default/weights/aback_Cuts.class.C

0001 // Class: ReadCuts
0002 // Automatically generated by MethodBase::MakeClass
0003 //
0004
0005 /* configuration options =====================================================
0006
0007 #GEN -*-*-*-*-*-*-*-*-*-*-*- general info -*-*-*-*-*-*-*-*-*-*-*-
0008
0009 Method         : Cuts::Cuts
0010 TMVA Release   : 4.2.1         [262657]
0011 ROOT Release   : 6.16/00       [397312]
0012 Creator        : vassalli
0013 Date           : Tue Jul 23 11:56:01 2019
0014 Host           : Linux cvmfswrite01.sdcc.bnl.gov 3.10.0-693.11.6.el7.x86_64 #1 SMP Wed Jan 3 18:09:42 CST 2018 x86_64 x86_64 x86_64 GNU/Linux
0015 Dir            : /direct/phenix+u/vassalli/sphenix/single/Training
0016 Training events: 16285
0017 Analysis type  : [Classification]
0018
0019
0020 #OPT -*-*-*-*-*-*-*-*-*-*-*-*- options -*-*-*-*-*-*-*-*-*-*-*-*-
0021
0022 # Set by User:
0023 # Default:
0024 V: "False" [Verbose output (short form of "VerbosityLevel" below - overrides the latter one)]
0025 VerbosityLevel: "Default" [Verbosity level]
0026 VarTransform: "None" [List of variable transformations performed before training, e.g., "D_Background,P_Signal,G,N_AllClasses" for: "Decorrelation, PCA-transformation, Gaussianisation, Normalisation, each for the given class of events ('AllClasses' denotes all events of all classes, if no class indication is given, 'All' is assumed)"]
0027 H: "False" [Print method-specific help message]
0028 CreateMVAPdfs: "False" [Create PDFs for classifier outputs (signal and background)]
0029 IgnoreNegWeightsInTraining: "False" [Events with negative weights are ignored in the training (but are included for testing and performance evaluation)]
0030 FitMethod: "GA" [Minimisation Method (GA, SA, and MC are the primary methods to be used; the others have been introduced for testing purposes and are depreciated)]
0031 EffMethod: "EffSel" [Selection Method]
0032 CutRangeMin[0]: "-1.000000e+00" [Minimum of allowed cut range (set per variable)]
0033     CutRangeMin[1]: "-1.000000e+00"
0034     CutRangeMin[2]: "-1.000000e+00"
0035     CutRangeMin[3]: "-1.000000e+00"
0036     CutRangeMin[4]: "-1.000000e+00"
0037     CutRangeMin[5]: "-1.000000e+00"
0038     CutRangeMin[6]: "-1.000000e+00"
0039     CutRangeMin[7]: "-1.000000e+00"
0040     CutRangeMin[8]: "-1.000000e+00"
0041     CutRangeMin[9]: "-1.000000e+00"
0042 CutRangeMax[0]: "-1.000000e+00" [Maximum of allowed cut range (set per variable)]
0043     CutRangeMax[1]: "-1.000000e+00"
0044     CutRangeMax[2]: "-1.000000e+00"
0045     CutRangeMax[3]: "-1.000000e+00"
0046     CutRangeMax[4]: "-1.000000e+00"
0047     CutRangeMax[5]: "-1.000000e+00"
0048     CutRangeMax[6]: "-1.000000e+00"
0049     CutRangeMax[7]: "-1.000000e+00"
0050     CutRangeMax[8]: "-1.000000e+00"
0051     CutRangeMax[9]: "-1.000000e+00"
0052 VarProp[0]: "NotEnforced" [Categorisation of cuts]
0053     VarProp[1]: "NotEnforced"
0054     VarProp[2]: "NotEnforced"
0055     VarProp[3]: "NotEnforced"
0056     VarProp[4]: "NotEnforced"
0057     VarProp[5]: "NotEnforced"
0058     VarProp[6]: "NotEnforced"
0059     VarProp[7]: "NotEnforced"
0060     VarProp[8]: "NotEnforced"
0061     VarProp[9]: "NotEnforced"
0062 ##
0063
0064
0065 #VAR -*-*-*-*-*-*-*-*-*-*-*-* variables *-*-*-*-*-*-*-*-*-*-*-*-
0066
0067 NVar 10
0068 track_deta                    track_deta                    track_deta                    track_deta                                                      'F'    [5.96046447754e-08,1.94615316391]
0069 track_dlayer                  track_dlayer                  track_dlayer                  track_dlayer                                                    'I'    [-31,31]
0070 track_layer                   track_layer                   track_layer                   track_layer                                                     'I'    [0,38]
0071 track_pT                      track_pT                      track_pT                      track_pT                                                        'F'    [0.169785350561,79.8480682373]
0072 approach_dist                 approach_dist                 approach_dist                 approach_dist                                                   'F'    [1.25233009385e-06,44.061088562]
0073 vtx_radius                    vtx_radius                    vtx_radius                    vtx_radius                                                      'F'    [3.56204419596e-37,102.31892395]
0074 vtx_chi2                      vtx_chi2                      vtx_chi2                      vtx_chi2                                                        'F'    [5.22654283354e-38,23.2217674255]
0075 vtxTrackRZ_dist               vtxTrackRZ_dist               vtxTrackRZ_dist               vtxTrackRZ_dist                                                 'F'    [0,114.041381836]
0076 photon_pT                     photon_pT                     photon_pT                     photon_pT                                                       'F'    [0.00301368604414,12548.6572266]
0077 cluster_prob                  cluster_prob                  cluster_prob                  cluster_prob                                                    'F'    [0,0.999658644199]
