Merge pull request #11502 from cms-btv-pog/JetFlavorFixes_from-CMSSW_…

…7_5_3

Flavor bugfix in jetTools.py (75X)

PhysicsTools/JetExamples/test/printJetFlavourInfo.py

@@ -60,11 +60,12 @@
     subjets                  = cms.InputTag("ak8PFJetsPruned", "SubJets"),
     bHadrons                 = cms.InputTag("selectedHadronsAndPartons","bHadrons"),
     cHadrons                 = cms.InputTag("selectedHadronsAndPartons","cHadrons"),
-    partons                  = cms.InputTag("selectedHadronsAndPartons","partons"),
+    partons                  = cms.InputTag("selectedHadronsAndPartons","algorithmicPartons"),
+    leptons                  = cms.InputTag("selectedHadronsAndPartons","leptons"),
     jetAlgorithm             = cms.string("AntiKt"),
     rParam                   = cms.double(0.8),
     ghostRescaling           = cms.double(1e-18),
-    hadronFlavourHasPriority = cms.bool(True)
+    hadronFlavourHasPriority = cms.bool(False)
 )
 
 process.printEventAK8PFJets = cms.EDAnalyzer("printJetFlavourInfo",
@@ -109,11 +110,12 @@
     subjets                  = cms.InputTag("caHEPTopTagJets", "caTopSubJets"),
     bHadrons                 = cms.InputTag("selectedHadronsAndPartons","bHadrons"),
     cHadrons                 = cms.InputTag("selectedHadronsAndPartons","cHadrons"),
-    partons                  = cms.InputTag("selectedHadronsAndPartons","partons"),
+    partons                  = cms.InputTag("selectedHadronsAndPartons","algorithmicPartons"),
+    leptons                  = cms.InputTag("selectedHadronsAndPartons","leptons"),
     jetAlgorithm             = cms.string("CambridgeAachen"),
     rParam                   = cms.double(1.5),
     ghostRescaling           = cms.double(1e-18),
-    hadronFlavourHasPriority = cms.bool(True)
+    hadronFlavourHasPriority = cms.bool(False)
 )
 
 process.printEventCA15PFJets = cms.EDAnalyzer("printJetFlavourInfo",

PhysicsTools/JetMCAlgos/plugins/JetFlavourClustering.cc

@@ -7,7 +7,7 @@
  * \brief Clusters hadrons, partons, and jet contituents to determine the jet flavour
  *
  * This producer clusters hadrons, partons and jet contituents to determine the jet flavour. The jet flavour information
- * is stored in the event as an AssociationVector which associates an object of type JetFlavorInfo to each of the jets.
+ * is stored in the event as an AssociationVector which associates an object of type JetFlavourInfo to each of the jets.
  *
  * The producer takes as input jets and hadron and partons selected by the HadronAndPartonSelector producer. The hadron
  * and parton four-momenta are rescaled by a very small number (default rescale factor is 10e-18) which turns them into
@@ -30,38 +30,40 @@
  * - jet is considered a c jet if there is at least one c and no b "ghost" partons clustered inside it (partonFlavour = 4)
  * 
  * - jet is considered a light-flavour jet if there are light-flavour and no b or c "ghost" partons clustered inside it.
- *   The jet is assigned the flavour of the hardest light-flavour "ghost" parton clustered inside it (partonFlavour = 1,2,3, or 21)
+ *   The jet is assigned the flavour of the hardest light-flavour "ghost" parton clustered inside it (partonFlavour = 1, 2, 3, or 21)
  * 
  * - jet has an undefined flavour if there are no "ghost" partons clustered inside it (partonFlavour = 0)
  *
  * In rare instances a conflict between the hadron- and parton-based flavours can occur. In such cases it is possible to
  * keep both flavours or to give priority to the hadron-based flavour. This is controlled by the 'hadronFlavourHasPriority'
- * switch which is enabled by default. The priority is given to the hadron-based flavour as follows:
+ * switch. The priority is given to the hadron-based flavour as follows:
  * 
  * - if hadronFlavour==0 && (partonFlavour==4 || partonFlavour==5): partonFlavour is set to the flavour of the hardest
  *   light-flavour parton clustered inside the jet if such parton exists. Otherwise, the parton flavour is left undefined
  * 
  * - if hadronFlavour!=0 && hadronFlavour!=partonFlavour: partonFlavour is set equal to hadronFlavour
  *
- * The producer is also capable of assigning the flavor to subjets of fat jets, in which case it produces an additional
- * AssociationVector providing the flavour information for subjets. In order to assign the flavor to subjets, three input
+ * The producer is also capable of assigning the flavour to subjets of fat jets, in which case it produces an additional
+ * AssociationVector providing the flavour information for subjets. In order to assign the flavour to subjets, three input
  * jet collections are required:
  *
  * - jets, in this case represented by fat jets
  * 
- * - groomed jets, which is a collection of fat jets from which the subjets are derived
+ * - groomed jets, which is a collection of fat jets from which the subjets are derived (e.g. pruned, filtered, soft drop, top-tagged, etc. jets)
  * 
  * - subjets, derived from the groomed fat jets
  *
  * The "ghost" hadrons and partons clustered inside a fat jet are assigned to the closest subjet in the rapidity-phi
- * space. Once hadrons and partons have been assigned to subjets, the subjet flavor is determined in the same way as for
+ * space. Once hadrons and partons have been assigned to subjets, the subjet flavour is determined in the same way as for
  * jets. The reason for requiring three jet collections as input in order to determine the subjet flavour is to avoid
  * possible inconsistencies between the fat jet and subjet flavours (such as a non-b fat jet having a b subjet and vice
- * versa) as well as the fact that reclustering the constituents of groomed fat jets will generally result in a jet
- * collection different from the input groomed fat jets.
+ * versa) as well as the fact that re-clustering the constituents of groomed fat jets will generally result in a jet
+ * collection different from the input groomed fat jets. Also note that "ghost" particles generally cannot be clustered
+ * inside subjets in the same way this is done for fat jets. This is because some of the jet grooming techniques could
+ * reject such very soft particle. So instead, the "ghost" particles are assigned to the closest subjet.
  * 
- * In addition, "ghost" leptons can also be clustered inside jets but they are not used in any way to determine the jet
- * flavor. This functionality is disabled by default.
+ * Finally, "ghost" leptons can also be clustered inside jets but they are not used in any way to determine the jet
+ * flavour. This functionality is optional and is potentially useful to identify jets from hadronic taus.
  * 
  * For more details, please refer to
  * https://twiki.cern.ch/twiki/bin/view/CMSPublic/SWGuideBTagMCTools

