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.

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

new Prompt Lepton ID MVA (and renaming) #44503

Merged
merged 9 commits into from
Mar 31, 2024
Merged

Conversation

vlimant
Copy link
Contributor

@vlimant vlimant commented Mar 21, 2024

rework of #44322 due to #44392

This PR is to introduce the newest training of the Muon mvaTTH in CMSSW. The training has been performed following what was done already done for Run 2, but using Run 3 MC samples for training and validation.

Context of the PR

The goal for this new training is to be used as a substitute of the current mvaTTH only in Run 3 MC production. That is: for Run 2 we still need to keep the current mvaTTH implementation (can be found in these lines), and for Run 3 we want to make use of an era modifier to fetch the proper --new -- weights that have been computed.

Linked PRs

This is the link for the PR that includes the weights in CMS-data: cms-data/PhysicsTools-NanoAOD#16.

@vlimant
Copy link
Contributor Author

vlimant commented Mar 21, 2024

enable nano

@cmsbuild
Copy link
Contributor

cmsbuild commented Mar 21, 2024

cms-bot internal usage

@vlimant
Copy link
Contributor Author

vlimant commented Mar 21, 2024

type egamma

@vlimant
Copy link
Contributor Author

vlimant commented Mar 21, 2024

type muon

@cmsbuild cmsbuild added the muon label Mar 21, 2024
@cmsbuild
Copy link
Contributor

+code-checks

Logs: https://cmssdt.cern.ch/SDT/code-checks/cms-sw-PR-44503/39619

@vlimant
Copy link
Contributor Author

vlimant commented Mar 21, 2024

test parameters:

@cmsbuild
Copy link
Contributor

A new Pull Request was created by @vlimant for master.

It involves the following packages:

  • Configuration/Eras (operations)
  • PhysicsTools/NanoAOD (xpog)
  • PhysicsTools/PatAlgos (xpog, reconstruction)

@davidlange6, @vlimant, @hqucms, @antoniovilela, @cmsbuild, @mandrenguyen, @rappoccio, @fabiocos, @jfernan2 can you please review it and eventually sign? Thanks.
@ahinzmann, @fabiocos, @gpetruc, @Martin-Grunewald, @gouskos, @seemasharmafnal, @hatakeyamak, @azotz, @JyothsnaKomaragiri, @andrzejnovak, @mbluj, @AlexDeMoor, @AnnikaStein, @Ming-Yan, @mmarionncern, @demuller, @emilbols, @mariadalfonso, @gkasieczka, @jdolen, @jdamgov, @makortel, @missirol, @Senphy, @nhanvtran, @schoef, @rappoccio this is something you requested to watch as well.
@antoniovilela, @sextonkennedy, @rappoccio you are the release manager for this.

cms-bot commands are listed here

@vlimant
Copy link
Contributor Author

vlimant commented Mar 21, 2024

please test

@cmsbuild
Copy link
Contributor

+1

Summary: https://cmssdt.cern.ch/SDT/jenkins-artifacts/pull-request-integration/PR-d05221/38332/summary.html
COMMIT: 110adb7
CMSSW: CMSSW_14_1_X_2024-03-21-1100/el8_amd64_gcc12
Additional Tests: NANO
User test area: For local testing, you can use /cvmfs/cms-ci.cern.ch/week1/cms-sw/cmssw/44503/38332/install.sh to create a dev area with all the needed externals and cmssw changes.

Comparison Summary

Summary:

  • You potentially removed 106 lines from the logs
  • ROOTFileChecks: Some differences in event products or their sizes found
  • Reco comparison results: 39 differences found in the comparisons
  • DQMHistoTests: Total files compared: 48
  • DQMHistoTests: Total histograms compared: 3297369
  • DQMHistoTests: Total failures: 98
  • DQMHistoTests: Total nulls: 0
  • DQMHistoTests: Total successes: 3297251
  • DQMHistoTests: Total skipped: 20
  • DQMHistoTests: Total Missing objects: 0
  • DQMHistoSizes: Histogram memory added: 0.0 KiB( 47 files compared)
  • Checked 202 log files, 165 edm output root files, 48 DQM output files
  • TriggerResults: no differences found

