ValidationAndOptimisationTask Class Reference

Inheritance diagram for ValidationAndOptimisationTask:

Public Member Functions
	output (self)
	requires (self)
	create_optimisation_and_validation_path (self)
	create_path (self)
	remove_output (self)

Public Attributes
	job_name = self.task_id
	set the job name (inherited variable)

Static Public Attributes
	experiment_number = b2luigi.IntParameter()
	Experiment number of the conditions database, e.g.
	n_events_training = b2luigi.IntParameter()
	Number of events to generate for the training data set.
	fast_bdt_option_state_filter
	FastBDT option to use to train the StateFilters.
	fast_bdt_option_result_filter
	FastBDT option to use to train the Result Filter.
	n_events_testing = b2luigi.IntParameter()
	Number of events to generate for the testing, validation, and optimisation data set.
	state_filter_cut = b2luigi.FloatParameter()
	Value of the cut on the MVA classifier output for accepting a state during CKF tracking.
	use_n_best_states = b2luigi.IntParameter()
	How many states should be kept at maximum in the combinatorial part of the CKF tree search.
	result_filter_cut = b2luigi.FloatParameter()
	Value of the cut on the MVA classifier output for a result candidate.
	use_n_best_results = b2luigi.IntParameter()
	How many results should be kept at maximum to search for overlaps.
str	batch_system = 'lsf'
	batch system
str	queue = 's'
	queue

Detailed Description

Validate the performance of the trained filters by trying various combinations of FastBDT options, as well as cut values for
the states, the number of best candidates kept after each filter, and similar for the result filter.

Definition at line 897 of file combined_to_pxd_ckf_mva_training.py.

Member Function Documentation

create_optimisation_and_validation_path()

create_optimisation_and_validation_path

(

self

)

Create a path to validate the trained filters.

Definition at line 973 of file combined_to_pxd_ckf_mva_training.py.

    def create_optimisation_and_validation_path(self):
        """
        Create a path to validate the trained filters.
        """
        path = basf2.create_path()
 
        # get all the file names from the list of input files that are meant for optimisation / validation
        file_list = [fname for fname in self.get_all_input_file_names()
                     if "generated_mc_N" in fname and "optimisation" in fname and fname.endswith(".root")]
        path.add_module("RootInput", inputFileNames=file_list)
 
        path.add_module("Gearbox")
        path.add_module("Geometry")
        path.add_module("SetupGenfitExtrapolation")
 
        add_hit_preparation_modules(path, components=["SVD", "PXD"])
 
        add_track_finding(path, reco_tracks="CDCSVDRecoTracks", components=["CDC", "SVD"], prune_temporary_tracks=False)
 
        path.add_module("DAFRecoFitter", recoTracksStoreArrayName="CDCSVDRecoTracks")
 
        fbdt_state_filter_string = create_fbdt_option_string(self.fast_bdt_option_state_filter)
        fbdt_result_filter_string = create_fbdt_option_string(self.fast_bdt_option_result_filter)
 
        # write the tracking MVA filter parameters and the cut on MVA classifier to be applied on a local db
        iov = [0, 0, 0, -1]
        write_tracking_mva_filter_payloads_to_db(
            f"trk_ToPXDStateFilter_1_Parameter{fbdt_state_filter_string}",
            iov,
            f"trk_ToPXDStateFilter_1{fbdt_state_filter_string}",
            self.state_filter_cut)
 
        write_tracking_mva_filter_payloads_to_db(
            f"trk_ToPXDStateFilter_2_Parameter{fbdt_state_filter_string}",
            iov,
            f"trk_ToPXDStateFilter_2{fbdt_state_filter_string}",
            self.state_filter_cut)
 
        write_tracking_mva_filter_payloads_to_db(
            f"trk_ToPXDStateFilter_3_Parameter{fbdt_state_filter_string}",
            iov,
            f"trk_ToPXDStateFilter_3{fbdt_state_filter_string}",
            self.state_filter_cut)
 
        write_tracking_mva_filter_payloads_to_db(
            f"trk_ToPXDResultFilter_Parameter{fbdt_result_filter_string}",
            iov,
            f"trk_ToPXDResultFilter{fbdt_result_filter_string}",
            self.result_filter_cut)
 
