TestNG GLM neg testcase : Beta constraints enabled => Lower bound > Upper bound => builds model instead of error

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.

Apache License 2.0

6.92k stars 2k forks source link

On Flow :

1)Upload datasets from smalldata/testng/airquality_train1.csv smalldata/testng/airquality_validation1.csv

2)Parse above files

3)Create beta constraints.csv as below names lower_bounds upper_bounds Solar.R 100 0 Wind 100 0 Temp 100 0 Month 100 0 Day 100 0

4) Build GLM model as below:

buildModel 'glm', {"model_id":"glm2-b02ce6c7-2a00-47de-970b-409ae9184e05","training_frame":"Key_Frame__airquality_train1.hex","validation_frame":"Key_Frameairquality_validation1.hex","nfolds":0,"response_column":"Ozone","ignored_columns":[],"ignore_const_cols":true,"family":"gaussian","solver":"L_BFGS","alpha":[0],"lambda":[],"lambda_search":false,"standardize":true,"non_negative":false,"beta_constraints":"Key_Framebeta_constraints_air_quality2.hex","score_each_iteration":false,"max_iterations":-1,"link":"family_default","intercept":true,"objective_epsilon":0.00001,"beta_epsilon":0.00001,"gradient_epsilon":0.0001,"prior":-1,"max_active_predictors":-1}

GLM model is built, instead of reporting error

h2oai / h2o-3

TestNG GLM neg testcase : Beta constraints enabled => Lower bound > Upper bound => builds model instead of error #15047