Skip to content

Added mixed datasets, updated b-tag SF-efficiency calculation and minor #49

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
thierryharte wants to merge 5 commits into
base: main
Choose a base branch
from
Open

Added mixed datasets, updated b-tag SF-efficiency calculation and minor #49

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
5963ac0
Added mixed dataset to datasets
thierryharte Apr 28, 2026
3c4525b
Merge remote-tracking branch 'matteo/main'
thierryharte Apr 28, 2026
58716a9
Added mixed dataset and added editable cms text to plots
thierryharte Apr 28, 2026
f1603a4
New configs, allow separate weight save, update b-tag SF efficiencies
thierryharte Apr 28, 2026
b3ddd9c
Fixed different smaller issues, separated mixeddata and larger contro…
thierryharte Apr 29, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
87 changes: 56 additions & 31 deletions configs/HH4b/HH4b_parton_matching_config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,7 +87,7 @@

# Defining the used samples
sample_ggF_list = [
# "GluGlutoHHto4B_spanet_kl-1p00_kt-1p00_c2-0p00_skimmed",
"GluGlutoHHto4B_spanet_kl-1p00_kt-1p00_c2-0p00_skimmed",
# "GluGlutoHHto4B_spanet_kl-5p00_kt-1p00_c2-0p00_skimmed",
# "GluGlutoHHto4B_spanet_kl-2p45_kt-1p00_c2-0p00_skimmed",
# "GluGlutoHHto4B_spanet_kl-m2p00_kt-1p00_c2-0p00_skimmed",
Expand All @@ -100,23 +100,34 @@
# "GluGlutoHHto4B_spanet_kl-1p50_kt-1p00_c2-0p00_skimmed",
# "GluGlutoHHto4B_spanet_kl-0p50_kt-1p00_c2-0p00_skimmed",
]
sample_list = [
# "DATA_JetMET_JMENano_C_skimmed",
# "DATA_JetMET_JMENano_D_skimmed",
# "DATA_JetMET_JMENano_E_skimmed",
"DATA_JetMET_JMENano_F_skimmed",
# "DATA_JetMET_JMENano_G_skimmed",
# "GluGlutoHHto4B_spanet_skimmed",
# "GluGlutoHHto4B_spanet_skimmed_SM",
# "GluGlutoHHto4B_spanet_skimmed",
# "GluGlutoHHto4B",
# "DATA_JetMET_JMENano_2023_Cv1_skimmed",
# "DATA_JetMET_JMENano_2023_Cv2_skimmed",
# "DATA_ParkingHH_2023_Cv3",
# "DATA_ParkingHH_2023_Cv4",
# "DATA_ParkingHH_2023_Dv1",
# "DATA_ParkingHH_2023_Dv2",
] + sample_ggF_list
sample_mixed_list = [
# "MixedData_2022_preEE",
"MixedData_2022_postEE",
# "MixedData_2023_preBPix",
# "MixedData_2023_postBPix"
]

if config_options_dict["mixeddata"]:
sample_list = sample_mixed_list
else:
sample_list = [
# "DATA_JetMET_JMENano_C_skimmed",
# "DATA_JetMET_JMENano_D_skimmed",
# "DATA_JetMET_JMENano_E_skimmed",
# "DATA_JetMET_JMENano_F_skimmed",
"DATA_JetMET_JMENano_G_skimmed",
# "GluGlutoHHto4B_spanet_skimmed",
# "GluGlutoHHto4B_spanet_skimmed_SM",
# "GluGlutoHHto4B_spanet_skimmed",
# "GluGlutoHHto4B",
# "DATA_JetMET_JMENano_2023_Cv1_skimmed",
# "DATA_JetMET_JMENano_2023_Cv2_skimmed",
# "DATA_ParkingHH_2023_Cv3",
# "DATA_ParkingHH_2023_Cv4",
# "DATA_ParkingHH_2023_Dv1",
# "DATA_ParkingHH_2023_Dv2",
] + sample_ggF_list


