-
Notifications
You must be signed in to change notification settings - Fork 2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add ability to Sort grid search results with failed model #8382
Comments
Nidhi Mehta commented: looks like {noformat}> gg =h2o.getGrid("grid-88d599ea-9fa7-4f25-9fd5-ce195e63a3f9",sort_by = "residual_deviance") [2020-02-12 16:39:47] failure_stack_traces: water.exceptions.H2OModelBuilderIllegalArgumentException: Illegal argument(s) for DRF model: grid-88d599ea-9fa7-4f25-9fd5-ce195e63a3f9_model_3. Details: ERRR on field: _sample_rate: sample_rate should be in interval ]0,1] but it is 2.0.
Hyper-parameter: min_rows, 40 [2020-02-12 16:39:47] failure_stack_traces: water.exceptions.H2OModelBuilderIllegalArgumentException: Illegal argument(s) for DRF model: grid-88d599ea-9fa7-4f25-9fd5-ce195e63a3f9_model_4. Details: ERRR on field: _sample_rate: sample_rate should be in interval ]0,1] but it is 2.0.
Grid ID: grid-88d599ea-9fa7-4f25-9fd5-ce195e63a3f9
Hyper-Parameter Search Summary: ordered by increasing residual_deviance
|
JIRA Issue Migration Info Jira Issue: PUBDEV-7253 Linked PRs from JIRA |
presently cannot sort the results if there is a cancelled or failed job-
{code:java}> rf_gridperf <- h2o.getGrid(grid_id = "rf_grid_id",
failure_stack_traces: water.Job$JobCancelledException
at hex.tree.SharedTree$Driver.scoreAndBuildTrees(SharedTree.java:450)
at hex.tree.SharedTree$Driver.computeImpl(SharedTree.java:360)
at hex.ModelBuilder$Driver.compute2(ModelBuilder.java:222)
at hex.ModelBuilder.trainModelNested(ModelBuilder.java:348)...{code}
steps to repro
parse data from R, build grid in flow with a few failed models and then call h2o.getGrid from R
{noformat}> xx = h2o.importFile("https://s3.amazonaws.com/h2o-public-test-data/bigdata/laptop/kdd2009/small-churn/kdd_train.csv")
|==================================================================================================================================| 100%
[2020-02-12 16:32:03] failure_stack_traces: water.exceptions.H2OModelBuilderIllegalArgumentException: Illegal argument(s) for DRF model: grid-88d599ea-9fa7-4f25-9fd5-ce195e63a3f9_model_3. Details: ERRR on field: _sample_rate: sample_rate should be in interval ]0,1] but it is 2.0.
Hyper-parameter: min_rows, 40
Hyper-parameter: sample_rate, 2
[2020-02-12 16:32:03] failure_details: Illegal argument(s) for DRF model: grid-88d599ea-9fa7-4f25-9fd5-ce195e63a3f9_model_4. Details: ERRR on field: _sample_rate: sample_rate should be in interval ]0,1] but it is 2.0.
[2020-02-12 16:32:03] failure_stack_traces: water.exceptions.H2OModelBuilderIllegalArgumentException: Illegal argument(s) for DRF model: grid-88d599ea-9fa7-4f25-9fd5-ce195e63a3f9_model_4. Details: ERRR on field: _sample_rate: sample_rate should be in interval ]0,1] but it is 2.0.
{noformat}
flow command
{noformat}buildModel 'drf', {"model_id":"drf-7abf4113-43e7-4a36-b83d-587a3baff74c","training_frame":"kdd_train.hex_sid_99b6_1","nfolds":0,"response_column":"churn","ignored_columns":[],"ignore_const_cols":true,"ntrees":50,"max_depth":20,"nbins":20,"seed":-1,"mtries":-1,"score_each_iteration":false,"score_tree_interval":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,"col_sample_rate_per_tree":1,"min_split_improvement":0.00001,"histogram_type":"AUTO","categorical_encoding":"AUTO","distribution":"AUTO","build_tree_one_node":false,"sample_rate_per_class":[],"binomial_double_trees":false,"col_sample_rate_change_per_level":1,"calibrate_model":false,"check_constant_response":true,"grid_id":"grid-88d599ea-9fa7-4f25-9fd5-ce195e63a3f9","hyper_parameters":{"min_rows":[1,40],"sample_rate":[0.632,2]},"search_criteria":{"strategy":"Cartesian"}}{noformat}
The text was updated successfully, but these errors were encountered: