-
Notifications
You must be signed in to change notification settings - Fork 49
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add plots for metrics and timeseries #84
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nice work! Really neat and easy to understand code, well done! I just add some remarks concerning documentation and issues related to linting (and the in-coming hooker)! In addition, can you please edit your PR message to link this PR to related issues ?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I can't wait to see this feature merged! We should make a notebook with it, congratulations Antonin! 🎉
Some minor changes in line with @lucashervier, nothing major ;)
fe2498a
to
9e52e0d
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM, All my comments are addressed, once Lucas is ok you can merge ;)
9e52e0d
to
be8ff60
Compare
The remarks from Lucas has been taken into account. I hope this is better ! I just have a pylint check that does not pass, but it does not seems to come from my code but from the checking (impossible to load keras issue). |
Even better, I approved 2 days ago, I agree for Pylint I made fix the issue in David's PR that should be merge as soon as someone approve (I already approved it) 👍 |
be8ff60
to
c2c2593
Compare
Plots for metrics and timeseries
For metrics, the plots are added in 996fad3 and tested in d755524.
For timeseries, the plots are added in 70ded0d and tested in be8ff60.
Metrics
Those are two plots that I often use. I though they may need to be integrated in Xplique.
I also made is so that each method can be assign a color and match between both plots.
Metrics histograms
This one to compare the attribution methods through several metrics:
Fidelity curves
This plot show the evolution of the score depending on the number of features perturbed. It is also used to compare methods. It can easily be done thank to the
detailed_evaluate()
method ofCausalFidelity
andCausalFidelity
introduced in pull request #70.Note that the lines on this plot are just here for testing the function.
Timeseries
The following plots come from the same function, they both output heatmaps. But for the first, a numpy array is given while the second receives a dictionary of numpy arrays.
One explanation heatmap
Several explanations heatmaps
This plot should adapt the arrangement of the subplots based on the heatmap shape and their number.