Clarify differences between h2o.performance and h2o.predict

[exalate-issue-sync]

h2o.predict and h2o.performance can be more clarified based on user [questions|https://stackoverflow.com/questions/59286816/threshold-used-at-prediction/59366423#59366423]. [Documentation|http://docs.h2o.ai/h2o/latest-stable/h2o-r/docs/reference/h2o.performance.html] does not explain how the threshold is estimated h2o.performance. We can add in definition:

{{For binary classification, the threshold will be recalculated using newdata to achieve the max F1 score.}}

Also, we can simplify the explanation for [Prediction Threshold|http://docs.h2o.ai/h2o/latest-stable/h2o-docs/performance-and-prediction.html#prediction-threshold] to:

• {{If you only have training data - the max F1 threshold comes from the train data model.}}
• {{If there is validation data during training - the max F1 threshold comes from the validation data model.}}

[exalate-issue-sync]

Angela Bartz commented: Pull request merged into rel-yu.

[h2o-ops]

JIRA Issue Migration Info

Jira Issue: PUBDEV-7155
Assignee: Angela Bartz
Reporter: Neema Mashayekhi
State: Resolved
Fix Version: 3.28.0.2
Attachments: N/A
Development PRs: Available

Linked PRs from JIRA

#4183