Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Cannot get the recommender queries? #69

Open
noahwork opened this issue Nov 21, 2019 · 3 comments
Open

Cannot get the recommender queries? #69

noahwork opened this issue Nov 21, 2019 · 3 comments

Comments

@noahwork
Copy link

I want to get the recommended data correctly.

Your thoughts and ideas

I followed the steps in the official documentation https://actionml.com/docs/h_ur.

  1. Install with docker, no problem, document page: https://actionml.com/docs/harness_container_guide
  2. Add the recommendation engine with harness_cli, no problem, the documentation page: https://actionml.com/docs/h_ur_quickstart
  3. After the engine is added, the test function is normal.

Describe your problem

After the data was successfully entered by post and the training was activated, the recommendation engine did not give me feedback.

1
avatar
2
avatar
3
avatar
The training event was triggered and about 10,000 pieces of data were entered in advance. When the request was routed to the queries, the recommended items were not returned to me. The recommendation engine was running normally, and the log was not reported. I don’t know why.

@noahwork noahwork changed the title cannot get the recommender queries? Cannot get the recommender queries? Nov 21, 2019
@mick912
Copy link

mick912 commented Dec 12, 2019

I have same scenario

@mick912
Copy link

mick912 commented Dec 15, 2019

ERROR SparkContextSupport$ - Spark context failed for job JobDescription(321e0ee5-f824-4b72-8589-fcc4e1e2270f,queued,Spark job,Some(Sun Dec 15 08:43:38 GMT 2019),None)
org.apache.spark.SparkException: A master URL must be set in your configuration
at org.apache.spark.SparkContext.(SparkContext.scala:367)
at com.actionml.core.spark.SparkContextSupport$$anonfun$1.apply(SparkContextSupport.scala:133)
at com.actionml.core.spark.SparkContextSupport$$anonfun$1.apply(SparkContextSupport.scala:120)
at scala.concurrent.impl.Future$PromiseCompletingRunnable.liftedTree1$1(Future.scala:24)
at scala.concurrent.impl.Future$PromiseCompletingRunnable.run(Future.scala:24)
at scala.concurrent.impl.ExecutionContextImpl$AdaptedForkJoinTask.exec(ExecutionContextImpl.scala:121)
at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)

@th4m
Copy link

th4m commented Dec 18, 2019

I believe the issue in the original question is that the user John Doe simply doesn't get any recommendations, because there's only one event posted (unless you've omitted other events in your post). If you try to post some more events for more items, you ought to get some recommendations.
E.g. have John Doe buy items a and b, then have Jane Doe buy a. If you query for Jane Doe's recommendations, you should get b.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants