R xgboost wrapper doesn't pass maximize parameter to xgb.train

[ielbert]

R package xgboost version 0.4-3:

xgboost function takes maximize parameter but does not pass it to xgb.train:
Line from xgboost:
bst <- xgb.train(params, dtrain, nrounds, watchlist, verbose = verbose,
print.every.n = print.every.n, early.stop.round = early.stop.round)

xgb.train then complains:
Error in xgb.train(params, dtrain, nrounds, watchlist, verbose = verbose, :
Please set maximize to note whether the model is maximizing the evaluation or not.

[khotilov]

It was fixed in August b0be833

[ielbert]

The xgboost_0.4-3.tar.gz at CRAN seems to still have this issue with maximize in xgboost.R

[thirdwing]

@ielbert Can you try the drat repo version?

install.packages("drat", repos="https://cran.rstudio.com")
drat:::addRepo("dmlc")
install.packages("xgboost", repos="http://dmlc.ml/drat/", type="source")

[rwarnung]

I see the same problem in the current version on CRAN, which I use via mlr. But the drat repo version works! Thanks!

[ielbert]

Yes, the problem is still there. I just hot-patch the function on the fly.

On Sep 6, 2016, at 4:45 AM, Richard Warnung notifications@github.com wrote:

I see the same problem in the current version on CRAN, which I use via mlr.

—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or mute the thread.