-
Notifications
You must be signed in to change notification settings - Fork 4.3k
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
HCALDQM - Add occupancy-per-LS based ML monitoring plots #42212
Conversation
-code-checks Logs: https://cmssdt.cern.ch/SDT/code-checks/cms-sw-PR-42212/36218
Code check has found code style and quality issues which could be resolved by applying following patch(s)
|
-code-checks Logs: https://cmssdt.cern.ch/SDT/code-checks/cms-sw-PR-42212/36219
Code check has found code style and quality issues which could be resolved by applying following patch(s)
|
+code-checks Logs: https://cmssdt.cern.ch/SDT/code-checks/cms-sw-PR-42212/36220 |
A new Pull Request was created by @lwang046 for master. It involves the following packages:
@nothingface0, @emanueleusai, @cmsbuild, @pmandrik, @syuvivida, @tjavaid, @micsucmed, @rvenditti can you please review it and eventually sign? Thanks. cms-bot commands are listed here |
type hcal |
please test |
+1 Summary: https://cmssdt.cern.ch/SDT/jenkins-artifacts/pull-request-integration/PR-23dc62/33625/summary.html Comparison SummarySummary:
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can these comments be removed?
+code-checks Logs: https://cmssdt.cern.ch/SDT/code-checks/cms-sw-PR-42212/36383
|
Pull request #42212 was updated. @nothingface0, @emanueleusai, @cmsbuild, @pmandrik, @syuvivida, @tjavaid, @micsucmed, @rvenditti can you please check and sign again. |
test parameters: |
@cmsbuild please test |
+1 Summary: https://cmssdt.cern.ch/SDT/jenkins-artifacts/pull-request-integration/PR-23dc62/33884/summary.html The following merge commits were also included on top of IB + this PR after doing git cms-merge-topic:
You can see more details here: Comparison SummarySummary:
|
+1 |
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 now be reviewed by the release team before it's merged. @perrotta, @dpiparo, @rappoccio (and backports should be raised in the release meeting by the corresponding L2) |
+1 |
PR description:
Add an
HcalMLTask
to run ML models at the end of each LS for each cell, model description can be found here.The configurable
flagDecisionThr
is a sensitivity control variable for the anomaly detection to balance between false negatives (missing to capture anomaly channel) and false positives (mis-flagging of healthy channel). It is a threshold value used when generating channel anomaly status flags from the estimated channel anomaly score strength. The higher flagDecisionThr reduces the anomaly detection sensitivity (captures extreme channel faults such as dead and hot issues but may miss some anomalies). In contrast, the lowering the flagDecisionThr increases the sensitivity (captures also degrading channels but may also increase false detections). Generally, the anomaly scores are proportional to channel deterioration (degrading, dead, and hot channel faults, respectively).The general recommend values for the latest models are between 10 and 30. If the AD model is generating too much false flags, increase the
flagDecisionThr
and if it is missing too much actual anomalies, reduce flagDecisionThr. Note that tuningflagDecisionThr
is not repeatative task and may need to be done only during initial phase of the deployment and not for every experiment.PR validation:
Tested with
runTheMatrix.py
, desired plots were shown added.