void TestCondSoftMaxParamLearning(bool DeleteNet)
{
// BayesNet *net = SimpleCondSoftMaxModel();
BayesNet *netToLearn = SimpleCondSoftMaxModel();
float eps = 1e-1f;
int nEvid = 100;
netToLearn->GenerateEvidences(nEvid);
netToLearn->LearnParameters();
String nodes[] = {"node0", "node1", "node2"};
/* int i, j;
TokArr LearnParam, Param;
for(i = 0; i < 3; i++)
{
LearnParam = netToLearn->GetGaussianMean(nodes[i]);
Param = net->GetGaussianMean(nodes[i]);
if(LearnParam[0].fload.size() != Param[0].fload.size())
{
PNL_THROW(pnl::CAlgorithmicException, "Parameters learning is wrong");
}
for(j = 0; j < LearnParam[0].fload.size(); j++)
{
if( LearnParam[0].FltValue(j).fl - Param[0].FltValue(j).fl > eps)
{
PNL_THROW(pnl::CAlgorithmicException, "Parameters learning is wrong");
}
}
LearnParam = netToLearn->GetGaussianCovar(nodes[i]);
Param = net->GetGaussianCovar(nodes[i]);
if(LearnParam[0].fload.size() != Param[0].fload.size())
{
PNL_THROW(pnl::CAlgorithmicException, "Parameters learning is wrong");
}
for(j = 0; j < LearnParam[0].fload.size(); j++)
{
if( LearnParam[0].FltValue(j).fl - Param[0].FltValue(j).fl > eps)
{
PNL_THROW(pnl::CAlgorithmicException, "Parameters learning is wrong");
}
}
}
*/
if (DeleteNet)
{
delete netToLearn;
};
std::cout << "TestCondSoftMaxParamLearning is completed successfully" << std::endl;
}
int main(int arg,char * argv[])
{
int a=1,b=2;
int c=a+b;
cout<<c<<endl;
//creating bayes net
//BayesNet net;
BayesNet net;
//adding node
net.AddNode("discrete^Cloudy","true false");
net.AddNode(discrete^"Sprinkler Rain WetGrass","true false");
//adding edges
net.AddArc("Cloudy","Sprinkler Rain");
net.AddArc("Sprinkler Rain","WetGrass");
//sopecfify the CPD
//cloudy
net.SetPTabular("Cloudy^true","0.6");
net.SetPTabular("Cloudy^false","0.4");
//spprinkler
net.SetPTabular("Sprinkler^true Sprinkler^false","0.1 0.9","Cloudy^true");
net.SetPTabular("Sprinkler^true Sprinkler^false","0.5 0.5","Cloudy^false");
//rain
net.SetPTabular("Rain^true Rain^false","0.8 0.2","Cloudy^true");
net.SetPTabular("Rain^true Rain^false","0.2 0.8","Cloudy^false");
//WetGrass
net.SetPTabular("WetGrass^true WetGrass^false","0.99 0.01","Sprinkler^true Rain^true");
net.SetPTabular("WetGrass^true WetGrass^false","0.9 0.1","Sprinkler^true Rain^false");
net.SetPTabular("WetGrass^true WetGrass^false","0.9 0.1","Sprinkler^false Rain^true");
net.SetPTabular("WetGrass^true WetGrass^false","0.0 1.0","Sprinkler^false Rain^false");
//get the cpd
TokArr PCloudy=net.GetPTabular("Cloudy");
String PCloudyStr=String(PCloudy);
float PCloudyTrueF=PCloudy[0].FltValue();
float PCloudyFalseF=PCloudy[1].FltValue();
cout<<endl<<"Cloudy"<<endl;
cout<<PCloudyStr<<endl;
cout<<PCloudyTrueF<<endl;
cout<<PCloudyFalseF<<endl;
/*
//adding evidence
//net.AddEvidToBuf("Rain^true WetGrass^true");
net.EditEvidence("Rain^true WetGrass^true");
net.CurEvidToBuf();
net.LearnParameters();
cout<<endl<<"evidence Rain^true WetGrass^true"<<endl;
//get the jpd
TokArr WetGrassMarg=net.GetJPD("WetGrass");
String WetGrassMargStr=String(WetGrassMarg);
cout<<endl<<"WetGrass JPD"<<endl<<WetGrassMargStr<<endl;
TokArr WetGrassAndSprinklerMarg=net.GetJPD("WetGrass Sprinkler Rain");
String WetGrassAndSprinklerMargStr=String(WetGrassAndSprinklerMarg);