PhysicsTools/JetMCAlgos/src/Pythia8PartonSelector.cc

@@ -1,8 +1,8 @@
 
 /**
- * This is a Pythia8-specific parton selector that selects all status==71 or 72 partons. An explanation of
- * the particle status codes returned by Pythia8 can be found in Pythia8 online manual
- * (http://home.thep.lu.se/~torbjorn/pythia81html/ParticleProperties.html).
+ * This is a Pythia8-specific parton selector that selects all partons that don't have other partons as daughters, i.e., partons
+ * from the end of the parton showering sequence. An explanation of the particle status codes returned by Pythia8 can be found in
+ * Pythia8 online manual (http://home.thep.lu.se/~torbjorn/pythia81html/ParticleProperties.html).
  */
 
 #include "PhysicsTools/JetMCAlgos/interface/Pythia8PartonSelector.h"
@@ -25,10 +25,20 @@ Pythia8PartonSelector::run(const edm::Handle<reco::GenParticleCollection> & part
    for(reco::GenParticleCollection::const_iterator it = particles->begin(); it != particles->end(); ++it)
    {
      int status = it->status();
-     if( !(status==71 || status==72) ) continue;       // only accept status==71 or 72 particles
+     if( status==1 ) continue;                         // skip stable particles
+     if( status==2 ) continue;                         // skip decayed Standard Model hadrons and leptons
      if( !CandMCTagUtils::isParton( *it ) ) continue;  // skip particle if not a parton
 
-     partons->push_back( reco::GenParticleRef( particles, it - particles->begin() ) );
+     // check if the parton has other partons as daughters
+     int nparton_daughters = 0;
+     for(unsigned i=0; i<it->numberOfDaughters(); ++i)
+     {
+       if( CandMCTagUtils::isParton( *(it->daughter(i)) ) )
+         ++nparton_daughters;
+     }
+
+     if( nparton_daughters==0 )
+       partons->push_back( reco::GenParticleRef( particles, it - particles->begin() ) );
    }
 
    return;

PhysicsTools/PatAlgos/python/slimming/prunedGenParticles_cfi.py

@@ -16,7 +16,7 @@
         "keep abs(pdgId) == 23 || abs(pdgId) == 24 || abs(pdgId) == 25 || abs(pdgId) == 6 || abs(pdgId) == 37 ",   # keep VIP(articles)s
         "keep abs(pdgId) == 310 && abs(eta) < 2.5 && pt > 1 ",                                                     # keep K0
 # keep heavy flavour quarks for parton-based jet flavour
-	"keep (4 <= abs(pdgId) <= 5) & (status = 2 || status = 11 || status = 71 || status = 72)",
+	"keep (4 <= abs(pdgId) <= 5)",
 # keep light-flavour quarks and gluons for parton-based jet flavour
 	"keep (1 <= abs(pdgId) <= 3 || pdgId = 21) & (status = 2 || status = 11 || status = 71 || status = 72) && pt>5", 
 # keep b and c hadrons for hadron-based jet flavour

PhysicsTools/PatAlgos/python/tools/jetTools.py

@@ -318,7 +318,7 @@ def toolCode(self, process):
                 _newPatJetFlavourAssociation.rParam=rParam
                 _newPatJetFlavourAssociation.bHadrons=cms.InputTag("patJetPartons"+postfix,"bHadrons")
                 _newPatJetFlavourAssociation.cHadrons=cms.InputTag("patJetPartons"+postfix,"cHadrons")
-                _newPatJetFlavourAssociation.partons=cms.InputTag("patJetPartons"+postfix,"physicsPartons")
+                _newPatJetFlavourAssociation.partons=cms.InputTag("patJetPartons"+postfix,"algorithmicPartons")
                 _newPatJetFlavourAssociation.leptons=cms.InputTag("patJetPartons"+postfix,"leptons")
             else :
                 setattr(process, 'patJetFlavourAssociation'+_labelName+postfix,
@@ -328,7 +328,7 @@ def toolCode(self, process):
                             rParam=rParam,
                             bHadrons = cms.InputTag("patJetPartons"+postfix,"bHadrons"),
                             cHadrons = cms.InputTag("patJetPartons"+postfix,"cHadrons"),
-                            partons = cms.InputTag("patJetPartons"+postfix,"physicsPartons"),
+                            partons = cms.InputTag("patJetPartons"+postfix,"algorithmicPartons"),
                             leptons = cms.InputTag("patJetPartons"+postfix,"leptons")
                         )
                 )