From b910e485c55b45edc7ee78f8e68a68d9f6a26430 Mon Sep 17 00:00:00 2001
From: Olivier Couet <olivier.couet@cern.ch>
Date: Mon, 19 Dec 2016 14:26:22 +0100
Subject: [PATCH] - math formula in latex - Doxygen format - in group TMVA -
remove trailing spaces - spell check
---
tmva/tmva/inc/TMVA/MethodRuleFit.h | 20 ++---
tmva/tmva/src/MethodPlugins.cxx | 52 +++++------
tmva/tmva/src/MethodRuleFit.cxx | 134 ++++++++++++++---------------
3 files changed, 103 insertions(+), 103 deletions(-)
diff --git a/tmva/tmva/inc/TMVA/MethodRuleFit.h b/tmva/tmva/inc/TMVA/MethodRuleFit.h
index 69c66bb687e..fc610927a23 100644
--- a/tmva/tmva/inc/TMVA/MethodRuleFit.h
+++ b/tmva/tmva/inc/TMVA/MethodRuleFit.h
@@ -8,15 +8,15 @@
* Web : http://tmva.sourceforge.net *
* *
* Description: *
- * Friedman's RuleFit method *
+ * Friedman's RuleFit method *
* *
* Authors (alphabetical): *
* Fredrik Tegenfeldt <Fredrik.Tegenfeldt@cern.ch> - Iowa State U., USA *
* *
* Copyright (c) 2005: *
- * CERN, Switzerland *
+ * CERN, Switzerland *
* Iowa State U. *
- * MPI-K Heidelberg, Germany *
+ * MPI-K Heidelberg, Germany *
* *
* Redistribution and use in source and binary forms, with or without *
* modification, are permitted according to the terms listed in LICENSE *
@@ -59,7 +59,7 @@ namespace TMVA {
public:
MethodRuleFit( const TString& jobName,
- const TString& methodTitle,
+ const TString& methodTitle,
DataSetInfo& theData,
const TString& theOption = "");
@@ -188,28 +188,28 @@ namespace TMVA {
Int_t fRFNendnodes; // max number of rules (only Friedmans module)
std::vector<DecisionTree *> fForest; // the forest
Int_t fNTrees; // number of trees in forest
- Double_t fTreeEveFrac; // fraction of events used for traing each tree
+ Double_t fTreeEveFrac; // fraction of events used for training each tree
SeparationBase *fSepType; // the separation used in node splitting
Double_t fMinFracNEve; // min fraction of number events
Double_t fMaxFracNEve; // ditto max
Int_t fNCuts; // grid used in cut applied in node splitting
TString fSepTypeS; // forest generation: separation type - see DecisionTree
TString fPruneMethodS; // forest generation: prune method - see DecisionTree
- TMVA::DecisionTree::EPruneMethod fPruneMethod; // forest generation: method used for pruning - see DecisionTree
+ TMVA::DecisionTree::EPruneMethod fPruneMethod; // forest generation: method used for pruning - see DecisionTree
Double_t fPruneStrength; // forest generation: prune strength - see DecisionTree
TString fForestTypeS; // forest generation: how the trees are generated
Bool_t fUseBoost; // use boosted events for forest generation
//
Double_t fGDPathEveFrac; // GD path: fraction of subsamples used for the fitting
Double_t fGDValidEveFrac; // GD path: fraction of subsamples used for the fitting
- Double_t fGDTau; // GD path: def threshhold fraction [0..1]
+ Double_t fGDTau; // GD path: def threshold fraction [0..1]
Double_t fGDTauPrec; // GD path: precision of estimated tau
- Double_t fGDTauMin; // GD path: min threshhold fraction [0..1]
- Double_t fGDTauMax; // GD path: max threshhold fraction [0..1]
+ Double_t fGDTauMin; // GD path: min threshold fraction [0..1]
+ Double_t fGDTauMax; // GD path: max threshold fraction [0..1]
UInt_t fGDTauScan; // GD path: number of points to scan
Double_t fGDPathStep; // GD path: step size in path
Int_t fGDNPathSteps; // GD path: number of steps
- Double_t fGDErrScale; // GD path: stop
+ Double_t fGDErrScale; // GD path: stop
Double_t fMinimp; // rule/linear: minimum importance
//
TString fModelTypeS; // rule ensemble: which model (rule,linear or both)
diff --git a/tmva/tmva/src/MethodPlugins.cxx b/tmva/tmva/src/MethodPlugins.cxx
index 0bc4dabb05c..546c4cf0eff 100644
--- a/tmva/tmva/src/MethodPlugins.cxx
+++ b/tmva/tmva/src/MethodPlugins.cxx
@@ -1,5 +1,5 @@
-// @(#)root/tmva $Id$
-// Author: Andreas Hoecker, Joerg Stelzer, Helge Voss, Kai Voss
+// @(#)root/tmva $Id$
+// Author: Andreas Hoecker, Joerg Stelzer, Helge Voss, Kai Voss
/**********************************************************************************
* Project: TMVA - a Root-integrated toolkit for multivariate Data analysis *
@@ -30,22 +30,22 @@
* (http://tmva.sourceforge.net/LICENSE) *
**********************************************************************************/
-////////////////////////////////////////////////////////////////////////////////
+/*! \class TMVA::CreateMethodPlugins
+\ingroup TMVA
-/* Begin_Html
+Plugins analysis
- Plugins analysis
-
- <p>
- The MethodPlugins is actually not a real method, but it is just a wrapper to call the TPluginsManager of ROOT and find
- a external method which can be used to extend TMVA by another classifier. The only methods which are actually really implemented are the
- constructors which fulfill the plugins handling. The others will produce FATAL warnings and stop TMVA execution.