cout<<endl<<"WetGrass and Sprinkler JPD"<<endl<<WetGrassAndSprinklerMargStr<<endl;
TokArr WetGrassMPE=net.GetMPE("WetGrass");
String WetGrassMPEStr=String(WetGrassMPE);
cout<<endl<<"WetGrass MPE"<<endl<<WetGrassMPEStr<<endl;
TokArr WetGrassAndSprinklerMPE=net.GetMPE("WetGrass Sprinkler Rain");
String WetGrassAndSprinklerMPEStr=String(WetGrassAndSprinklerMPE);
cout<<endl<<"WetGrass and Spinkler MPE"<<endl<<WetGrassAndSprinklerMPEStr<<endl;
//delete evidence
net.ClearEvid();
cout<<"ok"<<endl;*/
//net.AddEvidToBuf("Sprinkler^true WetGrass^true");
net.EditEvidence("Sprinkler^true WetGrass^true");
net.CurEvidToBuf();
net.LearnParameters();
cout<<endl<<"evidence Sprinkler^true WetGrass^true"<<endl;
//get jpd
TokArr WetGrassMarg=net.GetJPD("WetGrass");
String WetGrassMargStr=String(WetGrassMarg);
cout<<endl<<"WetGrass JPD"<<endl<<WetGrassMargStr<<endl;
TokArr WetGrassAndSprinklerMarg=net.GetJPD("WetGrass Sprinkler Rain");
String WetGrassAndSprinklerMargStr=String(WetGrassAndSprinklerMarg);
cout<<endl<<"WetGrass and Sprinkler JPD"<<endl<<WetGrassAndSprinklerMargStr<<endl;
TokArr WetGrassMPE=net.GetMPE("WetGrass");
String WetGrassMPEStr=String(WetGrassMPE);
cout<<endl<<"WetGrass MPE"<<endl<<WetGrassMPEStr<<endl;
TokArr WetGrassAndSprinklerMPE=net.GetMPE("WetGrass Sprinkler Rain Cloudy");
String WetGrassAndSprinklerMPEStr=String(WetGrassAndSprinklerMPE);
cout<<endl<<"WetGrass and Spinkler MPE"<<endl<<WetGrassAndSprinklerMPEStr<<endl;
cout<<endl<<"moonsea"<<endl;
return 0;
}
void TestsPnlHigh::TestCondGaussianParamLearning()
{
BayesNet *net = SimpleCGM2();
BayesNet *netToLearn = SimpleCGM2();
float eps = 1e-2f;
int nEvidences = 5000;
netToLearn->GenerateEvidences(nEvidences);
netToLearn->LearnParameters();
/*
int nNodes = netToLearn->Net().Graph().nNode();
//Checking step
int i;
int j;
TokArr LearnParam, Param;
for (i = 0; i < nNodes; i++)
{
//if it is gaussian without tabular parents
if (true)
{
LearnParam = netToLearn->GetGaussianMean(nodes[i]);
Param = net->GetGaussianMean(nodes[i]);
if(LearnParam[0].fload.size() != Param[0].fload.size())
{
PNL_THROW(pnl::CAlgorithmicException, "Parameters learning is wrong");
};
for(j = 0; j < LearnParam[0].fload.size(); j++)
{
if( LearnParam[0].FltValue(j).fl - Param[0].FltValue(j).fl > eps)
{
PNL_THROW(pnl::CAlgorithmicException, "Parameters learning is wrong");
}
};
LearnParam = netToLearn->GetGaussianCovar(nodes[i]);
Param = net->GetGaussianCovar(nodes[i]);
if(LearnParam[0].fload.size() != Param[0].fload.size())
{
PNL_THROW(pnl::CAlgorithmicException, "Parameters learning is wrong");
};
for(j = 0; j < LearnParam[0].fload.size(); j++)
{
if( LearnParam[0].FltValue(j).fl - Param[0].FltValue(j).fl > eps)
{
PNL_THROW(pnl::CAlgorithmicException, "Parameters learning is wrong");
}
};
TokArr parents = netToLearn->GetParents(nodes[i]);
LearnParam = netToLearn->GetGaussianWeights(nodes[i], parents);
Param = net->GetGaussianWeights(nodes[i], parents);
if(LearnParam[0].fload.size() != Param[0].fload.size())
{
PNL_THROW(pnl::CAlgorithmicException, "Parameters learning is wrong");
};
for(j = 0; j < LearnParam[0].fload.size(); j++)
{
if( LearnParam[0].FltValue(j).fl - Param[0].FltValue(j).fl > eps)
{
PNL_THROW(pnl::CAlgorithmicException, "Parameters learning is wrong");
}
};
};
};
*/
delete net;
delete netToLearn;
}
