Plotting TP/FN Bar Chart from Confusion Matrix

Version 1.0.4 (3.21 KB) by David Heise
This code provides an alternative view of confusion matrix data by plotting as a bar chart.
16 Downloads
Updated 20 Aug 2023

View License

This function will produce a bar plot to show the true positives (TP) versus the false negative (FN) for each target class. Both correct and incorrect classifications are color-coded to show the predicted class.
Inputs:
C - an integer matrix of the confusion data to plot, with ground truth labels in rows and predicted labels in columns
c_labels - a cell array of class labels, given in the same order as in C
cmap - [optional] a colormap matrix specifying colors to use in displaying each class from c_labels
max_y - [optional] integer maximum value for y axis in the produced plot
Outputs:
b_fig - a handle to the figure produced

Cite As

D. Heise and H. Bear, "Evaluating the Potential and Realized Impact of Data Augmentations", submitted to 2023 IEEE Symposium Series on Computational Intelligence, in review.

MATLAB Release Compatibility
Created with R2023a
Compatible with any release
Platform Compatibility
Windows macOS Linux
Tags Add Tags
Acknowledgements

Inspired by: Plot Groups of Stacked Bars

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!
Version Published Release Notes
1.0.4

updated citation

1.0.3

removed extraneous '\n' from error messages

1.0.2

corrected additional errors

1.0.1

correcting small (but fatal) errors

1.0.0