def optimize_reco():
var_edges = numpy.linspace(200, 1200, 31)
kv_val = 1.0
num_kappa_bins = 100
k2v_val_range = numpy.linspace(-2, 4, num_kappa_bins + 1)
kl_val_range = numpy.linspace(-14, 16, num_kappa_bins + 1)
grid_pixel_area = (k2v_val_range[1] -
k2v_val_range[0]) * (kl_val_range[1] - kl_val_range[0])
all_variations = [
(1, 1, 1),
(0, 1, 1),
(0.5, 1, 1),
(1.5, 1, 1),
(2, 1, 1),
(3, 1, 1),
(1, 0, 1),
(1, 2, 1),
(1, 10, 1),
(1, 1, 0.5),
(1, 1, 1.5),
(0, 0, 1),
#(2.5 , 10 , 1 )
#(-0.5 , 8 , 0.5 )
(3, -9, 1)
#(2 , 7 , 1 )
]
valid_bases = []
total = 0
for couplings in itertools.combinations(all_variations, 6):
# Unwrap each combination
if (1.0, 1.0, 1.0) not in couplings: continue
if not combination_utils.is_valid_combination(
couplings, base_equations=combination_utils.full_scan_terms):
continue
#solidarity_integral = weight_contribution_map.get_theoretical_solidarity_map(couplings, 1, k2v_val_range, kl_val_range,
#mask=lambda k2v, kl: ((k2v-1)/1)**2 + ((kl-1)/10)**2 < 1 )
#solidarity_integral = weight_contribution_map.get_theoretical_solidarity_map(couplings, 1, k2v_val_range, kl_val_range)
#solidarity_integral = (weight_contribution_map.get_theory_effective_stats_map(couplings, 1, k2v_val_range, kl_val_range)).sum()
#valid_bases.append( (solidarity_integral, couplings) )
effective_stat_integral = weight_contribution_map.get_theory_effective_stats_map(
couplings, 1, k2v_val_range, kl_val_range)
#mask=lambda k2v, kl: ((k2v-1)/1)**2 + ((kl-1)/10)**2 < 1 )
valid_bases.append((effective_stat_integral, couplings))
total += 1
if total % 10 == 0: print(total)
print('Integrals computed, sorting and printing...')
valid_bases.sort(reverse=True)
for rank, (integral, couplings) in enumerate(valid_bases):
print(rank, int(integral), couplings)
#draw_rankings([0,1,2,3], valid_bases, var_edges, kv_val, k2v_val_range, kl_val_range, 'masktop')
#draw_rankings([0,1,2,3], valid_bases, var_edges, kv_val, k2v_val_range, kl_val_range, 'neomasktop')
draw_rankings([0], valid_bases, var_edges, kv_val, k2v_val_range,
kl_val_range, 'neoeffectiveB')
def get_sorted_acceptances():
var_edges = numpy.linspace(200, 1200, 31)
kv_val = 1.0
num_bins = 21
k2v_val_range = numpy.linspace(-2, 4, num_bins)
kl_val_range = numpy.linspace(-14, 16, num_bins)
data_files = fileio_utils.read_coupling_file()
all_cutflows = fileio_utils.get_combined_cutflow_values(
data_files.keys(), data_files).values(
) # It's a really good things that python dicts are ordered...
all_events = fileio_utils.get_events(data_files.keys(), data_files)
all_histograms = [
fileio_utils.retrieve_reco_weights(var_edges, events)
for events in all_events
]
# Wrap all variations up together with their histograms so I can find combinations
all_variations = list(
zip(data_files.keys(), all_histograms, all_cutflows,
all_events)) #[:7]
print('All variations loaded, proceeding to retrieve metrics...')
theory_function = combination_utils.get_theory_xsec_function()
total = 0
basis_metrics = {}
Nweight_acceptance_list = []
for basis_set in itertools.combinations(all_variations, 6):
# Unwrap each combination
couplings, histograms, cutflows, events_list = list(zip(*basis_set))
if not combination_utils.is_valid_combination(couplings): continue
#if (1.0,1.0,1.0) not in couplings: continue
weights, errors = numpy.array(list(zip(*histograms)))
Nweight_integral = negative_weight_map.get_Nweight_sum(
couplings, weights, kv_val, k2v_val_range, kl_val_range)
accXeff = metric_accXeff_list(theory_function, couplings, cutflows)
total += 1
if total % 10 == 0: print(total)
if total % 20 != 0: continue
Nweight_acceptance_list.append([Nweight_integral, accXeff])
return Nweight_acceptance_list
def optimize_reco(which_coupling):
var_edges = numpy.linspace(200, 1200, 31)
kv_val = 1.0
num_kappa_bins = 100
data_files = fileio_utils.read_coupling_file()
if which_coupling == 'k2v':
hold_index = 1
base_equations = combination_utils.k2v_scan_terms
k2v_vals = numpy.linspace(-2, 4, num_kappa_bins + 1)
kl_vals = 1
elif which_coupling == 'kl':
hold_index = 0
base_equations = combination_utils.kl_scan_terms
k2v_vals = 1
kl_vals = numpy.linspace(-14, 16, num_kappa_bins + 1)
else:
print("What are you doing??")