        basf2.conditions.prepend_testing_payloads("localdb/database.txt")
        first_high_filter_parameters = {"DBPayloadName": f"trk_ToPXDStateFilter_1_Parameter{fbdt_state_filter_string}",
                                        "direction": "backward"}
        second_high_filter_parameters = {"DBPayloadName": f"trk_ToPXDStateFilter_2_Parameter{fbdt_state_filter_string}"}
        third_high_filter_parameters = {"DBPayloadName": f"trk_ToPXDStateFilter_3_Parameter{fbdt_state_filter_string}"}
        filter_parameters = {"DBPayloadName":  f"trk_ToPXDResultFilter_Parameter{fbdt_result_filter_string}"}
 
        path.add_module("ToPXDCKF",
                        inputRecoTrackStoreArrayName="CDCSVDRecoTracks",
                        outputRecoTrackStoreArrayName="PXDRecoTracks",
                        outputRelationRecoTrackStoreArrayName="CDCSVDRecoTracks",
 
                        relationCheckForDirection="backward",
                        reverseSeed=False,
                        writeOutDirection="backward",
 
                        firstHighFilter="mva_with_direction_check",
                        firstHighFilterParameters=first_high_filter_parameters,
                        firstHighUseNStates=self.use_n_best_states,
 
                        advanceHighFilter="advance",
                        advanceHighFilterParameters={"direction": "backward"},
 
                        secondHighFilter="mva",
                        secondHighFilterParameters=second_high_filter_parameters,
                        secondHighUseNStates=self.use_n_best_states,
 
                        updateHighFilter="fit",
 
                        thirdHighFilter="mva",
                        thirdHighFilterParameters=third_high_filter_parameters,
                        thirdHighUseNStates=self.use_n_best_states,
 
                        filter="mva",
                        filterParameters=filter_parameters,
                        useBestNInSeed=self.use_n_best_results,
 
                        exportTracks=True,
                        enableOverlapResolving=True)
 
        path.add_module('RelatedTracksCombiner',
                        VXDRecoTracksStoreArrayName="PXDRecoTracks",
                        CDCRecoTracksStoreArrayName="CDCSVDRecoTracks",
                        recoTracksStoreArrayName="RecoTracks")
 
        path.add_module('TrackFinderMCTruthRecoTracks',
                        RecoTracksStoreArrayName="MCRecoTracks",
                        WhichParticles=[],
                        UsePXDHits=True,
                        UseSVDHits=True,
                        UseCDCHits=True)
 
        path.add_module("MCRecoTracksMatcher", UsePXDHits=True, UseSVDHits=True, UseCDCHits=True,
                        mcRecoTracksStoreArrayName="MCRecoTracks",
                        prRecoTracksStoreArrayName="RecoTracks")
 
        path.add_module(
            CombinedTrackingValidationModule(
                output_file_name=self.get_output_file_name(
                    f"to_pxd_ckf_validation{fbdt_state_filter_string}{fbdt_result_filter_string}.root"),
                reco_tracks_name="RecoTracks",
                mc_reco_tracks_name="MCRecoTracks",
                name="",
                contact="",
                expert_level=200))
 
        return path
 

create_path()

create_path

(

self

)

Create basf2 path to process with event generation and simulation.

Definition at line 1091 of file combined_to_pxd_ckf_mva_training.py.

    def create_path(self):
        """
        Create basf2 path to process with event generation and simulation.
        """
        return self.create_optimisation_and_validation_path()
 

output()

output

(

self

)

Generate list of output files that the task should produce.
The task is considered finished if and only if the outputs all exist.

Definition at line 932 of file combined_to_pxd_ckf_mva_training.py.

    def output(self):
        """
        Generate list of output files that the task should produce.
        The task is considered finished if and only if the outputs all exist.
        """
        fbdt_state_filter_string = create_fbdt_option_string(self.fast_bdt_option_state_filter)
        fbdt_result_filter_string = create_fbdt_option_string(self.fast_bdt_option_result_filter)
        yield self.add_to_output(
            f"to_pxd_ckf_validation{fbdt_state_filter_string}{fbdt_result_filter_string}.root")
 

remove_output()

remove_output

(

self

)

Default function from base b2luigi.Task class.