NANO Comparison Summary

Summary:

  • You potentially removed 4 lines from the logs
  • ROOTFileChecks: Some differences in event products or their sizes found
  • Reco comparison results: 28 differences found in the comparisons
  • DQMHistoTests: Total files compared: 15
  • DQMHistoTests: Total histograms compared: 16402
  • DQMHistoTests: Total failures: 70
  • DQMHistoTests: Total nulls: 0
  • DQMHistoTests: Total successes: 16332
  • DQMHistoTests: Total skipped: 0
  • DQMHistoTests: Total Missing objects: 0
  • DQMHistoSizes: Histogram memory added: 0.0 KiB( 14 files compared)
  • Checked 47 log files, 27 edm output root files, 15 DQM output files

Nano size comparison Summary:

Sample kb/ev ref kb/ev diff kb/ev ev/s/thd ref ev/s/thd diff rate mem/thd ref mem/thd
2500.0 2.548 2.548 0.000 ( +0.0% ) 5.19 5.16 +0.5% 2.229 2.176
2500.001 2.698 2.698 0.000 ( +0.0% ) 4.62 4.58 +0.8% 2.629 2.606
2500.002 2.638 2.638 0.000 ( +0.0% ) 4.83 4.84 -0.2% 2.630 2.609
2500.01 1.318 1.318 0.000 ( +0.0% ) 9.31 9.39 -0.9% 2.333 2.256
2500.011 1.740 1.740 0.000 ( +0.0% ) 5.17 5.13 +0.8% 2.432 2.416
2500.012 1.581 1.581 0.000 ( +0.0% ) 7.17 7.36 -2.5% 2.416 2.300
2500.1 2.192 2.192 0.000 ( +0.0% ) 5.22 5.22 +0.0% 2.059 1.998
2500.2 2.308 2.308 0.000 ( +0.0% ) 5.98 6.01 -0.5% 1.974 1.892
2500.21 1.181 1.181 0.000 ( +0.0% ) 4.26 4.29 -0.6% 2.272 2.209
2500.211 1.545 1.545 0.000 ( +0.0% ) 3.70 3.74 -1.1% 2.337 2.230
2500.3 2.058 2.058 0.001 ( +0.0% ) 12.13 12.26 -1.1% 1.964 1.891
2500.301 2.631 2.631 0.000 ( +0.0% ) 9.65 9.98 -3.3% 1.948 1.827
2500.31 1.254 1.254 0.000 ( +0.0% ) 18.99 19.11 -0.6% 2.340 2.246
2500.311 1.640 1.640 0.000 ( +0.0% ) 13.38 13.39 -0.1% 2.437 2.323
2500.312 7.159 7.159 0.000 ( +0.0% ) 1.37 1.45 -5.9% 1.707 1.703
2500.313 1.564 1.564 0.000 ( +0.0% ) 6.41 6.74 -5.0% 1.061 1.049
2500.314 1.163 1.163 0.000 ( +0.0% ) 13.29 13.56 -2.0% 2.061 2.022
2500.315 1.758 1.758 0.000 ( +0.0% ) 13.07 13.54 -3.5% 2.325 2.317
2500.316 3.091 3.091 0.000 ( +0.0% ) 2.20 2.23 -1.7% 2.266 2.116
2500.317 1.787 1.787 0.000 ( +0.0% ) 12.51 13.43 -6.9% 2.167 2.153
2500.4 2.058 2.058 0.001 ( +0.0% ) 12.03 12.00 +0.2% 1.854 1.826
2500.401 1.824 1.824 0.000 ( +0.0% ) 9.82 10.21 -3.8% 1.768 1.787
2500.402 2.631 2.631 0.000 ( +0.0% ) 9.45 9.85 -4.1% 1.804 1.826
2500.403 5.188 5.188 0.000 ( +0.0% ) 1.55 1.57 -0.9% 1.957 1.947
2500.404 2.620 2.620 0.000 ( +0.0% ) 9.37 9.74 -3.8% 1.751 1.872
2500.5 19.575 19.575 0.000 ( +0.0% ) 1.20 0.93 +29.6% 1.372 1.333

