Hugo Delatte

Thanks Carlo, I had a look and `CombinatorialPurgedCV` uses ` n_folds=10` and `n_test_folds=8` as default parameters. That implies `n_train_folds=2` which is what the graph is showing. But I agree that's...

I think that because only two params are necessary, the API should probably also have 2 params to reduce confusion. So either: * (`n_folds`, `n_test_folds`) * (`n_folds`, `n_train_folds`) * (`n_train_folds`,...

Work in progress in [this branch](https://github.com/skfolio/skfolio/blob/08a7a7df5addc48d704d6806f503e8337aa9bc79/src/skfolio/model_selection/_combinatorial.py#L506)

Every plot methods in skfolio returns a plotly figure. Depending on where you try to run your code, to display a plotly figure you may need to call show() and...

Let me know if it works so I can close this issue. For the stable realise, hopefully before year end.

Yes could be useful, where do you think it could live? As a `Portfolio` method?

Thank you very much. Noted, I'll start working on them.

Implementation done in dev branch here: https://github.com/skfolio/skfolio/blob/d0d3b33f5ca3e27e45ac525c788ead119c83e92c/src/skfolio/portfolio/_portfolio.py#L670 https://github.com/skfolio/skfolio/blob/d0d3b33f5ca3e27e45ac525c788ead119c83e92c/src/skfolio/portfolio/_multi_period_portfolio.py#L560

Yes I agree, let's implement it. We can follow the same logic as `composition`: * make it an `abstractmethod` in `BasePortfolio` * move `plot_contribution` from `Portfolio` to `BasePortfolio` * implement...

Implementation done in dev branch here: For MultiPeriodPortfolio: https://github.com/skfolio/skfolio/blob/128f619960494f827fb2205e1a9d5cca383092d8/src/skfolio/portfolio/_multi_period_portfolio.py#L559 And for Population: https://github.com/skfolio/skfolio/blob/128f619960494f827fb2205e1a9d5cca383092d8/src/skfolio/population/_population.py#L407 And Plot: https://github.com/skfolio/skfolio/blob/128f619960494f827fb2205e1a9d5cca383092d8/src/skfolio/population/_population.py#L648