TrainParticleClassifier

class ctapipe.tools.train_particle_classifier.TrainParticleClassifier(**kwargs: Any)

Bases: ctapipe.core.tool.Tool

Tool to train a ParticleClassifier on dl1b/dl2 data.

The tool first performs a cross validation to give an initial estimate on the quality of the estimation and then finally trains one model per telescope type on the full dataset.

Attributes Summary

aliases
classes
description
examples
input_url_background	Input dl1b/dl2 file for the background class.
input_url_signal	Input dl1b/dl2 file for the signal class.
n_background	Number of background events to be used for training.
n_signal	Number of signal events to be used for training.
name
output_path	Output file for the trained reconstructor.
random_seed	Random number seed for sampling and the cross validation splitting

Methods Summary

finish()	Write-out trained models and cross-validation results.
setup()	Initialize components from config
start()	Train models per telescope type.

Attributes Documentation

aliases: Dict[Union[str, Tuple[str, …]], Union[str, Tuple[str, str]]] = {'signal': 'TrainParticleClassifier.input_url_signal', 'background': 'TrainParticleClassifier.input_url_background', 'n-signal': 'TrainParticleClassifier.n_signal', 'n-background': 'TrainParticleClassifier.n_background', ('o', 'output'): 'TrainParticleClassifier.output_path', 'cv-output': 'CrossValidator.output_path'}

classes: List[Type[Any]] = [<class 'ctapipe.io.tableloader.TableLoader'>, <class 'ctapipe.reco.sklearn.ParticleClassifier'>, <class 'ctapipe.reco.sklearn.CrossValidator'>]

description: Union[str, ctapipe.core.traits.Unicode] = '\n    Tool to train a `~ctapipe.reco.ParticleClassifier` on dl1b/dl2 data.\n\n    The tool first performs a cross validation to give an initial estimate\n    on the quality of the estimation and then finally trains one model\n    per telescope type on the full dataset.\n    '

examples: Union[str, ctapipe.core.traits.Unicode] = '\n    ctapipe-train-particle-classifier \\\n        -c train_particle_classifier.yaml \\\n        --signal gamma.dl2.h5 \\\n        --background proton.dl2.h5 \\\n        -o particle_classifier.pkl\n    '

input_url_background

Input dl1b/dl2 file for the background class.

input_url_signal

Input dl1b/dl2 file for the signal class.

n_background

Number of background events to be used for training. If not given, all available events will be used.

n_signal

Number of signal events to be used for training. If not given, all available events will be used.

name: Union[str, ctapipe.core.traits.Unicode] = 'ctapipe-train-particle-classifier'

output_path

Output file for the trained reconstructor. At the moment, pickle is the only supported format.

random_seed

Random number seed for sampling and the cross validation splitting

Methods Documentation

finish()

Write-out trained models and cross-validation results.

setup()

Initialize components from config

start()

Train models per telescope type.