@vlimant
Copy link
Contributor Author

vlimant commented Mar 28, 2024

+1

@vlimant
Copy link
Contributor Author

vlimant commented Mar 28, 2024

please test

@cmsbuild
Copy link
Contributor

+code-checks

Logs: https://cmssdt.cern.ch/SDT/code-checks/cms-sw-PR-44503/39718

@cmsbuild
Copy link
Contributor

Pull request #44503 was updated. @antoniovilela, @rappoccio, @davidlange6, @fabiocos, @mandrenguyen, @jfernan2 can you please check and sign again.

@cmsbuild
Copy link
Contributor

+1

Summary: https://cmssdt.cern.ch/SDT/jenkins-artifacts/pull-request-integration/PR-d05221/38484/summary.html
COMMIT: b95f405
CMSSW: CMSSW_14_1_X_2024-03-27-2300/el8_amd64_gcc12
Additional Tests: NANO
User test area: For local testing, you can use /cvmfs/cms-ci.cern.ch/week0/cms-sw/cmssw/44503/38484/install.sh to create a dev area with all the needed externals and cmssw changes.

Comparison Summary

Summary:

  • You potentially added 6 lines to the logs
  • ROOTFileChecks: Some differences in event products or their sizes found
  • Reco comparison results: 51 differences found in the comparisons
  • DQMHistoTests: Total files compared: 48
  • DQMHistoTests: Total histograms compared: 3297359
  • DQMHistoTests: Total failures: 9
  • DQMHistoTests: Total nulls: 0
  • DQMHistoTests: Total successes: 3297330
  • DQMHistoTests: Total skipped: 20
  • DQMHistoTests: Total Missing objects: 0
  • DQMHistoSizes: Histogram memory added: 0.23400000000000007 KiB( 47 files compared)
  • DQMHistoSizes: changed ( 11634.0,... ): 0.018 KiB Physics/NanoAODDQM
  • DQMHistoSizes: changed ( 13234.0,... ): 0.012 KiB Physics/NanoAODDQM
  • Checked 202 log files, 165 edm output root files, 48 DQM output files
  • TriggerResults: no differences found

NANO Comparison Summary

The workflows 2500.2 have different files in step1_dasquery.log than the ones found in the baseline. You may want to check and retrigger the tests if necessary. You can check it in the "files" directory in the results of the comparisons

Summary:

  • No significant changes to the logs found
  • ROOTFileChecks: Some differences in event products or their sizes found
  • Reco comparison results: 28 differences found in the comparisons
  • DQMHistoTests: Total files compared: 15
  • DQMHistoTests: Total histograms compared: 16332
  • DQMHistoTests: Total failures: 0
  • DQMHistoTests: Total nulls: 0
  • DQMHistoTests: Total successes: 16332
  • DQMHistoTests: Total skipped: 0
  • DQMHistoTests: Total Missing objects: 0
  • DQMHistoSizes: Histogram memory added: 0.21 KiB( 14 files compared)
  • DQMHistoSizes: changed ( 2500.001,... ): 0.018 KiB Physics/NanoAODDQM
  • DQMHistoSizes: changed ( 2500.011,... ): 0.012 KiB Physics/NanoAODDQM
  • Checked 47 log files, 27 edm output root files, 15 DQM output files

Nano size comparison Summary:

