Detailed Tutorials

[Saadi4469]

Hello and good day,

First of all thank you so much for creating such a handy package. I am a total beginner in ML at the moment so right now I am trying to familiarize myself with the package. I read through this, this and this to get some basic knowledge.

However, I would like to learn more in detail with different use case examples with interpretation of ML results. In regard to this are there vignettes that you could please point me to?

Thank you!

[jmanacup]

They have a website dedicated for the package, which is this but has not yet updated to the latest version.

[Saadi4469]

Looking forward to the updates and thank you for the quick response.

[HubertR21]

Hi, we are already in the middle of developing the next version of the package where we focus on fixing some bugs and we will also bear in mind to update the tutorial. We've also began publishing a series of blogs about the package here: https://medium.com/responsibleml

[Saadi4469]

Thank you for the quick response, looking forward to it.

[RickPack]

Does the current Github version allow one to see the ranked list of models? The example for the train() function shows train_output$ranked_list, but that does not work:

+ lightgbm: Bayesian Optimization was successful!
✔ Ranked and models list created. 
✔ Best models list created. 
> train_output$ranked_list
NULL

train_output was created by:

library(forester)
data('lisbon')
train_output <- train(lisbon, 'Price')
train_output$ranked_list

[kozaka93]

Please check the latest version of the package. We have now added the possibility to check the ranking list on specific datasets: train, valid and test. The list elements are called score_train, score_valid and score_test respectively.

[HubertR21]

The package web page has been updated recently, and we've provided a new Tutorial / Workshop called Knowledge Check that introduces the user to the package and how it works.

[Saadi4469]

Cheers, much appreciated!