Reference Issues/PRs

Fixes #7

What does this implement/fix? Explain your changes.

Updated fit_predict_async to support custom data handles alongside demo datasets. Previously it only worked with built-in datasets like "airline" now users can pass a data_handle from load_data_source to train models on their own data in the background.

Changes:

• Added optional data_handle parameter to fit_predict_async_tool in fit_predict.py.
• Updated Executor.fit_predict_async to branch between demo dataset and custom data handle.
• Updated the server tool schema and dispatch to pass through the new parameter.
• Added validation so exactly one of dataset or data_handle must be provided.
• Added tests covering both data sources and error cases.

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

No.

What should a reviewer concentrate their feedback on?

• The validation logic in fit_predict_async_tool making sure the either/or check is solid.
• The data loading branch in Executor.fit_predict_async the data_handle path vs the dataset path.

Any other comments?

Backward compatible existing calls with dataset= still work exactly as before.

PR checklist

For all contributions

• I've added myself to the list of contributors.
• Optionally, I've updated sktime's CODEOWNERS to receive notifications about future changes to these files.
• I've added unit tests and made sure they pass locally.

For new estimators

• I've added the estimator to the online documentation.
• I've updated the existing example notebooks or provided a new one to showcase how my estimator works.