def bparking_binned(dir, test, egamma, has_pfgsf_branches=True, AxE=True):
print(
'##### BPARKING BINNED ##########################################################'
)
#############
# ROC CURVE #
#############
plt.figure(figsize=(6, 6))
ax = plt.subplot(111)
plt.title('Low-pT electron performance (BParking)')
plt.xlim(1.e-4, 1.)
plt.ylim([0., 1.])
plt.xlabel('Mistag rate (w.r.t. KF tracks, pT > 0.5 GeV)')
plt.ylabel('Efficiency (w.r.t. KF tracks, pT > 0.5 GeV)')
ax.tick_params(axis='x', pad=10.)
plt.gca().set_xscale('log')
plt.grid(True)
########################################
# "by chance" line
plt.plot(np.arange(0., 1.,
plt.xlim()[0]),
np.arange(0., 1.,
plt.xlim()[0]),
ls='dotted',
lw=0.5,
label="By chance")
########################################
# Electron (pT > 0.5 GeV, VL WP for Seed BDT)
has_trk = (test.has_trk) & (test.trk_pt > 0.5) & (np.abs(test.trk_eta) <
2.5)
has_ele = (test.has_ele) & (test.ele_pt > 0.5) & (np.abs(test.ele_eta) <
2.5)
denom = has_trk & test.is_e
numer = has_ele & denom
ele_eff = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
denom = has_trk & (~test.is_e)
numer = has_ele & denom
ele_fr = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
plt.plot(
[ele_fr],
[ele_eff],
marker='o',
markerfacecolor='blue',
markeredgecolor='blue',
markersize=8,
linestyle='none',
label='Low-pT electron',
)
id_branch = 'ele_mva_value_depth15'
id_fpr, id_tpr, id_score = roc_curve(test.is_e[has_ele],
test[id_branch][has_ele])
id_auc = roc_auc_score(
test.is_e[has_ele],
test[id_branch][has_ele]) if len(set(test.is_e[has_ele])) > 1 else 0.
plt.plot(id_fpr * ele_fr,
id_tpr * ele_eff,
linestyle='solid',
color='blue',
linewidth=1.0,
label='ID, 2020Feb24 (AUC={:.3f})'.format(id_auc))
########################################
# Electron (pT > 2.0 GeV, VL WP for Seed BDT)
has_trk = (test.has_trk) & (test.trk_pt > 0.5) & (np.abs(test.trk_eta) <
2.5)
has_ele = (test.has_ele) & (test.ele_pt > 0.5) & (np.abs(
test.ele_eta) < 2.5) & (test.ele_pt > 2.0)
denom = has_trk & test.is_e
numer = has_ele & denom
ele_high_eff = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
denom = has_trk & (~test.is_e)
numer = has_ele & denom
ele_high_fr = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
plt.plot(
[ele_high_fr],
[ele_high_eff],
marker='^',
markerfacecolor='blue',
markeredgecolor='blue',
markersize=8,
linestyle='none',
label='pT > 2.0 GeV',
)
id_high_branch = 'ele_mva_value_depth15'
id_high_fpr, id_high_tpr, id_high_score = roc_curve(
test.is_e[has_ele], test[id_high_branch][has_ele])
id_high_auc = roc_auc_score(test.is_e[has_ele],
test[id_high_branch][has_ele]) if len(
set(test.is_e[has_ele])) > 1 else 0.
plt.plot(
id_high_fpr * ele_high_fr,
id_high_tpr * ele_high_eff,
linestyle='dotted',
color='blue',
linewidth=1.0,
#label='ID, 2020Feb24 (AUC={:.3f})'.format(id_high_auc)
)
########################################
# Electron (pT < 2.0 GeV, VL WP for Seed BDT)
has_trk = (test.has_trk) & (test.trk_pt > 0.5) & (np.abs(test.trk_eta) <
2.5)
has_ele = (test.has_ele) & (test.ele_pt > 0.5) & (np.abs(
test.ele_eta) < 2.5) & (test.ele_pt < 2.0)
denom = has_trk & test.is_e
numer = has_ele & denom
ele_low_eff = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
denom = has_trk & (~test.is_e)
numer = has_ele & denom
ele_low_fr = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
plt.plot(
[ele_low_fr],
[ele_low_eff],
marker='v',
markerfacecolor='blue',
markeredgecolor='blue',
markersize=8,
linestyle='none',
label='pT < 2.0 GeV',
)
id_low_branch = 'ele_mva_value_depth15'
id_low_fpr, id_low_tpr, id_low_score = roc_curve(
test.is_e[has_ele], test[id_low_branch][has_ele])
id_low_auc = roc_auc_score(test.is_e[has_ele],
test[id_low_branch][has_ele]) if len(
set(test.is_e[has_ele])) > 1 else 0.
plt.plot(id_low_fpr * ele_low_fr,
id_low_tpr * ele_low_eff,
linestyle='dotted',
color='blue',
linewidth=1.0
#label='ID, 2020Feb24 (AUC={:.3f})'.format(id_low_auc)
)
########################################
# EGamma PF GSF electrons
has_trk = (egamma.has_trk) & (egamma.trk_pt > 0.5) & (np.abs(
egamma.trk_eta) < 2.5)
has_ele = (egamma.has_ele) & (egamma.ele_pt > 0.5) & (np.abs(
egamma.ele_eta) < 2.5)
denom = has_trk & egamma.is_e
numer = has_ele & denom
pf_eff = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
denom = has_trk & (~egamma.is_e)
numer = has_ele & denom
pf_fr = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
plt.plot([pf_fr], [pf_eff],
marker='o',
color='purple',
markersize=8,
linestyle='none',
label='PF electron')
pf_id_fpr, pf_id_tpr, pf_id_score = roc_curve(
egamma.is_e[has_ele], egamma['ele_mva_value_retrained'][has_ele])
pf_id_auc = roc_auc_score(
egamma.is_e[has_ele], egamma['ele_mva_value_retrained']
[has_ele]) if len(set(egamma.is_e[has_ele])) > 1 else 0.
plt.plot(pf_id_fpr * pf_fr,
pf_id_tpr * pf_eff,
linestyle='solid',
color='purple',
linewidth=1.0,
label='ID, retrain (AUC={:.3f})'.format(pf_id_auc))
pf_id2_fpr, pf_id2_tpr, pf_id2_score = roc_curve(
egamma.is_e[has_ele], egamma['ele_mva_value'][has_ele])
pf_id2_auc = roc_auc_score(egamma.is_e[has_ele],
egamma['ele_mva_value'][has_ele]) if len(
set(egamma.is_e[has_ele])) > 1 else 0.
plt.plot(pf_id2_fpr * pf_fr,
pf_id2_tpr * pf_eff,
linestyle='dashed',
color='purple',
linewidth=1.0,
label='ID, EGamma (AUC={:.3f})'.format(pf_id2_auc))
########################################
# Working points
id_ELE = np.abs(id_fpr * ele_fr - pf_fr).argmin()
same_fr = test[id_branch] > id_score[id_ELE]
x, y = id_fpr[id_ELE] * ele_fr, id_tpr[id_ELE] * ele_eff
#plt.plot([x], [y], marker='o', markerfacecolor='white', markeredgecolor='blue', markersize=8)
#plt.text(x, y+0.03, "WP", fontsize=8, ha='center', va='center', color='blue' )
id_high_ELE = np.abs(id_high_fpr * ele_high_fr - pf_fr).argmin()
same_fr_high = test[id_high_branch] > id_high_score[id_high_ELE]
x, y = id_high_fpr[id_high_ELE] * ele_high_fr, id_high_tpr[
id_high_ELE] * ele_high_eff
#plt.plot([x], [y], marker='^', markerfacecolor='white', markeredgecolor='blue', markersize=8)
#plt.text(x, y+0.03, "WP", fontsize=8, ha='center', va='center', color='blue' )
id_low_ELE = np.abs(id_low_fpr * ele_low_fr - pf_fr).argmin()
same_fr_low = test[id_low_branch] > id_low_score[id_low_ELE]
x, y = id_low_fpr[id_low_ELE] * ele_low_fr, id_low_tpr[
id_low_ELE] * ele_low_eff
#plt.plot([x], [y], marker='v', markerfacecolor='white', markeredgecolor='blue', markersize=8)
#plt.text(x, y+0.03, "WP", fontsize=8, ha='center', va='center', color='blue' )
##########
# Finish up ...
plt.legend(loc='upper left',
facecolor='white',
framealpha=None,
frameon=False)
plt.tight_layout()
plt.savefig(dir + '/roc.pdf')
plt.clf()
plt.close()
##############
# EFF CURVES #
##############
# Binning
bin_edges = np.linspace(0., 4., 8, endpoint=False)
bin_edges = np.append(bin_edges, np.linspace(4., 8., 4, endpoint=False))
bin_edges = np.append(bin_edges, np.linspace(8., 12., 3, endpoint=True))
bin_centres = (bin_edges[:-1] + bin_edges[1:]) / 2.
bin_widths = (bin_edges[1:] - bin_edges[:-1])
bin_width = bin_widths[0]
bin_widths /= bin_width
#print("bin_edges",bin_edges)
#print("bin_centres",bin_centres)
#print("bin_widths",bin_widths)
#print("bin_width",bin_width)
tuple = ([
'gen_pt',
'gsf_pt',
'gsf_mode_pt',
'gsf_dxy',
'gsf_dz',
'rho',
], [
bin_edges,
bin_edges,
bin_edges,
np.linspace(0., 3.3, 12),
np.linspace(0., 22., 12),
np.linspace(0., 44., 12),
], [
'Generator-level transverse momentum (GeV)',
'Transverse momentum (GeV)',
'Mode transverse momentum (GeV)',
'Transverse impact parameter w.r.t. beamspot (cm)',
'Longitudinal impact parameter w.r.t. beamspot (cm)',
'Median energy density from UE/pileup (GeV / unit area)',
])
print("Efficiency curves ...")