Definition at line 1097 of file combined_to_pxd_ckf_mva_training.py.

    def remove_output(self):
        """
        Default function from base b2luigi.Task class.
        """
        self._remove_output()
 
 

requires()

requires

(

self

)

This task requires trained result filters, trained state filters, and that an independent data set for validation was
created using the SplitMergeSimTask with the random seed optimisation.

Definition at line 942 of file combined_to_pxd_ckf_mva_training.py.

    def requires(self):
        """
        This task requires trained result filters, trained state filters, and that an independent data set for validation was
        created using the SplitMergeSimTask with the random seed optimisation.
        """
        fbdt_state_filter_string = create_fbdt_option_string(self.fast_bdt_option_state_filter)
        yield CKFResultFilterTeacherTask(
            result_filter_records_name=f"filter_records{fbdt_state_filter_string}.root",
            experiment_number=self.experiment_number,
            n_events=self.n_events_training,
            fast_bdt_option_state_filter=self.fast_bdt_option_state_filter,
            fast_bdt_option_result_filter=self.fast_bdt_option_result_filter,
            random_seed='training'
        )
        yield SplitNMergeSimTask(
            bkgfiles_dir=SummaryTask.bkgfiles_by_exp[self.experiment_number],
            experiment_number=self.experiment_number,
            n_events=self.n_events_testing,
            random_seed="optimisation",
        )
        filter_numbers = [1, 2, 3]
        for filter_number in filter_numbers:
            yield self.clone(
                CKFStateFilterTeacherTask,
                experiment_number=self.experiment_number,
                n_events=self.n_events_training,
                random_seed="training",
                filter_number=filter_number,
                fast_bdt_option_state_filter=self.fast_bdt_option_state_filter
            )
 

Member Data Documentation

batch_system

str batch_system = 'lsf'

staticinherited

batch system

Definition at line 189 of file combined_to_pxd_ckf_mva_training.py.

experiment_number

experiment_number = b2luigi.IntParameter()

static

Experiment number of the conditions database, e.g.

defines simulation geometry.

Definition at line 903 of file combined_to_pxd_ckf_mva_training.py.

fast_bdt_option_result_filter

fast_bdt_option_result_filter

static

Initial value:

=  b2luigi.ListParameter(
        # ## 
 
 
    )

FastBDT option to use to train the Result Filter.

Definition at line 913 of file combined_to_pxd_ckf_mva_training.py.

fast_bdt_option_state_filter

fast_bdt_option_state_filter

static

Initial value:

=  b2luigi.ListParameter(
        # ## 
 
 
    )

FastBDT option to use to train the StateFilters.

Definition at line 907 of file combined_to_pxd_ckf_mva_training.py.

job_name

job_name = self.task_id

inherited

set the job name (inherited variable)

Definition at line 197 of file combined_to_pxd_ckf_mva_training.py.

n_events_testing

n_events_testing = b2luigi.IntParameter()

static

Number of events to generate for the testing, validation, and optimisation data set.

Definition at line 919 of file combined_to_pxd_ckf_mva_training.py.

n_events_training

n_events_training = b2luigi.IntParameter()

static

Number of events to generate for the training data set.

Definition at line 905 of file combined_to_pxd_ckf_mva_training.py.

queue

str queue = 's'

staticinherited

queue

Definition at line 191 of file combined_to_pxd_ckf_mva_training.py.

result_filter_cut

result_filter_cut = b2luigi.FloatParameter()

static

Value of the cut on the MVA classifier output for a result candidate.

Definition at line 925 of file combined_to_pxd_ckf_mva_training.py.

state_filter_cut

state_filter_cut = b2luigi.FloatParameter()

static

Value of the cut on the MVA classifier output for accepting a state during CKF tracking.

Definition at line 921 of file combined_to_pxd_ckf_mva_training.py.

use_n_best_results

use_n_best_results = b2luigi.IntParameter()

static

How many results should be kept at maximum to search for overlaps.

Definition at line 927 of file combined_to_pxd_ckf_mva_training.py.

use_n_best_states

use_n_best_states = b2luigi.IntParameter()

static

How many states should be kept at maximum in the combinatorial part of the CKF tree search.

Definition at line 923 of file combined_to_pxd_ckf_mva_training.py.

---

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

• tracking/scripts/ckf_training/to_pxd/combined_to_pxd_ckf_mva_training.py