sage.plotting.epoch_separation

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

Created on 2026-03-21 17:57:49

__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_separation_over_epochs(all_network_outputs, ...)

Track signal/noise ranking-statistic separation across training epochs.

Module Contents

plot_separation_over_epochs(all_network_outputs, all_labels, epochs, export_dir=None, save=True)[source]

Track signal/noise ranking-statistic separation across training epochs.

Plots KDE curves of the ranking statistic for signal and noise samples for each epoch, coloured by epoch so convergence trends are visible over training.

Parameters:

  • all_network_outputs (dict[epoch, array-like]) – Mapping from epoch to network output arrays.

  • all_labels (dict[epoch, array-like]) – Mapping from epoch to binary label arrays.

  • epochs (list) – Ordered list of epoch keys to include in the plot.

  • export_dir (str or None) – Output directory for the saved figure.

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