class TMVA::MethodPDEFoam: public TMVA::MethodBase

 init PDEFoam objects

 constructor from weight file

 PDEFoam can handle classification with 2 classes and regression with one or more regression-targets

 default initialization called by all constructors

 Declare MethodPDEFoam options

 process user options

 destructor

 determine foam range for all dimensions
 loop over all testing events -> Get Xmin and Xmax

 Creation of 2 separated foams: one for signal events, one for
 backgound events.

 Create only one unified foam which contains discriminator
 (N_sig)/(N_sig + N_bg)

 Training for mono target regression
 - foam density = average Target(0)
 - dimension of foam = number of non-targets
 - cell content = average target 0

 Training multi target regression
 - foam density = Event density
 - dimension of foam = number of non-targets + number of targets
 - cell content = event density

 Return Mva-Value for both separated and unified foams

 Set Xmin, Xmax in every dimension to pdefoam

 Set foam options and initialize foam

 Return regression values for both multi and mono target regression

 save options and internal parameters

 create XML output of PDEFoam method variables

 Write pure foams to xml file

 read options and internal parameters

 read PDEFoam variables from xml weight file

 read pure foams from xml file

 fill variable names into foam

 write PDEFoam-specific classifier response

 provide help message

 ranking of input variables

 possible kernels (option)