for attr, binning, xlabel in zip(*tuple):
print(attr)
plt.figure()
ax = plt.subplot(111)
has_trk = (test.has_trk) & (test.trk_pt > 0.5) & (np.abs(test.trk_eta)
< 2.5)
has_ele = (test.has_ele) & (test.ele_pt > 0.5) & (np.abs(test.ele_eta)
< 2.5)
has_ele_low = (test.has_ele) & (test.ele_pt > 0.5) & (np.abs(
test.ele_eta) < 2.5) & (test.ele_pt < 2.0)
has_ele_high = (test.has_ele) & (test.ele_pt > 0.5) & (np.abs(
test.ele_eta) < 2.5) & (test.ele_pt > 2.0)
has_trk_ = (egamma.has_trk) & (egamma.trk_pt > 0.5) & (np.abs(
egamma.trk_eta) < 2.5)
has_ele_ = (egamma.has_ele) & (egamma.ele_pt > 0.5) & (np.abs(
egamma.ele_eta) < 2.5)
curves = [
{
"label": "Low-pT electron",
"var": test[attr],
"mask": (test.is_e) & (has_trk),
"condition": (has_ele),
"colour": "blue",
"fill": True,
"size": 8,
},
{
"label": "Same mistag rate",
"var": test[attr],
"mask": (test.is_e) & (has_trk),
"condition": (has_ele) & (same_fr),
"colour": "blue",
"fill": False,
"size": 8,
},
{
"label": "Same mistag rate",
"var": test[attr],
"mask": (test.is_e) & (has_trk),
"condition": (has_ele_high) & (same_fr_high),
"colour": "blue",
"fill": False,
"size": 8,
"marker": "^"
},
{
"label": "Same mistag rate",
"var": test[attr],
"mask": (test.is_e) & (has_trk),
"condition": (has_ele_low) & (same_fr_low),
"colour": "blue",
"fill": False,
"size": 8,
"marker": "v"
},
{
"label": "PF electron",
"var": egamma[attr],
"mask": (egamma.is_e) & (has_trk_),
"condition": (has_ele_),
"colour": "purple",
"fill": True,
"size": 8,
},
]
for idx, curve in enumerate(curves):
his_total, _ = np.histogram(curve["var"][curve["mask"]],
bins=binning)
his_passed, _ = np.histogram(curve["var"][curve["mask"]
& curve["condition"]],
bins=binning)
x = binning[:-1]
y = [x / y if y > 0 else 0. for x, y in zip(his_passed, his_total)]
yhigh = [
binomial_hpdr(p, t)[1] - (p / t) if t > 0 else 0.
for p, t in zip(his_passed, his_total)
]
ylow = [(p / t) - binomial_hpdr(p, t)[0] if t > 0 else 0.
for p, t in zip(his_passed, his_total)]
yerr = [ylow, yhigh]
label='{:s} (mean={:5.3f})'.format(curve["label"],
float(his_passed.sum())/float(his_total.sum()) \
if his_total.sum() > 0 else 0.)
ax.errorbar(
x=x,
y=y,
yerr=yerr,
#color=None,
label=label,
marker=curve.get("marker", 'o'),
color=curve["colour"],
markerfacecolor=curve["colour"] if curve["fill"] else "white",
markersize=curve["size"],
linewidth=0.5,
elinewidth=0.5)
# #########
# Finish up ...
plt.title('Low-pT electron performance (BParking)')
plt.xlabel(xlabel)
plt.ylabel('Efficiency (w.r.t. KF tracks, pT > 0.5 GeV)')
ax.set_xlim(binning[0], binning[-2])
plt.ylim([0., 1.])
plt.legend(loc='lower right',
facecolor='white',
framealpha=None,
frameon=False)
plt.tight_layout()
plt.savefig(dir + '/eff_vs_{:s}.pdf'.format(attr))
plt.clf()
plt.close()
#################
# MISTAG CURVES #
#################
print("Mistag curves ...")
for attr, binning, xlabel in zip(*tuple):
print(attr)
plt.figure()
ax = plt.subplot(111)
has_trk = (test.has_trk) & (test.trk_pt > 0.5) & (np.abs(test.trk_eta)
< 2.5)
has_ele = (test.has_ele) & (test.ele_pt > 0.5) & (np.abs(test.ele_eta)
< 2.5)
has_ele_low = (test.has_ele) & (test.ele_pt > 0.5) & (np.abs(
test.ele_eta) < 2.5) & (test.ele_pt < 2.0)
has_ele_high = (test.has_ele) & (test.ele_pt > 0.5) & (np.abs(
test.ele_eta) < 2.5) & (test.ele_pt > 2.0)
has_trk_ = (egamma.has_trk) & (egamma.trk_pt > 0.5) & (np.abs(
egamma.trk_eta) < 2.5)
has_ele_ = (egamma.has_ele) & (egamma.ele_pt > 0.5) & (np.abs(
egamma.ele_eta) < 2.5)
curves = [
{
"label": "Low-pT electron",
"var": test[attr],
"mask": (~test.is_e) & (has_trk),
"condition": (has_ele),
"colour": "blue",
"fill": True,
"size": 8,
},
{
"label": "Same mistag rate",
"var": test[attr],
"mask": (~test.is_e) & (has_trk),
"condition": (has_ele) & (same_fr),
"colour": "blue",
"fill": False,
"size": 8,
},
{
"label": "Same mistag rate",
"var": test[attr],
"mask": (~test.is_e) & (has_trk),
"condition": (has_ele_high) & (same_fr_high),
"colour": "blue",
"fill": False,
"size": 8,
"marker": "^"
},
{
"label": "Same mistag rate",
"var": test[attr],
"mask": (~test.is_e) & (has_trk),
"condition": (has_ele_low) & (same_fr_low),
"colour": "blue",
"fill": False,
"size": 8,
"marker": "v"
},
{
"label": "PF electron",
"var": egamma[attr],
"mask": (~egamma.is_e) & (has_trk_),
"condition": (has_ele_),
"colour": "purple",
"fill": True,
"size": 8,
},
]
for idx, curve in enumerate(curves):
his_total, _ = np.histogram(curve["var"][curve["mask"]],
bins=binning)
his_passed, _ = np.histogram(curve["var"][curve["mask"]
& curve["condition"]],
bins=binning)
x = binning[:-1]
y = [x / y if y > 0 else 0. for x, y in zip(his_passed, his_total)]
yhigh = [
binomial_hpdr(p, t)[1] - (p / t) if t > 0 else 0.
for p, t in zip(his_passed, his_total)
]
ylow = [(p / t) - binomial_hpdr(p, t)[0] if t > 0 else 0.
for p, t in zip(his_passed, his_total)]
yerr = [ylow, yhigh]
label='{:s} (mean={:6.4f})'.format(curve["label"],
float(his_passed.sum())/float(his_total.sum()) \
if his_total.sum() > 0 else 0.)
ax.errorbar(
x=x,
y=y,
yerr=yerr,
#color=None,
label=label,
marker=curve.get("marker", 'o'),
color=curve["colour"],
markerfacecolor=curve["colour"] if curve["fill"] else "white",
markersize=curve["size"],
linewidth=0.5,
elinewidth=0.5)
# #########
# Finish up ...
plt.title('Low-pT electron performance (BParking)')
plt.xlabel(xlabel)
plt.ylabel('Mistag rate (w.r.t. KF tracks, pT > 0.5 GeV)')
plt.gca().set_yscale('log')
ax.set_xlim(binning[0], binning[-2])
ax.set_ylim([1.e-4, 1.])
plt.legend(loc='lower right',
facecolor='white',
framealpha=None,
frameon=False)
plt.tight_layout()
plt.savefig(dir + '/mistag_vs_{:s}.pdf'.format(attr))
plt.clf()
plt.close()
def mauro(dir, test, egamma, has_pfgsf_branches=True, AxE=True):
print(
'##### MAURO ##########################################################'
)
#############
# ROC CURVE #
#############
plt.figure(figsize=(6, 6))
ax = plt.subplot(111)
plt.title('Efficiency and mistag rate w.r.t. GSF tracks')
plt.xlim(1.e-3, 1.1)
plt.ylim([0., 0.6]) if AxE is True else plt.ylim([0., 1.03])
plt.xlabel('FPR')
plt.ylabel('TPR')
ax.tick_params(axis='x', pad=10.)
plt.gca().set_xscale('log')
plt.grid(True)
########################################
# "by chance" line
plt.plot(np.arange(0., 1.,
plt.xlim()[0]),
np.arange(0., 1.,
plt.xlim()[0]),
'k--',
lw=0.5)
########################################
# Low-pT GSF electrons + ROC curves
has_gsf = (test.has_gsf) & (test.gsf_pt > 0.5) & (np.abs(test.gsf_eta) <
2.5)
has_pfgsf = (test.has_pfgsf) & (test.pfgsf_pt > 0.5) & (np.abs(
test.pfgsf_eta) < 2.5)
#has_gsf |= has_pfgsf
has_ele = (test.has_ele) & (test.ele_pt > 0.5) & (np.abs(test.ele_eta) <
2.5)
# Eff and FR
if AxE is True:
denom = test.is_e
numer = has_ele & denom
ele_eff = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
else:
denom = has_gsf & test.is_e
numer = has_ele & denom
ele_eff = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
denom = has_gsf & (~test.is_e)
numer = has_ele & denom
ele_fr = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
plt.plot([ele_fr], [ele_eff],
marker='o',
color='blue',
markersize=8,
linestyle=None)
id_fpr, id_tpr, id_score = roc_curve(test.is_e[has_ele],
test['training_out'][has_ele])
id_auc = roc_auc_score(test.is_e[has_ele], test['training_out'][has_ele])
plt.plot(id_fpr * ele_fr,
id_tpr * ele_eff,
linestyle='solid',
color='black',
linewidth=1.0,
label='Low-pT GSF electron + ID, AUC={:.3f}'.format(id_auc))
# Unbiased seed BDT
ele_unb_fpr, ele_unb_tpr, ele_unb_score = roc_curve(
test.is_e[has_ele], test.gsf_bdtout1[has_ele])
ele_unb_auc = roc_auc_score(test.is_e[has_ele], test.gsf_bdtout1[has_ele])
plt.plot(
ele_unb_fpr * ele_fr,
ele_unb_tpr * ele_eff,
linestyle='solid',
color='blue',
linewidth=1.0,
label='Low-pT GSF electron + unbiased seed BDT, AUC={:.3f}'.format(
ele_unb_auc))
# Biased seed BDT
ele_b_fpr, ele_b_tpr, ele_b_score = roc_curve(test.is_e[has_ele],
test.gsf_bdtout2[has_ele])
ele_b_auc = roc_auc_score(
test.is_e[has_ele],
test.gsf_bdtout2[has_ele]) if len(set(test.is_e[has_ele])) > 1 else 0.
plt.plot(ele_b_fpr * ele_fr,
ele_b_tpr * ele_eff,
linestyle='dashed',
color='blue',
linewidth=0.5,
label='Low-pT GSF electron + biased seed BDT, AUC={:.3f}'.format(
ele_b_auc))
########################################
# Low-pT GSF tracks + ROC curves
has_gsf = (test.has_gsf) & (test.gsf_pt > 0.5) & (np.abs(test.gsf_eta) <
2.5)
has_pfgsf = (test.has_pfgsf) & (test.pfgsf_pt > 0.5) & (np.abs(
test.pfgsf_eta) < 2.5)
#has_gsf |= has_pfgsf
has_ele = None
# Eff and FR
if AxE is True:
denom = test.is_e
numer = has_gsf & denom
gsf_eff = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
else:
denom = has_gsf & test.is_e
numer = has_gsf & denom
gsf_eff = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
denom = has_gsf & (~test.is_e)
numer = has_gsf & denom
gsf_fr = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
plt.plot([gsf_fr], [gsf_eff],
marker='o',
color='red',
markersize=8,
linestyle='None')
# Unbiased seed BDT
gsf_unb_fpr, gsf_unb_tpr, gsf_unb_score = roc_curve(
test.is_e[has_gsf], test.gsf_bdtout1[has_gsf])
gsf_unb_auc = roc_auc_score(test.is_e[has_gsf], test.gsf_bdtout1[has_gsf])
plt.plot(gsf_unb_fpr * gsf_fr,
gsf_unb_tpr * gsf_eff,
linestyle='solid',
color='red',
linewidth=1.0,
label='Low-pT GSF track + unbiased seed BDT, AUC={:.3f}'.format(
gsf_unb_auc))
# Biased seed BDT
gsf_b_fpr, gsf_b_tpr, gsf_b_score = roc_curve(test.is_e[has_gsf],
test.gsf_bdtout2[has_gsf])
gsf_b_auc = roc_auc_score(
test.is_e[has_gsf],
test.gsf_bdtout2[has_gsf]) if len(set(test.is_e[has_gsf])) > 1 else 0.
plt.plot(gsf_b_fpr * gsf_fr,
gsf_b_tpr * gsf_eff,
linestyle='dashed',
color='red',
linewidth=0.5,
label='Low-pT GSF track + biased seed BDT, AUC={:.3f}'.format(
gsf_b_auc))
########################################
# EGamma GSF tracks and PF GSF electrons
has_gsf = (egamma.has_gsf) & (egamma.gsf_pt > 0.5) & (np.abs(
egamma.gsf_eta) < 2.5)
has_pfgsf = (egamma.has_pfgsf) & (egamma.pfgsf_pt > 0.5) & (np.abs(
egamma.pfgsf_eta) < 2.5)
#has_gsf |= has_pfgsf
#has_gsf |= egamma.seed_ecal_driven
has_ele = (egamma.has_ele) & (egamma.ele_pt > 0.5) & (np.abs(
egamma.ele_eta) < 2.5)
# Eff and FR (EGamma GSF tracks)
if AxE is True:
denom = egamma.is_e
numer = has_pfgsf & denom
eg_eff = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
else:
denom = has_gsf & egamma.is_e
numer = has_pfgsf & denom
eg_eff = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
denom = has_gsf & (~egamma.is_e)
numer = has_pfgsf & denom
eg_fr = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
plt.plot([eg_fr], [eg_eff],
marker='o',
color='green',
markersize=8,
linestyle='None',
label='EGamma GSF track')
# Eff and FR (EGamma PF GSF electrons)
if AxE is True:
denom = egamma.is_e
numer = has_ele & denom
pf_eff = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
else:
denom = has_gsf & egamma.is_e
numer = has_ele & denom
pf_eff = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
denom = has_gsf & (~egamma.is_e)
numer = has_ele & denom
pf_fr = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
plt.plot([pf_fr], [pf_eff],
marker='o',
color='purple',
markersize=8,
linestyle='None',
label='PF GSF electron')
print('eff: {:.3f}, mistag: {:.4f}'.format(ele_eff, ele_fr),
'Low-pT GSF electrons + ID')
print('eff: {:.3f}, mistag: {:.4f}'.format(gsf_eff, gsf_fr),
'Low-pT GSF electrons + unbiased seed BDT')
print('eff: {:.3f}, mistag: {:.4f}'.format(eg_eff, eg_fr),
'EGamma GSF tracks')
print('eff: {:.3f}, mistag: {:.4f}'.format(pf_eff, pf_fr),
'EGamma GSF electrons')
##########
# EGamma GSF electrons (ECAL-driven)
# has_gsf |= egamma.seed_ecal_driven
# has_ele &= egamma.seed_ecal_driven
#
# if AxE is True :
# denom = egamma.is_e; numer = has_ele&denom
# _eff = float(numer.sum()) / float(denom.sum()) if float(denom.sum()) > 0. else 0.
# else :
# denom = has_gsf&egamma.is_e; numer = has_ele&denom
# _eff = float(numer.sum()) / float(denom.sum()) if float(denom.sum()) > 0. else 0.
# denom = has_gsf&(~egamma.is_e); numer = has_ele&denom
# _fr = float(numer.sum()) / float(denom.sum()) if float(denom.sum()) > 0. else 0.
# plt.plot([_fr], [_eff],
# marker='o', markerfacecolor='none', markeredgecolor='purple', markersize=8, linestyle='None',
# label='PF GSF electron (ECAL-driven)')
# print('eff: {:.3f}, mistag: {:.4f}'.format(_eff,_fr),'EGamma GSF electrons (ECAL-driven)')
# "New" WPs
unb_L = np.abs(gsf_unb_fpr * gsf_fr - eg_fr * 10.).argmin()
unb_M = np.abs(gsf_unb_fpr * gsf_fr - eg_fr * 3.).argmin()
unb_T = np.abs(gsf_unb_fpr * gsf_fr - eg_fr).argmin()
unb_VT = np.abs(gsf_unb_tpr * gsf_eff - eg_eff).argmin()
unb_ELE = np.abs(gsf_unb_fpr * gsf_fr - pf_fr).argmin() # same FR
id_ELE = np.abs(id_fpr * ele_fr - pf_fr).argmin() # same FR
print("EG GSF track: FR, Eff, score:",
"{:.4f}, {:.3f}, {:5.2f} ".format(eg_fr, eg_eff, np.nan))
print("VLoose (10% FR): FR, Eff, score:",
"{:.4f}, {:.3f}, {:5.2f} ".format(gsf_fr, gsf_eff, np.nan))
print(
"Loose (x10 FR): FR, Eff, score:",
"{:.4f}, {:.3f}, {:5.2f} ".format(gsf_unb_fpr[unb_L] * gsf_fr,
gsf_unb_tpr[unb_L] * gsf_eff,
gsf_unb_score[unb_L]))
print(
"Medium (x3 FR): FR, Eff, score:",
"{:.4f}, {:.3f}, {:5.2f} ".format(gsf_unb_fpr[unb_M] * gsf_fr,
gsf_unb_tpr[unb_M] * gsf_eff,
gsf_unb_score[unb_M]))
print(
"Tight (same FR): FR, Eff, score:",
"{:.4f}, {:.3f}, {:5.2f} ".format(gsf_unb_fpr[unb_T] * gsf_fr,
gsf_unb_tpr[unb_T] * gsf_eff,
gsf_unb_score[unb_T]))
print(
"VTight (same eff): FR, Eff, score:",
"{:.4f}, {:.3f}, {:5.2f} ".format(gsf_unb_fpr[unb_VT] * gsf_fr,
gsf_unb_tpr[unb_VT] * gsf_eff,
gsf_unb_score[unb_VT]))
print("PF GSF electron: FR, Eff, score:",
"{:.4f}, {:.3f}, {:5.2f} ".format(pf_fr, pf_eff, np.nan))
print(
"Unb/PF (same FR): FR, Eff, score:",
"{:.4f}, {:.3f}, {:5.2f} ".format(ele_unb_fpr[unb_ELE] * ele_fr,
ele_unb_tpr[unb_ELE] * ele_eff,
ele_unb_score[unb_ELE]))
print(
"ID/PF (same FR): FR, Eff, score:",
"{:.4f}, {:.3f}, {:5.2f} ".format(id_fpr[id_ELE] * ele_fr,
id_tpr[id_ELE] * ele_eff,
id_score[id_ELE]))
x, y = gsf_unb_fpr[unb_L] * gsf_fr, gsf_unb_tpr[unb_L] * gsf_eff
plt.plot([x], [y],
marker='o',
markerfacecolor='none',
markeredgecolor='green',
markersize=4)
plt.text(x,
y - 0.02,
"L",
fontsize=10,
ha='center',
va='center',
color='green')
x, y = gsf_unb_fpr[unb_M] * gsf_fr, gsf_unb_tpr[unb_M] * gsf_eff
plt.plot([x], [y],
marker='o',
markerfacecolor='none',
markeredgecolor='green',
markersize=4)
plt.text(x,
y - 0.02,
"M",
fontsize=10,
ha='center',
va='center',
color='green')
x, y = gsf_unb_fpr[unb_T] * gsf_fr, gsf_unb_tpr[unb_T] * gsf_eff
plt.plot([x], [y],
marker='o',
markerfacecolor='none',
markeredgecolor='green',
markersize=4)
plt.text(x,
y - 0.02,
"T",
fontsize=10,
ha='center',
va='center',
color='green')
x, y = gsf_unb_fpr[unb_VT] * gsf_fr, gsf_unb_tpr[unb_VT] * gsf_eff
plt.plot([x], [y],
marker='o',
markerfacecolor='none',
markeredgecolor='green',
markersize=4)
plt.text(x,
y - 0.02,
"VT",
fontsize=10,
ha='center',
va='center',
color='green')
x, y = ele_unb_fpr[unb_ELE] * ele_fr, ele_unb_tpr[unb_ELE] * ele_eff
plt.plot([x], [y],
marker='o',
markerfacecolor='none',
markeredgecolor='purple',
markersize=4)
plt.text(x,
y - 0.02,
"E",
fontsize=10,
ha='center',
va='center',
color='purple')
x, y = id_fpr[id_ELE] * ele_fr, id_tpr[id_ELE] * ele_eff
plt.plot([x], [y],
marker='o',
markerfacecolor='none',
markeredgecolor='purple',
markersize=4)
plt.text(x,
y - 0.02,
"E",
fontsize=10,
ha='center',
va='center',
color='purple')
# Original WPs
# https://github.com/cms-sw/cmssw/blob/CMSSW_10_2_X/RecoEgamma/EgammaElectronProducers/python/lowPtGsfElectronSeeds_cfi.py
#orig_VL = np.abs(gsf_unb_score-0.19).argmin()
#orig_L = np.abs(gsf_unb_score-1.20).argmin()
#orig_M = np.abs(gsf_unb_score-2.02).argmin()
#orig_T = np.abs(gsf_unb_score-3.05).argmin()
#orig_ELE = np.abs(gsf_unb_score-5.26).argmin() # same FR?
