Appendix A - ParametersΒΆ
This Appendix provides detailed descriptions of parameters that can be specified in the H2O algorithms. Note that this Appendix is a work in progress.
- GBM Parameters
balance_classesbuild_tree_one_nodecategorical_encodingcheckpointclass_sampling_factorscol_sample_ratecol_sample_rate_change_per_levelcol_sample_rate_per_treedistributionfold_assignmentfold_columnhistogram_typehuber_alphaignored_columnsignore_const_colskeep_cross_validation_fold_assignmentkeep_cross_validation_predictionslearn_ratelearn_rate_annealingmax_abs_leafnode_predmax_after_balance_sizemax_depthmax_hit_ratio_kmax_runtime_secsmin_rowsmin_split_improvementmodel_idnbinsnbins_catsnbins_top_levelnfoldsntreesoffset_columnpred_noise_bandwidthquantile_alphasample_ratesample_rate_per_classscore_each_iterationscore_tree_intervalseedstopping_metricstopping_roundsstopping_tolerancetraining_frametweedie_powervalidation_frameweights_columny