[jira] [Commented] (SPARK-39446) Add relevance score for nDCG evaluation in MLLIB

["Apache Spark (Jira)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/SPARK-39446?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17553070#comment-17553070 ] 

Apache Spark commented on SPARK-39446:
--------------------------------------

User 'uchiiii' has created a pull request for this issue:
https://github.com/apache/spark/pull/36843

> Add relevance score for nDCG evaluation in MLLIB
> ------------------------------------------------
>
>                 Key: SPARK-39446
>                 URL: https://issues.apache.org/jira/browse/SPARK-39446
>             Project: Spark
>          Issue Type: Improvement
>          Components: MLlib
>    Affects Versions: 3.2.1
>            Reporter: Ryosuke Horiuchi
>            Priority: Major
>
> The current implementation of ndcgAt function treats relevance score as binary (as written [Document|[https://spark.apache.org/docs/latest/api/python/reference/api/pyspark.mllib.evaluation.RankingMetrics.html#pyspark.mllib.evaluation.RankingMetrics.ndcgAt]|https://spark.apache.org/docs/latest/api/python/reference/api/pyspark.mllib.evaluation.RankingMetrics.html#pyspark.mllib.evaluation.RankingMetrics.ndcgAt].]
>  
> However, it is better to extend this to accept a user-defined relevance score to calculate nDCG more flexibly. 



--
This message was sent by Atlassian Jira
(v8.20.7#820007)

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