#x,y = gsf_unb_fpr[orig_VL]*gsf_fr,gsf_unb_tpr[orig_VL]*gsf_eff
#plt.plot([x],[y], marker='^', markerfacecolor='none', markeredgecolor='green', markersize=4)
#plt.text(x, y-0.02, "VL", fontsize=10, ha='center', va='center', color='green' )
#x,y = gsf_unb_fpr[orig_L]*gsf_fr,gsf_unb_tpr[orig_L]*gsf_eff
#plt.plot([x],[y], marker='^', markerfacecolor='none', markeredgecolor='green', markersize=4)
#plt.text(x, y-0.02, "L", fontsize=10, ha='center', va='center', color='green' )
#x,y = gsf_unb_fpr[orig_M]*gsf_fr,gsf_unb_tpr[orig_M]*gsf_eff
#plt.plot([x],[y], marker='^', markerfacecolor='none', markeredgecolor='green', markersize=4)
#plt.text(x, y-0.02, "M", fontsize=10, ha='center', va='center', color='green' )
#x,y = gsf_unb_fpr[orig_T]*gsf_fr,gsf_unb_tpr[orig_T]*gsf_eff
#plt.plot([x],[y], marker='^', markerfacecolor='none', markeredgecolor='green', markersize=4)
#plt.text(x, y-0.02, "T", fontsize=10, ha='center', va='center', color='green' )
#x,y = gsf_unb_fpr[orig_ELE]*gsf_fr,gsf_unb_tpr[orig_ELE]*gsf_eff
#plt.plot([x],[y], marker='^', markerfacecolor='none', markeredgecolor='purple', markersize=4)
#plt.text(x, y+0.02, "E", fontsize=10, ha='center', va='center', color='purple' )
##########
# Finish up ...
plt.legend(loc='upper left', framealpha=None, frameon=False)
plt.tight_layout()
plt.savefig(dir + '/roc.pdf')
plt.clf()
plt.close()
##############
# EFF CURVES #
##############
# Binning
bin_edges = np.linspace(0., 4., 8, endpoint=False)
bin_edges = np.append(bin_edges, np.linspace(4., 8., 4, endpoint=False))
bin_edges = np.append(bin_edges, np.linspace(8., 10., 2, endpoint=True))
bin_centres = (bin_edges[:-1] + bin_edges[1:]) / 2.
bin_widths = (bin_edges[1:] - bin_edges[:-1])
bin_width = bin_widths[0]
bin_widths /= bin_width
#print("bin_edges",bin_edges)
#print("bin_centres",bin_centres)
#print("bin_widths",bin_widths)
#print("bin_width",bin_width)
plt.figure()
ax = plt.subplot(111)
has_gsf = (test.has_gsf) & (test.gsf_pt > 0.5) & (np.abs(test.gsf_eta) <
2.5)
has_ele = (test.has_ele) & (test.ele_pt > 0.5) & (np.abs(test.ele_eta) <
2.5)
has_gsf_ = (egamma.has_gsf) & (egamma.gsf_pt > 0.5) & (np.abs(
egamma.gsf_eta) < 2.5)
has_pfgsf = (egamma.has_pfgsf) & (egamma.pfgsf_pt > 0.5) & (np.abs(
egamma.pfgsf_eta) < 2.5)
has_ele_ = (egamma.has_ele) & (egamma.ele_pt > 0.5) & (np.abs(
egamma.ele_eta) < 2.5)
curves = [
{
"label": "EG GSF",
"var": egamma.gsf_pt,
"mask": (egamma.is_e) & (has_gsf_),
"condition": (has_pfgsf),
"colour": "green",
"size": 7,
},
{
"label": "PF ELE",
"var": egamma.gsf_pt,
"mask": (egamma.is_e) & (has_gsf_),
"condition": (has_ele_),
"colour": "purple",
"size": 7,
},
{
"label": "Unbiased",
"var": test.gsf_pt,
"mask": (test.is_e) & (has_gsf),
"condition":
(has_ele) & (test.gsf_bdtout1 > gsf_unb_score[unb_ELE]),
"colour": "blue",
"size": 7,
},
{
"label": "ID",
"var": test.gsf_pt,
"mask": (test.is_e) & (has_gsf),
"condition": (has_ele) & (test['training_out'] > id_score[id_ELE]),
"colour": "black",
"size": 7,
},
#{"label":"Track (VT)","var":test.gsf_pt, "mask":(test.is_e)&(has_gsf), "condition":(has_ele)&(test.gsf_bdtout1>gsf_unb_score[unb_VT]),"colour":"red","size":7,},
#{"label":"Track (T)", "var":test.gsf_pt, "mask":(test.is_e)&(has_gsf), "condition":(has_ele)&(test.gsf_bdtout1>gsf_unb_score[unb_T]),"colour":"red","size":6,},
#{"label":"Track (M)", "var":test.gsf_pt, "mask":(test.is_e)&(has_gsf), "condition":(has_ele)&(test.gsf_bdtout1>gsf_unb_score[unb_M]),"colour":"red","size":5,},
#{"label":"Track (L)", "var":test.gsf_pt, "mask":(test.is_e)&(has_gsf), "condition":(has_ele)&(test.gsf_bdtout1>gsf_unb_score[unb_L]),"colour":"red","size":4,},
#{"label":"Track (VL)","var":test.gsf_pt, "mask":(test.is_e)&(has_gsf), "condition":(has_ele)&(test.gsf_bdtout1>gsf_unb_score[unb_VL]),"colour":"red","size":3,},
{
"label": "Open",
"var": test.gsf_pt,
"mask": (test.is_e) & (has_gsf),
"condition": (has_ele),
"colour": "red",
"size": 7,
},
]
for idx, curve in enumerate(curves):
#print("label:",curve["label"])
his_total, _ = np.histogram(curve["var"][curve["mask"]],
bins=bin_edges)
his_passed, _ = np.histogram(curve["var"][curve["mask"]
& curve["condition"]],
bins=bin_edges)
x = bin_edges[:-1]
y = [x / y if y > 0 else 0. for x, y in zip(his_passed, his_total)]
yhigh = [
binomial_hpdr(p, t)[1] - (p / t) if t > 0 else 0.
for p, t in zip(his_passed, his_total)
]
ylow = [(p / t) - binomial_hpdr(p, t)[0] if t > 0 else 0.
for p, t in zip(his_passed, his_total)]
yerr = [ylow, yhigh]
label='{:s} (mean={:5.3f})'.format(curve["label"],
float(his_passed.sum())/float(his_total.sum()) \
if his_total.sum() > 0 else 0.)
ax.errorbar(
x=x,
y=y,
yerr=yerr,
#color=None,
label=label,
marker='o',
color=curve["colour"],
markerfacecolor="white",
markersize=curve["size"],
linewidth=0.5,
elinewidth=0.5)
##########
# Finish up ...
plt.title('Efficiency as a function of GSF track pT')
plt.xlabel('Transverse momentum (GeV)')
plt.ylabel('Efficiency')
ax.set_xlim(bin_edges[0], bin_edges[-2])
plt.ylim([0., 1.])
