#################
import ROOT, Imports, sys
from Imports import *
sys.path.append('./MassFitting/')
from fittingDict import fittingDict
getData = True # Load data.
makesWeights = True # Generate sWeights, write to workspace. Requires getData.
makeFriendTree = True # create friend tree for simple future sweight plotting. Requires makesWeights.
plotVariable = False # make an sPlot using sWeights in RooDataSet from workspace.
testFriendTree = True # test sWeights from friend tree to do an sPlot.
inputdir = "/dcache/bfys/scalo/binned_files/"
outputdir = "/dcache/bfys/cpawley/sWeights/"
cuts = Imports.getDataCuts()
#folders_dict = {"39":["2018_MagDown",2155] , "31":["2017_MagDown", 1843], "40":["2016_MagDown",1859], "41":["2015_MagDown", 579], "42":["2012_MagDown", 1155], "43":["2011_MagDown", 907], "45":["2011_MagUp", 817], "46":["2012_MagUp", 1342], "47":["2015_MagUp", 370], "48":["2016_MagUp", 1771], "49":["2017_MagUp", 1839], "50":["2018_MagUp", 2298] } #a dictionary containing the details of the all the years' data according to joblog.txt
folders_dict = {
"42": ["2012_MagDown", 1155],
"46": ["2012_MagUp", 1342]
} #a dictionary containing the details of the all the years' data according to joblog.txt
y_bins = ["_y2.0-2.5", "_y2.5-3.0", "_y3.0-3.5", "_y3.5-4.0"]
pt_bins = [
"_pt3000-4000", "_pt4000-5000", "_pt5000-6000", "_pt6000-7000",
"_pt7000-8000", "_pt8000-10000", "_pt10000-20000"
]
particle_types = ["Lc", "Xic"]
def main():
#a dictionary containing the details of the all the years' data according to joblog.txt
#Run 1 is automatically Lc, and Run 2 has particle specified.
folders_dict = DATA_jobs_Dict
path = [TUPLE_PATH_NOTRIG,TUPLE_PATH]
for PATH in path:
if PATH == TUPLE_PATH:
trig = True
else:
trig = False
#vestige of using turbo output for run 2 data. Still present in case we want to switch back to using Turbo line.
withTurbo = False
for element in folders_dict:
if int(element) > 41 and int(element) < 47:
extra_variables = [
"lcplus_Hlt1TrackAllL0Decision_TOS",
"lcplus_Hlt2CharmHadD2HHHDecision_TOS",
"lcplus_L0HadronDecision_TOS",
]
cutsRun = 1
particle = "Lc"
else:
extra_variables = [
"nSPDHits",
"nTracks",
"lcplus_L0HadronDecision_TOS",
"lcplus_Hlt1TrackMVADecision_TOS",
"lcplus_Hlt2CharmHadXicpToPpKmPipTurboDecision_TOS",
"lcplus_Hlt2CharmHadLcpToPpKmPipTurboDecision_TOS",]
particle = "Lc"
cutsRun = 2
name = folders_dict[element][0]
subjobs = folders_dict[element][1]
saving_directory = PATH + name + "_clusters/"
cuts = Imports.getDataCuts(cutsRun, trig)
if not os.path.exists(saving_directory):
os.makedirs(saving_directory)
file_directory = RAW_TUPLE_PATH + element
print ("\nStarting process for " + name)
step = subjobs//20 #carry out the process in 20 clusters of datafiles to avoid memory overflow
Max = step
Min = 0
# Loop used to apply global cuts on the data
print("Creation of Clusters")
n = 20
i = 0
while (Max <= subjobs):
#FOR THE PROGRASSION BAR
if i < n:
j = (i + 1) / n
sys.stdout.write('\r')
sys.stdout.write("[%-20s] %d%%" % ('='*int(20*j), 100*j))
sys.stdout.flush()
i += 1
if Max == Min:
break
strip_n_save(Min, Max, cuts, file_directory, saving_directory, extra_variables, particle)
temp = Max
