VXDTrackQEEvaluationTask Class Reference

Inheritance diagram for VXDTrackQEEvaluationTask:

Public Member Functions
TrackQETeacherBaseTask	teacher_task (self)
Basf2PathTask	data_collection_task (self)
	task_acronym (self)
	requires (self)
	output (self)
	run (self)

Static Public Attributes
	git_hash
	Use git hash / release of basf2 version as additional luigi parameter.
	n_events_testing = b2luigi.IntParameter()
	Number of events to generate for the test data set.
	n_events_training = b2luigi.IntParameter()
	Number of events to generate for the training data set.
	experiment_number = b2luigi.IntParameter()
	Experiment number of the conditions database, e.g.
	process_type
	Define which kind of process shall be used.
	training_target
	Feature/variable to use as truth label in the quality estimator MVA classifier.
	exclude_variables
	List of collected variables to not use in the training of the QE MVA classifier.
	fast_bdt_option
	Hyperparameter options for the FastBDT algorithm.

Detailed Description

Run ``basf2_mva_evaluate.py`` for the VXD quality estimator on separate test data

Definition at line 1937 of file combined_quality_estimator_teacher.py.

Member Function Documentation

data_collection_task()

Basf2PathTask data_collection_task ( self )

inherited

Property defining the specific ``DataCollectionTask`` to require.  Must
implemented by the inheriting specific teacher task class.

Definition at line 1811 of file combined_quality_estimator_teacher.py.

    def data_collection_task(self) -> Basf2PathTask:
        """
        Property defining the specific ``DataCollectionTask`` to require.  Must
        implemented by the inheriting specific teacher task class.
        """
        raise NotImplementedError(
            "Evaluation Tasks must define a data collection task to require "
        )
 

output()

output ( self )

inherited

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 1858 of file combined_quality_estimator_teacher.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.
        """
        weightfile_details = create_fbdt_option_string(self.fast_bdt_option)
        evaluation_pdf_output = self.teacher_task.weightfile_identifier_basename + weightfile_details + ".pdf"
        yield self.add_to_output(evaluation_pdf_output)
 

requires()

requires ( self )

inherited

Generate list of luigi Tasks that this Task depends on.

Reimplemented in RecoTrackQEEvaluationTask.

Definition at line 1829 of file combined_quality_estimator_teacher.py.

    def requires(self):
        """
        Generate list of luigi Tasks that this Task depends on.
        """
        yield self.teacher_task(
            n_events_training=self.n_events_training,
            experiment_number=self.experiment_number,
            process_type=self.process_type,
            training_target=self.training_target,
            exclude_variables=self.exclude_variables,
            fast_bdt_option=self.fast_bdt_option,
        )
        if 'USEREC' in self.process_type:
            if 'USERECBB' in self.process_type:
                process = 'BBBAR'
            elif 'USERECEE' in self.process_type:
                process = 'BHABHA'
            yield CheckExistingFile(
                filename='datafiles/qe_records_N' + str(self.n_events_testing) + '_' + process + '_test_' +
                         self.task_acronym + '.root'
                )
        else:
            yield self.data_collection_task(
                num_processes=MasterTask.num_processes,
                n_events=self.n_events_testing,
                experiment_number=self.experiment_number,
                random_seed=self.process_type + '_test',
                )
 

run()

run ( self )

inherited

Run ``basf2_mva_evaluate.py`` subprocess to evaluate QE MVA.

The MVA weight file created from training on the training data set is
evaluated on separate test data.

Definition at line 1868 of file combined_quality_estimator_teacher.py.

    def run(self):
        """
        Run ``basf2_mva_evaluate.py`` subprocess to evaluate QE MVA.
 
        The MVA weight file created from training on the training data set is
        evaluated on separate test data.
        """
        weightfile_details = create_fbdt_option_string(self.fast_bdt_option)
        evaluation_pdf_output_basename = self.teacher_task.weightfile_identifier_basename + weightfile_details + ".pdf"
 
        evaluation_pdf_output_path = self.get_output_file_name(evaluation_pdf_output_basename)
 
        if 'USEREC' in self.process_type:
            if 'USERECBB' in self.process_type:
                process = 'BBBAR'
            elif 'USERECEE' in self.process_type:
                process = 'BHABHA'
            datafiles = 'datafiles/qe_records_N' + str(self.n_events_testing) + '_' + \
                process + '_test_' + self.task_acronym + '.root'
        else:
            datafiles = self.get_input_file_names(
                self.data_collection_task.get_records_file_name(
                    self.data_collection_task,
                    n_events=self.n_events_testing,
                    random_seed=self.process + '_test_' +
                    self.task_acronym))[0]
        cmd = [
            "basf2_mva_evaluate.py",
            "--identifiers",
            self.get_input_file_names(
                self.teacher_task.get_weightfile_xml_identifier(
                    self.teacher_task,
                    fast_bdt_option=self.fast_bdt_option))[0],
            "--datafiles",
            datafiles,
            "--treename",
            self.teacher_task.tree_name,
            "--outputfile",
            evaluation_pdf_output_path,
        ]
 