plt.legend(loc='best')
plt.tight_layout()
plt.savefig(dir + '/eff.pdf')
plt.clf()
plt.close()
#################
# MISTAG CURVES #
#################
plt.figure()
ax = plt.subplot(111)
has_gsf = (test.has_gsf) & (test.gsf_pt > 0.5) & (np.abs(test.gsf_eta) <
2.5)
has_ele = (test.has_ele) & (test.ele_pt > 0.5) & (np.abs(test.ele_eta) <
2.5)
has_gsf_ = (egamma.has_gsf) & (egamma.gsf_pt > 0.5) & (np.abs(
egamma.gsf_eta) < 2.5)
has_pfgsf = (egamma.has_pfgsf) & (egamma.pfgsf_pt > 0.5) & (np.abs(
egamma.pfgsf_eta) < 2.5)
has_ele_ = (egamma.has_ele) & (egamma.ele_pt > 0.5) & (np.abs(
egamma.ele_eta) < 2.5)
curves = [
{
"label": "EG GSF",
"var": egamma.gsf_pt,
"mask": (~egamma.is_e) & (has_gsf_),
"condition": (has_pfgsf),
"colour": "green",
"size": 7,
},
{
"label": "PF ELE",
"var": egamma.gsf_pt,
"mask": (~egamma.is_e) & (has_gsf_),
"condition": (has_ele_),
"colour": "purple",
"size": 7,
},
{
"label": "Unbiased",
"var": test.gsf_pt,
"mask": (~test.is_e) & (has_gsf),
"condition":
(has_ele) & (test.gsf_bdtout1 > gsf_unb_score[unb_ELE]),
"colour": "blue",
"size": 7,
},
{
"label": "ID",
"var": test.gsf_pt,
"mask": (~test.is_e) & (has_gsf),
"condition": (has_ele) & (test['training_out'] > id_score[id_ELE]),
"colour": "black",
"size": 7,
},
#{"label":"Track (VT)","var":test.gsf_pt, "mask":(~test.is_e)&(has_gsf), "condition":(has_ele)&(test.gsf_bdtout1>gsf_unb_score[unb_VT]),"colour":"red","size":7,},
#{"label":"Track (T)", "var":test.gsf_pt, "mask":(~test.is_e)&(has_gsf), "condition":(has_ele)&(test.gsf_bdtout1>gsf_unb_score[unb_T]),"colour":"red","size":6,},
#{"label":"Track (M)", "var":test.gsf_pt, "mask":(~test.is_e)&(has_gsf), "condition":(has_ele)&(test.gsf_bdtout1>gsf_unb_score[unb_M]),"colour":"red","size":5,},
#{"label":"Track (L)", "var":test.gsf_pt, "mask":(~test.is_e)&(has_gsf), "condition":(has_ele)&(test.gsf_bdtout1>gsf_unb_score[unb_L]),"colour":"red","size":4,},
#{"label":"Track (VL)","var":test.gsf_pt, "mask":(~test.is_e)&(has_gsf), "condition":(has_ele)&(test.gsf_bdtout1>gsf_unb_score[unb_VL]),"colour":"red","size":3,},
{
"label": "Open",
"var": test.gsf_pt,
"mask": (~test.is_e) & (has_gsf),
"condition": (has_ele),
"colour": "red",
"size": 7,
},
]
for idx, curve in enumerate(curves):
#print("label:",curve["label"])
his_total, _ = np.histogram(curve["var"][curve["mask"]],
bins=bin_edges)
his_passed, _ = np.histogram(curve["var"][curve["mask"]
& curve["condition"]],
bins=bin_edges)
x = bin_edges[:-1]
y = [x / y if y > 0 else 0. for x, y in zip(his_passed, his_total)]
yhigh = [
binomial_hpdr(p, t)[1] - (p / t) if t > 0 else 0.
for p, t in zip(his_passed, his_total)
]
ylow = [(p / t) - binomial_hpdr(p, t)[0] if t > 0 else 0.
for p, t in zip(his_passed, his_total)]
yerr = [ylow, yhigh]
label='{:s} (mean={:5.3f})'.format(curve["label"],
float(his_passed.sum())/float(his_total.sum()) \
if his_total.sum() > 0 else 0.)
ax.errorbar(
x=x,
y=y,
yerr=yerr,
#color=None,
label=label,
marker='o',
color=curve["colour"],
markerfacecolor="white",
markersize=curve["size"],
linewidth=0.5,
elinewidth=0.5)
##########
# Finish up ...
plt.title('Mistag rate as a function of GSF track pT')
plt.xlabel('Transverse momentum (GeV)')
plt.ylabel('Mistag rate')
plt.gca().set_yscale('log')
ax.set_xlim(bin_edges[0], bin_edges[-2])
ax.set_ylim([0.0001, 1.])
plt.legend(loc='best')
plt.tight_layout()
plt.savefig(dir + '/mistag.pdf')
plt.clf()
plt.close()
def miniaod(dir, test, egamma, has_pfgsf_branches=True, AxE=True):
print(
'##### MINIAOD ##########################################################'
)
#############
# ROC CURVE #
#############
plt.figure(figsize=(6, 6))
ax = plt.subplot(111)
plt.title('Efficiency and mistag rate w.r.t. GSF tracks')
plt.xlim(1.e-3, 1.1)
plt.ylim([0., 1.02])
plt.xlabel('FPR')
plt.ylabel('TPR')
ax.tick_params(axis='x', pad=10.)
plt.gca().set_xscale('log')
plt.grid(True)
########################################
# "by chance" line
plt.plot(np.arange(0., 1.,
plt.xlim()[0]),
np.arange(0., 1.,
plt.xlim()[0]),
'k--',
lw=0.5)
########################################
# Low-pT GSF tracks + ROC curves
# pT > 0.5 GeV, VL WP for Seed BDT
has_gsf = (test.has_gsf) & (test.gsf_pt > 0.5) & (np.abs(test.gsf_eta) <
2.5)
denom = has_gsf & test.is_e
numer = has_gsf & denom
gsf_eff = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
denom = has_gsf & (~test.is_e)
numer = has_gsf & denom
gsf_fr = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
plt.plot(
[gsf_fr],
[gsf_eff],
marker='o',
markerfacecolor='none',
markeredgecolor='red',
markersize=8,
linestyle='none',
label='Low-pT GSF track, pT > 0.5 GeV, VLoose Seed',
)
# pT > 1.0 GeV, Tight WP for Seed BDT
has_gsf_T = has_gsf & (test.gsf_pt > 1.0) & ((test.gsf_bdtout1 > 3.05) |
(test.gsf_bdtout2 > 2.42))
denom = has_gsf & test.is_e
numer = has_gsf_T & denom
gsf_eff = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
denom = has_gsf & (~test.is_e)
numer = has_gsf_T & denom
gsf_fr = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
plt.plot(
[gsf_fr],
[gsf_eff],
marker='o',
markerfacecolor='none',
markeredgecolor='blue',
markersize=8,
linestyle='none',
label='Low-pT GSF track, pT > 1.0 GeV, Tight Seed',
)
########################################
# Low-pT GSF electrons + ROC curves
# pT > 0.5 GeV, VL WP for Seed BDT
has_gsf = (test.has_gsf) & (test.gsf_pt > 0.5) & (np.abs(test.gsf_eta) <
2.5)
has_ele = (test.has_ele) & (test.ele_pt > 0.5) & (np.abs(test.ele_eta) <
2.5)
denom = has_gsf & test.is_e
numer = has_ele & denom
ele_eff = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
denom = has_gsf & (~test.is_e)
numer = has_ele & denom
ele_fr = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
plt.plot(
[ele_fr],
[ele_eff],
marker='o',
markerfacecolor='red',
markeredgecolor='red',
markersize=8,
linestyle='none',
label='Low-pT GSF electron, pT > 0.5 GeV, VLoose Seed',
)
# pT > 1.0 GeV, Tight WP for Seed BDT
has_ele = has_ele & (test.gsf_pt > 1.0) & ((test.gsf_bdtout1 > 3.05) |
(test.gsf_bdtout2 > 2.42))
denom = has_gsf & test.is_e
numer = has_ele & denom
ele_eff = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
denom = has_gsf & (~test.is_e)
numer = has_ele & denom
ele_fr = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
plt.plot(
[ele_fr],
[ele_eff],
marker='o',
markerfacecolor='blue',
markeredgecolor='blue',
markersize=8,
linestyle='none',
label='Low-pT GSF electron, pT > 1.0 GeV, Tight Seed',
)
id_fpr, id_tpr, id_score = roc_curve(test.is_e[has_ele],
test['training_out'][has_ele])
id_auc = roc_auc_score(test.is_e[has_ele],
test['training_out'][has_ele]) if len(
set(test.is_e[has_ele])) > 1 else 0.
plt.plot(id_fpr * ele_fr,
id_tpr * ele_eff,
linestyle='solid',
color='black',
linewidth=1.0,
label='Low-pT ID, AUC={:.3f}'.format(id_auc))
########################################
# EGamma GSF tracks and PF GSF electrons
has_gsf = (egamma.has_gsf) & (egamma.gsf_pt > 0.5) & (np.abs(
egamma.gsf_eta) < 2.5)
has_pfgsf = (egamma.has_pfgsf) & (egamma.pfgsf_pt > 0.5) & (np.abs(
egamma.pfgsf_eta) < 2.5)
denom = has_gsf & egamma.is_e
numer = has_pfgsf & denom
eg_eff = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
denom = has_gsf & (~egamma.is_e)
numer = has_pfgsf & denom
eg_fr = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
plt.plot([eg_fr], [eg_eff],
marker='o',
color='green',
markersize=8,
linestyle='none',
label='EGamma GSF track')
has_ele = (egamma.has_ele) & (egamma.ele_pt > 0.5) & (np.abs(
egamma.ele_eta) < 2.5)
denom = has_gsf & egamma.is_e
numer = has_ele & denom
pf_eff = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
denom = has_gsf & (~egamma.is_e)
numer = has_ele & denom
pf_fr = float(numer.sum()) / float(denom.sum()) if float(
denom.sum()) > 0. else 0.