if (Max+step > subjobs):
Max = subjobs
else:
Max += step
Min = temp
clusters = os.listdir(saving_directory)
print("\n\nTChaining the clusters")
final_chain = TChain("DecayTree")
n = len(clusters)
i = 0
for element in clusters:
if i < n:
j = (i + 1) / n
sys.stdout.write('\r')
sys.stdout.write("[%-20s] %d%%" % ('='*int(20*j), 100*j))
sys.stdout.flush()
i += 1
final_chain.Add(saving_directory + element)
if not os.path.exists(PATH + name + "/bins"):
os.makedirs(PATH + name + "/bins")
saving_dir = PATH + name + "/bins/"
print("\n\nCreating the final files")
split_in_bins_n_save(final_chain, saving_dir, withTurbo, particle) # split the datafile into mass-y-pt bins
print ("\nProcess completed for " + name)
#CREATION OF THE TOTAL YEAR DATA FILES (e.g. 2012_MagUp/Xic_Total.root)
print("\Creation of the Total Year data files")
mother_particle = ["Xic", "Lc"]
BASE_PATH = PATH
n = len(os.listdir(BASE_PATH))
p = 0
for i in os.listdir(BASE_PATH):
if p < n:
j = (p + 1) / n
sys.stdout.write('\r')
sys.stdout.write("[%-20s] %d%%" % ('='*int(20*j), 100*j))
sys.stdout.flush()
p += 1
if "cluster" in i:
continue
for part in mother_particle:
totfile = ROOT.TFile.Open(BASE_PATH + i + "/{}_total.root".format(part),"RECREATE")
totfile.cd()
tree = TChain("DecayTree")
for j in os.listdir(BASE_PATH + i +"/bins/ybins"):
if part in j:
tree.Add(BASE_PATH + i +"/bins/ybins/"+j)
tree.Write()
totfile.Close()
del totfile
print("\nDeleting Clusters")
os.system("rm -rf {}*_clusters".format(BASE_PATH))
print("\nNTuple Preparation is done, happy analysis!")
def main(argv):
ROOT.gROOT.SetBatch(True) #STOP SHOWING THE GRAPH FOR ROOT
try:
opts, args = getopt.getopt(argv, "hstp")
except getopt.GetoptError:
print("The arguments are wrong")
sys.exit(2)
options = []
arguments = []
for opt, arg in opts:
options.append(opt)
arguments.append(arg)
if not options:
options = ["-s", "-t", "-p"]
if "-h" in options:
print(
textwrap.dedent("""\
Welcome to the efficiencies.py script.
The parameters are
-h : help
-s : Selection
-t : Trigger
-p : PID
Running with no parameter will output all the data at once.
"""))
sys.exit()
for opt in options:
if opt == "-s":
selecEffDict = {}
years = []
print("\nCreation of the selection efficiency files")
n = len(MC_jobs_Dict)
i = 0
for job in MC_jobs_Dict:
#FOR THE PROGRESSION BAR
if i < n:
j = (i + 1) / n
sys.stdout.write('\r')
sys.stdout.write("[%-20s] %d%%" %
('=' * int(20 * j), 100 * j))
sys.stdout.flush()
i += 1
if job == "NA":
continue
particle = MC_jobs_Dict[job][3]
year = MC_jobs_Dict[job][0]
pol = MC_jobs_Dict[job][1]
subjobs = MC_jobs_Dict[job][2]
identifier = MC_jobs_Dict[job][4]
if year not in years:
years.append(year)
filename = "MC_Lc2pKpiTuple_" + identifier + ".root"
if int(year) <= 2012:
run = 1
cuts = Imports.getDataCuts(run)
else:
run = 2
cuts = Imports.getDataCuts(run)
Lc_MC_tree = TChain(
"tuple_Lc2pKpi/DecayTree"
) # !!! QUESTION : NOT BETTER ISTEAD OF CHAIN; JUST GETENTRIES FROM EACH ONE BY ONE, ONCE WITHOUT CUT AND ONCE WITH?
for subjob in os.listdir(RAW_TUPLE_PATH + job):
Lc_MC_tree.Add(RAW_TUPLE_PATH + job + "/" + subjob + "/" +
filename)
N = float(Lc_MC_tree.GetEntries()
) #WHY DID SIMON USE A HARDCODED NUMBER OF ENTRIES??
