[
https://issues.apache.org/jira/browse/PIO-105?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16090989#comment-16090989
]
ASF GitHub Bot commented on PIO-105:
------------------------------------
Github user mars commented on the issue:
https://github.com/apache/incubator-predictionio/pull/412
@takezoe thank you for the feedback. As a relatively-new Scala programmer I
really appreciate this kind of review.
I am a bit hesitant to make these changes. I'm trying to maintain likeness
with the
[`CreateServer.scala`](https://github.com/mars/incubator-predictionio/blob/e7c6ebd8cfe2d4a150319025876520fc39be9a34/core/src/main/scala/org/apache/predictionio/workflow/CreateServer.scala)
code, to minimize differences in prediction behavior between `pio deploy` and
`pio batchpredict`. Any of these stylistic points should probably be matched in
CreateServer, so that it continues to be easy to reason about their similarity.
> Batch Predictions
> -----------------
>
> Key: PIO-105
> URL: https://issues.apache.org/jira/browse/PIO-105
> Project: PredictionIO
> Issue Type: New Feature
> Components: Core
> Reporter: Mars Hall
> Assignee: Mars Hall
>
> Implement a new {{pio batchpredict}} command to enable massive, fast, batch
> predictions from a trained model. Read a multi-object JSON file as the input
> format, with one query object per line. Similarly, write results to a
> multi-object JSON file, with one prediction result + its original query per
> line.
> Currently getting bulk predictions from PredictionIO is possible with either:
> * a {{pio eval}} script, which will always train a fresh, unvalidated model
> before getting predictions
> * a custom script that hits the {{queries.json}} HTTP API, which is a serious
> bottleneck when requesting hundreds-of-thousands or millions of predictions
> Neither of these existing bulk-prediction hacks are adequate for the reasons
> mentioned.
> It's time for this use-case to be a firstclass command :D
> Pull request https://github.com/apache/incubator-predictionio/pull/412
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
