if (X0_eventnum.shape[0] != X0.shape[0]):
print(
'problem when loading, #eventnumbers does not match #events, exit')
exit(1)
else:
# some samples won't have an eventnumber,
# but ATLAS ones should, since we use it to propagate the weight to reco-level events
if (DEBUG):
print("No eventnumber found in dataset.")
# load model and evaluate weights:
carl = RatioEstimator()
if (DEBUG):
print('Loading model from:', model_out_path)
carl.load(model_out_path + '/carl/')
r_hat, s_hat = carl.evaluate(X0)
# prevent -ve weights (should be rounding only):
r_hat = ensure_positive_weight(r_hat)
# prevent 0-division
r_hat = force_nonzero(r_hat, zero_w_bound)
weights = 1. / r_hat
# ensure <weights>=1 after cropping
weights = weights * len(weights) / weights.sum()
maxweight = -1
if (crop_weight_perc > 0):
weights, _maxweight = crop_weight_nperc(weights, crop_weight_perc)
maxweight = max(maxweight, _maxweight)
logger.info(
" Doing evaluation of model trained with datasets: %s , generator variation: %s with %s events.",
sample, var, n)
else:
logger.info(
" No datasets available for evaluation of model trained with datasets: %s , generator variation: %s with %s events.",
sample, var, n)
logger.info("ABORTING")
sys.exit()
loading = Loader()
carl = RatioEstimator()
carl.load('models/' + sample + '/' + var + '_carl_' + str(n))
evaluate = ['train', 'val']
for i in evaluate:
r_hat, _ = carl.evaluate(x='data/' + sample + '/' + var + '/X0_' + i +
'_' + str(n) + '.npy')
w = 1. / r_hat
loading.load_result(
x0='data/' + sample + '/' + var + '/X0_' + i + '_' + str(n) + '.npy',
x1='data/' + sample + '/' + var + '/X1_' + i + '_' + str(n) + '.npy',
weights=w,
label=i,
do=sample,
var=var,
plot=True,
n=n,
path=p,
)
carl.evaluate_performance(
x='data/' + sample + '/' + var + '/X_val_' + str(n) + '.npy',
y='data/' + sample + '/' + var + '/y_val_' + str(n) + '.npy')
logger.info(
" No datasets available for evaluation of model trained with datasets: [{},{}] with {} events."
.format(nominal, variation, n))
logger.info("ABORTING")
sys.exit()
loading = Loader()
carl = RatioEstimator()
if model:
carl.load(model)
else:
carl.load('models/' + global_name + '_carl_' + str(n))
evaluate = ['train', 'val']
for i in evaluate:
print("<evaluate.py::__init__>:: Running evaluation for {}".format(i))
r_hat, s_hat = carl.evaluate(x='data/' + global_name + '/X0_' + i + '_' +
str(n) + '.npy')
print("s_hat = {}".format(s_hat))
print("r_hat = {}".format(r_hat))
w = 1. / r_hat # I thought r_hat = p_{1}(x) / p_{0}(x) ???
print("w = {}".format(w))
print("<evaluate.py::__init__>:: Loading Result for {}".format(i))
loading.load_result(
x0='data/' + global_name + '/X0_' + i + '_' + str(n) + '.npy',
x1='data/' + global_name + '/X1_' + i + '_' + str(n) + '.npy',
w0='data/' + global_name + '/w0_' + i + '_' + str(n) + '.npy',
w1='data/' + global_name + '/w1_' + i + '_' + str(n) + '.npy',
metaData='data/' + global_name + '/metaData_' + str(n) + '.pkl',
weights=w,
features=features,
#weightFeature=weightFeature,
label=i,
#get the weight from carl-torch (weightCT) evaluated on the same model used for carlAthena and the root file from carlAthena
eventVarsCT = ['Njets', 'MET']
eventVarsCA = ['Njets', 'MET', 'weight']
jetVars = ['Jet_Pt', 'Jet_Mass']
lepVars = ['Lepton_Pt']
xCT, _ = load(f=p + '/test.root',
events=eventVarsCT,
jets=jetVars,
leps=lepVars,
n=int(n),
t='Tree',
do=sample)
xCT = xCT[sorted(xCT.columns)]
carl = RatioEstimator()
carl.load('models/' + sample + '/' + var + '_carl_2000001')
r_hat, s_hat = carl.evaluate(x=xCT.to_numpy())
weightCT = 1. / r_hat
###carlAthena inference###
#load sample with weight infered from carlAthena
xCA, _ = load(f=p + '/test.root',
events=eventVarsCA,
jets=jetVars,
leps=lepVars,
n=int(n),
t='Tree')
weightCA = xCA.weight
###compare weights###
# draw histograms comparing weight from carl-torch (weightCT) from weight infered through carlAthena (ca.weight)
loading = Loader()
# alternatively: crop X% of largest weight
crop_weight_perc = -1.
#-----------------------------------------------------------------------------
if not os.path.exists(out_csv_dir):
os.makedirs(out_csv_dir)
carl = RatioEstimator()
carl.load(model_out_path + '/carl/')
evaluate = ['train', 'val']
for i in evaluate:
x0 = data_out_path + '/X0_' + i + '.npy'
r_hat, s_hat = carl.evaluate(x=data_out_path + '/X0_' + i + '.npy')
## print('what is Carl returning?')
## r=r_hat[0]
## s=s_hat[0]
## print('r=p0/p1,s=p0/(p0+p1)')
## print(r,s,r/(1+r))
## print('r=p1/p0,s=p0/(p0+p1)') # this
## print(r,s,1/(1+r))
## print('r=p0/p1,s=p1/(p0+p1)') # this
## print(r,s,1/(1+r))
## print('r=p1/p0,s=p1/(p0+p1)')
## print(r,s,r/(1+r))
##
## exit(0)
# Carl is returning this:
# s_hat = p1 / (p0+p1), where 0 corresponds to X0