Summary

In R, the return statement is not strictly required in functions.

# this returns NULL
gives_nothing <- function(x, y){
    print(x)
    print(y)
}

# this returns the value of n
gives_sum <- function(x, y){
    n <- x + y
    n
}

This means that it can sometimes be difficult to understand, from looking at the code, what a function will return.

How

I have a simple regression task (using a LightGBMRegressor) where I want to penalize negative predictions more than positive ones. Is there a way to achieve this with the default regression LightGBM objectives (see https://lightgbm.readthedocs.io/en/latest/Parameters.html)? If not, is it somehow possible to define (many example for default LightGBM model) and pass a custom regression objective?

Support DataFrame.select_dtypes

I'm sorry if I missed this functionality, but CLI version hasn't it for sure (I saw the related code only in generate_code_examples.py). I guess it will be very useful to eliminate copy-paste phase, especially for large models.

Of course, piping is a solution, but not for development in Jupyter Notebook, for example.

It will be fantastic to add ROC curve in a README.md report file for the model in a binary classification task.