autoweka
Class ExperimentBatch.ExperimentComponent

java.lang.Object
  extended by autoweka.ExperimentBatch.ExperimentComponent
Enclosing class:
ExperimentBatch

public static class ExperimentBatch.ExperimentComponent
extends java.lang.Object

Captures all the settings of an experiment that are not related to a dataset


Field Summary
 java.util.List<java.lang.String> allowedClassifiers
          Forces Auto-WEKA to only use the list of classifiers here - if it is empty, then Auto-WEKA will try to use everything that it can
 boolean attributeSelection
          Boolean indicating if Attribute/Feature selection should happen
 float attributeSelectionTimeout
          How many seconds should be spent performing attribute selection?
 java.lang.String constructor
          The class name of the ExperimentConstructor to use
 java.util.List<java.lang.String> constructorArgs
          Any additional arguments that the ExperimentConstructor may want
 java.lang.String extraProps
          The property string with any extra properties that the experiment might need
 java.lang.String instanceGenerator
          The class name of the instance generator
 java.lang.String instanceGeneratorArgs
          The property string that the instance generator will use to make instances
 java.lang.String memory
          The string passed to the Xmx argument of a sub process limiting the RAM that WEKA will have
 java.lang.String name
          The experiment name's prefix
 java.lang.String resultMetric
          The name of the result metric to use - see ClassiferResult.Metric
 float trainTimeout
          How many seconds should be spent training a set of hyperparameters on a specific partition of the training and test data?.
 java.util.List<Experiment.TrajectoryPointExtra> trajectoryPointExtras
          For analysis experiements, these extra classifier evaluations will be done for every point along the trajectory.
 float tunerTimeout
          How many seconds should be spent for this experiment overall? (IE the SMBO method's budget)
 
Constructor Summary
ExperimentBatch.ExperimentComponent()
           
 
Method Summary
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

name

public java.lang.String name
The experiment name's prefix


resultMetric

public java.lang.String resultMetric
The name of the result metric to use - see ClassiferResult.Metric


constructor

public java.lang.String constructor
The class name of the ExperimentConstructor to use


constructorArgs

public java.util.List<java.lang.String> constructorArgs
Any additional arguments that the ExperimentConstructor may want


instanceGenerator

public java.lang.String instanceGenerator
The class name of the instance generator


instanceGeneratorArgs

public java.lang.String instanceGeneratorArgs
The property string that the instance generator will use to make instances


tunerTimeout

public float tunerTimeout
How many seconds should be spent for this experiment overall? (IE the SMBO method's budget)


trainTimeout

public float trainTimeout
How many seconds should be spent training a set of hyperparameters on a specific partition of the training and test data?. Note that this is more of a guideline, Auto-WEKA has quite a bit of slack built into to accomodate classifiers that can return partial results, or ones that decide to offload training onto their evaluation phase.


attributeSelection

public boolean attributeSelection
Boolean indicating if Attribute/Feature selection should happen


attributeSelectionTimeout

public float attributeSelectionTimeout
How many seconds should be spent performing attribute selection?


memory

public java.lang.String memory
The string passed to the Xmx argument of a sub process limiting the RAM that WEKA will have


extraProps

public java.lang.String extraProps
The property string with any extra properties that the experiment might need


trajectoryPointExtras

public java.util.List<Experiment.TrajectoryPointExtra> trajectoryPointExtras
For analysis experiements, these extra classifier evaluations will be done for every point along the trajectory. For example, if we want to look at the Testing performance all the way along, we would add a new TrajectoryPointExtra that contains an instance string of 'default', since that causes Auto-WEKA to preserve the provided training/test split


allowedClassifiers

public java.util.List<java.lang.String> allowedClassifiers
Forces Auto-WEKA to only use the list of classifiers here - if it is empty, then Auto-WEKA will try to use everything that it can

Constructor Detail

ExperimentBatch.ExperimentComponent

public ExperimentBatch.ExperimentComponent()