forked from asogaard/transferfactor
-
Notifications
You must be signed in to change notification settings - Fork 0
/
cutflow.py
233 lines (192 loc) · 7.06 KB
/
cutflow.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Script for producing cutflow numbers.
@file: tau21distributions.py
@author: Andreas Søgaard
@date: 30 September 2017
@email: [email protected]
"""
# Basic import(s)
import sys, glob, itertools
# Get ROOT to stop hogging the command-line options
import ROOT
ROOT.PyConfig.IgnoreCommandLineOptions = True
# Scientific import(s)
try:
import numpy as np
from root_numpy import *
except ImportError:
print "WARNING: One or more scientific python packages were not found. If you're in lxplus, try running:"
print " $ source /cvmfs/sft.cern.ch/lcg/views/LCG_88/x86_64-slc6-gcc49-opt/setup.sh"
sys.exit()
pass
# Local import(s)
try:
import transferfactor as tf
from rootplotting import ap
from rootplotting.tools import *
from rootplotting.style import *
from snippets.functions import dict_product, displayName, displayUnit, displayNameUnit
except ImportError:
print "WARNING: This script uses the 'snippets' package. Clone it as e.g.:"
print " $ git clone [email protected]:asogaard/snippets.git"
sys.exit()
pass
# Command-line arguments parser
import argparse
parser = argparse.ArgumentParser(description='Compute cutflow numbers')
parser.add_argument('--show', dest='show', action='store_const',
const=True, default=False,
help='Show plots (default: False)')
parser.add_argument('--save', dest='save', action='store_const',
const=True, default=False,
help='Save plots (default: False)')
# Main function definition.
def main ():
# Parse command-line arguments
args = parser.parse_args()
# Setup.
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Input file paths
paths = glob.glob('/afs/cern.ch/user/a/asogaard/Analysis/2016/BoostedJetISR/AnalysisTools/outputObjdef/objdef_MC_30836*.root')
base = 'BoostedJet+ISRgamma/Nominal/'
trees = [
'PreSelection/Nominal/GRL/Postcut',
'PreSelection/Nominal/HLT_g140_loose/Postcut',
'LargeRadiusJets/Nominal/eta/Postcut',
'LargeRadiusJets/Nominal/pt/Postcut',
'LargeRadiusJets/Nominal/dPhiPhoton/Postcut',
'LargeRadiusJets/Nominal/BoostedRegime/Postcut',
'LargeRadiusJets/Nominal/rhoDDT/Postcut',
'EventSelection/Pass/NumPhotons/Postcut',
'EventSelection/Pass/NumLargeRadiusJets/Postcut',
'EventSelection/Pass/Jet_tau21DDT/Postcut'
]
trees = [base + tree for tree in trees]
names = [
"GRL",
"Trigger",
"Jet eta",
"Jet pT",
"Jet dPhi(y)",
"Jet pT > 2m",
"Jet rhoDDT",
"Photon pT",
"(Jet count)",
"Jet tau21DDT"
]
DSIDs = [308363, 308364, 308365, 308366, 308367]
basecounts = base = {
308363: 50000,
308364: 48000,
308365: 50000,
308366: 50000,
308367: 48000,
}
genfilteff = {
308363: 2.9141e-01,
308364: 1.3795e-01,
308365: 7.5920e-02,
308366: 4.5985e-02,
308367: 2.9914e-02,
}
for idx, DSID in enumerate(DSIDs):
print "\nDSID: {}".format(DSID)
passingEvents = None
for name, tree in zip(names,trees):
# Getting data
data = loadData([paths[idx]], tree)
if passingEvents is None:
passingEvents = sorted(list(set(data['eventNumber'])))
assert len(passingEvents) == data.shape[0]
else:
passingEvents = sorted(list(set(passingEvents) & set(data['eventNumber'])))
pass
print " {:15s}: {:6d} | {:4.1f}% | {:4.1f}%".format(
name,
len(passingEvents),
len(passingEvents) / float(basecounts[DSID]) * 100.,
len(passingEvents) / float(basecounts[DSID]) * genfilteff[DSID] * 100.,
)
pass
pass
return
# Plotting tau21(DDT) profiles
# ----------------------------------------------------------------
slices = {
'pt': [
#( 200, 2000), # For inclusive distribution (test)
( 200, 300),
( 300, 500),
( 500, 1000),
],
'm': [
#(0,1000), # For inclusive distribution (test)
#( 50, 100),
(100, 150),
(150, 200),
(200, 250),
],
#'rhoDDT': [
# (1.5, 2.5),
# (2.5, 4.0),
# (4.0, 5.5),
# ],
}
colours = [ROOT.kRed + i for i in np.arange(0,5,2)] # Overwriting
keys = slices.keys()
key = keys[0]
category_names = ["[%.0f, %.0f] %s" % (slices[key][i][0], slices[key][i][1], displayUnit(key)) for i in range(len(slices[key]))]
for xvar, axis in axes.iteritems():
print "Plotting %s:" % xvar
c = ap.canvas(batch=not args.show)
bins = np.linspace(axis[1], axis[2], axis[0] + 1, endpoint=True)
if xvar in ['tau21DDT/Postcut', 'tau21'] and args.save:
f = ROOT.TFile('output/hists_isrgamma_%sdistributions.root' % xvar, 'RECREATE')
else:
f = None
pass
# Fill sliced histograms
histograms = list()
for i, sl in enumerate(dict_product(slices)):
print " %d:" % i, sl
# Create full mask for current slice
msk = np.ones_like(data['weight']).astype(bool)
for key, limits in sl.iteritems():
msk &= (data[key] >= limits[0]) & (data[key] < limits[1])
pass
# Create distribution for current slice
key = keys[1]
label = "[%.0f, %.0f] %s" % (sl[key][0], sl[key][1], displayUnit(key))
hist = c.hist(data[xvar][msk], bins=bins, weights=data['weight'][msk], linecolor=colours[i % 3], linestyle=1 + (i//3), label=label if i < 3 else None, normalise=True)
if f:
f.cd()
hist.SetName('h_%s_%d_%d_%s_%d_%s' % (keys[0], sl[keys[0]][0], sl[keys[0]][1], keys[1], sl[keys[1]][0], sl[keys[1]][1]))
#hist.Write()
pass
pass
if f:
f.Write()
f.Close()
pass
# Decorations
c.xlabel('Signal jet %s' % displayNameUnit(xvar))
c.ylabel('Jets (a.u.)')
c.text(["#sqrt{s} = 13 TeV", "ISR #gamma selection"], qualifier="Simulation Internal")
c.padding(0.50)
ymax = 0.735
c.legend(header='Jet %s in:' % displayName(keys[1]),
ymax=ymax)
c.legend(header='Jet %s in:' % displayName(keys[0]), categories=[
(category_names[idx], {'linestyle': 1 + idx}) for idx in range(len(category_names))
],
ymax=ymax, xmin=0.19)
if args.show: c.show()
if args.save: c.save('plots/tau21distributions_%s__%s_x_%s.pdf' % (xvar, keys[0], keys[1]))
pass
return
# Main function call.
if __name__ == '__main__':
main()
pass