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)
if self.p_dofullevtmerge is True:
merge_method(self.l_evt, self.f_totevt)
merge_method(self.l_evtorig, self.f_totevtorig)
def process_valevents_par(self):
print("doing event validation", self.mcordata, self.period)
create_folder_struc(self.d_val, self.l_path)
tmp_merged = f"/data/tmp/hadd/{self.case}_{self.typean}/val_{self.period}/{get_timestamp_string()}/"
arguments = [(i, ) for i in range(len(self.l_evtorig))]
self.parallelizer(self.process_valevents, arguments,
self.p_chunksizeskim)
mergerootfiles(self.l_evtvalroot, self.f_totevtvalroot, tmp_merged)
def plot_jet_lambda(self):
# Create directroy to save files
pTbins_ranges = get_pT_bin_list(self.pTbins)
create_folder_struc(self.j_dir, pTbins_ranges)
# Get the list of dataframes containing lambdas info per pT bin, beta, & jet R
lambdas_per_bin = self.calc_jet_lambda()
# Make plots per jet pT bin
print("Plotting jet lambda observable per pT bin")
for i, pTmin in list(enumerate(self.pTbins))[0:-1]:
pTmax = self.pTbins[i + 1]
fig, a = self.initialize_lambda_plots(pTmin, pTmax)
# Create subplot per jet R and beta (for each individual pT bin)
for j, jetR in enumerate(self.jetRadii):
for k, beta in enumerate(self.betas):
#lambda_list = lambdas_per_bin[i].at[beta, jetR]
binned_lambdas = lambdas_per_bin[i][j][k]
ax = a[k, j]
''' old df sln
# Normalize histogram by 1/N
wg = np.ones(len(lambda_list)) / len(lambda_list)
# Approx bin size for good statistics
n_bins = 100 #len(lambda_list) // (5 * 10**4) + 1
# Make the subplot a histogram
n, bins, patches = ax.hist(lambda_list, range=(0, 0.6), bins=n_bins, weights=wg)
'''
wg = sum(binned_lambdas)
x = [ (i + 0.5) * self.lambda_max / self.n_lambda_bins
for i in range(self.n_lambda_bins) ]
ax.bar(x, binned_lambdas/wg, width=(self.lambda_max / self.n_lambda_bins), align='center')
#ax.set_ylim(top=max(binned_lambdas/wg))
# Scientific notation on y-axis
#ax.ticklabel_format(style='sci', axis='y', scilimits=(0,0))
# Add labels to sub axes
ax.set_title(r"$\beta = " + str(beta) + "$, $R = " +
str(jetR) + "$, $N = " + str(wg) + '$')
ax.set_ylabel(r"$\frac{1}{N}\frac{dN}{d\lambda_\beta}$")
ax.set_xlabel(r"$\lambda_\beta$")
#if j == 0:
# ax.set_ylabel(r"$\beta = " + str(beta) + '$')
#if k == (len(self.betas) - 1):
# ax.set_xlabel(r"$R = " + str(jetR) + '$')
# Save plot
plt.subplots_adjust(left = 0.08, right = .97, top = 0.92, bottom = 0.08, wspace = 0.3, hspace = 0.3)
out_dir = concat_dir(self.j_dir, pTbins_ranges[i])
fig.savefig('%s/lambda.png' % out_dir)
print("Lambda plots successfully saved")
return 0
def plot_gen_jet(self):
# Create directroy to save files
pTbins_ranges = get_pT_bin_list(self.pTbins)
create_folder_struc(self.j_dir, pTbins_ranges)
# Get the dataframes containing relevant general info
N_constit, pT_dist, z_dist = self.calc_gen_jet()
# Make general plots
print("Plotting general jet distributions")
fig_pT, a_pT = self.initialize_gen_plot("Jet pT distribution")
fig_N, a_N = self.initialize_gen_plot("Jet constituent multiplicity distribution")
fig_z, a_z = self.initialize_gen_plot("Jet z=pT,track/pT,jet distribution")
for i, jetR in enumerate(self.jetRadii):
ax = a_pT[0, i]
pT_list = pT_dist[jetR]
n, bins, patches = ax.hist(pT_list)
# Scientific notation on y-axis
ax.ticklabel_format(style='sci', axis='y', scilimits=(0,0))
# Add labels to sub axes
ax.set_title(r"$R = " + str(jetR) + '$')
ax.set_ylabel(r"$\frac{dN}{dp_T}$")
ax.set_xlabel(r"$p_T$")
ax = a_N[0, i]
N_list = N_constit[jetR]
n, bins, patches = ax.hist(N_list)
# Scientific notation on y-axis
ax.ticklabel_format(style='sci', axis='y', scilimits=(0,0))
# Add labels to sub axes
ax.set_title(r"$R = " + str(jetR) + '$')
ax.set_ylabel(r"$\frac{dN}{dN_{constit}}$")
ax.set_xlabel(r"$N_{constit}$")
ax = a_z[0, i]
z_list = z_dist[jetR]
n, bins, patches = ax.hist(z_list)
# Scientific notation on y-axis
ax.ticklabel_format(style='sci', axis='y', scilimits=(0,0))
# Add labels to sub axes
ax.set_title(r"$R = " + str(jetR) + '$')
ax.set_ylabel(r"$\frac{dN}{dz}$")
ax.set_xlabel(r"$z$")
# Save plots
fig_pT.savefig('%s/pT_dist.png' % self.j_dir)
fig_N.savefig('%s/N_dist.png' % self.j_dir)
fig_z.savefig('%s/z_dist.png' % self.j_dir)
print("General jet plots successfully saved.")
