def test_coordinate_transforms(nevents, nparticles):
p4s = ef.gen_random_events(nevents, nparticles, dim=4,
mass='random').reshape(nevents, nparticles, 4)
ptyphims = ef.ptyphims_from_p4s(p4s)
new_p4s = ef.p4s_from_ptyphims(ptyphims)
assert epsilon_diff(p4s, new_p4s, 1e-11)
def fit_pfn(self, model_settings):
# convert labels to categorical
Y_PFN = energyflow.utils.to_categorical(self.y, num_classes=2)
# preprocess by centering jets and normalizing pts
X_PFN = self.X_particles
for x_PFN in X_PFN:
mask = x_PFN[:,0] > 0
yphi_avg = np.average(x_PFN[mask,1:3], weights=x_PFN[mask,0], axis=0)
x_PFN[mask,1:3] -= yphi_avg
x_PFN[mask,0] /= x_PFN[:,0].sum()
# handle particle id channel
if model_settings['use_pids']:
self.my_remap_pids(X_PFN)
else:
X_PFN = X_PFN[:,:,:3]
# Split data into train, val and test sets
(X_PFN_train, X_PFN_val, X_PFN_test,Y_PFN_train, Y_PFN_val, Y_PFN_test) = energyflow.utils.data_split(X_PFN, Y_PFN,
val=self.n_val, test=self.n_test)
# build architecture
pfn = energyflow.archs.PFN(input_dim=X_PFN.shape[-1],
Phi_sizes=model_settings['Phi_sizes'],
F_sizes=model_settings['F_sizes'])
# train model
pfn.fit(X_PFN_train, Y_PFN_train,
epochs=model_settings['epochs'],
batch_size=model_settings['batch_size'],
validation_data=(X_PFN_val, Y_PFN_val),
verbose=1)
# get predictions on test data
preds_PFN = pfn.predict(X_PFN_test, batch_size=1000)
# Get AUC and ROC curve + make plot
auc_PFN = sklearn.metrics.roc_auc_score(Y_PFN_test[:,1], preds_PFN[:,1])
print('Particle Flow Networks/Deep Sets: AUC = {} (test set)'.format(auc_PFN))
self.roc_curve_dict['PFN'] = sklearn.metrics.roc_curve(Y_PFN_test[:,1], preds_PFN[:,1])
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
# Now we compare the PFN ROC curve to single observables
# 1. Jet mass (Note: This takes in (pt,y,phi) and converts it to 4-vectors and computes jet mass)
# (Note: X_PFN_train is centered and normalized .. should be ok)
masses = np.asarray([energyflow.ms_from_p4s(energyflow.p4s_from_ptyphims(x).sum(axis=0)) for x in X_PFN_train])
self.roc_curve_dict['Jet_mass'] = sklearn.metrics.roc_curve(Y_PFN_train[:,1], -masses)
