Description
Hi,
I quickly skimmed through the paper and it states that 10-fold cross-validation is applied to fix the parameters min_samples_leaf, max_depth, max_features, n-estimators. But it seems to me that in the IPython notebooks in the repo, for example (https://github.com/mjbommar/scotus-predict/blob/master/build_scdb_model_20_extra_trees.ipynb) the values of n_estimators keep increasing for the fit in every term and the other values are not changed from the default values.
It would be great if you could point me to the part of the repository that does the cross-validation.
Thanks!!