exit(1)
which_variations = [
variation for variation in data_files.keys()
if variation[2] == 1 and variation[hold_index] == 1
]
all_events = fileio_utils.get_events(which_variations, data_files)
all_histograms = [
fileio_utils.retrieve_reco_weights(var_edges, events)
for events in all_events
]
# Wrap all variations up together with their histograms so I can find combinations
all_variations = list(zip(which_variations, all_histograms))
print('Histograms loaded, proceeding to integrate Nweight grids...')
valid_bases = []
total = 0
for basis_set in itertools.combinations(all_variations,
len(base_equations)):
# Unwrap each combination
couplings, histograms = list(zip(*basis_set))
if (1.0, 1.0, 1.0) not in couplings: continue
if not combination_utils.is_valid_combination(
couplings, base_equations=base_equations):
continue
weights, errors = numpy.array(list(zip(*histograms)))
nWeight_integral = negative_weight_map.get_Nweight_sum1D(
couplings,
weights,
k2v_vals,
kl_vals,
kv_val,
base_equations=base_equations,
which_coupling=which_coupling)
valid_bases.append((nWeight_integral, couplings, weights))
total += 1
if total % 10 == 0: print(total)
print('Integrals computed, sorting and printing...')
valid_bases.sort()
for rank, (integral, couplings, weight) in enumerate(valid_bases):
print(rank, f'{integral:.9f}', couplings)
ranks_to_draw = 0, 1, 2
draw_rankings(ranks_to_draw, valid_bases, which_variations, var_edges,
k2v_vals, kl_vals, kv_val, which_coupling, base_equations)
combination_utils.get_amplitude_function(valid_bases[0][1],
base_equations=base_equations,
name='optimalR0_' +
which_coupling,
output='tex')
combination_utils.get_amplitude_function(valid_bases[1][1],
base_equations=base_equations,
name='optimalR1_' +
which_coupling,
output='tex')
def optimize_reco(mode='reco', extra_files={}, extra_name=''):
var_edges = numpy.linspace(200, 1200, 31)
kv_val = 1.0
num_kappa_bins = 100
k2v_val_range = numpy.linspace(-2, 4, num_kappa_bins + 1)
kl_val_range = numpy.linspace(-14, 16, num_kappa_bins + 1)
grid_pixel_area = (k2v_val_range[1] -
k2v_val_range[0]) * (kl_val_range[1] - kl_val_range[0])
truth_data_files = None
if mode == 'reco':
data_files = fileio_utils.read_coupling_file()
all_events = fileio_utils.get_events(data_files.keys(), data_files)
all_histograms = [
fileio_utils.retrieve_reco_weights(var_edges, events)
for events in all_events
]
all_weights, all_errors = numpy.array(list(zip(*all_histograms)))
# Wrap all variations up together with their histograms so I can find combinations
all_variations = list(zip(data_files.keys(), all_weights))
elif mode == 'truth':
truth_data_files = fileio_utils.read_coupling_file(
coupling_file='basis_files/truth_LHE_couplings.dat')
truth_data_files.update(extra_files)
truth_weights, truth_errors = fileio_utils.extract_lhe_truth_data(
truth_data_files.values(), var_edges)
all_variations = list(zip(truth_data_files.keys(), truth_weights))
else:
print('What are you doing?!')
print(mode)
exit(1)
print('Histograms loaded, proceeding to integrate Nweight grids...')
valid_bases = []
total = 0
for basis_set in itertools.combinations(all_variations, 6):
# Unwrap each combination
couplings, weights = list(zip(*basis_set))
if (1.0, 1.0, 1.0) not in couplings: continue
if not combination_utils.is_valid_combination(
couplings, base_equations=combination_utils.full_scan_terms):
continue
nWeight_integral = get_Nweight_sum(couplings, weights, kv_val,
k2v_val_range, kl_val_range)
#nWeight_integral = get_Nweight_sum(couplings, weights, kv_val, k2v_val_range, kl_val_range,
# mask=lambda k2v, kl: ((k2v-1)/1)**2 + ((kl-1)/10)**2 < 1 )
valid_bases.append((nWeight_integral, couplings, weights))
total += 1
if total % 10 == 0: print(total)
print('Integrals computed, sorting and printing...')