#k = float(Lc_MC_tree.GetEntries(cuts + " && " + turbo)) SIMON VERSION
k = float(Lc_MC_tree.GetEntries(cuts))
eff = float(k / N)
binom_error = (1 / N) * ((k * (1 - k / N))**(0.5))
selecEffDict[particle + "_" + str(year) + "_" + pol] = {
'val': eff,
'err': binom_error
}
print("\nSelection efficiency calculations are done!")
latexTable(selecEffDict, years, "Selection")
prettyEffDict = pprint.pformat(selecEffDict)
dictF = open(dict_path + "Selection_Eff_Dict.py", "w")
dictF.write("selDict = " + str(prettyEffDict))
dictF.close()
elif opt == "-t":
print("\nCreation of the trigger efficiency files")
trigEffDict = {}
years = []
n = len(MC_jobs_Dict)
i = 0
for job in MC_jobs_Dict:
#FOR THE PROGRESSION BAR
if i < n:
j = (i + 1) / n
sys.stdout.write('\r')
sys.stdout.write("[%-20s] %d%%" %
('=' * int(20 * j), 100 * j))
sys.stdout.flush()
i += 1
if job == "NA":
continue
particle = MC_jobs_Dict[job][3]
year = MC_jobs_Dict[job][0]
pol = MC_jobs_Dict[job][1]
subjobs = MC_jobs_Dict[job][2]
identifier = MC_jobs_Dict[job][4]
if year not in years:
years.append(year)
filename = "MC_Lc2pKpiTuple_" + identifier + ".root"
if int(year) <= 2012:
run = 1
cuts = "lcplus_L0HadronDecision_TOS == 1 && lcplus_Hlt1TrackAllL0Decision_TOS == 1"
turbo = "lcplus_Hlt2CharmHadD2HHHDecision_TOS==1"
else:
run = 2
cuts = Imports.getDataCuts(run)
turbo = "lcplus_Hlt1TrackMVADecision_TOS==1"
#WHAT DO I NEED FOR TRIGGER CUTS?!!
Lc_MC_tree = TChain(
"tuple_Lc2pKpi/DecayTree"
) # !!! QUESTION : NOT BETTER ISTEAD OF CHAIN; JUST GETENTRIES FROM EACH ONE BY ONE, ONCE WITHOUT CUT AND ONCE WITH?
for subjob in os.listdir(RAW_TUPLE_PATH + job):
Lc_MC_tree.Add(RAW_TUPLE_PATH + job + "/" + subjob + "/" +
filename)
N = float(
Lc_MC_tree.GetEntries(
turbo + " && lcplus_L0HadronDecision_TOS==1"))
k = float(Lc_MC_tree.GetEntries(cuts + " && " + turbo))
eff = float(k / N)
binom_error = (1 / N) * ((k * (1 - k / N))**(0.5))
trigEffDict[particle + "_" + str(year) + "_" + pol] = {
'val': eff,
'err': binom_error
}
print("\nTrigger efficiency calculations are done!")