# Define the categories to save
categories_dict = define_categories(
Expand All @@ -125,6 +136,7 @@
spanet=config_options_dict["spanet"],
run2=config_options_dict["run2"],
vr1=config_options_dict["vr1"],
expandCR=config_options_dict["expandCR"],
)
# AKA if no model is applied
# print(onnx_model_dict)
Expand Down Expand Up @@ -169,6 +181,7 @@
"jet_eta": ["JetGoodFromHiggsOrdered5Jets", "eta", "norm"],
"jet_phi": ["JetGoodFromHiggsOrdered5Jets", "phi", "norm"],
"jet_log_mass": ["JetGoodFromHiggsOrdered5Jets", "mass", "log_norm"],
"add_jet1pt_btag_wp": ["add_jet1pt", "btagPNetB_5wp"],
}
)
if config_options_dict["spanet"]:
Expand Down Expand Up @@ -210,7 +223,7 @@
column_listRun2 += get_columns_list({"events": ["sig_bkg_dnn_scoreRun2"]})
if config_options_dict["spanet"] and not any(
["DATA" in sample for sample in sample_list]
):
) and not any(["Mixed" in sample for sample in sample_list]):
column_list += get_columns_list(
{
"events": [
Expand All @@ -233,6 +246,18 @@
}
)

save_separate_weights = False
if save_separate_weights:
column_list += get_columns_list(
{
"events": [
"weight_single_lumi",
"weight_single_XS",
"weight_single_pileup",
"weight_single_sf_btag_fixed_multiple_wp",
]
}
)

bysample_bycategory_column_dict = {}
for sample in sample_list:
Expand All @@ -248,7 +273,7 @@
get_columns_list(
{"events": ["bkg_morphing_spread_dnn_weightsRun2"]}
)
if "DATA" in sample
if "DATA" in sample.upper()
and config_options_dict["bkg_morphing_spread_dnn"]
and "postW" in category
else []
Expand All @@ -259,8 +284,8 @@
column_list
+ (
get_columns_list({"events": ["bkg_morphing_spread_dnn_weights"]})
if "DATA" in sample
and config_options_dict["bkg_morphing_spread_dnn"]
# if "DATA" in sample
if config_options_dict["bkg_morphing_spread_dnn"]
and "postW" in category
else []
)
Expand All @@ -270,7 +295,7 @@
# Define the weights to apply
bysample_bycategory_weight_dict = {}
for sample in sample_list:
if "DATA" in sample:
if "DATA" in sample.upper():
bysample_bycategory_weight_dict[sample] = {"inclusive": [], "bycategory": {}}
for category in categories_dict.keys():
if "postW" in category:
Expand All @@ -295,6 +320,7 @@
f"{localdir}/../HH4b_common/datasets/GluGlutoHHto4B_spanet_skimmed_SM.json",
f"{localdir}/../HH4b_common/datasets/GluGlutoHHto4B_spanet_skimmed_separateSamples.json",
f"{localdir}/../HH4b_common/datasets/DATA_JetMET_skimmed.json",
f"{localdir}/../HH4b_common/datasets/mixeddata.json",
# f"{localdir}/../HH4b_common/datasets/QCD.json",
# f"{localdir}/../HH4b_common/datasets/SPANet_classification.json",
# f"{localdir}/../HH4b_common/datasets/signal_ggF_HH4b_local.json",
Expand All @@ -314,14 +340,13 @@
skim=cuts.skimming_cut_list(config_options_dict),
preselections=preselection,
categories=categories_dict,
weights_classes=common_weights
+ [bkg_morphing_dnn_weight, bkg_morphing_dnn_weightRun2, SF_btag_fixed_multiple_wp],
# calibrators=[legacy_cal.JetsCalibrator, legacy_cal.JetsPtRegressionCalibrator],
calibrators=[JetsCalibrator],
# weights_classes=[bkg_morphing_dnn_weight],# common_weights
weights_classes=common_weights + [bkg_morphing_dnn_weight, bkg_morphing_dnn_weightRun2, SF_btag_fixed_multiple_wp] ,
calibrators=[JetsCalibrator] if not config_options_dict['mixeddata'] else [],
weights={
"common": {
"inclusive": ["genWeight", "lumi", "XS", "pileup", "sf_btag_fixed_multiple_wp"],
# "inclusive": ["genWeight", "lumi", "XS", "pileup"],
# "inclusive": ["genWeight", "lumi", "XS", "pileup", "sf_btag_fixed_multiple_wp"],
"inclusive": ["genWeight", "lumi", "XS", "pileup"],
# "inclusive": ["genWeight", "lumi", "XS"],
# "inclusive": [],
"bycategory": {
Expand All @@ -332,8 +357,8 @@
variations={
"weights": {
"common": {
"inclusive": ["XS", "lumi", "pileup", "sf_btag_fixed_multiple_wp"],
# "inclusive": [],
# "inclusive": ["XS", "lumi", "pileup", "sf_btag_fixed_multiple_wp"],
"inclusive": [],
"bycategory": {},
},
"bysample": {},
Expand Down
Loading