def invokeGen(infile):
if infile[-6:] == '.djcdc':
dc = DataCollection(infile)
td = dc.dataclass()
tdclass = dc.dataclass
dc.setBatchSize(1)
gen = dc.invokeGenerator()
elif infile[-6:] == '.djctd':
td = TrainData_NanoML()
tdclass = TrainData_NanoML
td.readFromFile(infile)
gen = TrainDataGenerator()
gen.setBatchSize(1)
gen.setBuffer(td)
elif infile[-5:] == '.root':
print('reading from root file')
td = TrainData_NanoML()
tdclass = TrainData_NanoML
td.readFromSourceFile(infile,{},True)
td.writeToFile(infile+'.djctd')
td.readFromFile(infile+'.djctd')
gen = TrainDataGenerator()
gen.setBatchSize(1)
gen.setBuffer(td)
gen.setSkipTooLargeBatches(False)
nevents = gen.getNBatches()
gen.cast_to = tdclass
return gen.feedTrainData,nevents,td
parser = ArgumentParser('')
parser.add_argument('--inputFile')
parser.add_argument('--outputDir')
#parser.add_argument('--outName', default='recHits_3D.html',type=str)
args = parser.parse_args()
infile = args.inputFile
outdir = args.outputDir + "/"
events_max = 1
os.system('mkdir -p ' + outdir)
#outfile = args.outName
#if not outfile[-5:] == ".html":
# outfile+=".html"
td = TrainData_NanoML()
td.readFromFile(infile)
#for event_num in range(1,17,2): #looking at jsut one half of event
for event_num in range(1, 2, 2): #looking at jsut one half of event
df = (td.createPandasDataFrame(event_num)
) #[:1000] just looking at some 1000 hits
front_face_z = 323
noise_filter = (df['truthHitAssignementIdx'] > -1)
#hgcal_front_face_filter = (abs(df['truthHitAssignedZ']) < front_face_z) # < - on front, > not on front
hgcal_front_face_filter = (df['truthHitFullyContainedFlag'] > 0)
selected_pids = [22, 11, 211, 2211, 13, 2112]
pid_filter = np.isin(abs(df['truthHitAssignedPIDs']), selected_pids)
filt = noise_filter & hgcal_front_face_filter #if including the filter np.logical_not(pid_filter)
df = df[filt]
spectator_filter = (df['truthHitSpectatorFlag'] > 7)
df_spectators_only = df[spectator_filter]