valid_bases.sort()
for rank, (integral, couplings, weight) in enumerate(valid_bases):
print(rank, int(integral), couplings)
#draw_rankings([0,1,2,3], valid_bases, var_edges, kv_val, k2v_val_range, kl_val_range, 'quad', only_heatmap=True)
#draw_rankings([0,1], valid_bases, var_edges, kv_val, k2v_val_range, kl_val_range, 'top')
#draw_rankings([0,1,2,3], valid_bases, var_edges, kv_val, k2v_val_range, kl_val_range, extra_name+'_truth_quad', only_heatmap=True)
draw_rankings([0, 1],
valid_bases,
var_edges,
kv_val,
k2v_val_range,
kl_val_range,
extra_name + '_truth_top',
only_heatmap=False,
truth_level=True,
truth_data_files=truth_data_files,
skip_preview=True)
def generate_metric_values():
var_edges = numpy.linspace(200, 1200, 31)
kv_val = 1.0
num_bins = 100
k2v_val_range = numpy.linspace(-2, 4, num_bins + 1)
kl_val_range = numpy.linspace(-14, 16, num_bins + 1)
#data_files = fileio_utils.read_coupling_file()
#all_events = fileio_utils.get_events(data_files.keys(), data_files)
#all_histograms = [ fileio_utils.retrieve_reco_weights(var_edges,events) for events in all_events ]
#all_variations = list(zip(data_files.keys(), all_histograms, all_events))#[:7]
#all_cutflows = fileio_utils.get_combined_cutflow_values(data_files.keys(), data_files).values() # It's a really good things that python dicts are ordered...
truth_data_files = fileio_utils.read_coupling_file(
coupling_file='basis_files/truth_LHE_couplings_extended.dat')
truth_weights, truth_errors = fileio_utils.extract_lhe_truth_data(
truth_data_files.values(), var_edges)
all_variations = list(
zip(truth_data_files.keys(), truth_weights, truth_errors))
#assert list(data_files.keys()) == list(truth_data_files.keys())
#all_variations = list(zip(data_files.keys(), all_histograms, all_events, all_events, truth_weights, truth_errors))
# Wrap all variations up together with their histograms so I can find combinations
#all_variations = list(zip(data_files.keys(), all_histograms, all_cutflows, all_events))#[:7]
print('All variations loaded, proceeding to retrieve metrics...')
#for variation, cuts in zip(data_files.keys(), all_cutflows):
# accXeff = cuts['Signal'] / cuts['Initial']
# print(variation, accXeff)
#exit()
total = 0
basis_metrics = {}
for basis_set in itertools.combinations(all_variations, 6):
# Unwrap each combination
#couplings, histograms, cutflows, events_list, truth_weights, truth_errors = list(zip(*basis_set))
#couplings, histograms, events_list = list(zip(*basis_set))
couplings, truth_weights, truth_errors = list(zip(*basis_set))
if not is_valid_combination(couplings): continue
#if (1.0,1.0,1.0) not in couplings: continue
#weights, errors = numpy.array( list(zip(*histograms)) )
basis_metrics[couplings] = {
#'Nweight_integral': get_Nweight_sum(couplings, weights, kv_val, k2v_val_range, kl_val_range),
'Nweight_truth_integral':
get_Nweight_sum(couplings, truth_weights, kv_val, k2v_val_range,
kl_val_range),
#'orthogonality': metric_orthogonality(couplings),
#'reco_effective_stats_integral': metric_reco_effective_stats_integral(couplings, events_list, kv_val, k2v_val_range, kl_val_range),
'theory_effective_stats_integral':
get_theory_effective_stats_map(couplings, kv_val, k2v_val_range,
kl_val_range),
#'reco_solidarity_integral': get_reco_solidarity_map(couplings, weights, kv_val, k2v_val_range, kl_val_range),
'theory_solidarity_integral':
get_theoretical_solidarity_map(couplings, kv_val, k2v_val_range,
kl_val_range),
#'theory_test_val': metric_theory_test_val(couplings),
#'contribution_integral': metric_contribution_integral(couplings, kv_val, k2v_val_range, kl_val_range),
#'accXeff_list': metric_accXeff_list(cutflows),
#'accXeff_sum': metric_accXeff_sum(cutflows),
#'accXeff_geometric': metric_accXeff_geometric_mean(cutflows),
#'accXeff_rms': metric_accXeff_rms(cutflows),
#'accXeff_avg_stdev': metric_accXeff_avg_stdev(cutflows),
#'accXeff_min': metric_accXeff_min(cutflows),
#'accXeff_sigma': metric_accXeff_sigma(cutflows),
#'accXeff_harmonic': metric_accXeff_harmonic_mean(cutflows),
#'eventCount_sum': metric_eventCount_sum(events_list)
}
total += 1
if total % 10 == 0: print(total)
print('Variations traversed, plotting...')
metric_lists = {key: [] for key in list(basis_metrics.values())[0].keys()}
for basis, metrics in basis_metrics.items():
for key, val in metrics.items():
metric_lists[key].append(val)
return metric_lists