Merge pull request #3 from hatakeyamak/PFValidationUpdate

Pf validation update
Sam-Harper · Mar 10, 2020 · 4723b88 · 4723b88
2 parents 2e12079 + 7e3c57a
commit 4723b88
Show file tree

Hide file tree

Showing 6 changed files with 42 additions and 73 deletions.
diff --git a/Validation/RecoParticleFlow/README.md b/Validation/RecoParticleFlow/README.md
@@ -8,8 +8,7 @@ Set up the work area
 for lxplus with SLC7 (default since April 2019)
 
 ~~~
-export SCRAM_ARCH=slc7_amd64_gcc700
-# for SLC6 use 'slc6_amd64_gcc700' instead above
+export SCRAM_ARCH=slc7_amd64_gcc820
 cmsrel CMSSW_11_0_0
 cd CMSSW_11_0_0
 cmsenv
@@ -35,14 +34,14 @@ Create input file lists under test/tmp/das_cache
 (You can modify which datasets are being used in the end of datasets.py script)
 
 ~~~
-python test/datasets.py
+cd test; python datasets.py; cd ..
 ~~~
 
 Proceed to RECO step, about 30 minutes
 
 This is necessary if you need to re-reco events to test introduced changes to PF reco.
 
-Note 1: the default era & condition is now set to 2018. Change CONDITIONS and
+Note 1: the default era & condition is now set to 2021. Change CONDITIONS and
 ERA in test/run_relval.sh when trying other era, before trying the above commands.
 
 Note 2: the execution will fail if the destination directory (test/tmp/QCD etc.)
@@ -123,18 +122,17 @@ be included in the DQM step, so delete files you don't want to study.
 
 
 
-Note that the default era, condition, and samples are now set to 2018. Change CONDITIONS and ERA in test/run_relval.sh when trying other era, before trying the above commands. Also check (and if necessary, update) input samples and conf.Site.storageSite specified in $CMSSW_BASE/src/Validation/RecoParticleFlow/crab/multicrab.py (default storage site is T2_US_Caltech, but change it to your favorite site you have access to. use crab checkwrite --site=<site> to check your permission).
+Note that the default era, condition, and samples are now set to 2021. Change CONDITIONS and ERA in test/run_relval.sh when trying other era, before trying the above commands. Also check (and if necessary, update) input samples and conf.Site.storageSite specified in $CMSSW_BASE/src/Validation/RecoParticleFlow/crab/multicrab.py (default storage site is T2_US_Caltech, but change it to your favorite site you have access to. use crab checkwrite --site=<site> to check your permission).
 Take note that the CMSSW python configuration for running the RECO sequence is dumped into `crab/step3_dump.py`.
 
 
 # Running DQM steps from existing MINIAOD samples
 
 ~~~
-# For example (default for 2018):
-#CONDITIONS=auto:phase1_2017_realistic ERA=Run2_2017 # for 2017 scenarios
+# For example (default for 2021):
 #CONDITIONS=auto:phase1_2018_realistic ERA=Run2_2018 # for 2018 scenarios
 CONDITIONS=auto:phase1_2021_realistic ERA=Run3 # for run 3 
-#CONDITIONS=auto:phase2_realistic ERA=Phase2C8 # for phase2 
+#CONDITIONS=auto:phase2_realistic ERA=Phase2C9 # for phase2 
 #Running with 2 threads allows to use more memory on grid
 NTHREADS=2 TMPDIR=tmp
 
@@ -149,13 +147,9 @@ make -p tmp/NuGunPU; cd tmp/NuGunPU
 # Make a text file for input files. For example:
 
 ~~~
-dasgoclient --query="file dataset=/RelValQCD_FlatPt_15_3000HS_13/CMSSW_11_0_0-106X_upgrade2018_realistic_v4-v1/MINIAODSIM" > step3_filelist.txt
+dasgoclient --query="file dataset=/RelValQCD_FlatPt_15_3000HS_14/CMSSW_11_0_0_patch1-110X_mcRun3_2021_realistic_v6-v1/MINIAODSIM" > step3_filelist.txt
 #(or
-dasgoclient --query="file dataset=/RelValQCD_FlatPt_15_3000HS_13/CMSSW_11_0_0-PU25ns_106X_upgrade2018_realistic_v4-v1/MINIAODSIM" > step3_filelist.txt
-dasgoclient --query="file dataset=/RelValNuGun/CMSSW_11_0_0-PU25ns_106X_upgrade2018_realistic_v4-v1/MINIAODSIM" > step3_filelist.txt
-dasgoclient --query="file dataset=/RelValQCD_Pt-15To7000_Flat_14TeV/CMSSW_11_0_0-106X_upgrade2023_realistic_v2_2023D41noPU-v2/MINIAODSIM" > step3_filelist.txt
-dasgoclient --query="file dataset=/RelValQCD_Pt-15To7000_Flat_14TeV/CMSSW_11_0_0-PU25ns_106X_upgrade2023_realistic_v2_2023D41PU200-v1/MINIAODSIM" > step3_filelist.txt
-dasgoclient --query="file dataset=/RelValNuGun/CMSSW_11_0_0-PU25ns_106X_upgrade2023_realistic_v2_2023D41PU200-v1/MINIAODSIM"  > step3_filelist.txt
+dasgoclient --query="file dataset=/RelValQCD_Pt15To7000_Flat_14TeV/CMSSW_11_0_0-110X_mcRun4_realistic_v2_2026D49noPU-v1/MINIAODSIM" > step3_filelist.txt
 or using the list of files from your crab output areas.