# 2. Multiplicity (Is this a useful observable for pp vs AA?)
mults = np.asarray([np.count_nonzero(x[:,0]) for x in X_PFN_train])
self.roc_curve_dict['Multiplicity'] = sklearn.metrics.roc_curve(Y_PFN_train[:,1], -mults)
def test_phis_from_p4s(nevents, nparticles, phi_ref):
phis = 2 * np.pi * np.random.rand(nevents, nparticles, 1)
ys = 6 * np.random.rand(nevents, nparticles, 1) - 3
pts = 100 * np.random.rand(nevents, nparticles, 1)
ms = np.random.rand(nevents, nparticles, 1)
p4s = ef.p4s_from_ptyphims(np.concatenate((pts, ys, phis, ms), axis=-1))
if isinstance(phi_ref, str) and phi_ref == 'array':
phi_ref = 2 * np.pi * np.random.rand(nevents)
new_phis = ef.phis_from_p4s(p4s, phi_ref=phi_ref)
if phi_ref is None:
assert epsilon_diff(new_phis, phis[..., 0])
else:
if isinstance(phi_ref, str) and phi_ref == 'hardest':
phi_ref = np.asarray(
[phis[i, np.argmax(pts[i, :, 0]), 0] for i in range(nevents)])
assert np.all(np.abs(new_phis.T - phi_ref) <= np.pi)
def test_sum_ptyphims(nparticles, scheme):
p4s = ef.gen_random_events(10, nparticles, dim=4, mass='random')
ptyphims = ef.ptyphims_from_p4s(p4s)
if scheme == 'escheme':
for ev_p4s, ev_ptyphims in zip(p4s, ptyphims):
tot = ef.p4s_from_ptyphims(
ef.sum_ptyphims(ev_ptyphims, scheme=scheme))
tot_p4 = ev_p4s.sum(axis=0)
assert epsilon_diff(tot, tot_p4, 10**-12)
elif scheme == 'ptscheme':
for ev_ptyphims in ptyphims:
tot = ef.sum_ptyphims(ev_ptyphims, scheme=scheme)
pt = ev_ptyphims[:, 0].sum()
y = np.sum(ev_ptyphims[:, 0] * ev_ptyphims[:, 1]) / pt
phi = np.sum(ev_ptyphims[:, 0] * ev_ptyphims[:, 2]) / pt
assert epsilon_diff(tot, np.array([pt, y, phi]), 10**-12)
auc = roc_auc_score(Y_test[:, 1], preds[:, 1])
print()
print('EFN AUC:', auc)
print()
# some nicer plot settings
plt.rcParams['font.family'] = 'serif'
plt.rcParams['figure.autolayout'] = True
fig, axes = plt.subplots(1, 2, figsize=(8, 4))
######################### ROC Curve Plot #########################
# get multiplicity and mass for comparison
masses = np.asarray(
[ef.ms_from_p4s(ef.p4s_from_ptyphims(x).sum(axis=0)) for x in X])
mults = np.asarray([np.count_nonzero(x[:, 0]) for x in X])
mass_fp, mass_tp, threshs = roc_curve(Y[:, 1], -masses)
mult_fp, mult_tp, threshs = roc_curve(Y[:, 1], -mults)
# plot the ROC curves
axes[0].plot(efn_tp, 1 - efn_fp, '-', color='black', label='EFN')
axes[0].plot(mass_tp, 1 - mass_fp, '-', color='blue', label='Jet Mass')
axes[0].plot(mult_tp, 1 - mult_fp, '-', color='red', label='Multiplicity')
# axes labels
axes[0].set_xlabel('Quark Jet Efficiency')
axes[0].set_ylabel('Gluon Jet Rejection')
# axes limits
axes[0].set_xlim(0, 1)
def __init__(self, sim):
sim_numbers = set(sim.evns)
t1_start = process_time()
self.event_list = []
self.event_jet_labels = []
self.event_pts = []
self.event_etas = []
self.event_phis = []
self.event_ms = []
i = 1
print("Starting event processing")
for evn_num in sim_numbers:
if i % 1000 == 0:
print("Working on event " + str(i))
self.event_list.append(
np.asarray(sim.particles[sim.jets_i[:, sim.evn] == evn_num]))
self.event_jet_labels.append(
np.asarray(sim.hard_pids[sim.jets_i[:, sim.evn] == evn_num]))
self.event_pts.append(
np.asarray(sim.jet_pts[sim.jets_i[:, sim.evn] == evn_num]))
self.event_etas.append(
np.asarray(sim.jet_etas[sim.jets_i[:, sim.evn] == evn_num]))
self.event_phis.append(
np.asarray(sim.jet_phis[sim.jets_i[:, sim.evn] == evn_num]))
