GAM failed with numknot=2

[exalate-issue-sync]

No description provided.

[exalate-issue-sync]

Wendy Wong commented: From [~accountid:61953434c510bc006b344b83] , this code is failing:

{noformat}# set the predictor and response columns
y = "wage"
x = ["year","age"]

build the GAM model

h2o_model = H2OGeneralizedAdditiveEstimator(family='gaussian',
bs=[2],
gam_columns=["age"],
scale=[1],
seed=9,
num_knots = [2],
spline_orders = [1])

N+k-2 = (num_knots) + (spline_orders) - 2 = 2 + 1 - 2 = 1

h2o_model.train(x=x, y=y, training_frame=train)

get the model coefficients

h2oCoeffs = h2o_model.coef()
h2oCoeffs{noformat}

[h2o-ops]

JIRA Issue Details

Jira Issue: PUBDEV-8865
Assignee: Wendy Wong
Reporter: Wendy Wong
State: Resolved
Fix Version: 3.38.0.3
Attachments: N/A
Development PRs: Available

[h2o-ops]

Linked PRs from JIRA

#6385
https://github.com/h2oai/h2oai-serving/pull/1135