[
https://issues.apache.org/jira/browse/SPARK-18408?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15703467#comment-15703467
]
Joseph K. Bradley commented on SPARK-18408:
-------------------------------------------
Note this is marked now as 2.1.1 b/c of RC1 being cut, but it will be changed
to 2.1.0 once RC2 is cut.
> API Improvements for LSH
> ------------------------
>
> Key: SPARK-18408
> URL: https://issues.apache.org/jira/browse/SPARK-18408
> Project: Spark
> Issue Type: Improvement
> Components: ML
> Reporter: Yun Ni
> Assignee: Yun Ni
> Fix For: 2.1.1, 2.2.0
>
>
> As the first improvements to current LSH Implementations, we are planning to
> do the followings:
> - Change output schema to {{Array of Vector}} instead of {{Vectors}}
> - Use {{numHashTables}} as the dimension of {{Array}} and
> {{numHashFunctions}} as the dimension of {{Vector}}
> - Rename {{RandomProjection}} to {{BucketedRandomProjectionLSH}},
> {{MinHash}} to {{MinHashLSH}}
> - Make randUnitVectors/randCoefficients private
> - Make Multi-Probe NN Search and {{hashDistance}} private for future
> discussion
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
