predictionio-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Pat Ferrel <...@occamsmachete.com>
Subject Re: mahout spark-rowsimilarity error
Date Fri, 19 May 2017 16:20:06 GMT
Some ideas are left on the SO question


On May 18, 2017, at 6:14 PM, Daniel Gabrieli <dgabrieli@salesforce.com> wrote:

Hi,

I am trying to research potential features to feed into the Universal Recommendation engine
by using the mahout command line interface.  I can successfully run mahout spark-rowsimilarity
<https://mahout.apache.org/users/recommender/intro-cooccurrence-spark.html> on up to
about 500 rows of data. After that I get the error below:

INFO DAGScheduler: Job 7 failed: saveAsTextFile at TextDelimitedReaderWriter.scala:294, took
1.110184 s
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure:
Task 0 in stage 12.0 failed 1 times, most recent failure: Lost task 0.0 in stage 12.0 (TID
24, localhost): java.lang.IllegalArgumentException

I tried various cli options like below but get the same error:

mahout spark-rowsimilarity --maxObservations 500000 -sem 6g -ma "local[4]" --input items.csv
--output /tmp/output

Any suggestions would be most helpful.

I cross posted on Stack Overflow here <http://stackoverflow.com/questions/44059463/mahout-spark-rowsimilarity-error>

Thanks



Mime
View raw message