[jira] [Commented] (SPARK-24298) PCAModel Memory in Pipeline
[ https://issues.apache.org/jira/browse/SPARK-24298?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16478802#comment-16478802 ] Marco Gaido commented on SPARK-24298: - May you please provide a small program/simple list of steps to reproduce the problem you are seeing? Thanks. > PCAModel Memory in Pipeline > --- > > Key: SPARK-24298 > URL: https://issues.apache.org/jira/browse/SPARK-24298 > Project: Spark > Issue Type: Improvement > Components: ML >Affects Versions: 2.3.0 >Reporter: Hayri Volkan Agun >Priority: Major > > Java memory aggregates when using PCAModel transformer in classification > pipeline. Although it is a dimensionality reduction method memory increases > continously during classification. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-24298) PCAModel Memory in Pipeline
[ https://issues.apache.org/jira/browse/SPARK-24298?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16477983#comment-16477983 ] Hayri Volkan Agun commented on SPARK-24298: --- Decision Tree classifier is used after PCA transformer with k=500 > PCAModel Memory in Pipeline > --- > > Key: SPARK-24298 > URL: https://issues.apache.org/jira/browse/SPARK-24298 > Project: Spark > Issue Type: Improvement > Components: ML >Affects Versions: 2.3.0 >Reporter: Hayri Volkan Agun >Priority: Major > > Java memory aggregates when using PCAModel transformer in classification > pipeline. Although it is a dimensionality reduction method memory increases > continously during classification. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org