Merge branch 'main' of https://github.com/rkansal47/HHbbVV

.codespell-whitelist.txt

@@ -1,3 +1,4 @@
 subjet
 fpr
 tpr
+datas

.gitignore

@@ -189,8 +189,9 @@ tau_check.ipynb
 src/HHbbVV/postprocessing/testBDT
 src/HHbbVV/postprocessing/templates/*test*
 src/HHbbVV/postprocessing/templates/*Test*
+src/HHbbVV/postprocessing/test_templates
 tmp
+src/HHbbVV/postprocessing/templates_old
 
 # logs
 src/HHbbVV/postprocessing/outs
-src/HHbbVV/postprocessing/templates_old

.pre-commit-config.yaml

@@ -1,10 +1,11 @@
 ci:
   autoupdate_commit_msg: "chore: update pre-commit hooks"
   autofix_commit_msg: "style: pre-commit fixes"
+  autoupdate_schedule: quarterly
 
 repos:
   - repo: https://github.com/psf/black-pre-commit-mirror
-    rev: "24.2.0"
+    rev: "24.3.0"
     hooks:
       - id: black-jupyter
         args: [--line-length=100]
@@ -39,15 +40,15 @@ repos:
       - id: rst-directive-colons
       - id: rst-inline-touching-normal
 
-  - repo: https://github.com/pre-commit/mirrors-prettier
-    rev: "v3.1.0"
-    hooks:
-      - id: prettier
-        types_or: [yaml, markdown, html, css, scss, javascript, json]
-        args: [--prose-wrap=always]
+  # - repo: https://github.com/pre-commit/mirrors-prettier
+  #   rev: "v4.0.0-alpha.8"
+  #   hooks:
+  #     - id: prettier
+  #       types_or: [yaml, markdown, html, css, scss, javascript, json]
+  #       args: [--prose-wrap=always]
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: "v0.1.14"
+    rev: "v0.3.4"
     hooks:
       - id: ruff
         args: ["--fix", "--show-fixes"]
@@ -70,7 +71,7 @@ repos:
         args: ["--ignore-words", ".codespell-whitelist.txt"]
 
   - repo: https://github.com/shellcheck-py/shellcheck-py
-    rev: "v0.9.0.6"
+    rev: "v0.10.0.1"
     hooks:
       - id: shellcheck
 
@@ -89,7 +90,7 @@ repos:
         additional_dependencies: ["validate-pyproject-schema-store[all]"]
 
   - repo: https://github.com/python-jsonschema/check-jsonschema
-    rev: "0.27.3"
+    rev: "0.28.1"
     hooks:
       - id: check-dependabot
       - id: check-github-workflows

README.md

@@ -36,7 +36,7 @@ using the [coffea](https://coffeateam.github.io/coffea/) and
     - [BDT Pre-Processing](#bdt-pre-processing)
     - [BDT Trainings](#bdt-trainings)
     - [Post-Processing](#post-processing-1)
-      - [Control plots with resonant and nonresonant samples](#control-plots-with-resonant-and-nonresonant-samples)
+      - [Control plots](#control-plots)
       - [BDT sculpting plots](#bdt-sculpting-plots)
       - [Making separate background and signal templates for scan and bias tests (resonant)](#making-separate-background-and-signal-templates-for-scan-and-bias-tests-resonant)
     - [Create Datacard](#create-datacard)
@@ -325,29 +325,32 @@ python TrainBDT.py  --data-path "../../../../data/skimmer/Feb24/bdt_data" --year
 
 ### Post-Processing
 
+**Important:** If running on a Mac, make sure to install `gnu-getopt` first for
+bash scripts, see [here.](#getopt-for-mac)
+
 ```bash
 python postprocessing.py --templates --year "2017" --template-dir "templates/$TAG/" --plot-dir "../../../plots/PostProcessing/$TAG/" --data-dir "../../../../data/skimmer/Feb24/" (--resonant --signal-data-dir "" --control-plots)
 ```
 
 All years (non-resonant):
 
 ```bash
-for year in 2016 2016APV 2017 2018; do python -u postprocessing.py --templates --year $year --template-dir "templates/Jun14" --data-dir "../../../../data/skimmer/Feb24" --signal-data-dir "../../../../data/skimmer/Jun10" --bdt-preds-dir "../../../../data/skimmer/Feb24/23_05_12_multiclass_rem_feats_3/inferences"; done
+./bash_scripts/NonresTemplates.sh --tag $TAG  # remember to change data_dir as needed!
 ```
 
 Scan (non-resonant):
 
 ```bash
-for year in 2016 2016APV 2017 2018; do python -u postprocessing.py --templates --year $year --template-dir "templates/$TAG/" --data-dir "../../../../data/skimmer/Feb24/" --old-processor --nonres-txbb-wp "LP" "MP" "HP" --nonres-bdt-wp 0.995 0.998 0.999 --no-do-jshifts; done
+./bash_scripts/NonresTemplatesScan.sh --tag $TAG  # remember to change data_dir as needed!
 ```
 
