Dump histograms in parallel using Varial

dump_hists_varial.py

#!/usr/bin/env python
import glob
import sys

import varial.tools
from varial_ext.treeprojector import TreeProjectorFileBased

# The following all caps variables are module level constants that I would tweak by hand.
# Most of them are parameters are passed to the treeprojection_mr_impl.map_projection
# function, so check its docstring for more information.
# https://github.com/HeinerTholen/Varial/blob/acdbf65003aed3feff23c9a2edf4383d0714bfc6/varial_ext/treeprojection_mr_impl.py#L19-L40

# This is an important parameter and you definitely should plug in the logic from
# run_plot_from_tree.py into here so you can benefit from the routine that Heiner
# wrote which takes care of matching an input_pattern.
FILENAMES = {
    'Run2016BToG_MET_ReMiniAOD': glob.glob('/blah/blah/VHbbAnalysisNtuples/NanoAOD/Run2016BToG_MET_ReMiniAOD/*.root'),
}

# The histograms for Varial to generate. The dictionary key becomes the
# name of the TH1 object saved in the output ROOT file. The dictionary value
# holds the (variable, histogram_title, nbins, xmin, xmax). The variable can
# be just a branch name up to a TTreeFormula expression, basically anything
# allowed by TTree.Draw.
HISTOGRAMS = {
    'H_mass': ('H_mass', 'Higgs Mass [GeV]', 50, 0, 500),
}

# The maximum number of multiprocessing workers.
MAXJOBS = 8

# Any selections to apply.
SELECTION = 'cutFlow>=2'

# Any weights to apply.
WEIGHT = 'weight'

def main():
    params = {'treename': 'Events', 'histos': HISTOGRAMS}
    # This is a list of tuples of (title, selection, weight).
    sec_sel_weight = [('Histograms', SELECTION, WEIGHT)]
    # Create the TreeProjector object, shove it into a parallelized tool chain, and run it.
    # It will generate an output directory in the current working directory called HistosFromTree.
    # Inside that output directory will be a subdirectory called TreeProjectorFileBased. And finally
    # within that subdirectory will be ROOT files named after the keys in the FILENAMES dictionary.
    # Each ROOT file contains a TDirectoryFile named Histograms which contains all of the requested
    # histograms for that corresponding sample.
    projector = TreeProjectorFileBased(FILENAMES, params, sec_sel_weight, add_aliases_to_analysis=False)
    plotter = varial.tools.ToolChainParallel('HistosFromTree', [projector], n_workers=MAXJOBS)
    varial.tools.Runner(plotter)
 

if __name__ == '__main__':

    status = main()
    sys.exit(status)