sage.plotting.paramfrac_above_thresh
Filename : paramfrac_above_thresh.py Description : Short description of the file
Created on 2026-03-21 17:39:39
__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
|
Detection fraction above threshold in bins of each source parameter. |
Module Contents
- plot_paramfrac_detected_above_thresh(epoch, ranking_stat, labels, sample_params, export_dir=None, save=True, nbins=4)[source]
Detection fraction above threshold in bins of each source parameter.
For each parameter, divides signals into
nbinsequal-count bins and plots the fraction detected (ranking statistic above a sweep of thresholds) in each bin. Reveals which parameter values the model finds hardest to detect.- Parameters:
epoch (int or str) – Epoch identifier used in the output subdirectory.
ranking_stat (array-like, shape
(N,)) – Network ranking statistics.labels (array-like, shape
(N,)) – Binary ground-truth labels.sample_params (dict[str, array-like]) – Per-event parameter arrays.
export_dir (str or None) – Parent directory; plots saved under
PARAMFRAC_ABOVE_THRESH/epoch_{epoch}/.save (bool) – If
True, save to disk; otherwise display.nbins (int) – Number of equal-count parameter bins (default
4).