rail.interactive.evaluation.dist_to_dist_evaluator module

rail.interactive.evaluation.dist_to_dist_evaluator.dist_to_dist_evaluator(**kwargs)

Evaluate the performance of a photo-z estimator against reference PDFs

—

Evaluate the performance of an estimator

This will attach the input data and truth to this Evaluator (for introspection and provenance tracking).

Then it will call the run() and finalize() methods, which need to be implemented by the sub-classes.

The run() method will need to register the data that it creates to this Estimator by using self.add_data(‘output’, output_data).

—

This function was generated from the function rail.evaluation.dist_to_dist_evaluator.DistToDistEvaluator.evaluate

Parameters:

  • data (qp.Ensemble, required) – The sample to evaluate

  • truth (Any, required) – Table with the truth information

  • metrics (list, optional) – The metrics you want to evaluate. Default: []

  • exclude_metrics (list, optional) – List of metrics to exclude Default: []

  • metric_config (dict, optional) – configuration of individual_metrics Default: {}

  • chunk_size (int, optional) – Number of objects per chunk for parallel processing or to evalute per loop in single node processing Default: 10000

  • seed (float, optional) – Random seed value to use for reproducible results. Default: None

  • metric_integration_limits (list, optional) – The default end points for calculating metrics on a grid. Default: [0.0, 3.0]

  • dx (float, optional) – The default step size when calculating metrics on a grid. Default: 0.01

  • n_samples (int, optional) – The number of random samples to select for certain metrics. Default: 100

Returns:

The evaluation metrics

Return type:

dict[str, DataHandle]