Sample kb/ev ref kb/ev diff kb/ev ev/s/thd ref ev/s/thd diff rate mem/thd ref mem/thd
2500.0 2.548 2.548 0.000 ( +0.0% ) 4.33 4.53 -4.6% 2.093 2.173
2500.001 2.697 2.697 0.000 ( +0.0% ) 3.89 4.06 -4.1% 2.489 2.598
2500.002 2.637 2.637 0.000 ( +0.0% ) 4.02 4.22 -4.6% 2.493 2.591
2500.01 1.318 1.318 0.000 ( +0.0% ) 7.50 8.07 -7.1% 2.206 2.291
2500.011 1.739 1.739 0.000 ( +0.0% ) 4.31 4.53 -5.0% 2.341 2.430
2500.012 1.580 1.580 0.000 ( +0.0% ) 6.06 6.35 -4.5% 2.338 2.377
2500.1 2.192 2.192 0.000 ( +0.0% ) 4.32 4.57 -5.3% 1.946 2.065
2500.2 2.308 2.308 0.000 ( +0.0% ) 4.82 5.17 -6.9% 1.847 1.974
2500.21 1.181 1.181 0.000 ( +0.0% ) 3.35 3.49 -4.1% 2.133 2.256
2500.211 1.545 1.545 0.000 ( +0.0% ) 2.82 3.03 -7.0% 2.159 2.337
2500.3 2.064 2.064 0.000 ( +0.0% ) 8.96 9.63 -7.0% 1.847 1.959
2500.301 2.637 2.637 0.000 ( +0.0% ) 7.60 8.02 -5.3% 1.787 1.947
2500.31 1.255 1.255 0.000 ( +0.0% ) 11.56 12.25 -5.7% 2.188 2.344
2500.311 1.642 1.642 0.000 ( +0.0% ) 8.71 9.57 -9.0% 2.246 2.412
2500.312 7.159 7.159 0.000 ( +0.0% ) 1.29 1.34 -4.1% 1.655 1.705
2500.313 1.564 1.564 0.000 ( +0.0% ) 6.09 6.65 -8.5% 1.059 1.059
2500.314 1.163 1.163 0.000 ( +0.0% ) 9.17 9.29 -1.3% 2.056 2.236
2500.315 1.758 1.758 0.000 ( +0.0% ) 9.03 9.68 -6.7% 2.131 2.294
2500.316 3.093 3.093 0.000 ( +0.0% ) 1.59 1.73 -7.7% 2.048 2.248
2500.317 1.789 1.789 0.000 ( +0.0% ) 8.95 9.36 -4.4% 2.155 2.159
2500.4 2.221 2.221 0.000 ( +0.0% ) 8.77 9.34 -6.1% 1.795 1.878
2500.401 1.755 1.755 0.000 ( +0.0% ) 7.68 7.85 -2.2% 1.694 1.690
2500.402 2.766 2.766 0.000 ( +0.0% ) 7.21 7.91 -8.9% 1.729 1.843
2500.403 5.068 5.068 0.000 ( +0.0% ) 1.21 1.28 -5.3% 1.797 1.829
2500.404 2.774 2.774 0.000 ( +0.0% ) 7.08 7.28 -2.7% 1.701 1.700
2500.5 4.936 4.936 0.000 ( +0.0% ) 14.38 15.19 -5.4% 1.479 1.599
2500.51 8.960 8.960 0.000 ( +0.0% ) 8.90 9.33 -4.5% 1.409 1.441

@vlimant
Copy link
Contributor Author

vlimant commented Mar 30, 2024

@cms-sw/orp-l2 : I think we’re good to go with this one. What is blocking @cms-sw/reconstruction-l2 and @cms-sw/operations-l2 signatures?

@mandrenguyen
Copy link
Contributor

+reconstruction
@vlimant please consider a slightly more detailed PR title, e.g., new Prompt lepton ID MVA or something.

@vlimant vlimant changed the title new Prompt MVA (and renaming) new Prompt Lepton ID MVA (and renaming) Mar 31, 2024
@antoniovilela
Copy link
Contributor

+1

@cmsbuild
Copy link
Contributor

This pull request is fully signed and it will be integrated in one of the next master IBs (tests are also fine). This pull request will be automatically merged.

@cmsbuild cmsbuild merged commit f8ce14a into cms-sw:master Mar 31, 2024
14 checks passed
@vlimant vlimant deleted the rebase_of_44322 branch April 2, 2024 12:18
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

6 participants