Belle II Software light-2406-ragdoll
fastbdt_ugboost.py
1#!/usr/bin/env python3
2
3
10
11import basf2_mva
12
13if __name__ == "__main__":
14 from basf2 import conditions, find_file
15 # NOTE: do not use testing payloads in production! Any results obtained like this WILL NOT BE PUBLISHED
16 conditions.testing_payloads = [
17 'localdb/database.txt'
18 ]
19
20 variables = ['p', 'pt', 'pz', 'phi',
21 'daughter(0, p)', 'daughter(0, pz)', 'daughter(0, pt)', 'daughter(0, phi)',
22 'daughter(1, p)', 'daughter(1, pz)', 'daughter(1, pt)', 'daughter(1, phi)',
23 'daughter(2, p)', 'daughter(2, pz)', 'daughter(2, pt)', 'daughter(2, phi)',
24 'chiProb', 'dr', 'dz', 'dphi',
25 'daughter(0, dr)', 'daughter(1, dr)', 'daughter(0, dz)', 'daughter(1, dz)',
26 'daughter(0, dphi)', 'daughter(1, dphi)',
27 'daughter(0, chiProb)', 'daughter(1, chiProb)', 'daughter(2, chiProb)',
28 'daughter(0, kaonID)', 'daughter(0, pionID)', 'daughter(1, kaonID)', 'daughter(1, pionID)',
29 'daughterAngle(0, 1)', 'daughterAngle(0, 2)', 'daughterAngle(1, 2)',
30 'daughter(2, daughter(0, E))', 'daughter(2, daughter(1, E))',
31 'daughter(2, daughter(0, clusterTiming))', 'daughter(2, daughter(1, clusterTiming))',
32 'daughter(2, daughter(0, clusterE9E25))', 'daughter(2, daughter(1, clusterE9E25))',
33 'daughter(2, daughter(0, minC2TDist))', 'daughter(2, daughter(1, minC2TDist))',
34 'M']
35
36 variables2 = ['p', 'pt', 'pz', 'phi',
37 'chiProb', 'dr', 'dz', 'dphi',
38 'daughter(2, chiProb)',
39 'daughter(0, kaonID)', 'daughter(0, pionID)', 'daughter(1, kaonID)', 'daughter(1, pionID)',
40 'daughter(2, daughter(0, E))', 'daughter(2, daughter(1, E))',
41 'daughter(2, daughter(0, clusterTiming))', 'daughter(2, daughter(1, clusterTiming))',
42 'daughter(2, daughter(0, clusterE9E25))', 'daughter(2, daughter(1, clusterE9E25))',
43 'daughter(2, daughter(0, minC2TDist))', 'daughter(2, daughter(1, minC2TDist))']
44
45 train_file = find_file("mva/train_D0toKpipi.root", "examples")
46 training_data = basf2_mva.vector(train_file)
47
48 general_options = basf2_mva.GeneralOptions()
49 general_options.m_datafiles = training_data
50 general_options.m_treename = "tree"
51 general_options.m_variables = basf2_mva.vector(*variables)
52 # Spectators are the variables for which the selection should be uniform
53 general_options.m_spectators = basf2_mva.vector('daughterInvM(0, 1)', 'daughterInvM(0, 2)')
54 general_options.m_target_variable = "isSignal"
55 general_options.m_identifier = "fastbdt"
56
57 fastbdt_options = basf2_mva.FastBDTOptions()
58 fastbdt_options.m_nTrees = 100
59 fastbdt_options.m_nCuts = 10
60 fastbdt_options.m_nLevels = 5
61 fastbdt_options.m_shrinkage = 0.1
62 fastbdt_options.m_randRatio = 0.5
63 fastbdt_options.m_flatnessLoss = 10.0
64
65 basf2_mva.teacher(general_options, fastbdt_options)
66
67 general_options.m_identifier = "fastbdt_baseline"
68 fastbdt_options.m_flatnessLoss = -1.0
69 basf2_mva.teacher(general_options, fastbdt_options)
70
71 general_options.m_identifier = "fastbdt_drop_feature"
72 fastbdt_options.m_flatnessLoss = -1.0
73 general_options.m_variables = basf2_mva.vector(*variables2)
74 basf2_mva.teacher(general_options, fastbdt_options)