 #)
 cat step3_filelist.txt

diff --git a/Validation/RecoParticleFlow/plugins/PFJetAnalyzerDQM.cc b/Validation/RecoParticleFlow/plugins/PFJetAnalyzerDQM.cc
@@ -175,12 +175,6 @@ void PFJetAnalyzerDQM::prepareGenJetPlots(const std::vector<edm::ParameterSet>&
     const auto etabin_low = pset.getParameter<double>("etaBinLow");
     const auto etabin_high = pset.getParameter<double>("etaBinHigh");
 
-    /*  for (auto v : ptbins) {
-            std::cout << " " << v;
-        }
-        std::cout << std::endl;
-	*/
-
     genJetPlots.push_back(Plot1DInBinVariable(
         name,
         title,
@@ -258,8 +252,6 @@ void PFJetAnalyzerDQM::fillJetResponse(edm::View<pat::Jet>& recoJetCollection, e
 }
 
 void PFJetAnalyzerDQM::bookHistograms(DQMStore::IBooker& booker, edm::Run const&, edm::EventSetup const&) {
-  //std::cout << "PFJetAnalyzerDQM booking response histograms" << std::endl;
-
   booker.setCurrentFolder("ParticleFlow/JetResponse/" + jetCollectionName + "/JEC/");
   for (auto& plot : jetResponsePlots) {
     plot.book(booker);

diff --git a/Validation/RecoParticleFlow/test/crab/multicrab.py b/Validation/RecoParticleFlow/test/crab/multicrab.py
@@ -10,18 +10,11 @@ def submit(config):
     with open(config.General.workArea + "/crab_" + config.General.requestName + "/crab_config.py", "w") as fi:
         fi.write(config.pythonise_())
 
-#samples = [
-#    ("/RelValQCD_FlatPt_15_3000HS_13/CMSSW_10_6_0-106X_upgrade2018_realistic_v4-v1/GEN-SIM-DIGI-RAW", "QCD_noPU"),
-#    ("/RelValQCD_FlatPt_15_3000HS_13/CMSSW_10_6_0-PU25ns_106X_upgrade2018_realistic_v4-v1/GEN-SIM-DIGI-RAW", "QCD_PU"),
-#    #("/RelValZMM_13/CMSSW_10_6_0-106X_upgrade2018_realistic_v4-v1/GEN-SIM-DIGI-RAW", "ZMM"),
-#    #("/RelValMinBias_13/CMSSW_10_6_0-106X_upgrade2018_design_v3-v1/GEN-SIM-DIGI-RAW", "MinBias"),
-#    ("/RelValNuGun/CMSSW_10_6_0-PU25ns_106X_upgrade2018_realistic_v4-v1/GEN-SIM-DIGI-RAW", "NuGun_PU"),
-#]
-#
 samples = [
     ("/RelValQCD_FlatPt_15_3000HS_14/CMSSW_11_0_0_patch1-110X_mcRun3_2021_realistic_v6-v1/GEN-SIM-DIGI-RAW", "QCD_noPU"),
-    (" /RelValQCD_FlatPt_15_3000HS_14/CMSSW_11_0_0_patch1-PU_110X_mcRun3_2021_realistic_v6-v1/GEN-SIM-DIGI-RAW", "QCD_PU"),
