINTMAP& trainEvidSet, const char* mFName, const char* sdFName,int leaveOutData)
{
ofstream mFile;
ofstream sdFile;
if(!random)
{
if((mFName!=NULL) && (sdFName!=NULL))
{
mFile.open(mFName);
sdFile.open(sdFName);
}
}
int evidCnt=trainEvidSet.size();
if(leaveOutData!=-1)
{
evidCnt=evidCnt-1;
}
//First get the mean and then the variance
int dId=0;
for(INTINTMAP_ITER eIter=trainEvidSet.begin();eIter!=trainEvidSet.end();eIter++)
{
if(dId==leaveOutData)
{
dId++;
continue;
}
EMAP* evidMap=NULL;
if(random)
{
evidMap=evMgr->getRandomEvidenceAt(eIter->first);
}
else
{
evidMap=evMgr->getEvidenceAt(eIter->first);
}
for(EMAP_ITER vIter=evidMap->begin();vIter!=evidMap->end(); vIter++)
{
int vId=vIter->first;
Evidence* evid=vIter->second;
double val=evid->getEvidVal();
if(gMean.find(vId)==gMean.end())
{
gMean[vId]=val;
}
else
{
gMean[vId]=gMean[vId]+val;
}
}
dId++;
}
//Now estimate the mean
for(INTDBLMAP_ITER idIter=gMean.begin();idIter!=gMean.end();idIter++)
{
if(idIter->first==176)
{
//cout <<"Stop here: Variable " << idIter->first << " mean " << idIter->second << endl;
}
idIter->second=idIter->second/(double) evidCnt;
if(!random)
{
if(mFile.good())
{
mFile<<idIter->first<<"\t" << idIter->second<< endl;
}
}
}
int covPair=0;
//Now the variance
for(INTINTMAP_ITER eIter=trainEvidSet.begin();eIter!=trainEvidSet.end();eIter++)
{
EMAP* evidMap=NULL;
if(random)
{
evidMap=evMgr->getRandomEvidenceAt(eIter->first);
}
else
{
evidMap=evMgr->getEvidenceAt(eIter->first);
}
for(EMAP_ITER vIter=evidMap->begin();vIter!=evidMap->end(); vIter++)
{
int vId=vIter->first;
Evidence* evid=vIter->second;
double vval=evid->getEvidVal();
double vmean=gMean[vId];
INTDBLMAP* vcov=NULL;
if(gCovar.find(vId)==gCovar.end())
{
vcov=new INTDBLMAP;
gCovar[vId]=vcov;
}
else
{
vcov=gCovar[vId];
}
for(EMAP_ITER uIter=vIter;uIter!=evidMap->end();uIter++)
{
int uId=uIter->first;
//Don't compute covariance of vId uId pairs that both are not in the restrictedNeighborSet, when
//the restrictedNeighborSet is empty
/* if((!random) && (vId!=uId) && (restrictedNeighborSet.size()>0))
{
if((restrictedNeighborSet.find(vId)==restrictedNeighborSet.end()) && (restrictedNeighborSet.find(uId)==restrictedNeighborSet.end()))
{
continue;
}
}*/
Evidence* evid1=uIter->second;
double uval=evid1->getEvidVal();
double umean=gMean[uId];
double diffprod=(vval-vmean)*(uval-umean);
INTDBLMAP* ucov=NULL;
if(gCovar.find(uId)==gCovar.end())
{
ucov=new INTDBLMAP;
gCovar[uId]=ucov;
}
else
{
ucov=gCovar[uId];
}
if(vcov->find(uId)==vcov->end())
{
covPair++;
(*vcov)[uId]=diffprod;
}
else
{
(*vcov)[uId]=(*vcov)[uId]+diffprod;
}
if(uId!=vId)
{
if(ucov->find(vId)==ucov->end())
{
(*ucov)[vId]=diffprod;
}
else
{
(*ucov)[vId]=(*ucov)[vId]+diffprod;
}
}
}
}
}
cout <<"Total covariance pairs estimated " << covPair << endl;
//Now estimate the variance
for(map<int,INTDBLMAP*>::iterator idIter=gCovar.begin();idIter!=gCovar.end();idIter++)
{
INTDBLMAP* var=idIter->second;
for(INTDBLMAP_ITER vIter=var->begin();vIter!=var->end();vIter++)
{
if(vIter->first==idIter->first)
{
//vIter->second=2*vIter->second/((double)(gCovar.size()-1));
//vIter->second=2*vIter->second/((double)(evidCnt-1));
//vIter->second=(0.001+vIter->second)/((double)(evidCnt-1));
vIter->second=(vIter->second)/((double)(evidCnt-1));
double variance=vIter->second;
if(idIter->first==176)
{
// cout <<"Stop here: Variable " << idIter->first << " variance " << idIter->second << endl;
}
}
else
{
vIter->second=vIter->second/((double)(evidCnt-1));
//vIter->second=vIter->second/((double)(gCovar.size()-1));
//vIter->second=0;
}
if(!random)
{
if(sdFile.good())
{
sdFile<<idIter->first<<"\t" << vIter->first <<"\t" << vIter->second << endl;
}
}
}
}
if(!random)
{
if(mFile.good())
{
mFile.close();
}
if(sdFile.good())
{
sdFile.close();
}
}
return 0;
}
int
EvidenceManager::populateEvidence(Evidence** evid,const char* evidStr)
{
//first check for validity of evidStr
if(strchr(evidStr,'=')==NULL)
{
return -1;
}
*evid=new Evidence;
INTDBLMAP evidData;
int currInd=0;
int ttInd=0;
int tokId=0;
char tempTok[256];
while(evidStr[currInd]!='\0')
{
if((evidStr[currInd]=='=') ||
(evidStr[currInd]==']') ||
(evidStr[currInd]==',')
)
{
tempTok[ttInd]='\0';
ttInd=0;
if(tokId==0)
{
//This is the variable
int vId=atoi(tempTok);
Variable* var=vMgr->getVariableAt(vId);
var->initEvidence(evidData);
(*evid)->assocVariable(vId);
}
else
{
char* pos=strchr(tempTok,'|');
//Hard evidence
if(pos==NULL)
{
int varVal=atoi(tempTok);
if(evidData.find(varVal)==evidData.end())
{
cout <<"No value "<< varVal << " in the domain of a variable" << endl;
return -1;
}
evidData[varVal]=1.0;
(*evid)->setType(Evidence::HARD);
}
else
{
*pos='\0';
int varVal=atoi(tempTok);
double varValProb=atof(pos+1);
if(evidData.find(varVal)==evidData.end())
{
cout <<"No value "<< varVal << " in the domain of a variable" << endl;
return -1;
}
evidData[varVal]=varValProb;
//Will be setting it multiple times but its ok for now.
(*evid)->setType(Evidence::SOFT);
}
}
tokId++;
}
else if(evidStr[currInd]!='[')
{
tempTok[ttInd]=evidStr[currInd];
ttInd++;
}
currInd++;
}
(*evid)->setData(evidData);
return 0;
}