- <p>
- Right after the constructor, the additional method 'getPlugedinMethod()' is called, which returns the method loaded by the plugin manager,
- and the MethodPlugins object is already deleted.
+The MethodPlugins is actually not a real method, but it is just a wrapper to call
+the TPluginsManager of ROOT and find a external method which can be used to extend
+TMVA by another classifier. The only methods which are actually really implemented
+are the constructors which fulfill the plugins handling. The others will produce
+FATAL warnings and stop TMVA execution.
- End_Html */
-//_______________________________________________________________________
+Right after the constructor, the additional method 'getPlugedinMethod()' is called,
+which returns the method loaded by the plugin manager, and the MethodPlugins object
+is already deleted.
+
+*/
#include "TPluginManager.h"
#include "TROOT.h"
@@ -58,10 +58,10 @@
#include <cstdio>
#include <iostream>
-namespace
-{
+namespace
+{
TMVA::IMethod* CreateMethodPlugins(const TString& jobName, const TString& methodTitle, TMVA::DataSetInfo& theData, const TString& theOption)
- {
+ {
//std::cout << "CreateMethodPlugins is called with options : '" << jobName << "', '" << methodTitle<< "', " << theOption<< "'" << std::endl;
TPluginManager *pluginManager(0);
TPluginHandler *pluginHandler(0);
@@ -78,30 +78,30 @@ namespace
else myMethodTitle = methodTitle;
pluginHandler = pluginManager->FindHandler("TMVA@@MethodBase", myMethodTitle);
if(!pluginHandler)
- {
+ {
std::cerr << "Couldn't find plugin handler for TMVA@@MethodBase and " << methodTitle << std::endl;
return 0;
}
//std::cout << "pluginHandler found myMethodTitle=" << myMethodTitle<<std::endl;
if (pluginHandler->LoadPlugin() == 0) {
- if(jobName=="" && methodTitle=="") {
+ if(jobName=="" && methodTitle=="") {
//std::cout << "Calling ExpertPlugin " << std::endl;
return (TMVA::IMethod*) pluginHandler->ExecPlugin(2, &theData, &theOption);
- } else {
+ } else {
//std::cout << "Calling TeacherPlugin " << std::endl;
// pluginHandler->Print("a");
return (TMVA::IMethod*) pluginHandler->ExecPlugin(4, &jobName, &methodTitle, &theData, &theOption);
- }
+ }
}
//std::cout << "plugin done" << std::endl;
return 0; // end of function should never be reached. This is here to silence the compiler
}
- struct registration {
- registration() {
+ struct registration {
+ registration() {
TMVA::ClassifierFactory::Instance().Register("Plugins", CreateMethodPlugins);
- TMVA::Types::Instance().AddTypeMapping(TMVA::Types::kPlugins, "Plugins");
- }
+ TMVA::Types::Instance().AddTypeMapping(TMVA::Types::kPlugins, "Plugins");
+ }
} instance;
}
diff --git a/tmva/tmva/src/MethodRuleFit.cxx b/tmva/tmva/src/MethodRuleFit.cxx
index e7222599c15..61a2ddd36d0 100644
--- a/tmva/tmva/src/MethodRuleFit.cxx
+++ b/tmva/tmva/src/MethodRuleFit.cxx
@@ -14,19 +14,19 @@
* Fredrik Tegenfeldt <Fredrik.Tegenfeldt@cern.ch> - Iowa State U., USA *
* *
* Copyright (c) 2005: *
- * CERN, Switzerland *
+ * CERN, Switzerland *
* Iowa State U. *
- * MPI-K Heidelberg, Germany *
+ * MPI-K Heidelberg, Germany *
* *
* Redistribution and use in source and binary forms, with or without *
* modification, are permitted according to the terms listed in LICENSE *
* (http://tmva.sourceforge.net/LICENSE) *
**********************************************************************************/
-//_______________________________________________________________________
-//
-// J Friedman's RuleFit method
-//_______________________________________________________________________
+/*! \class TMVA::
+\ingroup TMVA
+J Friedman's RuleFit method
+*/
#include "TMVA/MethodRuleFit.h"
@@ -63,13 +63,13 @@ using std::min;
REGISTER_METHOD(RuleFit)
ClassImp(TMVA::MethodRuleFit)
-
+
////////////////////////////////////////////////////////////////////////////////