0078 NSpec 0
0079
0080
0081 ============================================================================ */
0082
0083 #include <array>
0084 #include <vector>
0085 #include <cmath>
0086 #include <string>
0087 #include <iostream>
0088
0089 #ifndef IClassifierReader__def
0090 #define IClassifierReader__def
0091
0092 class IClassifierReader {
0093
0094  public:
0095
0096    // constructor
0097    IClassifierReader() : fStatusIsClean( true ) {}
0098    virtual ~IClassifierReader() {}
0099
0100    // return classifier response
0101    virtual double GetMvaValue( const std::vector<double>& inputValues ) const = 0;
0102
0103    // returns classifier status
0104    bool IsStatusClean() const { return fStatusIsClean; }
0105
0106  protected:
0107
0108    bool fStatusIsClean;
0109 };
0110
0111 #endif
0112
0113 class ReadCuts : public IClassifierReader {
0114
0115  public:
0116
0117    // constructor
0118    ReadCuts( std::vector<std::string>& theInputVars )
0119       : IClassifierReader(),
0120         fClassName( "ReadCuts" ),
0121         fNvars( 10 )
0122    {
0123       // the training input variables
0124       const char* inputVars[] = { "track_deta", "track_dlayer", "track_layer", "track_pT", "approach_dist", "vtx_radius", "vtx_chi2", "vtxTrackRZ_dist", "photon_pT", "cluster_prob" };
0125
0126       // sanity checks
0127       if (theInputVars.size() <= 0) {
0128          std::cout << "Problem in class \"" << fClassName << "\": empty input vector" << std::endl;
0129          fStatusIsClean = false;
0130       }
0131
0132       if (theInputVars.size() != fNvars) {
0133          std::cout << "Problem in class \"" << fClassName << "\": mismatch in number of input values: "
0134                    << theInputVars.size() << " != " << fNvars << std::endl;
0135          fStatusIsClean = false;
0136       }
0137
0138       // validate input variables
0139       for (size_t ivar = 0; ivar < theInputVars.size(); ivar++) {
0140          if (theInputVars[ivar] != inputVars[ivar]) {
0141             std::cout << "Problem in class \"" << fClassName << "\": mismatch in input variable names" << std::endl
0142                       << " for variable [" << ivar << "]: " << theInputVars[ivar].c_str() << " != " << inputVars[ivar] << std::endl;
0143             fStatusIsClean = false;
0144          }
0145       }
0146
0147       // initialize min and max vectors (for normalisation)
0148       fVmin[0] = 0;
0149       fVmax[0] = 0;
0150       fVmin[1] = 0;
0151       fVmax[1] = 0;
0152       fVmin[2] = 0;
0153       fVmax[2] = 0;
0154       fVmin[3] = 0;
0155       fVmax[3] = 0;
0156       fVmin[4] = 0;
0157       fVmax[4] = 0;
0158       fVmin[5] = 0;
0159       fVmax[5] = 0;
0160       fVmin[6] = 0;
0161       fVmax[6] = 0;
0162       fVmin[7] = 0;
0163       fVmax[7] = 0;
0164       fVmin[8] = 0;
0165       fVmax[8] = 0;
0166       fVmin[9] = 0;
0167       fVmax[9] = 0;
0168
0169       // initialize input variable types
0170       fType[0] = 'F';
0171       fType[1] = 'I';
0172       fType[2] = 'I';
0173       fType[3] = 'F';
0174       fType[4] = 'F';
0175       fType[5] = 'F';
0176       fType[6] = 'F';
0177       fType[7] = 'F';
0178       fType[8] = 'F';
0179       fType[9] = 'F';
0180
0181       // initialize constants
0182       Initialize();
0183
0184    }
0185
0186    // destructor
0187    virtual ~ReadCuts() {
0188       Clear(); // method-specific
0189    }
0190
0191    // the classifier response
0192    // "inputValues" is a vector of input values in the same order as the
0193    // variables given to the constructor
0194    double GetMvaValue( const std::vector<double>& inputValues ) const override;
0195
0196  private:
0197
0198    // method-specific destructor
0199    void Clear();
0200
0201    // common member variables
0202    const char* fClassName;
0203
0204    const size_t fNvars;
0205    size_t GetNvar()           const { return fNvars; }
0206    char   GetType( int ivar ) const { return fType[ivar]; }
0207
0208    // normalisation of input variables
0209    double fVmin[10];
0210    double fVmax[10];
0211    double NormVariable( double x, double xmin, double xmax ) const {
0212       // normalise to output range: [-1, 1]
0213       return 2*(x - xmin)/(xmax - xmin) - 1.0;
0214    }
0215
0216    // type of input variable: 'F' or 'I'
0217    char   fType[10];
0218
0219    // initialize internal variables
0220    void Initialize();
0221    double GetMvaValue__( const std::vector<double>& inputValues ) const;
0222
0223    // private members (method specific)
0224    // not implemented for class: "ReadCuts"
0225 };
0226    inline double ReadCuts::GetMvaValue( const std::vector<double>& inputValues ) const
0227    {
0228       // classifier response value
0229       double retval = 0;
0230
0231       // classifier response, sanity check first
0232       if (!IsStatusClean()) {
0233          std::cout << "Problem in class \"" << fClassName << "\": cannot return classifier response"
0234                    << " because status is dirty" << std::endl;
0235          retval = 0;
0236       }
0237       else {
0238             retval = GetMvaValue__( inputValues );
0239       }
0240
0241       return retval;
0242    }