Julian Fong

[ENH] refactored `_proximity_forest` to use `sktime.utils.parallelize`

28

#### Reference Issues/PRs Refactoring Proximity Tree in #5380. #### What does this implement/fix? Explain your changes. Refactoring Proximity tree to use sktime.utils.parallelize #### What should a reviewer concentrate their feedback...

**Mentee:** Julian Fong, [Github](https://github.com/julian-fong) **Mentor(s):** @fkiraly , @kirilral , @yarnabrina **Why did you join sktime's mentorship program?** I joined sktime's mentorship program in order to learn how to do collaborative...

[ENH] interfacing `momentfm` forecaster as a deep learning module

16

#### Reference Issues/PRs Issue link #6542 . #### What does this implement/fix? Explain your changes. This is a draft pr for the `momentfm` module that I am looking to implement...

[ENH] Creating documentation/extension template for the Global Forecasting API

2

As https://github.com/sktime/sktime/pull/6228 is now merged inside sktime, it would be helpful to have some documentation or an extension template as part of the `_BaseGlobalForecaster`. Developers/mentees that work on interfacing different...

This PR Is only to document CI workflows to test whether or not duplicate rows in sampling are occurring for non backend parallelization methods @fkiraly for reference

Opening a separate issue as requested by @fkiraly to track the on going mismatch array issue with `ProximityForest` and the incompatible sktime format error. **To Reproduce** To reproduce run `test_fit_idempotent`...

[ENH] Enhancing polars support by introducing `set_output`

16

Introduces files `set_output` inside `skpro.utils` and new tests file `test_set_output` inside the `tests` folder. As part of https://github.com/sktime/enhancement-proposals/pull/34 and the notes written in my mentorship programme . In this pr:...

Hi there, Is it possible to have the moment models fit on a new dataset from scratch for the forecasting and classification methods? Or is the only to load a...

[ENH] testing global forecasters: reduces number of obs in `_make_hierarchical` for test data generation to ensure shorter runtimes

13

@Xinyu-Wu-0000 @fkiraly @benHeid This pr reduces the number of observations from 50,000 to 500 in `_multiindex_data` and `_multiindex_hier_data` in order to reduce the computation load for local testing and CI...

[ENH] Fine-tuning global forecasters via PeFT

5

As discussed in #6580, one potential solution to fine-tune deep learning global forecasters is to use PeFT methods. @benHeid has kindly described some base code that we could leverage in...