/// standard constructor
TMVA::MethodRuleFit::MethodRuleFit( const TString& jobName,
const TString& methodTitle,
- DataSetInfo& theData,
+ DataSetInfo& theData,
const TString& theOption) :
MethodBase( jobName, Types::kRuleFit, methodTitle, theData, theOption)
, fSignalFraction(0)
@@ -90,7 +90,7 @@ ClassImp(TMVA::MethodRuleFit)
, fRFNendnodes(0)
, fNTrees(0)
, fTreeEveFrac(0)
- , fSepType(0)
+ , fSepType(0)
, fMinFracNEve(0)
, fMaxFracNEve(0)
, fNCuts(0)
@@ -137,7 +137,7 @@ TMVA::MethodRuleFit::MethodRuleFit( DataSetInfo& theData,
, fRFNendnodes(0)
, fNTrees(0)
, fTreeEveFrac(0)
- , fSepType(0)
+ , fSepType(0)
, fMinFracNEve(0)
, fMaxFracNEve(0)
, fNCuts(0)
@@ -170,7 +170,7 @@ TMVA::MethodRuleFit::~MethodRuleFit( void )
}
////////////////////////////////////////////////////////////////////////////////
-/// RuleFit can handle classification with 2 classes
+/// RuleFit can handle classification with 2 classes
Bool_t TMVA::MethodRuleFit::HasAnalysisType( Types::EAnalysisType type, UInt_t numberClasses, UInt_t /*numberTargets*/ )
{
@@ -179,51 +179,51 @@ Bool_t TMVA::MethodRuleFit::HasAnalysisType( Types::EAnalysisType type, UInt_t n
}
////////////////////////////////////////////////////////////////////////////////
-/// define the options (their key words) that can be set in the option string
+/// define the options (their key words) that can be set in the option string
/// know options.
-///---------
-/// general
-///---------
-/// RuleFitModule <string>
-/// available values are: RFTMVA - use TMVA implementation
-/// RFFriedman - use Friedmans original implementation
-///----------------------
-/// Path search (fitting)
-///----------------------
-/// GDTau <float> gradient-directed path: fit threshhold, default
-/// GDTauPrec <float> gradient-directed path: precision of estimated tau
-/// GDStep <float> gradient-directed path: step size
-/// GDNSteps <float> gradient-directed path: number of steps
-/// GDErrScale <float> stop scan when error>scale*errmin
-///-----------------
-/// Tree generation
-///-----------------
-/// fEventsMin <float> minimum fraction of events in a splittable node
-/// fEventsMax <float> maximum fraction of events in a splittable node
-/// nTrees <float> number of trees in forest.
-/// ForestType <string>
-/// available values are: Random - create forest using random subsample and only random variables subset at each node
-/// AdaBoost - create forest with boosted events
///
-///-----------------
-/// Model creation
-///-----------------
-/// RuleMinDist <float> min distance allowed between rules
-/// MinImp <float> minimum rule importance accepted
-/// Model <string> model to be used
-/// available values are: ModRuleLinear <default>
-/// ModRule
-/// ModLinear
+/// #### general
+///
+/// - RuleFitModule <string>
+/// available values are:
+/// - RFTMVA - use TMVA implementation
+/// - RFFriedman - use Friedmans original implementation
+///
+/// #### Path search (fitting)
///
+/// - GDTau <float> gradient-directed path: fit threshold, default
+/// - GDTauPrec <float> gradient-directed path: precision of estimated tau
+/// - GDStep <float> gradient-directed path: step size
+/// - GDNSteps <float> gradient-directed path: number of steps
+/// - GDErrScale <float> stop scan when error>scale*errmin
///-----------------
-/// Friedmans module
+/// #### Tree generation
///-----------------
-/// RFWorkDir <string> directory where Friedmans module (rf_go.exe) is installed
-/// RFNrules <int> maximum number of rules allowed
-/// RFNendnodes <int> average number of end nodes in the forest of trees
+/// - fEventsMin <float> minimum fraction of events in a splittable node
+/// - fEventsMax <float> maximum fraction of events in a splittable node
+/// - nTrees <float> number of trees in forest.
