[ https://issues.apache.org/jira/browse/SPARK-20723?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
madhukara phatak updated SPARK-20723: ------------------------------------- Description: Currently Random Forest implementation cache as the intermediatery data using *MEMORY_AND_DISK* storage level. This creates issues in low memory scenarios. So we should expose an expert param *intermediateStorageLevel* which allows user to customise the storage level. This is similar to als options like specified in below jira https://issues.apache.org/jira/browse/SPARK-14412 was: Currently Random Forest implementation cache as the intermediatery data using *MEMORY_AND_DISK* storage level. This creates issues in low memory scenarios. So we should expose an expert param *intermediateRDDStorageLevel* which allows user to customise the storage level. This is similar to als options like specified in below jira https://issues.apache.org/jira/browse/SPARK-14412 > Random Forest Classifier should expose intermediateRDDStorageLevel similar to > ALS > --------------------------------------------------------------------------------- > > Key: SPARK-20723 > URL: https://issues.apache.org/jira/browse/SPARK-20723 > Project: Spark > Issue Type: New Feature > Components: ML > Affects Versions: 2.3.0 > Reporter: madhukara phatak > Priority: Minor > > Currently Random Forest implementation cache as the intermediatery data using > *MEMORY_AND_DISK* storage level. This creates issues in low memory scenarios. > So we should expose an expert param *intermediateStorageLevel* which allows > user to customise the storage level. This is similar to als options like > specified in below jira > https://issues.apache.org/jira/browse/SPARK-14412 -- This message was sent by Atlassian JIRA (v6.3.15#6346) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org