diff --git a/benchmarks/imaging_shower_ML/options/imaging_ml_data.py b/benchmarks/imaging_shower_ML/options/imaging_ml_data.py index 8a570becf3d517de2f5debab454badeddd71efd4..6bf9d7c1022972075c272db361a29df7ded24c41 100644 --- a/benchmarks/imaging_shower_ML/options/imaging_ml_data.py +++ b/benchmarks/imaging_shower_ML/options/imaging_ml_data.py @@ -6,7 +6,6 @@ from GaudiKernel import SystemOfUnits as units from Configurables import ApplicationMgr, EICDataSvc, PodioInput, PodioOutput, GeoSvc from GaudiKernel.SystemOfUnits import MeV, GeV, mm, cm, mrad -from Configurables import Jug__Base__InputCopier_dd4pod__Geant4ParticleCollection_dd4pod__Geant4ParticleCollection_ as MCCopier from Configurables import Jug__Digi__CalorimeterHitDigi as CalHitDigi from Configurables import Jug__Reco__CalorimeterHitReco as CalHitReco from Configurables import Jug__Reco__CalorimeterHitsMerger as CalHitsMerger @@ -38,11 +37,6 @@ podev = EICDataSvc('EventDataSvc', inputs=[f.strip() for f in kwargs['input'].sp podin = PodioInput('PodioReader', collections=['mcparticles', 'EcalBarrelHits', 'EcalBarrelScFiHits']) podout = PodioOutput('out', filename=kwargs['output']) -copier = MCCopier('MCCopier', - OutputLevel=WARNING, - inputCollection='mcparticles', - outputCollection='mcparticles2') - # Central Barrel Ecal (Imaging Cal.) becal_img_daq = dict( dynamicRangeADC=3*MeV, @@ -139,7 +133,7 @@ podout.outputCommands = [ ] ApplicationMgr( - TopAlg=[podin, copier, + TopAlg=[podin, becal_img_digi, becal_img_reco, becal_img_merger, becal_img_sorter, becal_scfi_digi, becal_scfi_reco, becal_scfi_merger, becal_scfi_sorter, becal_combiner, diff --git a/benchmarks/imaging_shower_ML/scripts/prepare_tf_dataset.py b/benchmarks/imaging_shower_ML/scripts/prepare_tf_dataset.py index 52b2d5290708e774e6c81793b2f585eb183ed21c..d94d1cb6ad9f177625367a8aa134e8da5d917018 100644 --- a/benchmarks/imaging_shower_ML/scripts/prepare_tf_dataset.py +++ b/benchmarks/imaging_shower_ML/scripts/prepare_tf_dataset.py @@ -85,8 +85,8 @@ if __name__ == '__main__': df.loc[:, 'rc'] = rc df.loc[:, 'eta'] = eta - dfm = flatten_collection(rdf, 'mcparticles2', ['genStatus', 'pdgID', 'ps.x', 'ps.y', 'ps.z', 'mass']) - dfm.rename(columns={c: c.replace('mcparticles2.', '') for c in dfm.columns}, inplace=True) + dfm = flatten_collection(rdf, 'mcparticles', ['genStatus', 'pdgID', 'ps.x', 'ps.y', 'ps.z', 'mass']) + dfm.rename(columns={c: c.replace('mcparticles.', '') for c in dfm.columns}, inplace=True) # selete incident particles dfm = dfm[dfm['genStatus'].isin([0, 1])] # NOTE: assumed single particles