-
Notifications
You must be signed in to change notification settings - Fork 0
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
Ticl em vs had bdt #3
base: TICL_inReco
Are you sure you want to change the base?
Conversation
reader_->AddVariable("ts_pcasig2", &ts_pcasig2); | ||
|
||
std::string CMSSW_BASE(std::getenv("CMSSW_BASE")); | ||
std::string weightfilename_ = CMSSW_BASE+"/src/RecoHGCal/data/em_vs_had_xgboost.xml"; |
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.
Why not trying the usual FileInPath approach?
See, e.g., FWCore/ParameterSet/interface/FileInPath.h
There is also the corresponding python parameter cms.FileInPath
.
If you git grep FileInPath
in CMSSW
, you will find plenty of examples.
@@ -36,6 +40,9 @@ namespace ticl { | |||
const int eidNLayers_; | |||
const int eidNClusters_; | |||
|
|||
TMVA::Reader* reader_; | |||
float ts_energy, ts_x, ts_y, ts_z, ts_pcaeigval0, ts_pcasig0, ts_pcaeigval1, ts_pcasig1, ts_pcaeigval2, ts_pcasig2; |
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.
Private variables should always be terminated by an underscore character: _
, so that people reading code can understand where they are coming from.
|
||
float mva_ = 1.; | ||
for (unsigned int itrkster = 0; itrkster<tracksters.size(); ++itrkster) { | ||
ts_energy = tracksters.at(itrkster).raw_energy; |
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.
I'm not sure I like the approach of having private variables dedicated to run BDT inference.
I'll think a bit more about that.
Fixing I/O rules for ScoutingMuon backward accessibility
Recover fillDescriptions as requested
* remove comments, set constants constant * remove CASTOR cleaner and merger * Remove single generator customize function. It is not used anymore since the generator step is splitted in 3 steps. * remove unneeded filters * optimize embedding correction calculation * optimize selector loops * format cpp code with scram build code-format --------- Co-authored-by: cwinter <[email protected]>
Update prompt and displaced muon names to reflect GMT changes
Initial commit of a BDT to separate EM and HAD showers in TICL
This PR adds float to the Trackster object which is the BDT score
The weights file is kind of dummy - will be updated in the next few days.