sage.plotting.diagonal_compare

Filename : diagonal_compare.py Description : Short description of the file

Created on 2026-03-21 17:36:13

__author__ = Narenraju Nagarajan __copyright__ = Copyright 2026, ProjectName __license__ = MIT Licence __version__ = 0.0.1 __maintainer__ = Narenraju Nagarajan __affiliation__ = N/A __email__ = N/A __status__ = [‘inProgress’, ‘Archived’, ‘inUsage’, ‘Debugging’]

GitHub Repository: NULL

Documentation: NULL

Functions

plot_diagonal_compare(epoch, pred_params, true_params, ...)

True-vs-predicted scatter plots for each estimated parameter, coloured by SNR.

Module Contents

plot_diagonal_compare(epoch, pred_params, true_params, network_snrs, labels, export_dir=None, save=True)[source]

True-vs-predicted scatter plots for each estimated parameter, coloured by SNR.

Produces two scatter plots per parameter: the full signal set and a high-SNR (> 8) subset. Points are coloured by network optimal SNR. A dashed diagonal reference line marks perfect recovery.

Parameters:

  • epoch (int or str) – Epoch identifier used in the output subdirectory name.

  • pred_params (dict[str, array-like]) – Network point estimates per parameter.

  • true_params (dict[str, array-like]) – Ground-truth parameter values in the same layout.

  • network_snrs (array-like, shape (N,)) – Optimal network SNR for all validation events.

  • labels (array-like, shape (N,)) – Binary labels; signals selected with label == 1.

  • export_dir (str or None) – Parent directory; plots saved under DIAGONAL/epoch_{epoch}/.

  • save (bool) – If True, save to disk; otherwise display interactively.