I can't find a JIRA for this, though there are some related to the existing MLlib implementation (https://issues.apache.org/jira/browse/SPARK-10802 and https://issues.apache.org/jira/browse/SPARK-11968) - would be good to port it over, and in the process also speed it up as per SPARK-11968, and possibly add ability to recommend for a subset as per SPARK-10802. Perhaps file a JIRA ticket for this issue, and link the other two?
On Sun, Dec 6, 2015 at 9:59 PM, guillaume <guillaume.all...@schibsted.com> wrote: > I have experimented very low performance with the ALSModel.transform method > when feeding it with even a small cartesian product of user x items. > > The former mllib implementation has a recommendForAll method to return topn > items per users in an efficient way (using the blockify method to > distribute > parts of users and items factors). > > https://github.com/apache/spark/blob/master/mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala#L271 > > I could revert to mlib, but the ALS benefits nice optimization in ml > (https://issues.apache.org/jira/browse/SPARK-3541). Do you guys consider > to > port the recommendForAll to ml? > > Thanks in advance! > > > > -- > View this message in context: > http://apache-spark-user-list.1001560.n3.nabble.com/mllib-recommendations-als-recommendForAll-not-ported-to-ml-tp25609.html > Sent from the Apache Spark User List mailing list archive at Nabble.com. > > --------------------------------------------------------------------- > To unsubscribe, e-mail: user-unsubscr...@spark.apache.org > For additional commands, e-mail: user-h...@spark.apache.org > >