        # Prepare log files
        log_file_dir = get_log_file_dir(self)
        # check if directory already exists, if not, create it. I think this is necessary as this task does not
        # inherit properly from b2luigi and thus does not do it automatically??
        try:
            os.makedirs(log_file_dir, exist_ok=True)
        # the following should be unnecessary as exist_ok=True should take care that no FileExistError rises. I
        # might ask about a permission error...
        except FileExistsError:
            print('Directory ' + log_file_dir + 'already exists.')
        stderr_log_file_path = log_file_dir + "stderr"
        stdout_log_file_path = log_file_dir + "stdout"
        with open(stdout_log_file_path, "w") as stdout_file:
            stdout_file.write(f'stdout output of the command:\n{" ".join(cmd)}\n\n')
        if os.path.exists(stderr_log_file_path):
            # remove stderr file if it already exists b/c in the following it will be opened in appending mode
            os.remove(stderr_log_file_path)
 
        # Run evaluation via subprocess and write output into logfiles
        with open(stdout_log_file_path, "a") as stdout_file:
            with open(stderr_log_file_path, "a") as stderr_file:
                try:
                    subprocess.run(cmd, check=True, stdin=stdout_file, stderr=stderr_file)
                except subprocess.CalledProcessError as err:
                    stderr_file.write(f"Evaluation failed with error:\n{err}")
                    raise err
 
 

task_acronym()

task_acronym ( self )

inherited

Acronym to distinguish between cdc, vxd and rec(o) MVA

Definition at line 1821 of file combined_quality_estimator_teacher.py.

    def task_acronym(self):
        """
        Acronym to distinguish between cdc, vxd and rec(o) MVA
        """
        raise NotImplementedError(
            "Evaluation Tasks must define a task acronym."
        )
 

teacher_task()

TrackQETeacherBaseTask teacher_task ( self )

inherited

Property defining specific teacher task to require.

Definition at line 1802 of file combined_quality_estimator_teacher.py.

    def teacher_task(self) -> TrackQETeacherBaseTask:
        """
        Property defining specific teacher task to require.
        """
        raise NotImplementedError(
            "Evaluation Tasks must define a teacher task to require "
        )
 

Member Data Documentation

exclude_variables

exclude_variables

staticinherited

Initial value:

=  b2luigi.ListParameter(
        
 
 
    )

List of collected variables to not use in the training of the QE MVA classifier.

In addition to variables containing the "truth" substring, which are excluded by default.

Definition at line 1789 of file combined_quality_estimator_teacher.py.

experiment_number

experiment_number = b2luigi.IntParameter()

staticinherited

Experiment number of the conditions database, e.g.

defines simulation geometry

Definition at line 1772 of file combined_quality_estimator_teacher.py.

fast_bdt_option

fast_bdt_option

staticinherited

Initial value:

=  b2luigi.ListParameter(
        
 
 
    )

Hyperparameter options for the FastBDT algorithm.

Definition at line 1795 of file combined_quality_estimator_teacher.py.

git_hash

git_hash

staticinherited

Initial value:

=  b2luigi.Parameter(
        
 
 
    )

Use git hash / release of basf2 version as additional luigi parameter.

This parameter is already set in all other tasks that inherit from Basf2Task. For this task, I decided against inheriting from Basf2Task because it already calls a subprocess and therefore does not need a dispatchable process method.

Definition at line 1762 of file combined_quality_estimator_teacher.py.

n_events_testing

n_events_testing = b2luigi.IntParameter()

staticinherited

Number of events to generate for the test data set.

Definition at line 1768 of file combined_quality_estimator_teacher.py.

n_events_training

n_events_training = b2luigi.IntParameter()

staticinherited

Number of events to generate for the training data set.

Definition at line 1770 of file combined_quality_estimator_teacher.py.

process_type

process_type

staticinherited

Initial value:

=  b2luigi.Parameter(
        
 
 
    )

Define which kind of process shall be used.

Decide between simulating BBBAR or BHABHA, MUMU, YY, DDBAR, UUBAR, SSBAR, CCBAR, reconstructing DATA or already simulated files (USESIMBB/EE) or running on existing reconstructed files (USERECBB/EE)

Definition at line 1776 of file combined_quality_estimator_teacher.py.

training_target

training_target

staticinherited

Initial value:

=  b2luigi.Parameter(
        
 
 
    )

Feature/variable to use as truth label in the quality estimator MVA classifier.

Definition at line 1782 of file combined_quality_estimator_teacher.py.

---

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

• tracking/scripts/tracking/train/combined_quality_estimator_teacher.py