latexTable(trigEffDict, years, "Trigger")
prettyEffDict = pprint.pformat(trigEffDict)
dictF = open(dict_path + "Trigger_Eff_Dict.py", "w")
dictF.write("trigDict = " + str(prettyEffDict))
dictF.close()
elif opt == "-p":
pass
else:
sys.exit()
def main(script_run):
print ("Starting main")
#If you want to test on a small portion of data, then enable it here and add the data to the dictionary below
TESTING = True
if(TESTING):
folders_dict = {"115":["2016_MagDown",186,"Xic"]}
else:
#Dictionary for all the data
folders_dict = DATA_jobs_Dict
#Path to save the tuples
PATH = TUPLE_PATH+script_run+"/"
if not os.path.exists(PATH):
os.makedirs(PATH)
blind_data = True
makeFile(PATH, script_run, dictionary = folders_dict, blinded = blind_data)
useful_variables = []
if(blind_data):
variables = ["lcplus_MM",
"lcplus_P",
"lcplus_PT",
"lcplus_IPCHI2_OWNPV",
"lcplus_OWNPV_CHI2",
"lcplus_IP_OWNPV",
"lcplus_L0HadronDecision_TOS",
"lcplus_FD_OWNPV",
"lcplus_ENDVERTEX_CHI2",
"lcplus_ENDVERTEX_NDOF",
"lcplus_RAPIDITY",
"piplus_RAPIDITY",
"pplus_RAPIDITY",
"kminus_RAPIDITY",
"pplus_M",
"pplus_P",
"pplus_PT",
"pplus_ProbNNp",
"pplus_OWNPV_CHI2",
"kminus_OWNPV_CHI2",
"piplus_OWNPV_CHI2",
"piplus_M",
"piplus_P",
"piplus_PT",
"piplus_PIDK",
"piplus_PIDp",
"piplus_ProbNNpi",
"piplus_IP_OWNPV",
"pplus_PIDp",
"pplus_PIDK",
"kminus_M",
"kminus_P",
"kminus_PT",
"kminus_ProbNNk",
"kminus_PIDK",
"kminus_PIDp",
"PVNTRACKS",
"pplus_IP_OWNPV",
"kminus_IP_OWNPV",
"kminus_IPCHI2_OWNPV",
"piplus_IPCHI2_OWNPV",
"pplus_IPCHI2_OWNPV",
"pplus_TRACK_PCHI2",
"piplus_TRACK_PCHI2",
"kminus_TRACK_PCHI2",
"pplus_MC15TuneV1_ProbNNp",
"pplus_MC15TuneV1_ProbNNk",
"pplus_MC15TuneV1_ProbNNpi",
"pplus_MC15TuneV1_ProbNNghost",
"kminus_MC15TuneV1_ProbNNp",
"kminus_MC15TuneV1_ProbNNk",
"kminus_MC15TuneV1_ProbNNpi",
"kminus_MC15TuneV1_ProbNNghost",
"piplus_MC15TuneV1_ProbNNp",
"piplus_MC15TuneV1_ProbNNk",
"piplus_MC15TuneV1_ProbNNpi",
"piplus_MC15TuneV1_ProbNNghost"]
useful_variables = variables
else:
variables = ["lcplus_MM",
"lcplus_P",
"lcplus_PT",
"lcplus_ETA",
"lcplus_RAPIDITY",
"lcplus_TIP",
"lcplus_IPCHI2_OWNPV",
"lcplus_OWNPV_CHI2",
"lcplus_TAU",
"lcplus_L0HadronDecision_TOS",
"lcplus_FD_OWNPV",
"pplus_M",
"pplus_P",
"pplus_PT",
"pplus_RAPIDITY",
"pplus_ETA",
"pplus_ProbNNp",
"piplus_M",
"piplus_P",
"piplus_PT",
"piplus_RAPIDITY",
"piplus_ETA",
"piplus_ProbNNpi",
"pplus_PIDp",
"kminus_M",
"kminus_P",
"kminus_PT",
"kminus_RAPIDITY",
"piplus_IP_OWNPV",
"kminus_ETA",
"kminus_ProbNNk",
"kminus_PIDK",
"PVNTRACKS",
"piplus_PX",
"pplus_PX",
"kminus_PX",
"piplus_PY",
"pplus_PY",
"kminus_PY",
"piplus_PZ",
"pplus_PZ",
"kminus_PZ",
"pplus_IP_OWNPV",
"kminus_IP_OWNPV",
"kminus_IPCHI2_OWNPV",
"piplus_IPCHI2_OWNPV",
"pplus_IPCHI2_OWNPV"]
useful_variables = variables
appendVars(PATH, script_run, variables = useful_variables)
