Skip to content
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

Jump to bottom

Add producers for tau ID and trigger weights. #4

Merged
merged 11 commits into from
Dec 23, 2022
Merged

Add producers for tau ID and trigger weights. #4

Show file tree
Hide file tree
Changes from 8 commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
0ab5fa5
Add producers for tau ID and trigger weights.
riga Dec 19, 2022
d254a60
Typos.
riga Dec 20, 2022
5d8f551
Merge branch 'master' into feature/tau_and_trigger_weights.
riga Dec 20, 2022
3ef7031
Merge branch 'master' into feature/tau_and_trigger_weights.
riga Dec 20, 2022
56ef896
Merge branch 'master' into feature/tau_and_trigger_weights.
riga Dec 21, 2022
96a11ee
Merge branch 'master' into feature/tau_and_trigger_weights.
riga Dec 21, 2022
525815c
Add limted config.
riga Dec 21, 2022
58e5aaf
Simplify btag wp in config.
riga Dec 21, 2022
7e6ae07
Reduce code redundancy in tau trigger weight computation.
riga Dec 22, 2022
65fcdb8
Disable versioning for now.
riga Dec 22, 2022
41dcf33
Add comments about column origin to all producers / selectors.
riga Dec 22, 2022
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
18 changes: 16 additions & 2 deletions hbt/config/analysis_hbt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,8 +52,22 @@
# 2017
from hbt.config.configs_run2ul import add_config as add_config_run2ul
import cmsdb.campaigns.run2_2017_nano_v9
campaign_run2_2017_nano_v9 = cmsdb.campaigns.run2_2017_nano_v9.campaign_run2_2017_nano_v9.copy()

campaign_run2_2017_nano_v9 = cmsdb.campaigns.run2_2017_nano_v9.campaign_run2_2017_nano_v9

# default config
add_config_run2ul(
analysis_hbt,
campaign_run2_2017_nano_v9.copy(),
config_name=campaign_run2_2017_nano_v9.name,
config_id=2,
)

# config with limited number of files
add_config_run2ul(
analysis_hbt,
campaign_run2_2017_nano_v9,
campaign_run2_2017_nano_v9.copy(),
config_name=f"{campaign_run2_2017_nano_v9.name}_limited",
config_id=12,
limit_dataset_files=2,
)
110 changes: 42 additions & 68 deletions hbt/config/configs_run2ul.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,8 @@
Configuration of the HH → bb𝜏𝜏 analysis.
"""

from __future__ import annotations

import os
import re
import itertools
Expand All @@ -18,7 +20,13 @@
thisdir = os.path.dirname(os.path.abspath(__file__))


def add_config(analysis: od.Analysis, campaign: od.Campaign) -> od.Config:
def add_config(
analysis: od.Analysis,
campaign: od.Campaign,
config_name: str | None = None,
config_id: int | None = None,
pkausw marked this conversation as resolved.
Show resolved Hide resolved
limit_dataset_files: int | None = None,
) -> od.Config:
# some validations
assert campaign.x.year in [2016, 2017, 2018]
if campaign.x.year == 2016:
Expand All @@ -33,7 +41,7 @@ def add_config(analysis: od.Analysis, campaign: od.Campaign) -> od.Config:
procs = get_root_processes_from_campaign(campaign)

# create a config by passing the campaign, so id and name will be identical
cfg = analysis.add_config(campaign)
cfg = analysis.add_config(campaign, name=config_name, id=config_id)

# add processes we are interested in
cfg.add_process(procs.n.data)
Expand Down Expand Up @@ -126,6 +134,11 @@ def add_config(analysis: od.Analysis, campaign: od.Campaign) -> od.Config:
if dataset.name.startswith("tt"):
dataset.x.is_ttbar = True

# apply an optional limit on the number of files
if limit_dataset_files:
for info in dataset.info.values():
info.n_files = limit_dataset_files

# default objects, such as calibrator, selector, producer, ml model, inference model, etc
cfg.x.default_calibrator = "default"
cfg.x.default_selector = "default"
Expand Down Expand Up @@ -189,66 +202,26 @@ def add_config(analysis: od.Analysis, campaign: od.Campaign) -> od.Config:
cfg.x.minbias_xs = Number(69.2, 0.046j)

# whether to validate the number of obtained LFNs in GetDatasetLFNs
cfg.x.validate_dataset_lfns = True
cfg.x.validate_dataset_lfns = limit_dataset_files is None