+/// - ForestType <string>
+/// available values are:
+/// - Random - create forest using random subsample and only random variables subset at each node
+/// - AdaBoost - create forest with boosted events
///
+///#### Model creation
+///
+/// - RuleMinDist <float> min distance allowed between rules
+/// - MinImp <float> minimum rule importance accepted
+/// - Model <string> model to be used
+/// available values are:
+/// - ModRuleLinear <default>
+/// - ModRule
+/// - ModLinear
+///
+/// #### Friedmans module
+///
+/// - RFWorkDir <string> directory where Friedmans module (rf_go.exe) is installed
+/// - RFNrules <int> maximum number of rules allowed
+/// - RFNendnodes <int> average number of end nodes in the forest of trees
-void TMVA::MethodRuleFit::DeclareOptions()
+void TMVA::MethodRuleFit::DeclareOptions()
{
DeclareOptionRef(fGDTau=-1, "GDTau", "Gradient-directed (GD) path: default fit cut-off");
DeclareOptionRef(fGDTauPrec=0.01, "GDTauPrec", "GD path: precision of tau");
@@ -237,7 +237,7 @@ void TMVA::MethodRuleFit::DeclareOptions()
DeclareOptionRef(fMinFracNEve=0.1, "fEventsMin", "Minimum fraction of events in a splittable node");
DeclareOptionRef(fMaxFracNEve=0.9, "fEventsMax", "Maximum fraction of events in a splittable node");
DeclareOptionRef(fNTrees=20, "nTrees", "Number of trees in forest.");
-
+
DeclareOptionRef(fForestTypeS="AdaBoost", "ForestType", "Method to use for forest generation (AdaBoost or RandomForest)");
AddPreDefVal(TString("AdaBoost"));
AddPreDefVal(TString("Random"));
@@ -259,13 +259,13 @@ void TMVA::MethodRuleFit::DeclareOptions()
}
////////////////////////////////////////////////////////////////////////////////
-/// process the options specified by the user
+/// process the options specified by the user
-void TMVA::MethodRuleFit::ProcessOptions()
+void TMVA::MethodRuleFit::ProcessOptions()
{
if (IgnoreEventsWithNegWeightsInTraining()) {
Log() << kFATAL << "Mechanism to ignore events with negative weights in training not yet available for method: "
- << GetMethodTypeName()
+ << GetMethodTypeName()
<< " --> please remove \"IgnoreNegWeightsInTraining\" option from booking string."
<< Endl;
}
@@ -450,7 +450,7 @@ void TMVA::MethodRuleFit::Train( void )
if (fUseRuleFitJF) {
TrainJFRuleFit();
- }
+ }
else {
TrainTMVARuleFit();
}
@@ -464,8 +464,8 @@ void TMVA::MethodRuleFit::Train( void )
void TMVA::MethodRuleFit::TrainTMVARuleFit( void )
{
- if (IsNormalised()) Log() << kFATAL << "\"Normalise\" option cannot be used with RuleFit; "
- << "please remove the optoin from the configuration string, or "
+ if (IsNormalised()) Log() << kFATAL << "\"Normalise\" option cannot be used with RuleFit; "
+ << "please remove the option from the configuration string, or "
<< "use \"!Normalise\""
<< Endl;
@@ -475,7 +475,7 @@ void TMVA::MethodRuleFit::TrainTMVARuleFit( void )
// test tree nmin cut -> for debug purposes
// the routine will generate trees with stopping cut on N(eve) given by
// a fraction between [20,N(eve)-1].
