org.apache.spark.ml

Class Evaluator

Object

org.apache.spark.ml.Evaluator

All Implemented Interfaces:

java.io.Serializable, Identifiable

Direct Known Subclasses:

BinaryClassificationEvaluator

public abstract class Evaluator
extends Object
implements Identifiable

:: AlphaComponent :: Abstract class for evaluators that compute metrics from predictions.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
Evaluator()

Method Summary

Methods

Modifier and Type	Method and Description
abstract double	evaluate(SchemaRDD dataset, ParamMap paramMap) Evaluates the output.

Methods inherited from class Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface org.apache.spark.ml.Identifiable

uid

Constructor Detail

Evaluator

public Evaluator()

Method Detail

evaluate

public abstract double evaluate(SchemaRDD dataset,
              ParamMap paramMap)

Evaluates the output.

Parameters:

dataset - a dataset that contains labels/observations and predictions.

paramMap - parameter map that specifies the input columns and output metrics

Returns:

metric