Summary#

class liesel.goose.summary_m.Summary(results, additional_chain=None, quantiles=(0.05, 0.5, 0.95), hdi_prob=0.9, selected=None, deselected=None, per_chain=False)[source]#

Bases: object

A summary object.

Allows easy programmatic access via quantities[quantity_name][var_name]. The array has a similar shape as the parameter with var_name. However, if per_chain is True, and additionally for the quantities hdi and quantile, the dimensions are different. Please refer to the documentation of the attribute quantities for details.

The summary object can be turned into a DataFrame using to_dataframe().

Parameters
  • results (SamplingResults) – The sampling results to summarize.

  • additional_chain (Optional[NewType(Position, dict[str, Any])]) – can be supplied to add more parameters to the summary output. Must be a position (default: None) chain which matches chain and time dimension of the posterior chain as returned by SamplingResults.get_posterior_samples().

  • hdi_prob (float) – Level on which to return posterior highest density intervals. (default: 0.9)

  • selected (Optional[list[str]]) – Allow to get a summary only for a subset of the position keys. (default: None)

  • deselected (Optional[list[str]]) – Allow to get a summary only for a subset of the position keys. (default: None)

  • per_chain (bool) – If True, the summary is calculated on a per-chain basis. Certain measures like (default: False) rhat are not available if per_chain is True.

Notes

This class is still considered experimental. The API may still undergo larger changes.

Methods

from_result(result[, additional_chain, ...])

Alias for from_results() for backwards compatibility.

from_results(results[, additional_chain, ...])

Creates a Summary object from a results object.

to_dataframe()

Turns Summary object into a DataFrame object.

Attributes

per_chain

quantities

Dict of summarizing quantities.

config

sample_info

error_summary

kernels_by_pos_key