Belle II Software development
RealisticSegmentPairFilterTrainingRun Class Reference
Inheritance diagram for RealisticSegmentPairFilterTrainingRun:
ReadOrGenerateEventsRun MinimalRun EmptyRun

Public Member Functions

def identifier (self)
 
def create_path (self)
 

Public Attributes

 task
 Process each event according to the user's desired task (train, eval, explore)
 

Static Public Attributes

int n_events = 10000
 number of events to generate
 
str generator_module = "generic"
 use the generic event generator
 
os bkg_files = os.path.join(os.environ["VO_BELLE2_SW_DIR"], "bkg")
 overlay background hits from the events in these files
 
str truth = "truth_positive"
 degree of MC truth-matching
 

Detailed Description

Run to record segment pairs encountered at the SegmentPairCreator and retrain its mva method

Definition at line 19 of file trainRealisticSegmentPairFilter.py.

Member Function Documentation

◆ create_path()

def create_path (   self)
Setup the recording path after the simulation

Reimplemented from ReadOrGenerateEventsRun.

Definition at line 36 of file trainRealisticSegmentPairFilter.py.

36 def create_path(self):
37 """Setup the recording path after the simulation"""
38 path = super().create_path()
39
40 # In contrast to other training use only the first *half* loop for more aggressive training
41 path.add_module("TFCDC_WireHitPreparer",
42 flightTimeEstimation="outwards")
43
44 path.add_module('TFCDC_ClusterPreparer',
45 SuperClusterDegree=3,
46 SuperClusterExpandOverApogeeGap=True)
47
48 path.add_module("TFCDC_SegmentFinderFacetAutomaton")
49
50
51 if self.task == "train":
52 varSets = [
53 "realistic",
54 "filter(truth)",
55 "truth", # for weighting
56 ]
57 skim = "feasible"
58
59 elif self.task == "eval":
60 varSets = [
61 "filter(truth)",
62 "filter(realistic)",
63 "filter(feasible)",
64 "filter(fitless)",
65 "filter(simple)",
66 ]
67 skim = ""
68
69 elif self.task == "explore":
70 varSets = [
71 "basic",
72 # "realistic",
73 "fitless",
74 "pre_fit",
75 "fit",
76 "truth", # for weighting
77 # "old_fit",
78 # "filter(fitless)",
79 # "filter(simple)",
80 "filter(realistic)",
81 "filter(truth)",
82 ]
83 skim = "feasible"
84
85 else:
86 raise ValueError("Unknown task " + self.task)
87
88 path.add_module("TFCDC_TrackFinderSegmentPairAutomaton",
89 SegmentPairFilter="unionrecording",
90 SegmentPairFilterParameters={
91 "rootFileName": self.sample_file_name,
92 "varSets": varSets,
93 "skim": skim,
94 })
95
96 return path
97
98

◆ identifier()

def identifier (   self)
Database identifier of the filter being trained

Definition at line 32 of file trainRealisticSegmentPairFilter.py.

32 def identifier(self):
33 """Database identifier of the filter being trained"""
34 return "trackfindingcdc_RealisticSegmentPairFilter.xml"
35

Member Data Documentation

◆ bkg_files

os bkg_files = os.path.join(os.environ["VO_BELLE2_SW_DIR"], "bkg")
static

overlay background hits from the events in these files

Definition at line 26 of file trainRealisticSegmentPairFilter.py.

◆ generator_module

str generator_module = "generic"
static

use the generic event generator

Definition at line 24 of file trainRealisticSegmentPairFilter.py.

◆ n_events

int n_events = 10000
static

number of events to generate

Definition at line 22 of file trainRealisticSegmentPairFilter.py.

◆ task

task

Process each event according to the user's desired task (train, eval, explore)

Definition at line 51 of file trainRealisticSegmentPairFilter.py.

◆ truth

str truth = "truth_positive"
static

degree of MC truth-matching

Definition at line 29 of file trainRealisticSegmentPairFilter.py.


The documentation for this class was generated from the following file: