xgboost with tree_method = 'hist' in R


According to a benchmark of GBM vs. xgboost vs. LightGBM (https://www.kaggle.com/nschneider/gbm-vs-xgboost-vs-lightgbm) it is possible to implenet xgboost with the argument

tree_method = 'hist' 

in R.

However doing so gives me always an error:

Error in xgb.iter.update(bst$handle, dtrain, iteration - 1, obj) : 
Invalid Input: 'hist', valid values are: {'approx', 'auto', 'exact'}

What am I missing?


Posted 2017-10-11T08:36:18.057

Reputation: 131



The fast hist mode is available in newer versions of XGBoost. You can find infos on https://github.com/dmlc/xgboost/

For small data sets (100k lines), you wont feel much gain in training speed.

Michael M

Posted 2017-10-11T08:36:18.057

Reputation: 460