-#### Control plots with resonant and nonresonant samples
-
-Run `postprocessing/bash_scripts/ControlPlots.sh` from inside
-`postprocessing folder`.
+#### Control plots
 
-**Important:** If running on a Mac, make sure to install `gnu-getopt` first, see
-[here.](#getopt-for-mac)
+```bash
+./bash_scripts/ControlPlot.sh --tag $TAG  # w/ resonant and nonresonant samples and all control plot variables in postprocessing.py script by default
+./bash_scripts/ControlPlots.sh --tag $TAG --nonresonant --controlplotvars BDTScore --nohem2d  # BDT score only
+./bash_scripts/MassPlots.sh --tag $TAG  # mSD vs mReg plots
+```
 
 #### BDT sculpting plots
 
@@ -404,23 +407,16 @@ python PlotFits.py --fit-file "cards/test_tied_stats/fitDiagnosticsBlindedBkgOnl
 
 ### CMSSW + Combine Quickstart
 
-```bash
-cmsrel CMSSW_11_2_0
-cd CMSSW_11_2_0/src
-cmsenv
-git clone -b py3 https://github.com/cms-analysis/HiggsAnalysis-CombinedLimit.git HiggsAnalysis/CombinedLimit
-git clone -b v2.0.0 https://github.com/cms-analysis/CombineHarvester.git CombineHarvester
-scramv1 b clean; scramv1 b
-```
-
-New version:
+**Warning: this should be done outside of your conda/mamba environment!**
 
 ```bash
+source /cvmfs/cms.cern.ch/cmsset_default.sh
 cmsrel CMSSW_11_3_4
 cd CMSSW_11_3_4/src
 cmsenv
-# need my fork until regex for float parameters is merged into the main repo
-git clone -b regex-float-parameters https://github.com/rkansal47/HiggsAnalysis-CombinedLimit.git HiggsAnalysis/CombinedLimit
+# git clone -b main https://github.com/rkansal47/HiggsAnalysis-CombinedLimit.git HiggsAnalysis/CombinedLimit
+# float regex PR was merged so we should be able to switch to the main branch now:
+git clone -b v9.2.0 https://github.com/cms-analysis/HiggsAnalysis-CombinedLimit.git HiggsAnalysis/CombinedLimit
 git clone -b v2.0.0 https://github.com/cms-analysis/CombineHarvester.git CombineHarvester
 # Important: this scram has to be run from src dir
 scramv1 b clean; scramv1 b

data/indexpfnano.py

@@ -33,6 +33,7 @@ def get_subfolders(parent):
     "/store/user/lpcpfnano/cmantill/v2_3/2016/JetHT2016",
     "/store/user/lpcpfnano/cmantill/v2_3/2017/JetHT2017",
     "/store/user/lpcpfnano/cmantill/v2_3/2018/JetHT2018",
+    # recovering missing data from ^:
     "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016",
     "/store/user/lpcpfnano/rkansal/v2_3/2017/JetHT2017",
     "/store/user/lpcpfnano/rkansal/v2_3/2018/JetHT2018",
@@ -136,8 +137,7 @@ def get_subfolders(parent):
 # ignore_subsamples = ["SingleMuon_Run2016B_ver1_HIPM"]
 ignore_subsamples = []
 
-# for pyear in ["2016", "2016APV", "2017", "2018"]:
-for pyear in ["2016", "2016APV"]:
+for pyear in ["2016", "2016APV", "2017", "2018"]:
     print(pyear)
     index = {}
     for f1 in folders_to_index:

data/pfnanoindex_2016.json

@@ -5091,44 +5091,7 @@
         "/store/user/lpcpfnano/cmantill/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/220701_193717/0000/nano_data2016_96.root",
         "/store/user/lpcpfnano/cmantill/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/220701_193717/0000/nano_data2016_97.root",
         "/store/user/lpcpfnano/cmantill/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/220701_193717/0000/nano_data2016_98.root",
-        "/store/user/lpcpfnano/cmantill/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/220701_193717/0000/nano_data2016_99.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_1-1.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_1-10.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_1-11.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_1-13.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_1-14.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_1-3.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_1-4.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_1-5.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_1-6.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_1-7.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_1-9.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_1.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_10.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_11.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_12.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_13.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_14.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_15.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_17.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_18.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_21.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_22.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_23.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_24.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_25.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_26.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_27.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_28.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_29.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_3.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_30.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_31.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_32.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_34.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_5.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_6.root",
-        "/store/user/lpcpfnano/rkansal/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/240301_221443/0000/nano_data2016_8.root"
+        "/store/user/lpcpfnano/cmantill/v2_3/2016/JetHT2016/JetHT/JetHT_Run2016H/220701_193717/0000/nano_data2016_99.root"
       ]
     },
     "QCD": {