[jira] [Resolved] (SPARK-19939) Add support for association rules in ML

["Hyukjin Kwon (JIRA)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/SPARK-19939?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Hyukjin Kwon resolved SPARK-19939.
----------------------------------
    Resolution: Incomplete

> Add support for association rules in ML
> ---------------------------------------
>
>                 Key: SPARK-19939
>                 URL: https://issues.apache.org/jira/browse/SPARK-19939
>             Project: Spark
>          Issue Type: Improvement
>          Components: ML
>    Affects Versions: 2.2.0
>            Reporter: yuhao yang
>            Priority: Major
>              Labels: bulk-closed
>
> Adding another essential characteristic for the Association Rule in Spark ml.fpm.
> Support is an indication of how frequently the itemset of an association rule appears in the database and suggests if the rules are generally applicable to the dateset. refer to [https://en.wikipedia.org/wiki/Association_rule_learning] for more details.
> Before adding support:
> | rules | confidence |
> | beer -> soda | 0.5 |
> | pecan -> milk | 0.6 |
> After adding support: 
> | rules | confidence | support |
> | beer -> soda | 0.5 | 0.3 |
> | pecan -> milk | 0.6 | 0.01 |
> Thus to allow a better understanding for the generated association rules.
> Update:
> Another property for association rule is [Lift|https://en.wikipedia.org/wiki/Lift_(data_mining)], but I'm not sure if it's popular enough. Please comment below if you find Lift useful.



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

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