sanity_check_grl.py

Go to the documentation of this file.

#!/usr/bin/env python
# usage python sanity_check_grl.py GRLFILE.txt
from __future__ import print_function
from builtins import range
import numpy as np
import sys
import period_run_lists as pr
import pandas as pa

the_grl=sys.argv[1]

#period10c_start="35331"

if (the_grl.find("FD")>-1 ):
    DET="FD"
    runs_df = pr.pfd
elif (the_grl.find("ND")>-1 ):
    DET="ND"
    runs_df = pr.pnd
else:
    print("Expecting a grl name as argument with fd_ or nd_ in the name. Please try again...")
    exit(0)

print("Detector: ",DET)

# make a list of all the runs in this grl, including duplications due to multiple subruns within a run
grl_runs = []
with open(the_grl, "r") as f:
    grl = f.read().split('\n')
    for row in grl:
        if len(row)<1:
            continue
        run_in_grl = row.split(' ')[0]
        grl_runs.append(run_in_grl)

for i in range(0, len(grl_runs)): 
    grl_runs[i] = np.int64(grl_runs[i]) 

good_runs = pa.DataFrame(grl_runs, columns = ['Runs'])    
good_runs.drop_duplicates(subset ="Runs", 
                     keep = "first", inplace = True) 


for index, row in runs_df.iterrows():
    runs = row['Runs'] # a list of runs for this period
    period_runs = pa.DataFrame(runs, columns = ['Runs'])
    not_on_grl = list( set(period_runs['Runs'].values) - set(good_runs['Runs'].values) )
    not_on_grl.sort()


    nruns = len(period_runs)
    nruns_not_on_grl = len(not_on_grl)
    #print "nruns not on grl: ",nruns_not_on_grl
    #print "not_on_grl",not_on_grl
    
    frac_bad = 100.*float(nruns_not_on_grl)/float(nruns) 
    nruns_on_grl = nruns - nruns_not_on_grl 
    frac_good = 100.*float(nruns_on_grl)/float(nruns) 

    print("Percentage (number) of the %d runs from %s that are on this grl: %3.2f %% (%d)"%(nruns,row['Period'],frac_good,nruns_on_grl))