CNaiveBayes::CNaiveBayes(const CDataset &TrainSet,int USplitNum)
{
Name=MyName;
SplitNum=USplitNum;
//start time for training
clock_t start=clock();
//data
const MATRIX &OrgData=TrainSet.GetData();
const CASE_INFO &OrgInfo=TrainSet.GetInfo();
//initialize all data structure
for(int i=0;i<OrgInfo.ValidWidth-1;i++)
{
//each attribute
EstimatorStr Estim;
Estim.AttType=OrgInfo.ValidAttrs[i].AttType;
if(Estim.AttType==ATT_DISCRETE)
{
//Laplace estimator
Estim.DiscEst.Count=1;
int ValNum=(int)OrgInfo.ValidAttrs[i].Disc.size();
for(int j=0;j<ValNum;j++)
Estim.DiscEst.AttrCount.push_back(1.0/ValNum);
}
//continuous attribute
else
{
//Laplace estimator
Estim.ContEst.Count=SplitNum;
Estim.ContEst.Max=OrgInfo.ValidAttrs[i].Max;
Estim.ContEst.Min=OrgInfo.ValidAttrs[i].Min;
for(int j=0;j<SplitNum;j++)
Estim.ContEst.Vals.push_back(1);
}
//for each attribute: all class label
vector<EstimatorStr> EstiAttr;
for(int j=0;j<OrgInfo.ClassNum;j++)
EstiAttr.push_back(Estim);
//all attributes
Estims.push_back(EstiAttr);
}
//statistics
for(int i=0;i<OrgInfo.Height;i++)
{
int Class=OrgData[i][OrgInfo.ValidWidth-1].Discr;
for(int j=0;j<OrgInfo.ValidWidth-1;j++)
switch(OrgInfo.ValidAttrs[j].AttType)
{
case ATT_DISCRETE:
{
int Val=OrgData[i][j].Discr;
Estims[j][Class].DiscEst.Count++;
//j: attribute, Class: label, Val: value of attribute
Estims[j][Class].DiscEst.AttrCount[Val]++;
}
break;
case ATT_CONTINUOUS:
case ATT_DATETIME:
{
double Val=OrgData[i][j].Cont;
int ValNo;
if(OrgInfo.ValidAttrs[j].Max==OrgInfo.ValidAttrs[j].Min)
ValNo=0;
else
ValNo=(int)((OrgData[i][j].Cont-OrgInfo.ValidAttrs[j].Min)*10/
(OrgInfo.ValidAttrs[j].Max-OrgInfo.ValidAttrs[j].Min));
if(ValNo>=SplitNum)
ValNo=SplitNum-1;
if(ValNo<0)
ValNo=0;
Estims[j][Class].ContEst.Vals[ValNo]++;
Estims[j][Class].ContEst.Count++;
}
break;
default:
break;
}
}//for data
//get all statistics needed
for(int i=0;i<OrgInfo.ValidWidth-1;i++)
{
switch(OrgInfo.ValidAttrs[i].AttType)
{
case ATT_DISCRETE:
for(int j=0;j<OrgInfo.ClassNum;j++)
{
int ValNum=(int)OrgInfo.ValidAttrs[i].Disc.size();
for(int k=0;k<ValNum;k++)
Estims[i][j].DiscEst.AttrCount[k]/=Estims[i][j].DiscEst.Count;
}
break;
case ATT_CONTINUOUS:
case ATT_DATETIME:
for(int j=0;j<OrgInfo.ClassNum;j++)
{
for(int k=0;k<SplitNum;k++)
Estims[i][j].ContEst.Vals[k]/=Estims[i][j].ContEst.Count;
}
break;
default:
break;
}//switch
}//for attr
//time consumed
CreatingTime = (double)(clock() - start) / CLOCKS_PER_SEC;
}
void CNaiveBayes::Train(const CDataset &TrainSet)
{
//start time for training
clock_t start=clock();
//data
const MATRIX &OrgData=TrainSet.GetData();
const CASE_INFO &OrgInfo=TrainSet.GetInfo();
//if range of a continuous attribute changed (extended), should we re-calculate all existed statistics?
//we can't, some information has lost. We can only extend the first and the last intervals
//statistics
for(int i=0;i<OrgInfo.Height;i++)
{
//label of instance
int Class=OrgData[i][OrgInfo.ValidWidth-1].Discr;
//each attribute
for(int j=0;j<OrgInfo.ValidWidth-1;j++)
switch(OrgInfo.ValidAttrs[j].AttType)
{
case ATT_DISCRETE:
{
//value of this attribute
int Val=OrgData[i][j].Discr;
Estims[j][Class].DiscEst.Count++;
//j: attribute, Class: label, Val: value of attribute
Estims[j][Class].DiscEst.AttrCount[Val]++;
}
break;
case ATT_CONTINUOUS:
case ATT_DATETIME:
{
double Val=OrgData[i][j].Cont;
int ValNo;
if(OrgInfo.ValidAttrs[j].Max==OrgInfo.ValidAttrs[j].Min)
ValNo=0;
else
ValNo=(int)((OrgData[i][j].Cont-Estims[j][Class].ContEst.Min)*10/
(Estims[j][Class].ContEst.Max-Estims[j][Class].ContEst.Min));
if(ValNo>=SplitNum)
ValNo=SplitNum-1;
if(ValNo<0)
ValNo=0;
Estims[j][Class].ContEst.Vals[ValNo]++;
Estims[j][Class].ContEst.Count++;
}
break;
default:
break;
}//case: attribute type
}//for data
//calculate all other statistics
for(int i=0;i<OrgInfo.ValidWidth-1;i++)
{
switch(OrgInfo.ValidAttrs[i].AttType)
{
case ATT_DISCRETE:
for(int j=0;j<OrgInfo.ClassNum;j++)
{
int ValNum=(int)OrgInfo.ValidAttrs[i].Disc.size();
for(int k=0;k<ValNum;k++)
Estims[i][j].DiscEst.AttrCount[k]/=Estims[i][j].DiscEst.Count;
}
break;
case ATT_CONTINUOUS:
case ATT_DATETIME:
for(int j=0;j<OrgInfo.ClassNum;j++)
{
for(int k=0;k<SplitNum;k++)
Estims[i][j].ContEst.Vals[k]/=Estims[i][j].ContEst.Count;
}
break;
default:
break;
}//switch
}//for attributes
//time consumed
CreatingTime+=((double)(clock() - start) / CLOCKS_PER_SEC);
}