plt.plot([pf_fr], [pf_eff],
marker='o',
color='purple',
markersize=8,
linestyle='none',
label='PF GSF electron')
pf_id_fpr, pf_id_tpr, pf_id_score = roc_curve(
egamma.is_e[has_ele], egamma['ele_mva_value'][has_ele])
pf_id_auc = roc_auc_score(egamma.is_e[has_ele],
egamma['ele_mva_value'][has_ele]) if len(
set(egamma.is_e[has_ele])) > 1 else 0.
plt.plot(pf_id_fpr * pf_fr,
pf_id_tpr * pf_eff,
linestyle='dashed',
color='purple',
linewidth=1.0,
label='PF ID, AUC={:.3f}'.format(pf_id_auc))
#################
# Working points
id_ELE = np.abs(id_fpr * ele_fr - pf_fr).argmin()
same_fr = test['training_out'] > id_score[id_ELE]
x, y = id_fpr[id_ELE] * ele_fr, id_tpr[id_ELE] * ele_eff
plt.plot([x], [y],
marker='o',
markerfacecolor='black',
markeredgecolor='black',
markersize=7)
plt.text(x,
y + 0.03,
"Tight",
fontsize=8,
ha='center',
va='center',
color='black')
id_ELE = np.abs(id_fpr * ele_fr - pf_fr * 2.).argmin()
double_fr = test['training_out'] > id_score[id_ELE]
x, y = id_fpr[id_ELE] * ele_fr, id_tpr[id_ELE] * ele_eff
plt.plot([x], [y],
marker='o',
markerfacecolor='none',
markeredgecolor='black',
markersize=7)
plt.text(x,
y + 0.03,
"Loose",
fontsize=8,
ha='center',
va='center',
color='black')
##########
# Finish up ...
plt.legend(loc='lower right', framealpha=None, frameon=False)
plt.tight_layout()
plt.savefig(dir + '/roc.pdf')
plt.clf()
plt.close()
##############
# EFF CURVES #
##############
# Binning
bin_edges = np.linspace(0., 4., 8, endpoint=False)
bin_edges = np.append(bin_edges, np.linspace(4., 8., 4, endpoint=False))
bin_edges = np.append(bin_edges, np.linspace(8., 12., 3, endpoint=True))
bin_centres = (bin_edges[:-1] + bin_edges[1:]) / 2.
bin_widths = (bin_edges[1:] - bin_edges[:-1])
bin_width = bin_widths[0]
bin_widths /= bin_width
#print("bin_edges",bin_edges)
#print("bin_centres",bin_centres)
#print("bin_widths",bin_widths)
#print("bin_width",bin_width)
tuple = ([
'gsf_pt',
'gsf_mode_pt',
'gsf_dxy',
'gsf_dz',
'rho',
], [
bin_edges,
bin_edges,
np.linspace(0., 3.3, 12),
np.linspace(0., 22., 12),
np.linspace(0., 44., 12),
], [
'Transverse momentum (GeV)',
'Mode transverse momentum (GeV)',
'Transverse impact parameter w.r.t. beamspot (cm)',
'Longitudinal impact parameter w.r.t. beamspot (cm)',
'Median energy density from UE/pileup (GeV / unit area)',
])
print("Efficiency curves ...")
for attr, binning, xlabel in zip(*tuple):
print(attr)
plt.figure()
ax = plt.subplot(111)
has_gsf = (test.has_gsf) & (test.gsf_pt > 0.5) & (np.abs(test.gsf_eta)
< 2.5)
has_ele = (test.has_ele) & (test.ele_pt > 0.5) & (np.abs(test.ele_eta)
< 2.5)
has_ele_T = has_ele & (test.gsf_pt > 1.0) & (
(test.gsf_bdtout1 > 3.05) | (test.gsf_bdtout2 > 2.42))
has_gsf_ = (egamma.has_gsf) & (egamma.gsf_pt > 0.5) & (np.abs(
egamma.gsf_eta) < 2.5)
has_ele_ = (egamma.has_ele) & (egamma.ele_pt > 0.5) & (np.abs(
egamma.ele_eta) < 2.5)
curves = [
{
"label": "Open",
"var": test[attr],
"mask": (test.is_e) & (has_gsf),
"condition": (has_ele),
"colour": "red",
"fill": True,
"size": 7,
},
{
"label": "Tight Seed",
"var": test[attr],
"mask": (test.is_e) & (has_gsf),
"condition": (has_ele_T),
"colour": "blue",
"fill": True,
"size": 7,
},
{
"label": "PF ELE",
"var": egamma[attr],
"mask": (egamma.is_e) & (has_gsf_),
"condition": (has_ele_),
"colour": "purple",
"fill": True,
"size": 7,
},
{
"label": "ID (Tight)",
"var": test[attr],
"mask": (test.is_e) & (has_gsf),
"condition": (has_ele_T) & (same_fr),
"colour": "black",
"fill": True,
"size": 7,
},
{
"label": "ID (Loose)",
"var": test[attr],
"mask": (test.is_e) & (has_gsf),
"condition": (has_ele_T) & (double_fr),
"colour": "black",
"fill": False,
"size": 7,
},
]
for idx, curve in enumerate(curves):
# print("label:",curve["label"])
his_total, _ = np.histogram(curve["var"][curve["mask"]],
bins=binning)
his_passed, _ = np.histogram(curve["var"][curve["mask"]
& curve["condition"]],
bins=binning)
x = binning[:-1]
y = [x / y if y > 0 else 0. for x, y in zip(his_passed, his_total)]
yhigh = [
binomial_hpdr(p, t)[1] - (p / t) if t > 0 else 0.
for p, t in zip(his_passed, his_total)
]
ylow = [(p / t) - binomial_hpdr(p, t)[0] if t > 0 else 0.
for p, t in zip(his_passed, his_total)]
yerr = [ylow, yhigh]
label='{:s} (mean={:5.3f})'.format(curve["label"],
float(his_passed.sum())/float(his_total.sum()) \
if his_total.sum() > 0 else 0.)
ax.errorbar(
x=x,
y=y,
yerr=yerr,
#color=None,
label=label,
marker='o',
color=curve["colour"],
markerfacecolor=curve["colour"] if curve["fill"] else "white",
markersize=curve["size"],
linewidth=0.5,
elinewidth=0.5)
# #########
# Finish up ...
#plt.title('Efficiency as a function of GSF track pT')
plt.xlabel(xlabel)
plt.ylabel('Efficiency')
ax.set_xlim(binning[0], binning[-2])
plt.ylim([0., 1.])
plt.legend(loc='best')
plt.tight_layout()
plt.savefig(dir + '/eff_vs_{:s}.pdf'.format(attr))
plt.clf()
plt.close()
#################
# MISTAG CURVES #
#################
print("Mistag curves ...")
for attr, binning, xlabel in zip(*tuple):
print(attr)
plt.figure()
ax = plt.subplot(111)
has_gsf = (test.has_gsf) & (test.gsf_pt > 0.5) & (np.abs(test.gsf_eta)
< 2.5)
has_ele = (test.has_ele) & (test.ele_pt > 0.5) & (np.abs(test.ele_eta)
< 2.5)
has_ele_T = has_ele & (test.gsf_pt > 1.0) & (
(test.gsf_bdtout1 > 3.05) | (test.gsf_bdtout2 > 2.42))
has_gsf_ = (egamma.has_gsf) & (egamma.gsf_pt > 0.5) & (np.abs(
egamma.gsf_eta) < 2.5)
has_ele_ = (egamma.has_ele) & (egamma.ele_pt > 0.5) & (np.abs(
egamma.ele_eta) < 2.5)
curves = [
{
"label": "Open",
"var": test[attr],
"mask": (~test.is_e) & (has_gsf),
"condition": (has_ele),
"colour": "red",
"fill": True,
"size": 7,
},
{
"label": "Tight Seed",
"var": test[attr],
"mask": (~test.is_e) & (has_gsf),
"condition": (has_ele_T),
"colour": "blue",
"fill": True,
"size": 7,
},
{
"label": "PF ELE",
"var": egamma[attr],
"mask": (~egamma.is_e) & (has_gsf_),
"condition": (has_ele_),
"colour": "purple",
"fill": True,
"size": 7,
},
{
"label": "ID (Tight)",
"var": test[attr],
"mask": (~test.is_e) & (has_gsf),
"condition": (has_ele_T) & (same_fr),
"colour": "black",
"fill": True,
"size": 7,
},
{
"label": "ID (Loose)",
"var": test[attr],
"mask": (~test.is_e) & (has_gsf),
"condition": (has_ele_T) & (double_fr),
"colour": "black",
"fill": False,
"size": 7,
},
]
for idx, curve in enumerate(curves):
his_total, _ = np.histogram(curve["var"][curve["mask"]],
bins=binning)
his_passed, _ = np.histogram(curve["var"][curve["mask"]
& curve["condition"]],
bins=binning)
x = binning[:-1]
y = [x / y if y > 0 else 0. for x, y in zip(his_passed, his_total)]
yhigh = [
binomial_hpdr(p, t)[1] - (p / t) if t > 0 else 0.
for p, t in zip(his_passed, his_total)
]
ylow = [(p / t) - binomial_hpdr(p, t)[0] if t > 0 else 0.
for p, t in zip(his_passed, his_total)]
yerr = [ylow, yhigh]
label='{:s} (mean={:5.3f})'.format(curve["label"],
float(his_passed.sum())/float(his_total.sum()) \
if his_total.sum() > 0 else 0.)
