Add transform_frame to GLRM doc

[exalate-issue-sync]

No description provided.

[exalate-issue-sync]

Wendy Wong commented: I have added a new feature transform in Java and transform_frame in Python and R to GLRM.

Basically, we know given a dataset A to GLRM, it will build the following:

A = X*Y where Y is the archetype and X contains the coefficients to the archetype.

When a new dataset B is given to a GLRM model, it will perform the following:

B ~ Xnew * Y where Y is the original archetype generated from the training dataset where ~ means approximately equal.

When we call score in Java or predict in Python and R with a new dataset, the result Xnew*Y is returned.

Now, if we call transform in java or transform_frame in Python or R, the Xnew is returned instead.

Hannah: Can you please add some description and example of transform_frame to GLRM docs? Thanks, Wendy

[h2o-ops]

JIRA Issue Details

Jira Issue: PUBDEV-8751
Assignee: hannah.tillman
Reporter: Wendy Wong
State: Resolved
Fix Version: 3.36.1.3
Attachments: N/A
Development PRs: Available

[h2o-ops]

Linked PRs from JIRA

#6239