self.event_ms.append(
np.asarray(sim.jet_ms[sim.jets_i[:, sim.evn] == evn_num]))
if i % 1000 == 0:
print(str(i) + " events processed")
i += 1
print()
i = 1
print("Starting mass calculation")
self.event_stats = []
for i in range(len(self.event_pts)):
self.event_stats.append([])
for j in range(len(self.event_pts[i])):
ptyphims = []
ptyphims.append(self.event_pts[i][j])
ptyphims.append(self.event_etas[i][j])
ptyphims.append(self.event_phis[i][j])
ptyphims.append(self.event_ms[i][j])
p4s = ef.p4s_from_ptyphims(np.array(ptyphims))
self.event_stats[i].append(p4s.tolist())
if i % 1000 == 0:
print(str(i) + " event masses calculated")
i += 1
t1_stop = process_time()
print("Elapsed time during the whole program in seconds:",
t1_stop - t1_start)
# get ROC curve if we have sklearn
if roc_curve:
cnn_fp, cnn_tp, threshs = roc_curve(Y_test[:,1], preds[:,1])
# get area under the ROC curve
auc = roc_auc_score(Y_test[:,1], preds[:,1])
print()
print('CNN AUC:', auc)
print()
# make ROC curve plot if we have matplotlib
if plt:
# get multiplicity and mass for comparison
masses = np.asarray([ef.ms_from_p4s(ef.p4s_from_ptyphims(x).sum(axis=0)) for x in X])
mults = np.asarray([np.count_nonzero(x[:,0]) for x in X])
mass_fp, mass_tp, threshs = roc_curve(Y[:,1], -masses)
mult_fp, mult_tp, threshs = roc_curve(Y[:,1], -mults)
# some nicer plot settings
plt.rcParams['figure.figsize'] = (4,4)
plt.rcParams['font.family'] = 'serif'
plt.rcParams['figure.autolayout'] = True
# plot the ROC curves
plt.plot(cnn_tp, 1-cnn_fp, '-', color='black', label='CNN')
plt.plot(mass_tp, 1-mass_fp, '-', color='blue', label='Jet Mass')
plt.plot(mult_tp, 1-mult_fp, '-', color='red', label='Multiplicity')
# axes labels
def __init__(self, sim):
t1_start = process_time()
print("Starting event processing")
event_list = {}
event_jet_labels = {}
event_pts = {}
event_etas = {}
event_phis = {}
event_ms = {}
i = 0
for jet in sim.particles:
evn_num = sim.evns[i]
if evn_num in event_list:
event_list[evn_num].append(jet)
event_jet_labels[evn_num].append(sim.hard_pids[i])
event_pts[evn_num].append(sim.jet_pts[i])
event_etas[evn_num].append(sim.jet_etas[i])
event_phis[evn_num].append(sim.jet_phis[i])
event_ms[evn_num].append(sim.jet_ms[i])
else:
event_list[evn_num] = [jet]
event_jet_labels[evn_num] = [sim.hard_pids[i]]
event_pts[evn_num] = [sim.jet_pts[i]]
event_etas[evn_num] = [sim.jet_etas[i]]
event_phis[evn_num] = [sim.jet_phis[i]]
event_ms[evn_num] = [sim.jet_ms[i]]
i += 1
self.event_list = list(event_list.values())
self.event_jet_labels = list(event_jet_labels.values())
self.event_pts = list(event_pts.values())
self.event_etas = list(event_etas.values())
self.event_phis = list(event_phis.values())
self.event_ms = list(event_ms.values())
print("Event processing finished")
print("Starting 4-vector conversion")
i = 1
self.event_stats = []
for i in range(len(self.event_pts)):
self.event_stats.append([])
for j in range(len(self.event_pts[i])):
ptyphims = []
ptyphims.append(self.event_pts[i][j])
ptyphims.append(self.event_etas[i][j])
ptyphims.append(self.event_phis[i][j])
ptyphims.append(self.event_ms[i][j])
p4s = ef.p4s_from_ptyphims(np.array(ptyphims))
self.event_stats[i].append(p4s.tolist())
i += 1
t1_stop = process_time()
print("4-vector conversion finished")
print("Elapsed time during event and 4-vector parsing in seconds:",
t1_stop - t1_start)