# b-tag working points
if year == 2016:
if campaign.x.vfp == "pre":
# https://twiki.cern.ch/twiki/bin/view/CMS/BtagRecommendation106XUL16preVFP?rev=6
cfg.x.btag_working_points = DotDict.wrap({
"deepjet": {
"loose": 0.0508,
"medium": 0.2598,
"tight": 0.6502,
},
"deepcsv": {
"loose": 0.2027,
"medium": 0.6001,
"tight": 0.8819,
},
})
else: # post
# https://twiki.cern.ch/twiki/bin/view/CMS/BtagRecommendation106XUL16postVFP?rev=8
cfg.x.btag_working_points = DotDict.wrap({
"deepjet": {
"loose": 0.0480,
"medium": 0.2489,
"tight": 0.6377,
},
"deepcsv": {
"loose": 0.1918,
"medium": 0.5847,
"tight": 0.8767,
},
})
elif year == 2017:
# https://twiki.cern.ch/twiki/bin/view/CMS/BtagRecommendation106XUL17?rev=15
cfg.x.btag_working_points = DotDict.wrap({
"deepjet": {
"loose": 0.0532,
"medium": 0.3040,
"tight": 0.7476,
},
"deepcsv": {
"loose": 0.1355,
"medium": 0.4506,
"tight": 0.7738,
},
})
else: # 2018
# https://twiki.cern.ch/twiki/bin/view/CMS/BtagRecommendation106XUL17?rev=17
cfg.x.btag_working_points = DotDict.wrap({
"deepjet": {
"loose": 0.0490,
"medium": 0.2783,
"tight": 0.7100,
},
"deepcsv": {
"loose": 0.1208,
"medium": 0.4168,
"tight": 0.7665,
},
})
# https://twiki.cern.ch/twiki/bin/view/CMS/BtagRecommendation106XUL16preVFP?rev=6
# https://twiki.cern.ch/twiki/bin/view/CMS/BtagRecommendation106XUL16postVFP?rev=8
# https://twiki.cern.ch/twiki/bin/view/CMS/BtagRecommendation106XUL17?rev=15
# https://twiki.cern.ch/twiki/bin/view/CMS/BtagRecommendation106XUL17?rev=17
btag_key = f"2016{campaign.x.vfp}" if year == 2016 else year
cfg.x.btag_working_points = DotDict.wrap({
"deepjet": {
"loose": {"2016pre": 0.0508, "2016post": 0.0480, 2017: 0.0532, 2018: 0.0490}[btag_key],
"medium": {"2016pre": 0.2598, "2016post": 0.2489, 2017: 0.3040, 2018: 0.2783}[btag_key],
"tight": {"2016pre": 0.6502, "2016post": 0.6377, 2017: 0.7476, 2018: 0.7100}[btag_key],
},
"deepcsv": {
"loose": {"2016pre": 0.2027, "2016post": 0.1918, 2017: 0.1355, 2018: 0.1208}[btag_key],
"medium": {"2016pre": 0.6001, "2016post": 0.5847, 2017: 0.4506, 2018: 0.4168}[btag_key],
"tight": {"2016pre": 0.8819, "2016post": 0.8767, 2017: 0.7738, 2018: 0.7665}[btag_key],
},
})

# name of the btag_sf correction set
cfg.x.btag_sf_correction_set = "deepJet_shape"
Expand Down Expand Up @@ -547,25 +520,25 @@ def add_aliases(
)

# external files
corrlib_base = "/afs/cern.ch/user/m/mrieger/public/mirrors/jsonpog-integration-849c6a6e"
json_mirror = "/afs/cern.ch/user/m/mrieger/public/mirrors/jsonpog-integration-849c6a6e"
cfg.x.external_files = DotDict.wrap({
# jet energy correction
"jet_jerc": (f"{corrlib_base}/POG/JME/{year}{corr_postfix}_UL/jet_jerc.json.gz", "v1"),
"jet_jerc": (f"{json_mirror}/POG/JME/{year}{corr_postfix}_UL/jet_jerc.json.gz", "v1"),

# tau energy correction and scale factors
"tau_sf": (f"{corrlib_base}/POG/TAU/{year}{corr_postfix}_UL/tau.json.gz", "v1"),
"tau_sf": (f"{json_mirror}/POG/TAU/{year}{corr_postfix}_UL/tau.json.gz", "v1"),

# electron scale factors
"electron_sf": (f"{corrlib_base}/POG/EGM/{year}{corr_postfix}_UL/electron.json.gz", "v1"),
"electron_sf": (f"{json_mirror}/POG/EGM/{year}{corr_postfix}_UL/electron.json.gz", "v1"),

# muon scale factors
"muon_sf": (f"{corrlib_base}/POG/MUO/{year}{corr_postfix}_UL/muon_Z.json.gz", "v1"),
"muon_sf": (f"{json_mirror}/POG/MUO/{year}{corr_postfix}_UL/muon_Z.json.gz", "v1"),

# btag scale factor
"btag_sf_corr": (f"{corrlib_base}/POG/BTV/{year}{corr_postfix}_UL/btagging.json.gz", "v1"),
"btag_sf_corr": (f"{json_mirror}/POG/BTV/{year}{corr_postfix}_UL/btagging.json.gz", "v1"),

# met phi corrector
"met_phi_corr": (f"{corrlib_base}/POG/JME/{year}{corr_postfix}_UL/met.json.gz", "v1"),
"met_phi_corr": (f"{json_mirror}/POG/JME/{year}{corr_postfix}_UL/met.json.gz", "v1"),

# hh-btag repository (lightweight) with TF saved model directories
"hh_btag_repo": ("https://github.com/hh-italian-group/HHbtag/archive/1dc426053418e1cab2aec021802faf31ddf3c5cd.tar.gz", "v1"), # noqa
Expand Down Expand Up @@ -684,7 +657,8 @@ def add_aliases(

# versions per task family and optionally also dataset and shift
pkausw marked this conversation as resolved.
Show resolved Hide resolved
# None can be used as a key to define a default value
if cfg.name == "run2_2017_nano_v9":
# TODO: all configs use the same versioning right now, which needs to be a bit smarter
if cfg.name == "run2_2017_nano_v9" or True:
cfg.x.versions = {
# "cf.CalibrateEvents": "dev1",
# "cf.MergeSelectionStats": "dev1",
Expand Down
Loading