-    (" /RelValNuGun/CMSSW_11_0_0_patch1-PU_110X_mcRun3_2021_realistic_v6-v1/GEN-SIM-DIGI-RAW", "NuGun_PU"),
+    ("/RelValQCD_FlatPt_15_3000HS_14/CMSSW_11_0_0_patch1-PU_110X_mcRun3_2021_realistic_v6-v1/GEN-SIM-DIGI-RAW", "QCD_PU"),
+    #("/RelValZMM_14/CMSSW_11_0_0_patch1-PU_110X_mcRun3_2021_realistic_v6-v1/GEN-SIM-DIGI-RAW", "ZMM_PU"),
+    ("/RelValNuGun/CMSSW_11_0_0_patch1-PU_110X_mcRun3_2021_realistic_v6-v1/GEN-SIM-DIGI-RAW", "NuGun_PU"),
 ]
 
 if __name__ == "__main__":

diff --git a/Validation/RecoParticleFlow/test/crab/multicrab_phase2.py b/Validation/RecoParticleFlow/test/crab/multicrab_phase2.py
@@ -11,10 +11,10 @@ def submit(config):
         fi.write(config.pythonise_())
 
 samples = [
-    ("/RelValQCD_Pt-15To7000_Flat_14TeV/CMSSW_10_6_0-106X_upgrade2023_realistic_v2_2023D41noPU-v2/GEN-SIM-DIGI-RAW", "QCD_noPU_phase2"),
-    ("/RelValQCD_Pt-15To7000_Flat_14TeV/CMSSW_10_6_0-PU25ns_106X_upgrade2023_realistic_v2_2023D41PU200-v1/GEN-SIM-DIGI-RAW", "QCD_PU_phase2"),
-    #("/RelValZMM_14/CMSSW_10_6_0-106X_upgrade2023_realistic_v2_2023D41noPU-v2/GEN-SIM-DIGI-RAW", "ZMM_phase2"),
-    ("/RelValNuGun/CMSSW_10_6_0-PU25ns_106X_upgrade2023_realistic_v2_2023D41PU200-v1/GEN-SIM-DIGI-RAW", "NuGun_PU_phase2"),
+    ("/RelValQCD_Pt15To7000_Flat_14TeV/CMSSW_11_0_0-110X_mcRun4_realistic_v2_2026D49noPU-v1/GEN-SIM-DIGI-RAW", "QCD_noPU_phase2"),
+    ("/RelValQCD_Pt15To7000_Flat_14TeV/CMSSW_11_0_0-PU25ns_110X_mcRun4_realistic_v3_2026D49PU200-v1/GEN-SIM-DIGI-RAW", "QCD_PU_phase2"),
+    #("/RelValZMM_14/CMSSW_11_0_0-PU25ns_110X_mcRun4_realistic_v3_2026D49PU200-v1/GEN-SIM-DIGI-RAW", "ZMM_PU_phase2"),
+    ("/RelValNuGun/CMSSW_11_0_0-PU25ns_110X_mcRun4_realistic_v3_2026D49PU200-v1/GEN-SIM-DIGI-RAW", "NuGun_PU_phase2"),
 ]
 
 if __name__ == "__main__":

diff --git a/Validation/RecoParticleFlow/test/datasets.py b/Validation/RecoParticleFlow/test/datasets.py
@@ -28,16 +28,16 @@ def import_ROOT():
 class Dataset:
 
     """Datatype that represents a DAS dataset
-    
+
     Attributes:
         global_file_prefix (string): The ROOT TFile prefix that allows to open an LFN (/store/...)
