Skip to content

Unable to obtain non-zero scores on results #288

Description

@Cypre55

I have used the docker one-liner to use the universal recommender.
I have used the following config file.

{
    "engineId": "test",
       "engineFactory": "com.actionml.engines.ur.UREngine",
    "sparkConf": {
	    "master": "local",
        "spark.serializer": "org.apache.spark.serializer.KryoSerializer",
        "spark.kryo.registrator": "org.apache.mahout.sparkbindings.io.MahoutKryoRegistrator",
        "spark.kryo.referenceTracking": "false",
        "spark.kryoserializer.buffer": "300m",
        "spark.executor.memory": "20g",
        "spark.driver.memory": "10g",
		"spark.es.index.auto.create": "true",
		"es.index.auto.create": "true",
        "spark.es.nodes": "elasticsearch",
        "spark.es.nodes.wan.only": "true"
    },
    "algorithm":{
        "indicators": [ 
            {
                "name": "read",
		"maxCorrelatorsPerItem": 5
            }
        ]
    }
}

After adding events 'read', two for two separate users. After training, running a simple query with an empty JSON returns all the names of the items but with their corresponding scores as 0.

I would like to know how to obtain non-zero scores for the results.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Fields

    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions