[R-package] fix warnings in examples

[jameslamb]

The deprecation warnings added as part of #4226 introduced some warnings in the examples in {lightgbm}'s documentation.

For example, see https://lightgbm.readthedocs.io/en/latest/R/reference/lgb.train.html

This PR fixes them and converts examples to the new pattern we want to encourage as of v3.3.0 (#4310), passing all parameters through params.

[StrikerRUS]

Thank you very much for fixing warnings!
I've checked all @examples in all .R files and found only two issues. I think we can update them in this PR as one of them is super minor and another one is directly related to ... params.

I think we need to assign the following prediction result to some variable

LightGBM/R-package/R/lgb.Booster.R

Lines 758 to 759 in ee5636f

	#' # pass other prediction parameters
	#' predict(

Looks like a typo because I can't find test parameter. Probably should be label = test$label? I guess there is no warning about test keyword argument because we haven't deprecated ... params in Dataset constructor yet.

LightGBM/R-package/R/lgb.Dataset.R

Line 1153 in f5925c3

#' dtest <- lgb.Dataset(test$data, test = train$label)

[jameslamb]

I think we can update them in this PR

Agree with both of these, thanks! Just pushed ea5ab13 to fix these.

Looks like a typo because I can't find test parameter. Probably should be label = test$label?

Thanks for catching this! Just want to note this is a good example of the value of #4226 . In {lightgbm} 4.0.0, when ... is no longer respected, mistakes like this will become loud errors instead of unrecognized parameters being silently ignored.

[github-actions]

This pull request has been automatically locked since there has not been any recent activity since it was closed. To start a new related discussion, open a new issue at https://github.com/microsoft/LightGBM/issues including a reference to this.