         name (string): The DAS name of the dataset
         process (string): The nickname for the physics process that this dataset belongs to
     """
-    
+
     def __init__(self, name, process, global_file_prefix, cache_location, use_cache, tmpdir):
         """Summary
-        
+
         Args:
             name (string): The DAS name of the dataset
             process (string): The nickname for the physics process that this dataset belongs to
@@ -56,7 +56,7 @@ def __init__(self, name, process, global_file_prefix, cache_location, use_cache,
 
     def __repr__(self):
         """
-        
+
         Returns:
             string: The string representation of the Dataset
         """
@@ -65,7 +65,7 @@ def __repr__(self):
 
     def escape_name(self):
         """Removes any slashes and other characters from the name such that it can be used as a filename
-        
+
         Returns:
             string: The DAS name usable as a filename
         """
@@ -76,48 +76,48 @@ def escape_name(self):
 
     def get_das_cache_filename(self):
         """Summary
-        
+
         Returns:
             TYPE: Description
         """
 
         return os.path.join(self.tmpdir, "das_cache", self.process + ".txt")
         #return os.path.join(self.tmpdir, "das_cache", self.process + ".txt", self.escape_name() + ".txt")
-    
+
     def get_filenames(self):
         """Summary
-        
+
         Args:
             njob (TYPE): Description
-        
+
         Returns:
             TYPE: Description
         """
         ret = None
         with open(self.get_das_cache_filename(), "r") as fi:
             ret = [self.global_file_prefix + li.strip() for li in fi.readlines()]
         return ret
- 
+
     def cache_das_filenames(self):
         """Summary
-        
+
         Returns:
             TYPE: Description
         """
         LOG_MODULE_NAME.info("caching dataset {0}".format(self.name))
-        ret = subprocess.check_output('dasgoclient -dasmaps /tmp --query="file dataset={0}" --limit=0'.format(self.name), shell=True)
+        ret = subprocess.check_output('dasgoclient --query="file dataset={0}" --limit=0'.format(self.name), shell=True)
 
         target_dir = os.path.dirname(self.get_das_cache_filename())
         if not os.path.exists(target_dir):
             os.makedirs(target_dir)
-        
+
         nfiles = 0
         with open(self.get_das_cache_filename(), "w") as fi:
             for line in ret.split("\n"):
                 if line.endswith(".root"):
                     fi.write(self.global_file_prefix + line + "\n")
                     nfiles += 1
-        
+
         LOG_MODULE_NAME.info("retrieved {0} files from DAS".format(nfiles))
 
         return
@@ -129,16 +129,10 @@ def cache_das_filenames(self):
     #prefix = "root://xrootd-cms.infn.it//"
     tmpdir = "tmp"
     datasets = [
-        #Dataset("/RelValQCD_FlatPt_15_3000HS_13/CMSSW_10_6_0-106X_upgrade2018_realistic_v4-v1/GEN-SIM-DIGI-RAW", "QCD_noPU", prefix, None, False, tmpdir),
-        #Dataset("/RelValQCD_FlatPt_15_3000HS_13/CMSSW_10_6_0-PU25ns_106X_upgrade2018_realistic_v4-v1/GEN-SIM-DIGI-RAW", "QCD_PU", prefix, None, False, tmpdir),    
-        #Dataset("/RelValZMM_13/CMSSW_10_6_0-106X_upgrade2018_realistic_v4-v1/GEN-SIM-DIGI-RAW", "ZMM", prefix, None, False, tmpdir),
-        #Dataset("/RelValMinBias_13/CMSSW_10_6_0-106X_upgrade2018_design_v3-v1/GEN-SIM-DIGI-RAW", "MinBias", prefix, None, False, tmpdir),
-        #Dataset("/RelValNuGun/CMSSW_10_6_0-PU25ns_106X_upgrade2018_realistic_v4-v1/GEN-SIM-DIGI-RAW", "NuGun_PU", prefix, None, False, tmpdir)
