Skip to content

gesris/mlnll-analysis

 
 

Repository files navigation

How to run this

Step 1: Train and test ML model

./ml.sh ML_WORKDIR

Step 2: Create friend datasets with ML application

# Create jobs with model application
ml/create_jobs.sh ML_WORKDIR
cd ML_WORKDIR/MLScores_jobs
condor_submit job.jdl

# Check model application and eventually run remaining jobs locally
ml/check.sh ML_WORKDIR

# Merge application files
ml/merge.sh ML_WORKDIR

Step 3: Produce histograms for the analysis

# Create jobs with shape production
# NOTE: Point to the ML shapes in utils/config.py
shapes/create_jobs.sh SHAPES_WORKDIR
cd SHAPES_WORKDIR/shapes_jobs
condor_submit job.jdl

# Check shape production and eventually run jobs locally
shapes/check.sh SHAPES_WORKDIR

# Merge histograms
shapes/merge.sh SHAPES_WORKDIR

Step 4: Run postprocessing

./postproc.sh SHAPES_WORKDIR

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 90.3%
  • Shell 9.7%