spark-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Joseph K. Bradley (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (SPARK-3164) Store DecisionTree Split.categories as Set
Date Sat, 18 Oct 2014 00:14:33 GMT

     [ https://issues.apache.org/jira/browse/SPARK-3164?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Joseph K. Bradley updated SPARK-3164:
-------------------------------------
    Description: 
Improvement: computation

For categorical features with many categories, it could be more efficient to store Split.categories
as a Set, not a List.  (It is currently a List.)  A Set might be more scalable (for log n
lookups), though tests would need to be done to ensure that Sets do not incur too much more
overhead than Lists.


  was:
Improvement: computation

For categorical features with many categories, it could be more efficient to store Split.categories
as a Set, not a List.  (It is currently a List.)  A Set might be more scalable (for log(n)
lookups), though tests would need to be done to ensure that Sets do not incur too much more
overhead than Lists.



> Store DecisionTree Split.categories as Set
> ------------------------------------------
>
>                 Key: SPARK-3164
>                 URL: https://issues.apache.org/jira/browse/SPARK-3164
>             Project: Spark
>          Issue Type: Improvement
>          Components: MLlib
>            Reporter: Joseph K. Bradley
>            Priority: Trivial
>
> Improvement: computation
> For categorical features with many categories, it could be more efficient to store Split.categories
as a Set, not a List.  (It is currently a List.)  A Set might be more scalable (for log n
lookups), though tests would need to be done to ensure that Sets do not incur too much more
overhead than Lists.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org


Mime
View raw message