rail.interactive.estimation.algos.var_inf module

rail.interactive.estimation.algos.var_inf.var_inf_stack_informer(**kwargs)

Placeholder Informer

—

The main interface method for Informers

This will attach the input_data to this Informer (for introspection and provenance tracking).

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

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

Finally, this will return a ModelHandle providing access to the trained model.

—

This function was generated from the function rail.estimation.algos.var_inf.VarInfStackInformer.inform

Parameters:

  • training_data (qp.Ensemble | str, required) – Per-galaxy p(z), and any ancilary data associated with it, by default “None”

  • truth_data (TableLike | str, required) – Table with the true redshifts, by default “None”

  • hdf5_groupname (str, optional) – name of hdf5 group for data, if None, then set to ‘’ Default: photometry

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

Returns:

Handle providing access to trained model

Return type:

dict[str, ModelHandle]

rail.interactive.estimation.algos.var_inf.var_inf_stack_summarizer(**kwargs)

Variational inference summarizer based on notebook created by Markus Rau The summzarizer is appropriate for the likelihoods returned by template-based codes, for which the NaiveSummarizer are not appropriate.

—

Summarizer for VarInfStack which returns multiple items

—

This function was generated from the function rail.estimation.algos.var_inf.VarInfStackSummarizer.summarize

Parameters:

  • input_data (qp.Ensemble, required) – Per-galaxy p(z), and any ancillary data associated with it

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

  • zmin (float, optional) – The minimum redshift of the z grid or sample Default: 0.0

  • zmax (float, optional) – The maximum redshift of the z grid or sample Default: 3.0

  • nzbins (int, optional) – The number of gridpoints in the z grid Default: 301

  • seed (int, optional) – random seed Default: 87

  • n_iter (int, optional) – The number of iterations in the variational inference Default: 100

  • n_samples (int, optional) – The number of samples used in dirichlet uncertainty Default: 500

Returns:

Ensemble with n(z), and any ancillary data Return type depends on output_mode

Return type:

QPHandle | dict[str, QPHandle]