-        Dataset("/RelValQCD_FlatPt_15_3000HS_14/CMSSW_11_0_0_patch1-110X_mcRun3_2021_realistic_v6-v1/GEN-SIM-DIGI-RAW", "QCD_noPU", prefix, None, False, tmpdir), 
-        Dataset("/RelValQCD_FlatPt_15_3000HS_14/CMSSW_11_0_0_patch1-PU_110X_mcRun3_2021_realistic_v6-v1/GEN-SIM-DIGI-RAW", "QCD_PU", prefix, None, False, tmpdir),  
-        Dataset("/RelValZMM_13/CMSSW_11_1_0-106X_upgrade2018_realistic_v4-v1/GEN-SIM-DIGI-RAW", "ZMM", prefix, None, False, tmpdir),
-        Dataset("/RelValMinBias_13/CMSSW_11_1_0-106X_upgrade2018_design_v3-v1/GEN-SIM-DIGI-RAW", "MinBias", prefix, None, False, tmpdir),
+        Dataset("/RelValQCD_FlatPt_15_3000HS_14/CMSSW_11_0_0_patch1-110X_mcRun3_2021_realistic_v6-v1/GEN-SIM-DIGI-RAW", "QCD_noPU", prefix, None, False, tmpdir),
+        Dataset("/RelValQCD_FlatPt_15_3000HS_14/CMSSW_11_0_0_patch1-PU_110X_mcRun3_2021_realistic_v6-v1/GEN-SIM-DIGI-RAW", "QCD_PU", prefix, None, False, tmpdir),
+        Dataset("/RelValZMM_14/CMSSW_11_0_0_patch1-PU_110X_mcRun3_2021_realistic_v6-v1/GEN-SIM-DIGI-RAW", "ZMM_PU", prefix, None, False, tmpdir),
         Dataset("/RelValNuGun/CMSSW_11_0_0_patch1-PU_110X_mcRun3_2021_realistic_v6-v1/GEN-SIM-DIGI-RAW", "NuGun_PU", prefix, None, False, tmpdir)]
-    
+
     for ds in datasets:
         ds.cache_das_filenames()
diff --git a/Validation/RecoParticleFlow/test/run_relval.sh b/Validation/RecoParticleFlow/test/run_relval.sh
@@ -19,22 +19,21 @@ if [ -z "$PERJOB" ]; then
 fi
 
 #
-#set default conditions - phase1 run3 
-CONDITIONS=auto:phase1_2021_realistic ERA=Run3
-#CONDITIONS=auto:phase1_2018_realistic ERA=Run2_2018 GEOM=DB:Extended
+#set default conditions - run3 2021
+CONDITIONS=auto:phase1_2021_realistic ERA=Run3 GEOM=DB.Extended
 #
-#conditions - 2017
-#CONDITIONS=auto:phase1_2017_realistic ERA=Run2_2017,run2_nanoAOD_94XMiniAODv1 GEOM=DB.Extended
+#conditions - 2018
+#CONDITIONS=auto:phase1_2018_realistic ERA=Run2_2018 GEOM=DB.Extended
 #
 #conditions - phase2
-#CONDITIONS=auto:phase2_realistic ERA=Phase2C8 GEOM=Extended2023D41
+#CONDITIONS=auto:phase2_realistic ERA=Phase2C9 GEOM=Extended2026D49
 
 #Running with 2 threads allows to use more memory on grid
 NTHREADS=2
 
 #Argument parsing
 if [ "$#" -ne 3 ]; then
-    echo "Must pass exactly 3 arguments: run_relval.sh [QCD|QCDPU|ZMM|MinBias|NuGunPU] [reco|dqm] [njob]"
+    echo "Must pass exactly 3 arguments: run_relval.sh [QCD|QCDPU|ZMMPU|NuGunPU] [reco|dqm] [njob]"
     exit 0
 fi
 
@@ -63,20 +62,17 @@ if [ "$1" == "QCD" ]; then
 elif [ "$1" == "QCDPU" ]; then
     INPUT_FILELIST=${CMSSW_BASE}/src/Validation/RecoParticleFlow/test/tmp/das_cache/QCD_PU.txt
     NAME=QCDPU
-elif [ "$1" == "ZMM" ]; then
-    INPUT_FILELIST=${CMSSW_BASE}/src/Validation/RecoParticleFlow/test/tmp/das_cache/ZMM.txt
+elif [ "$1" == "ZMMPU" ]; then
+    INPUT_FILELIST=${CMSSW_BASE}/src/Validation/RecoParticleFlow/test/tmp/das_cache/ZMM_PU.txt
     NAME=ZMM
-elif [ "$1" == "MinBias" ]; then
-    INPUT_FILELIST=${CMSSW_BASE}/src/Validation/RecoParticleFlow/test/tmp/das_cache/MinBias.txt
-    NAME=MinBias
 elif [ "$1" == "NuGunPU" ]; then
     INPUT_FILELIST=${CMSSW_BASE}/src/Validation/RecoParticleFlow/test/tmp/das_cache/NuGun_PU.txt
     NAME=NuGunPU
 elif [ "$1" == "conf" ]; then  # special switch for creating conf file, 
     INPUT_FILELIST=${CMSSW_BASE}/src/Validation/RecoParticleFlow/test/tmp/das_cache/NuGun_PU.txt # dummy
     NAME=conf
 else
-    echo "Argument 1 must be [QCD|QCDPU|ZMM|MinBias|NuGunPU|conf] but was $1"
+    echo "Argument 1 must be [QCD|QCDPU|ZMMPU|NuGunPU|conf] but was $1"
     exit 1
 fi