Filippo Pellegrino

I have written down the following workaround: ```julia """ ndarray_to_matrix(X::Matrix{PyCall.PyObject}) Converts `X` into a Matrix{Union{Missing, Float64}} handling `None` appropriately. ndarray_to_matrix(X::Matrix{Float64}) Converts `X` into a Matrix{Union{Missing, Float64}} for internal consistency. """...

Yes, of course. I am writing a wrapper for a public package (happy to pass along the references if it may help). I have attached a short screenshot to highlight...

[This is an example with random forests ](https://scikit-learn.org/stable/auto_examples/ensemble/plot_random_forest_regression_multioutput.html) that shows something similar in ScikitLearn.

Hi, I think that in general allowing for weighted losses would be better. In my case, I would need a simple average. In terms of use cases, there may be...

Also, it seems that `loss` is only available for classification trees - not regression trees. Is it possible to repurpose the existing code for classification trees to run regression tasks?...

`labels` as in [this example](https://scikit-learn.org/stable/auto_examples/ensemble/plot_random_forest_regression_multioutput.html)

I am trying to use a random forest classifier with: - a custom version of the Gini Impurity, - ~~an additional stopping criterion based on some function.~~ [this can be...

@ablaom I think I figured how to do it using native APIs. In the case of classification trees, this is easy enough. All you need to do it to do...

@ablaom I have almost finished writing a custom implementation that allows for custom bootstrapping as well (e.g., stratified sampling). Do you think it would be best to keep it separate...

Hi Micah, > So if I understand correctly, a user would need to provide their own unrevised data from an external source (i.e. their own spreadsheet)? Yes, that's correct. Currently,...