ax.errorbar(
x=x,
y=y,
yerr=yerr,
#color=None,
label=label,
marker='o',
color=curve["colour"],
markerfacecolor=curve["colour"] if curve["fill"] else "white",
markersize=curve["size"],
linewidth=0.5,
elinewidth=0.5)
# #########
# Finish up ...
#plt.title('Mistag rate as a function of GSF track pT')
plt.xlabel(xlabel)
plt.ylabel('Mistag rate')
plt.gca().set_yscale('log')
ax.set_xlim(binning[0], binning[-2])
ax.set_ylim([0.0001, 1.])
plt.legend(loc='best')
plt.tight_layout()
plt.savefig(dir + '/mistag_vs_{:s}.pdf'.format(attr))
plt.clf()
plt.close()
def ultralegacy_vloose(dir,test,egamma,has_pfgsf_branches=True,AxE=True) :
print('##### ULTRA LEGACY VLOOSE ##########################################################')
#############
# ROC CURVE #
#############
plt.figure(figsize=(6,6))
ax = plt.subplot(111)
plt.title('Low-pT electron performance (UltraLegacy)')
plt.xlim(0.8e-3,1.)
plt.ylim([0., 1.])
plt.xlabel('Mistag rate (w.r.t. GSF tracks, pT > 0.5 GeV)')
plt.ylabel('Efficiency (w.r.t. GSF tracks, pT > 0.5 GeV)')
ax.tick_params(axis='x', pad=10.)
plt.gca().set_xscale('log')
plt.grid(True)
########################################
# "by chance" line
plt.plot(np.arange(0.,1.,plt.xlim()[0]),np.arange(0.,1.,plt.xlim()[0]),ls='dotted',lw=0.5,label="By chance")
########################################
# Low-pT GSF electrons + ROC curves
# pT > 0.5 GeV, VL WP for Seed BDT
has_gsf = (test.has_gsf) & (test.gsf_pt>0.5) & (np.abs(test.gsf_eta)<2.5)
has_ele = (test.has_ele) & (test.ele_pt>0.5) & (np.abs(test.ele_eta)<2.5)
denom = has_gsf&test.is_e; numer = has_ele&denom;
ele_eff = float(numer.sum()) / float(denom.sum()) if float(denom.sum()) > 0. else 0.
denom = has_gsf&(~test.is_e); numer = has_ele&denom;
ele_fr = float(numer.sum()) / float(denom.sum()) if float(denom.sum()) > 0. else 0.
plt.plot([ele_fr], [ele_eff],
marker='o', markerfacecolor='red', markeredgecolor='red',
markersize=8,linestyle='none',
label='BParking MINIAOD',
)
# pT > 1.0 GeV, Tight WP for Seed BDT
has_ele = has_ele & (test.gsf_pt>1.0) & ( (test.gsf_bdtout1>3.05) | (test.gsf_bdtout2>2.42) )
denom = has_gsf&test.is_e; numer = has_ele&denom;
ele_eff = float(numer.sum()) / float(denom.sum()) if float(denom.sum()) > 0. else 0.
denom = has_gsf&(~test.is_e); numer = has_ele&denom;
ele_fr = float(numer.sum()) / float(denom.sum()) if float(denom.sum()) > 0. else 0.
plt.plot([ele_fr], [ele_eff],
marker='o', markerfacecolor='blue', markeredgecolor='blue',
markersize=8, linestyle='none',
label='UltraLegacy AOD',
)
id_branch = 'ele_mva_value_depth15'
id_fpr,id_tpr,id_score = roc_curve(test.is_e[has_ele],test[id_branch][has_ele])
id_auc = roc_auc_score(test.is_e[has_ele],test[id_branch][has_ele]) if len(set(test.is_e[has_ele])) > 1 else 0.
plt.plot(id_fpr*ele_fr,
id_tpr*ele_eff,
linestyle='solid', color='blue', linewidth=1.0,
label='ID, 2020Feb24 (AUC={:.3f})'.format(id_auc))
id2_branch = 'training_out'
if id2_branch is not None :
id2_fpr,id2_tpr,id2_score = roc_curve(test.is_e[has_ele],test[id2_branch][has_ele])
id2_auc = roc_auc_score(test.is_e[has_ele],test[id2_branch][has_ele]) if len(set(test.is_e[has_ele])) > 1 else 0.
plt.plot(id2_fpr*ele_fr,
id2_tpr*ele_eff,
linestyle='dashed', color='blue', linewidth=1.0,
label='ID, 2019Aug07 (AUC={:.3f})'.format(id2_auc))
########################################
# EGamma PF GSF electrons
has_gsf = (egamma.has_gsf) & (egamma.gsf_pt>0.5) & (np.abs(egamma.gsf_eta)<2.5)
has_pfgsf = (egamma.has_pfgsf) & (egamma.pfgsf_pt>0.5) & (np.abs(egamma.pfgsf_eta)<2.5)
has_ele = (egamma.has_ele) & (egamma.ele_pt>0.5) & (np.abs(egamma.ele_eta)<2.5)
denom = has_gsf&egamma.is_e; numer = has_ele&denom
pf_eff = float(numer.sum()) / float(denom.sum()) if float(denom.sum()) > 0. else 0.
denom = has_gsf&(~egamma.is_e); numer = has_ele&denom
pf_fr = float(numer.sum()) / float(denom.sum()) if float(denom.sum()) > 0. else 0.
plt.plot([pf_fr], [pf_eff],
marker='o', color='purple',
markersize=8, linestyle='none',
label='PF electron')
pf_id_fpr,pf_id_tpr,pf_id_score = roc_curve(egamma.is_e[has_ele],egamma['ele_mva_value_retrained'][has_ele])
pf_id_auc = roc_auc_score(egamma.is_e[has_ele],egamma['ele_mva_value_retrained'][has_ele]) if len(set(egamma.is_e[has_ele])) > 1 else 0.
plt.plot(pf_id_fpr*pf_fr,
pf_id_tpr*pf_eff,
linestyle='solid', color='purple', linewidth=1.0,
label='ID, retrain (AUC={:.3f})'.format(pf_id_auc))
pf_id2_fpr,pf_id2_tpr,pf_id2_score = roc_curve(egamma.is_e[has_ele],egamma['ele_mva_value'][has_ele])
pf_id2_auc = roc_auc_score(egamma.is_e[has_ele],egamma['ele_mva_value'][has_ele]) if len(set(egamma.is_e[has_ele])) > 1 else 0.
plt.plot(pf_id2_fpr*pf_fr,
pf_id2_tpr*pf_eff,
linestyle='dashed', color='purple', linewidth=1.0,
label='ID, EGamma (AUC={:.3f})'.format(pf_id2_auc))
#################
# Working points
id_ELE = np.abs(id_fpr*ele_fr-pf_fr).argmin()
same_fr = test[id_branch]>id_score[id_ELE]
x,y = id_fpr[id_ELE]*ele_fr,id_tpr[id_ELE]*ele_eff
plt.plot([x], [y], marker='v', markerfacecolor='white', markeredgecolor='blue', markersize=8)
#plt.text(x, y+0.03, "Tight", fontsize=8, ha='center', va='center', color='blue' )
id_ELE = np.abs(id_fpr*ele_fr-pf_fr*2.).argmin()
double_fr = test[id_branch]>id_score[id_ELE]
x,y = id_fpr[id_ELE]*ele_fr,id_tpr[id_ELE]*ele_eff
plt.plot([x], [y], marker='^', markerfacecolor='white', markeredgecolor='blue', markersize=8)
#plt.text(x, y+0.03, "Loose", fontsize=8, ha='center', va='center', color='blue' )
##########
# Finish up ...
plt.legend(loc='lower right',facecolor='white',frameon=False)
plt.tight_layout()
plt.savefig(dir+'/roc.pdf')
plt.clf()
plt.close()
##############
# EFF CURVES #
##############
# Binning
bin_edges = np.linspace(0., 4., 8, endpoint=False)
bin_edges = np.append( bin_edges, np.linspace(4., 8., 4, endpoint=False) )
bin_edges = np.append( bin_edges, np.linspace(8., 12., 3, endpoint=True) )
bin_centres = (bin_edges[:-1] + bin_edges[1:])/2.
bin_widths = (bin_edges[1:] - bin_edges[:-1])
bin_width = bin_widths[0]
bin_widths /= bin_width
#print("bin_edges",bin_edges)
#print("bin_centres",bin_centres)
#print("bin_widths",bin_widths)
#print("bin_width",bin_width)
tuple = ([
'gen_pt',
'gsf_pt',
'gsf_mode_pt',
'gsf_dxy',
'gsf_dz',
'rho',
],
[
bin_edges,
bin_edges,
bin_edges,
np.linspace(0.,3.3,12),
np.linspace(0.,22.,12),
np.linspace(0.,44.,12),
],
[
'Generator-level transverse momentum (GeV)',
'Transverse momentum (GeV)',
'Mode transverse momentum (GeV)',
'Transverse impact parameter w.r.t. beamspot (cm)',
'Longitudinal impact parameter w.r.t. beamspot (cm)',
'Median energy density from UE/pileup (GeV / unit area)',
])
print("Efficiency curves ...")
