[ENH] ADD SAST transformer and SASTClassifier

[frankl1]

What does this implement/fix? Explain your changes.

Add implementation of the SAST ans SASTClassifier:

• SAST: a subsequence based transformation for time series
• SASTClassifier: as helper classifier to build a time series classifier based on the SAST transformation
  Associated paper

Does your contribution introduce a new dependency? If yes, which one?

matplotlib

PR checklist

For all contributions

• I've added myself to the list of contributors. Alternatively, you can use the @all-contributors bot to do this for you.
• The PR title starts with either [ENH], [MNT], [DOC], [BUG], [REF] or [GOV] indicating whether the PR topic is related to enhancement, maintenance, documentation, bugs, refactoring or governance.

For new estimators and functions

• I've added the estimator to the online API documentation.

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[aeon-actions-bot]

Thank you for contributing to aeon!

I have added the following labels to this PR based on the title: [ $\color{#FEF1BE}{\textsf{enhancement}}$ ].
I have added the following labels to this PR based on the changes made: [ $\color{#BCAE15}{\textsf{classification}}$, $\color{#45FD64}{\textsf{examples}}$, $\color{#41A8F6}{\textsf{transformations}}$ ]. Feel free to change these if they do not properly represent the PR.

The Checks tab will show the status of our automated tests. You can click on individual test runs in the tab or "Details" in the panel below to see more information if there is a failure.

If our pre-commit code quality check fails, any trivial fixes will automatically be pushed to your PR unless it is a draft.

Don't hesitate to ask questions on the aeon Slack channel if you have any!

[TonyBagnall]

awesome, thanks @frankl1, we will take a look next week.

[frankl1]

Hi all,

I could not figure out the cause of the failing test. It doesn't seem to be related to my changes. Since I couldn't manage to reproduce it locally, I wonder if there is a way to get more information on the error from the job log.

Thanks

[TonyBagnall]

Hi all,

I could not figure out the cause of the failing test. It doesn't seem to be related to my changes. Since I couldn't manage to reproduce it locally, I wonder if there is a way to get more information on the error from the job log.

Thanks

hi @frankl1 so sometimes the CI crashes when too much is running at once. Its passed all now. I'm away a couple of days but we will review it asap, thanks for the contribution, really pleased you made the effort. Did you join our slack? Be good to catch up

[frankl1]

Thanks for the reply @TonyBagnall. It is my pleasure to contribute to this great project and I plan to contribute more in the future. I haven't joined the Slack, will catch up.

[TonyBagnall]

I'd rather not introduce a whole new category, could this go in the shapelet package?

[frankl1]

Hi @TonyBagnall ,

Thanks for reviewing the PR.

I don't mind using the shapelet package for this since the method is able to learn shapelets. I will make the update today.

[baraline]

Hi, I'm jumping in on the review as I've seen the paper and wanted to look at the code !
If you don't mind, I think the following things could be changed.

Additionally, it would be nice to have some unit tests for the transformer and classifier.

[TonyBagnall]

LGTM, thanks

[MatthewMiddlehurst]

Thanks for the contribution @frankl1, I didnt see anything holding this back from going in on my look through. I think some tests would be good to add, but won't push for them in this PR.

Are there any more changes you want to make for this? If not, you can ping @baraline to re-review and we can move it forward I think if they agree.

Sorry for the delay!

[frankl1]

Hi,

I am sorry for the late reply, I was on vacation. There are no changes I would like to add to this @MatthewMiddlehurst. I will work on the multivariate version and make a new PR.

Thanks for merging with the main branch.

Regard