|
ROOT
Reference Guide |
|
Go to the documentation of this file.
40 #ifndef ROOT_TMVA_Factory
41 #define ROOT_TMVA_Factory
72 class DataInputHandler;
77 class VariableTransformBase;
187 TH1F*
GetImportance(
const int nbits,std::vector<Double_t> importances,std::vector<TString> varNames);
void TrainAllMethodsForRegression(void)
Bool_t fModelPersistence
the training type
TH1F * EvaluateImportanceRandom(DataLoader *loader, UInt_t nseeds, Types::EMVA theMethod, TString methodTitle, const char *theOption="")
TString fVerboseLevel
verbose mode
TString fJobName
used in contructor wihtout file
virtual void MakeClass(const TString &datasetname, const TString &methodTitle="") const
void PrintHelpMessage(const TString &datasetname, const TString &methodTitle="") const
Print predefined help message of classifier.
std::map< TString, Double_t > OptimizeAllMethods(TString fomType="ROCIntegral", TString fitType="FitGA")
Iterates through all booked methods and sees if they use parameter tuning and if so does just that,...
Bool_t IsSilentFile() const
A TTree represents a columnar dataset.
Double_t GetROCIntegral(DataLoader *loader, TString theMethodName, UInt_t iClass=0, Types::ETreeType type=Types::kTesting)
Calculate the integral of the ROC curve, also known as the area under curve (AUC),...
std::vector< IMethod * > MVector
void TestAllMethods()
Evaluates all booked methods on the testing data and adds the output to the Results in the corresponi...
TH1F * GetImportance(const int nbits, std::vector< Double_t > importances, std::vector< TString > varNames)
Bool_t IsModelPersistence() const
Bool_t fVerbose
list of transformations to test
Bool_t fCorrelations
verbosity level, controls granularity of logging
MethodBase * BookMethodWeightfile(DataLoader *dataloader, TMVA::Types::EMVA methodType, const TString &weightfile)
Adds an already constructed method to be managed by this factory.
void SetInputTreesFromEventAssignTrees()
void Greetings()
Print welcome message.
Bool_t Verbose(void) const
Class that contains all the data information.
ROCCurve * GetROC(DataLoader *loader, TString theMethodName, UInt_t iClass=0, Types::ETreeType type=Types::kTesting)
Private method to generate a ROCCurve instance for a given method.
void TrainAllMethodsForClassification(void)
MethodBase * BookMethod(DataLoader *, TMVA::Types::EMVA, TString, TString, TMVA::Types::EMVA, TString)
TMultiGraph * GetROCCurveAsMultiGraph(DataLoader *loader, UInt_t iClass, Types::ETreeType type=Types::kTesting)
Generate a collection of graphs, for all methods for a given class.
void DeleteAllMethods(void)
Delete methods.
void WriteDataInformation(DataSetInfo &fDataSetInfo)
TGraph * GetROCCurve(DataLoader *loader, TString theMethodName, Bool_t setTitles=kTRUE, UInt_t iClass=0, Types::ETreeType type=Types::kTesting)
Argument iClass specifies the class to generate the ROC curve in a multiclass setting.
TH1F * EvaluateImportance(DataLoader *loader, VIType vitype, Types::EMVA theMethod, TString methodTitle, const char *theOption="")
Evaluate Variable Importance.
TString fOptions
list of transformations on default DataSet
Factory(TString theJobName, TFile *theTargetFile, TString theOption="")
Standard constructor.
This is the main MVA steering class.
Virtual base Class for all MVA method.
Types::EAnalysisType fAnalysisType
jobname, used as extension in weight file names
TH1F * EvaluateImportanceAll(DataLoader *loader, Types::EMVA theMethod, TString methodTitle, const char *theOption="")
A ROOT file is a suite of consecutive data records (TKey instances) with a well defined format.
std::map< TString, MVector * > fMethodsMap
Interface for all concrete MVA method implementations.
IMethod * GetMethod(const TString &datasetname, const TString &title) const
Returns pointer to MVA that corresponds to given method title.
A TMultiGraph is a collection of TGraph (or derived) objects.
MethodBase * BookMethod(DataLoader *loader, TString theMethodName, TString methodTitle, TString theOption="")
Book a classifier or regression method.
virtual ~Factory()
Destructor.
A TGraph is an object made of two arrays X and Y with npoints each.
std::vector< TMVA::VariableTransformBase * > fDefaultTrfs
ROOT output file.
TDirectory * RootBaseDir()
void EvaluateAllVariables(DataLoader *loader, TString options="")
Iterates over all MVA input variables and evaluates them.
Bool_t fSilentFile
enable to calculate ROC values
1-D histogram with a float per channel (see TH1 documentation)}
Bool_t HasMethod(const TString &datasetname, const TString &title) const
Checks whether a given method name is defined for a given dataset.
#define ClassDef(name, id)
Describe directory structure in memory.
void OptimizeAllMethodsForRegression(TString fomType="ROCIntegral", TString fitType="FitGA")
TString fTransformations
option string given by construction (presently only "V")
Bool_t fROC
enable to calculate corelations
void OptimizeAllMethodsForClassification(TString fomType="ROCIntegral", TString fitType="FitGA")
void EvaluateAllMethods(void)
Iterates over all MVAs that have been booked, and calls their evaluation methods.
void TrainAllMethods()
Iterates through all booked methods and calls training.
TH1F * EvaluateImportanceShort(DataLoader *loader, Types::EMVA theMethod, TString methodTitle, const char *theOption="")
void SetVerbose(Bool_t v=kTRUE)
Class to perform cross validation, splitting the dataloader into folds.
create variable transformations