for attr,binning,xlabel in zip(*tuple) :
print(attr)
plt.figure()
ax = plt.subplot(111)
has_gsf = (test.has_gsf) & (test.gsf_pt>0.5) & (np.abs(test.gsf_eta)<2.5)
has_ele = (test.has_ele) & (test.ele_pt>0.5) & (np.abs(test.ele_eta)<2.5)
has_ele_T = has_ele & (test.gsf_pt>1.0) & ( (test.gsf_bdtout1>3.05) | (test.gsf_bdtout2>2.42) )
has_gsf_ = (egamma.has_gsf) & (egamma.gsf_pt>0.5) & (np.abs(egamma.gsf_eta)<2.5)
has_ele_ = (egamma.has_ele) & (egamma.ele_pt>0.5) & (np.abs(egamma.ele_eta)<2.5)
curves = [
{"label":"BParking MINIAOD","var":test[attr],"mask":(test.is_e)&(has_gsf),"condition":(has_ele),"colour":"red","fill":True,"size":8,},
{"label":"UltraLegacy AOD","var":test[attr],"mask":(test.is_e)&(has_gsf),"condition":(has_ele_T),"colour":"blue","fill":True,"size":8,},
{"label":"UL MINIAOD?","var":test[attr],"mask":(test.is_e)&(has_gsf),"condition":(has_ele_T)&(double_fr),"colour":"blue","fill":False,"size":8,"marker":"^"},
{"label":"UL MINIAOD?","var":test[attr],"mask":(test.is_e)&(has_gsf),"condition":(has_ele_T)&(same_fr),"colour":"blue","fill":False,"size":8,"marker":"v"},
{"label":"PF electron","var":egamma[attr],"mask":(egamma.is_e)&(has_gsf_),"condition":(has_ele_),"colour":"purple","fill":True,"size":8,},
]
for idx,curve in enumerate(curves) :
# print("label:",curve["label"])
his_total,_ = np.histogram(curve["var"][curve["mask"]],bins=binning)
his_passed,_ = np.histogram(curve["var"][curve["mask"]&curve["condition"]],bins=binning)
x=binning[:-1]
y=[ x/y if y > 0 else 0. for x,y in zip(his_passed,his_total) ]
yhigh=[ binomial_hpdr(p,t)[1]-(p/t) if t > 0 else 0. for p,t in zip(his_passed,his_total) ]
ylow =[ (p/t)-binomial_hpdr(p,t)[0] if t > 0 else 0. for p,t in zip(his_passed,his_total) ]
yerr =[ylow,yhigh]
label='{:s} (mean={:5.3f})'.format(curve["label"],
float(his_passed.sum())/float(his_total.sum()) \
if his_total.sum() > 0 else 0.)
ax.errorbar(x=x,
y=y,
yerr=yerr,
#color=None,
label=label,
marker=curve.get("marker",'o'),
color=curve["colour"],
markerfacecolor = curve["colour"] if curve["fill"] else "white",
markersize=curve["size"],
linewidth=0.5,
elinewidth=0.5)
# #########
# Finish up ...
plt.title('Low-pT electron performance (UltraLegacy)')
plt.xlabel(xlabel)
plt.ylabel('Efficiency (w.r.t. GSF tracks, pT > 0.5 GeV)')
ax.set_xlim(binning[0],binning[-2])
plt.ylim([0., 1.])
plt.legend(loc='lower right',facecolor='white',frameon=False)
plt.tight_layout()
plt.savefig(dir+'/eff_vs_{:s}.pdf'.format(attr))
plt.clf()
plt.close()
#################
# MISTAG CURVES #
#################
print("Mistag curves ...")
for attr,binning,xlabel in zip(*tuple) :
print(attr)
plt.figure()
ax = plt.subplot(111)
has_gsf = (test.has_gsf) & (test.gsf_pt>0.5) & (np.abs(test.gsf_eta)<2.5)
has_ele = (test.has_ele) & (test.ele_pt>0.5) & (np.abs(test.ele_eta)<2.5)
has_ele_T = has_ele & (test.gsf_pt>1.0) & ( (test.gsf_bdtout1>3.05) | (test.gsf_bdtout2>2.42) )
has_gsf_ = (egamma.has_gsf) & (egamma.gsf_pt>0.5) & (np.abs(egamma.gsf_eta)<2.5)
has_ele_ = (egamma.has_ele) & (egamma.ele_pt>0.5) & (np.abs(egamma.ele_eta)<2.5)
curves = [
{"label":"BParking MINIAOD","var":test[attr],"mask":(~test.is_e)&(has_gsf),"condition":(has_ele),"colour":"red","fill":True,"size":8,},
{"label":"UltraLegacy AOD","var":test[attr],"mask":(~test.is_e)&(has_gsf),"condition":(has_ele_T),"colour":"blue","fill":True,"size":8,},
{"label":"UL MINIAOD?","var":test[attr],"mask":(~test.is_e)&(has_gsf),"condition":(has_ele_T)&(double_fr),"colour":"blue","fill":False,"size":8,"marker":"^"},
{"label":"UL MINIAOD?","var":test[attr],"mask":(~test.is_e)&(has_gsf),"condition":(has_ele_T)&(same_fr),"colour":"blue","fill":False,"size":8,"marker":"v"},
{"label":"PF electron","var":egamma[attr],"mask":(~egamma.is_e)&(has_gsf_),"condition":(has_ele_),"colour":"purple","fill":True,"size":8,},
]
for idx,curve in enumerate(curves) :
his_total,_ = np.histogram(curve["var"][curve["mask"]],bins=binning)
his_passed,_ = np.histogram(curve["var"][curve["mask"]&curve["condition"]],bins=binning)
x=binning[:-1]
y=[ x/y if y > 0 else 0. for x,y in zip(his_passed,his_total) ]
yhigh=[ binomial_hpdr(p,t)[1]-(p/t) if t > 0 else 0. for p,t in zip(his_passed,his_total) ]
ylow =[ (p/t)-binomial_hpdr(p,t)[0] if t > 0 else 0. for p,t in zip(his_passed,his_total) ]
yerr =[ylow,yhigh]
label='{:s} (mean={:6.4f})'.format(curve["label"],
float(his_passed.sum())/float(his_total.sum()) \
if his_total.sum() > 0 else 0.)
ax.errorbar(x=x,
y=y,
yerr=yerr,
#color=None,
label=label,
marker=curve.get("marker",'o'),
color=curve["colour"],
markerfacecolor = curve["colour"] if curve["fill"] else "white",
markersize=curve["size"],
linewidth=0.5,
elinewidth=0.5)
# #########
# Finish up ...
plt.title('Low-pT electron performance (UltraLegacy)')
plt.xlabel(xlabel)
plt.ylabel('Mistag rate (w.r.t. GSF tracks, pT > 0.5 GeV)')
#plt.gca().set_yscale('log')
ax.set_xlim(binning[0],binning[-2])
#ax.set_ylim([1.e-3, 1.])
ax.set_ylim([0., 0.22])
plt.legend(loc='lower right',facecolor='white',frameon=False)
plt.tight_layout()
plt.savefig(dir+'/mistag_vs_{:s}.pdf'.format(attr))
plt.clf()
plt.close()
#############
# HISTOGRAM #
#############
tuple = ([
'gsf_pt',
'gsf_mode_pt',
'gsf_dxy',
'gsf_dz',
'rho',
],
[
bin_edges,
bin_edges,
np.linspace(0.,3.3,12),
np.linspace(0.,22.,12),
np.linspace(0.,44.,12),
],
[
'Transverse momentum (GeV)',
'Mode transverse momentum (GeV)',
'Transverse impact parameter w.r.t. beamspot (cm)',
'Longitudinal impact parameter w.r.t. beamspot (cm)',
'Median energy density from UE/pileup (GeV / unit area)',
])
print("Histograms ...")
for attr,binning,xlabel in zip(*tuple) :
print(attr)
plt.figure()
ax = plt.subplot(111)
has_gsf = (test.has_gsf) & (test.gsf_pt>0.5) & (np.abs(test.gsf_eta)<2.5)
has_ele = (test.has_ele) & (test.ele_pt>0.5) & (np.abs(test.ele_eta)<2.5)
has_gsf_ = (egamma.has_gsf) & (egamma.gsf_pt>0.5) & (np.abs(egamma.gsf_eta)<2.5)
has_ele_ = (egamma.has_ele) & (egamma.ele_pt>0.5) & (np.abs(egamma.ele_eta)<2.5)
curves = [
{"label":"Low-pT (signal)","var":test[attr],"mask":(test.is_e)&(has_gsf),"condition":(has_ele),"colour":"red","fill":False,"size":7,},
{"label":"Low-pT (bkgd)","var":test[attr],"mask":(~test.is_e)&(has_gsf),"condition":(has_ele),"colour":"red","fill":True,"size":7,},
{"label":"EGamma (signal)","var":egamma[attr],"mask":(egamma.is_e)&(has_gsf_),"condition":(has_ele_),"colour":"purple","fill":False,"size":7,},
{"label":"EGamma (bkgd)","var":egamma[attr],"mask":(~egamma.is_e)&(has_gsf_),"condition":(has_ele_),"colour":"purple","fill":True,"size":7,},
]
for idx,curve in enumerate(curves) :
# print("label:",curve["label"])
his_total,_ = np.histogram(curve["var"][curve["mask"]],bins=binning)
his_passed,_ = np.histogram(curve["var"][curve["mask"]&curve["condition"]],bins=binning)
x=binning[:-1]
y=[ y/w if y > 0 else 0. for w,x,y in zip(bin_widths,his_passed,his_total) ]
yhigh=[0.]*len(y)
ylow =[0.]*len(y)
yerr =[ylow,yhigh]
label='{:s} (mean={:5.3f})'.format(curve["label"],
float(his_passed.sum())/float(his_total.sum()) \
if his_total.sum() > 0 else 0.)
ax.errorbar(x=x,
y=y,
yerr=yerr,
#color=None,
label=label,
marker='o',
color=curve["colour"],
markerfacecolor = curve["colour"] if curve["fill"] else "white",
markersize=curve["size"],
linewidth=0.5,
elinewidth=0.5)
# #########
# Finish up ...
#plt.title('Low-pT electron performance (UltraLegacy)')
plt.xlabel(xlabel)
plt.ylabel('Denominator (w.r.t. GSF tracks, pT > 0.5 GeV)')
ax.set_xlim(binning[0],binning[-2])
plt.ylim([0.,None])
plt.legend(loc='lower right',facecolor='white',frameon=False)
plt.tight_layout()
plt.savefig(dir+'/denom_vs_{:s}.pdf'.format(attr))
plt.clf()
plt.close()