class TMVA::MethodBoost: public TMVA::MethodCompositeBase

 destructor

 Boost can handle classification with 2 classes and regression with one regression-target

 options that are used ONLY for the READER to ensure backward compatibility
   they are hence without any effect (the reader is only reading the training
   options that HAD been used at the training of the .xml weightfile at hand

 just registering the string from which the boosted classifier will be created

 initialisation routine

 resetting back the boosted weights of the events to 1

 process user options

 initialization

 find the CUT on the individual MVA that defines an event as
 correct or misclassified (to be used in the boosting process)

 the standard (discrete or real) AdaBoost algorithm

 Bagging or Bootstrap boosting, gives new random poisson weight for every event

 Get help message text

 typical length of text line:
         "|--------------------------------------------------------------|"

 return boosted MVA response

 Calculate the ROC integral of a single classifier or even the
 whole boosted classifier.  The tree type (training or testing
 sample) is specified by 'eTT'.

 If tree type kTraining is set, the original training sample is
 used to compute the ROC integral (original weights).

 - singleMethod - if kTRUE, return ROC integral of single (last
                  trained) classifier; if kFALSE, return ROC
                  integral of full classifier

 - eTT - tree type (Types::kTraining / Types::kTesting)

 - CalcOverlapIntergral - if kTRUE, the overlap integral of the
                          signal/background MVA distributions
                          is calculated and stored in
                          'fOverlap_integral'

 Calculate MVA values of current method fMethods.back() on
 training sample

 fill various monitoring histograms from information of the individual classifiers that
 have been boosted.
 of course.... this depends very much on the individual classifiers, and so far, only for
 Decision Trees, this monitoring is actually implemented

 clean up

 print fit results

 training a single classifier

 calculate weight of single method