Peter Gagarinov

Would it be possible to add the following shortcuts? a) split a cell at point (Ctrl-Shift + "-" in Jupyter) b) add a cell before current cell (A in Jupyter)...

The absence of of sparse data supports in OneHotEncoder and ContinousEncoder makes then unusable for the large number of features / categorical features with large number of categories. Yes, sparse...

@timkpaine I do not think this is a duplicate of #1122 because in #1122 the source of the problem is passing pivoted dataframes into perspective. Here I do not pass...

>For clarification, my understanding is that for your use case, the data is sparse as a result of one-hot encoding categorical features >with large number of modalities as opposed to...

More articles on the subject: https://catboost.ai/docs/concepts/educational-materials-papers.html https://towardsdatascience.com/categorical-features-parameters-in-catboost-4ebd1326bee5 We could use https://contrib.scikit-learn.org/category_encoders/_modules/category_encoders/cat_boost.html#CatBoostEncoder as a reference implementation. This package https://contrib.scikit-learn.org/category_encoders/index.html contains other useful categorical features encoders that are currently missing in MLJ....

Same problem here - I'm using JupyterLab with jupyterlab-lsp, the latter detects LS.jl but those "missing references" warnings completely kill the user experience. I would be good to know some...

Here is a script for installing Far2l on CentOS 8: https://github.com/pgagarinov/centos-config/blob/master/centos8/basic/install_far2l.sh

> > Here is a script for installing Far2l on CentOS 8: > > https://github.com/pgagarinov/centos-config/blob/master/centos8/basic/install_far2l.sh > > have two issues with this script on centos 8: > > 1. wxGTK3-devel...

@tlienart I can confirm that I was able to reproduce the performance problem reported by @irublev .

You probably will find it useful to talk to Kirill about HandleObjectCloner - he also has an experience of using this class.