TMVA::Factory

 standard constructor
   jobname       : this name will appear in all weight file names produced by the MVAs
   theTargetFile : output ROOT file; the test tree and all evaluation plots 
                   will be stored here
   theOption     : option string; currently: "V" for verbose, "NoPreprocessing" to switch of preproc.

 depreciated constructor

 print greeting message

 default destructor

 *** segmentation fault occurs when deleting this object :-( ***
   fTrainingTree->Delete();

 *** cannot delete: need to clarify ownership :-( ***
   fSignalTree->Delete();
   fBackgTree->Delete();

 delete methods

 fill input variables in data set

 define the input trees for signal and background; no cuts are applied

 define the input trees for signal and background from single input tree,
 containing both signal and background events distinguished by the type 
 identifiers: SigCut and BgCut

 create trees from these ascii files

 books multiple MVAs according to the variable, number of bins and 
 the cut array given

 possible user settings for Ntrain and Ntest:
   ------------------------------------------------------
   |              |              |        |             |
   ------------------------------------------------------
                                                        # input signal events
                                          # input signal events after cuts
   ------------------------------------------------------
   |              |              |             |       |
   ------------------------------------------------------
    \/  \/                      # input bg events
                                               # input bg events after cuts
      Ntrain/2       Ntest/2                         

 definitions:

         nsigTot = all signal events
         nbkgTot = all bkg events
         nTot    = nsigTot + nbkgTot
         i.g.: nsigTot != nbkgTot
         N:M     = use M events after event N (distinct event sample)
                   (read as: "from event N to event M")

 assumptions:

         a) equal number of signal and background events is used for training
         b) any numbers of signal and background events are used for testing
         c) an explicit syntax can violate a)

 cases (in order of importance)

 1)
      user gives         : N1
      PrepareTree does   : nsig_train=nbkg_train=min(N1,nsigTot,nbkgTot)
                           nsig_test =nsig_train:nsigTot, nbkg_test =nsig_train:nbkgTot
      -> give warning if nsig_test<=0 || nbkg_test<=0

 2)
      user gives         : N1, N2
      PrepareTree does   : nsig_train=nbkg_train=min(N1,nsigTot,nbkgTot)
                           nsig_test =nsig_train:min(N2,nsigTot-nsig_train),
                           nbkg_test =nsig_train:min(N2,nbkgTot-nbkg_train)
      -> give warning if nsig(bkg)_train != N1, or
                      if nsig_test<N2 || nbkg_test<N2

 3)
      user gives         : -1
      PrepareTree does   : nsig_train=nbkg_train=min(nsigTot,nbkgTot)
                           nsig_test =nsigTot, nbkg_test=nbkgTot
      -> give warning that same samples are used for testing and training

 4)
      user gives         : -1, -1
      PrepareTree does   : nsig_train=nsigTot, nbkg_train=nbkgTot
                           nsig_test =nsigTot, nbkg_test =nbkgTot
      -> give warning that same samples are used for testing and training,
         and, if nsig_train != nbkg_train, that an unequal number of 
         signal and background events are used in training
                          
 ------------------------------------------------------------------------
 Give in any case the number of signal and background events that are
 used for testing and training, and tell whether there are overlaps between
 the samples.
 ------------------------------------------------------------------------
 

 number of signal events (used to compute significance)

 number of background events (used to compute significance)

 booking via name; the names are translated into enums and the 
 corresponding overloaded BookMethod is called

 books MVA method; the option configuration string is custom for each MVA
 the TString field "theNameAppendix" serves to define (and distringuish) 
 several instances of a given MVA, eg, when one wants to compare the 
 performance of various configurations

 books MVA method; the option configuration string is custom for each MVA
 the TString field "theNameAppendix" serves to define (and distringuish) 
 several instances of a given MVA, eg, when one wants to compare the 
 performance of various configurations

 returns pointer to MVA that corresponds to "method"

 iterates over all MVAs that have been booked, and calls their training methods

 iterates over all MVAs that have been booked, and calls their testing methods

 iterates over all MVA input varables and evaluates them

 iterates over all MVAs that have been booked, and calls their evaluation methods

 multiple MVAs in different phase space regions are trained and tested

 modified name (remove TMVA::)