return 0
def process_efficiency(self):
print("Doing efficiencies", self.mcordata, self.period)
print("Using run selection for eff histo", \
self.runlistrigger[self.triggerbit], "for period", self.period)
if self.doml is True:
print("Doing ml analysis")
else:
print("No extra selection needed since we are doing std analysis")
create_folder_struc(self.d_results, self.l_path)
arguments = [(i,) for i in range(len(self.l_root))]
self.parallelizer(self.process_efficiency_single, arguments, self.p_chunksizeunp)
tmp_merged = f"/data/tmp/hadd/{self.case}_{self.typean}/histoeff_{self.period}/{get_timestamp_string()}/" # pylint: disable=line-too-long
mergerootfiles(self.l_histoeff, self.n_fileeff, tmp_merged)
def process_histomass(self):
print("Doing masshisto", self.mcordata, self.period)
print("Using run selection for mass histo", \
self.runlistrigger, "for period", self.period)
if self.doml is True:
print("Doing ml analysis")
else:
print("No extra selection needed since we are doing std analysis")
create_folder_struc(self.d_results, self.l_path)
arguments = [(i,) for i in range(len(self.l_root))]
self.parallelizer(self.process_histomass_single, arguments, self.p_chunksizeunp)
tmp_merged = \
f"/data/tmp/hadd/{self.case}_{self.typean}/mass_{self.period}/{get_timestamp_string()}/"
mergerootfiles(self.l_histomass, self.n_filemass, tmp_merged)
def process_efficiency(self):
print("Doing efficiencies", self.mcordata, self.period)
print("Using run selection for eff histo", \
self.runlistrigger, "for period", self.period)
if self.doml is True:
print("Doing ml analysis")
else:
print("No extra selection needed since we are doing std analysis")
for ibin2 in range(len(self.lvar2_binmin)):
if self.corr_eff_mult[ibin2] is True:
print("Reweighting efficiencies for bin", ibin2)
else:
print("Not reweighting efficiencies for bin", ibin2)
create_folder_struc(self.d_results, self.l_path)
arguments = [(i,) for i in range(len(self.l_root))]
self.parallelizer(self.process_efficiency_single, arguments, self.p_chunksizeunp)
tmp_merged = f"/data/tmp/hadd/{self.case}_{self.typean}/histoeff_{self.period}/{get_timestamp_string()}/"
mergerootfiles(self.l_histoeff, self.n_fileeff, tmp_merged)
def process_applymodel_par(self):
print("doing apply model", self.mcordata, self.period)
create_folder_struc(self.d_pkl_dec, self.l_path)
for ipt in range(self.p_nptbins):
arguments = [(i, ) for i in range(len(self.mptfiles_recosk[ipt]))]
self.parallelizer(self.applymodel, arguments, self.p_chunksizeskim)
def process_unpack_par(self):
print("doing unpacking", self.mcordata, self.period)
create_folder_struc(self.d_pkl, self.l_path)
arguments = [(i, ) for i in range(len(self.l_root))]
self.parallelizer(self.unpack, arguments, self.p_chunksizeunp)
def process_valevents_par(self):
print("doing event validation", self.mcordata, self.period)
create_folder_struc(self.d_val, self.l_path)
arguments = [(i,) for i in range(len(self.l_evtorig))]
self.parallelizer(self.process_valevents, arguments, self.p_chunksizeskim)
mergerootfiles(self.l_evtvalroot, self.f_totevtvalroot)