[ENH] Added BaseDeepForecaster in forecasting/deep_learning

[lucifer4073]

Reference Issues/PRs

Fixes #2904.

What does this implement/fix? Explain your changes.

To lay the groundwork for future deep learning forecasters in aeon, BaseDeepForecaster class has been developed. This class abstracts common deep learning workflows for forecasting, such as input conversion, sequence generation, model compilation, training, and prediction.

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

No.

Any other comments?

This modular base class will serve as the foundation for integrating advanced deep learning models like Informer, TCN, and DeepAR into the aeon toolkit.

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 after the PR has been merged.
• The PR title starts with either [ENH], [MNT], [DOC], [BUG], [REF], [DEP] or [GOV] indicating whether the PR topic is related to enhancement, maintenance, documentation, bugs, refactoring, deprecation or governance.

For new estimators and functions

• I've added the estimator/function to the online API documentation.
• (OPTIONAL) I've added myself as a __maintainer__ at the top of relevant files and want to be contacted regarding its maintenance. Unmaintained files may be removed. This is for the full file, and you should not add yourself if you are just making minor changes or do not want to help maintain its contents.

For developers with write access

• (OPTIONAL) I've updated aeon's CODEOWNERS to receive notifications about future changes to these files.

[aeon-actions-bot]

Thank you for contributing to aeon

I have added the following labels to this PR based on the title: [ enhancement ].
I have added the following labels to this PR based on the changes made: [ forecasting ]. 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.

PR CI actions

These checkboxes will add labels to enable/disable CI functionality for this PR. This may not take effect immediately, and a new commit may be required to run the new configuration.

• Run pre-commit checks for all files
• Run mypy typecheck tests
• Run all pytest tests and configurations
• Run all notebook example tests
• Run numba-disabled codecov tests
• Stop automatic pre-commit fixes (always disabled for drafts)
• Disable numba cache loading
• Push an empty commit to re-run CI checks

[hadifawaz1999]

LGTM, i like to get it in so we can use it in TCN and Informer PRs. @MatthewMiddlehurst @TonyBagnall any comments on it ?

[TonyBagnall]

I prefer exog to X. This appeared in the wrong place

def _predict(self, y, exog=None)

[hadifawaz1999]

didnt notice that good catch

[MatthewMiddlehurst]

No comments other than those Tony has posted for now. Try to match the syntax and terminology used in the module. Consider of things such as the new mixins as well, they may not be required here specifically but is there anything special for deep learners that we need to think about.

[hadifawaz1999]

No comments other than those Tony has posted for now. Try to match the syntax and terminology used in the module. Consider of things such as the new mixins as well, they may not be required here specifically but is there anything special for deep learners that we need to think about.

i would keep mixins for models themselves, as not all deep learners follow the same setup