def multi_skim_allperiods(self):
for indexp in range(self.prodnumber):
self.process_listsample[indexp].process_skim_par()
mergerootfiles(self.lper_evtorigroot, self.f_evtorigroot_mergedallp)
if self.p_dofullevtmerge is True:
merge_method(self.lper_evt, self.f_evt_mergedallp)
merge_method(self.lper_evtorig, self.f_evtorig_mergedallp)
def process_mergedec(self):
for ipt in range(self.p_nptbins):
merge_method(self.mptfiles_recoskmldec[ipt],
self.lpt_recodecmerged[ipt])
if self.mcordata == "mc":
merge_method(self.mptfiles_gensk[ipt],
self.lpt_gendecmerged[ipt])
def process_skim_par(self):
print("doing skimming", self.mcordata, self.period)
create_folder_struc(self.d_pklsk, self.l_path)
arguments = [(i, ) for i in range(len(self.l_reco))]
self.parallelizer(self.skim, arguments, self.p_chunksizeskim)
merge_method(self.l_evt, self.f_totevt)
merge_method(self.l_evtorig, self.f_totevtorig)
def multi_mergeml_allinone(self):
for ipt in range(self.p_nptbins):
merge_method(self.lptper_recoml[ipt], self.lpt_recoml_mergedallp[ipt])
for ipt in range(self.p_nptbins):
if self.mcordata == "mc":
merge_method(self.lptper_genml[ipt], self.lpt_genml_mergedallp[ipt])
merge_method(self.lper_evtml, self.f_evtml_mergedallp)
merge_method(self.lper_evtorigml, self.f_evtorigml_mergedallp)
if self.v_max_ncand_merge > 0:
for ipt in range(self.p_nptbins):
merge_method(self.lptper_recomlmax[ipt], self.lpt_recoml_mergedallpmax[ipt])
def multi_mergeml_allinone(self):
for ipt in range(self.p_nptbins):
merge_method(self.lptper_recoml[ipt],
self.lpt_recoml_mergedallp[ipt])
if self.mcordata == "mc":
merge_method(self.lptper_genml[ipt],
self.lpt_genml_mergedallp[ipt])
count_evt = 0
count_evtorig = 0
for evt_count_file in self.lper_evt_count_ml:
count_dict = parse_yaml(evt_count_file)
count_evt += count_dict["evt"]
count_evtorig += count_dict["evtorig"]
dump_yaml_from_dict({
"evt": count_evt,
"evtorig": count_evtorig
}, self.f_evtml_count)
def process_mergeforml(self):
indices_for_evt = []
for ipt in range(self.p_nptbins):
nfiles = len(self.mptfiles_recosk[ipt])
if not nfiles:
print("There are no files to be merged")
sys.exit(1)
print(f"Use merge fraction {self.p_frac_merge[ipt]} for pT bin {ipt}")
ntomerge = int(nfiles * self.p_frac_merge[ipt])
rd.seed(self.p_rd_merge)
filesel = rd.sample(range(0, nfiles), ntomerge)
indices_for_evt = list(set(indices_for_evt) | set(filesel))
list_sel_recosk = [self.mptfiles_recosk[ipt][j] for j in filesel]
merge_method(list_sel_recosk, self.lpt_reco_ml[ipt])
if self.mcordata == "mc":
list_sel_gensk = [self.mptfiles_gensk[ipt][j] for j in filesel]
merge_method(list_sel_gensk, self.lpt_gen_ml[ipt])
print("Count events...")
list_sel_evt = [self.l_evt[j] for j in indices_for_evt]
list_sel_evtorig = [self.l_evtorig[j] for j in indices_for_evt]
count_dict = {"evt": count_df_length_pkl(*list_sel_evt),
"evtorig": count_df_length_pkl(*list_sel_evtorig)}
dump_yaml_from_dict(count_dict, self.f_evt_count_ml)
def process_mergeforml(self):
nfiles = len(self.mptfiles_recosk[0])
if nfiles == 0:
print("increase the fraction of merged files or the total number")
print(" of files you process")
ntomerge = (int)(nfiles * self.p_frac_merge)
rd.seed(self.p_rd_merge)
filesel = rd.sample(range(0, nfiles), ntomerge)
for ipt in range(self.p_nptbins):
list_sel_recosk = [self.mptfiles_recosk[ipt][j] for j in filesel]
merge_method(list_sel_recosk, self.lpt_reco_ml[ipt])
if self.mcordata == "mc":
list_sel_gensk = [self.mptfiles_gensk[ipt][j] for j in filesel]
merge_method(list_sel_gensk, self.lpt_gen_ml[ipt])
list_sel_evt = [self.l_evt[j] for j in filesel]
list_sel_evtorig = [self.l_evtorig[j] for j in filesel]
merge_method(list_sel_evt, self.f_evt_ml)
merge_method(list_sel_evtorig, self.f_evtorig_ml)
def process_mergeforml(self):
print("doing merging", self.mcordata, self.period)
nfiles = len(self.mptfiles_recosk[0])
if nfiles == 0:
print("increase the fraction of merged files or the total number")
print(" of files you process")
for ipt in range(self.p_nptbins):
ntomerge = (int)(nfiles * self.p_frac_merge[ipt])
rd.seed(self.p_rd_merge
) #make sure we start with the same files for each pT bin
filesel = rd.sample(range(0, nfiles), ntomerge)
list_sel_recosk = [self.mptfiles_recosk[ipt][j] for j in filesel]
merge_method(list_sel_recosk, self.lpt_reco_ml[ipt])
if self.mcordata == "mc":
list_sel_gensk = [self.mptfiles_gensk[ipt][j] for j in filesel]
merge_method(list_sel_gensk, self.lpt_gen_ml[ipt])
#only merge event for first pT bin (smallest)
if ipt == 0:
list_sel_evt = [self.l_evt[j] for j in filesel]
list_sel_evtorig = [self.l_evtorig[j] for j in filesel]
merge_method(list_sel_evt, self.f_evt_ml)
merge_method(list_sel_evtorig, self.f_evtorig_ml)
def multi_skim_allperiods(self):
for indexp in range(self.prodnumber):
self.process_listsample[indexp].process_skim_par()
merge_method(self.lper_evt, self.f_evt_mergedallp)
merge_method(self.lper_evtorig, self.f_evtorig_mergedallp)