[
https://issues.apache.org/jira/browse/HIVEMALL-134?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17091730#comment-17091730
]
Valdar commented on HIVEMALL-134:
---------------------------------
Perhaps a good first step would be to create the fit/predict interface in SQL
using structs. Something like this:
* {{fit('model_name', features, target, map_of_parameters)}} (or the current
{{train_regressor}}/{{train_classifier}}) which returns a struct or map
representing the model
* {{predict(model_struct, features)}} which returns the predictions
The model struct/map could then be exported for use in standalone mode. This
kind of API has proved itself elsewhere (e.g., R / Python ecosystem) and is, in
my opinion, more consistent and user-friendly compared to the current one.
> Create Stanalone API for Scala/Java
> -----------------------------------
>
> Key: HIVEMALL-134
> URL: https://issues.apache.org/jira/browse/HIVEMALL-134
> Project: Hivemall
> Issue Type: Wish
> Reporter: Makoto Yui
> Priority: Major
>
> Standalone API of Hivemall would be useful for standalone application with
> enough local memory.
> A good example of a standalone API is Smile's Scala API.
> https://haifengl.github.io/smile/
> https://github.com/haifengl/smile/tree/master/scala/src/main/scala/smile
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
