Add parameter lambda_min to GLM output parameter

[exalate-issue-sync]

No description provided.

[exalate-issue-sync]

Wendy commented: Customers were trying to build models using lambda_search. However, when they tried to build individual GLM model using the same lambda values used in lambda_search, they get back GLM coefficients that are slightly different. The reason is because unless they customers specify cold_start=True, models built using lambda_search is generated by warm start. This means that each model is built using information from the previous model. Hence, to ensure that models built with lambda_search and from individual GLM using the same set of lambda values are the same, set the GLM parameter cold_start=True.

In addition, customers are asking to be able to access the max and min lambda values calculated for lambda_search directly. I added them to modelOutput.

[exalate-issue-sync]

Wendy commented: Also, add method to get lambda_best, lambda_min, lambda_max other than accessing the model parameters

[h2o-ops]

JIRA Issue Migration Info

Jira Issue: PUBDEV-7835
Assignee: Wendy
Reporter: Wendy
State: Resolved
Fix Version: 3.32.0.2
Attachments: N/A
Development PRs: Available

Linked PRs from JIRA

#5045