h2oai / h2o-3

H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.
http://h2o.ai
Apache License 2.0
6.94k stars 2k forks source link

Setting certain parameters on Gradient Boosting Machine give StackOverflow #8103

Open exalate-issue-sync[bot] opened 1 year ago

exalate-issue-sync[bot] commented 1 year ago

Building a GBM model with a 33000 sources and 40 attributes training frame and these parameters:

{quote} {"model_id":"33k_GBM_MODEL","training_frame":"33K_frame","nfolds":0,"response_column":"CLASSIFICATION_TYPE","ignored_columns":[],"ignore_const_cols":true,"ntrees":200,"max_depth":9999,"min_rows":1,"nbins":20,"seed":1,"learn_rate":0.1,"sample_rate":1,"col_sample_rate":1,"score_each_iteration":false,"score_tree_interval":0,"balance_classes":false,"max_confusion_matrix_size":20,"max_hit_ratio_k":0,"nbins_top_level":1024,"nbins_cats":1024,"r2_stopping":1.7976931348623157e+308,"stopping_rounds":0,"stopping_metric":"AUTO","stopping_tolerance":0.001,"max_runtime_secs":0,"learn_rate_annealing":1,"distribution":"AUTO","huber_alpha":0.9,"col_sample_rate_per_tree":1,"min_split_improvement":0.00001,"histogram_type":"AUTO","categorical_encoding":"AUTO","monotone_constraints":[],"build_tree_one_node":false,"sample_rate_per_class":[],"col_sample_rate_change_per_level":1,"max_abs_leafnode_pred":1.7976931348623157e+308,"pred_noise_bandwidth":0,"calibrate_model":false,"check_constant_response":true}{quote}

Gives this Error:

{noformat}05-15 13:49:57.377 3799 FJ-1-29 ERRR: java.lang.StackOverflowError 05-15 13:49:57.377 3799 FJ-1-29 ERRR: at water.AutoBuffer.put1(AutoBuffer.java:747) 05-15 13:49:57.377 3799 FJ-1-29 ERRR: at hex.tree.DTree$DecidedNode.compress(DTree.java:716) 05-15 13:49:57.377 3799 FJ-1-29 ERRR: at hex.tree.DTree$DecidedNode.compress(DTree.java:752) 05-15 13:49:57.377 3799 FJ-1-29 ERRR: at hex.tree.DTree$DecidedNode.compress(DTree.java:752) 05-15 13:49:57.377 3799 FJ-1-29 ERRR: at hex.tree.DTree$DecidedNode.compress(DTree.java:752) 05-15 13:49:57.377 3799 FJ-1-29 ERRR: at hex.tree.DTree$DecidedNode.compress(DTree.java:752) 05-15 13:49:57.377 3799 FJ-1-29 ERRR: at hex.tree.DTree$DecidedNode.compress(DTree.java:752) 05-15 13:49:57.377 3799 FJ-1-29 ERRR: at hex.tree.DTree$DecidedNode.compress(DTree.java:752) 05-15 13:49:57.377 3799 FJ-1-29 ERRR: at hex.tree.DTree$DecidedNode.compress(DTree.java:752){noformat}

Setting a smaller number for max_depth gives no error

h2o-ops commented 1 year ago

JIRA Issue Migration Info

Jira Issue: PUBDEV-7535 Assignee: New H2O Bugs Reporter: Lea Karbevska State: Open Fix Version: N/A Attachments: N/A Development PRs: N/A