- //
+ //
// MakeForestRnd();
// exit(1);
//
@@ -519,8 +519,8 @@ void TMVA::MethodRuleFit::TrainTMVARuleFit( void )
fNTSSB = rule->GetSSB();
fMonitorNtuple->Fill();
}
-
- fRuleFit.MakeVisHists();
+
+ fRuleFit.MakeVisHists();
fRuleFit.MakeDebugHists();
}
Log() << kDEBUG << "Training done" << Endl;
@@ -573,7 +573,7 @@ void TMVA::MethodRuleFit::TrainJFRuleFit( void )
////////////////////////////////////////////////////////////////////////////////
/// computes ranking of input variables
-const TMVA::Ranking* TMVA::MethodRuleFit::CreateRanking()
+const TMVA::Ranking* TMVA::MethodRuleFit::CreateRanking()
{
// create the ranking object
fRanking = new Ranking( GetName(), "Importance" );
@@ -588,7 +588,7 @@ const TMVA::Ranking* TMVA::MethodRuleFit::CreateRanking()
////////////////////////////////////////////////////////////////////////////////
/// add the rules to XML node
-void TMVA::MethodRuleFit::AddWeightsXMLTo( void* parent ) const
+void TMVA::MethodRuleFit::AddWeightsXMLTo( void* parent ) const
{
fRuleFit.GetRuleEnsemble().AddXMLTo( parent );
}
@@ -731,7 +731,7 @@ void TMVA::MethodRuleFit::MakeClassLinear( std::ostream& fout ) const
fout << " rval+="
// << std::setprecision(10) << rens->GetLinCoefficients(il)*norm << "*std::min(" << setprecision(10) << rens->GetLinDP(il)
// << ", std::max( inputValues[" << il << "]," << std::setprecision(10) << rens->GetLinDM(il) << "));"
- << std::setprecision(10) << rens->GetLinCoefficients(il)*norm
+ << std::setprecision(10) << rens->GetLinCoefficients(il)*norm
<< "*std::min( double(" << std::setprecision(10) << rens->GetLinDP(il)
<< "), std::max( double(inputValues[" << il << "]), double(" << std::setprecision(10) << rens->GetLinDM(il) << ")));"
<< std::flush;
@@ -743,7 +743,7 @@ void TMVA::MethodRuleFit::MakeClassLinear( std::ostream& fout ) const
////////////////////////////////////////////////////////////////////////////////
/// get help message text
///
-/// typical length of text line:
+/// typical length of text line:
/// "|--------------------------------------------------------------|"
void TMVA::MethodRuleFit::GetHelpMessage() const
@@ -785,12 +785,12 @@ void TMVA::MethodRuleFit::GetHelpMessage() const
Log() << "evolution of the path is defined by a cut-off parameter, tau." << Endl;
Log() << "This parameter is unknown and depends on the training data." << Endl;
Log() << "A large value will tend to give large weights to a few rules." << Endl;
- Log() << "Similarily, a small value will lead to a large set of rules" << Endl;
+ Log() << "Similarly, a small value will lead to a large set of rules" << Endl;
Log() << "with similar weights." << Endl;
Log() << Endl;
Log() << "A final point is the model used; rules and/or linear terms." << Endl;
Log() << "For a given training sample, the result may improve by adding" << Endl;
- Log() << "linear terms. If best performance is optained using only linear" << Endl;
+ Log() << "linear terms. If best performance is obtained using only linear" << Endl;
Log() << "terms, it is very likely that the Fisher discriminant would be" << Endl;
Log() << "a better choice. Ideally the fitting procedure should be able to" << Endl;
Log() << "make this choice by giving appropriate weights for either terms." << Endl;
@@ -800,7 +800,7 @@ void TMVA::MethodRuleFit::GetHelpMessage() const
Log() << "I. TUNING OF RULE ENSEMBLE:" << Endl;
Log() << Endl;
Log() << " " << col << "ForestType " << colres
- << ": Recomended is to use the default \"AdaBoost\"." << brk << Endl;
+ << ": Recommended is to use the default \"AdaBoost\"." << brk << Endl;
Log() << " " << col << "nTrees " << colres
<< ": More trees leads to more rules but also slow" << Endl;
Log() << " performance. With too few trees the risk is" << Endl;
@@ -829,7 +829,7 @@ void TMVA::MethodRuleFit::GetHelpMessage() const
Log() << " Increasing this fraction will improve the path" << Endl;
Log() << " finding. However, a too high value will give few" << Endl;
Log() << " unique events available for error estimation." << Endl;
- Log() << " It is recomended to usethe default = 0.5." << brk << Endl;
+ Log() << " It is recommended to use the default = 0.5." << brk << Endl;
Log() << " " << col << "GDTau " << colres
<< ": cutoff parameter tau" << Endl;
Log() << " By default this value is set to -1.0." << Endl;
--
GitLab