for element in folders_dict:
if int(element) > 41 and int(element) < 47:
extra_variables = ["lcplus_Hlt1TrackAllL0Decision_TOS", "lcplus_Hlt2CharmHadD2HHHDecision_TOS","*L0*","*Hlt*","*HLT*"]
run = 1
particle = "Lc"
else:
extra_variables = ["nSPDHits", "nTracks", "lcplus_Hlt1TrackMVADecision_TOS"]
particle = folders_dict[element][2]
run = 2
for extra_variable in extra_variables:
if not (extra_variable == ""):
#If an extra variable is needed, it will be appended
useful_variables.append(extra_variable)
subjobs = folders_dict[element][1]
if (blind_data):
name = folders_dict[element][0]+"_blinded"
else:
name = folders_dict[element][0]
saving_directory = PATH+name+"_clusters/"
cuts = Imports.getDataCuts(run, blinded = blind_data)
if not os.path.exists(saving_directory):
os.makedirs(saving_directory)
file_directory = RAW_TUPLE_PATH+element
print("\nStarting process for "+name)
#Carries out the process in steps of 20
step = subjobs//20
Max = step
Min = 0
#Clusters are created here
print("Creation of clusters")
n = 20
i = 0
while (Max<=subjobs):
#Progress bar
if (i<n):
j = (i+1)/n
sys.stdout.write("\r")
sys.stdout.write("[%-20s] %d%%" % ('='*int(20*j), 100*j))
sys.stdout.flush()
i+=1
if (Max == Min):
break
strip_and_save(Min, Max, cuts, file_directory, saving_directory, useful_variables, particle)
temp = Max
if (Max+step > subjobs):
Max = subjobs
else:
Max+=step
Min = temp
clusters = os.listdir(saving_directory)
print("\n\nTChaining the clusters")
final_chain = TChain("DecayTree")
n = len(clusters)
i = 0
for element in clusters:
if (i<n):
j = (i+1)/n
sys.stdout.write('\r')
sys.stdout.write("[%-20s] %d%%" % ('='*int(20*j), 100*j))
sys.stdout.flush()
i += 1
final_chain.Add(saving_directory+element)
if not os.path.exists(PATH+name+"/bins"):
os.makedirs(PATH+name+"/bins")
saving_directory = PATH+name+"/bins/"
print("\n\nCreating the final files")
split_in_bins_and_save(final_chain, saving_directory, run, useful_variables, particle)
print("\nProcess completed for "+name)
#Creation of the total Year Data files
print("\nCreation of the total year data files")
mother_particle = ["Xic","Lc"]
BASE_PATH = TUPLE_PATH+script_run+"/"
n = len(os.listdir(BASE_PATH))
p = 0
for i in os.listdir(BASE_PATH):
if (p < n):
j = (p + 1) / n
sys.stdout.write('\r')
sys.stdout.write("[%-20s] %d%%" % ('='*int(20*j), 100*j))
sys.stdout.flush()
p += 1
if "description" in i:
continue
if "cluster" in i:
continue
for particle in mother_particle:
totfile = ROOT.TFile.Open(BASE_PATH+i+"/{}_total.root".format(particle),"RECREATE")
totfile.cd()
tree = TChain("DecayTree")
for j in os.listdir(BASE_PATH+i+"/bins/ybins"):
if particle in j:
tree.Add(BASE_PATH+i+"/bins/ybins/"+j)
tree.Write()
totfile.Close()
del totfile
print("\nDeleting clusters")
os.system("rm -rf {}*_clusters".format(BASE_PATH))
print("\nNTuple preparation is done")