Package org.tribuo.ensemble

Class BaggingTrainer<T extends Output<T>>

java.lang.Object
org.tribuo.ensemble.BaggingTrainer<T>
Type Parameters:
T - The prediction type.
All Implemented Interfaces:
com.oracle.labs.mlrg.olcut.config.Configurable, com.oracle.labs.mlrg.olcut.provenance.Provenancable<TrainerProvenance>, Trainer<T>
Direct Known Subclasses:
ExtraTreesTrainer, RandomForestTrainer
public class BaggingTrainer<T extends Output<T>> extends Object implements Trainer<T>
A Trainer that wraps another trainer and produces a bagged ensemble.

A bagged ensemble is a set of models each of which was trained on a bootstrap sample of the original dataset, combined with an unweighted majority vote.

See: 

 J. Friedman, T. Hastie, & R. Tibshirani.
 "The Elements of Statistical Learning"
 Springer 2001. PDF

  • Field Details

    • innerTrainer

      @Config(mandatory=true, description="The trainer to use for each ensemble member.") protected Trainer<T extends Output<T>> innerTrainer

    • numMembers

      @Config(mandatory=true, description="The number of ensemble members to train.") protected int numMembers

    • seed

      @Config(mandatory=true, description="The seed for the RNG.") protected long seed

    • combiner

      @Config(mandatory=true, description="The combination function to aggregate each ensemble member\'s outputs.") protected EnsembleCombiner<T extends Output<T>> combiner

    • rng

      protected SplittableRandom rng

    • trainInvocationCounter

      protected int trainInvocationCounter

  • Constructor Details

    • BaggingTrainer

      protected BaggingTrainer()
      For the configuration system.

    • BaggingTrainer

      public BaggingTrainer(Trainer<T> trainer, EnsembleCombiner<T> combiner, int numMembers)
      Constructs a bagging trainer with the supplied parameters using Trainer.DEFAULT_SEED as the RNG seed.
      Parameters:
      trainer - The ensemble member trainer.
      combiner - The combination function.
      numMembers - The number of ensemble members to train.

    • BaggingTrainer

      public BaggingTrainer(Trainer<T> trainer, EnsembleCombiner<T> combiner, int numMembers, long seed)
      Constructs a bagging trainer with the supplied parameters.
      Parameters:
      trainer - The ensemble member trainer.
      combiner - The combination function.
      numMembers - The number of ensemble members to train.
      seed - The RNG seed used to bootstrap the datasets.

  • Method Details

    • postConfig

      public void postConfig()
      Used by the OLCUT configuration system, and should not be called by external code.
      Specified by:
      postConfig in interface com.oracle.labs.mlrg.olcut.config.Configurable

    • ensembleName

      protected String ensembleName()
      Default name of the generated ensemble.
      Returns:
      The default ensemble name.

    • toString

      public String toString()
      Overrides:
      toString in class Object

    • train

      public EnsembleModel<T> train(Dataset<T> examples)
      Description copied from interface: Trainer
      Trains a predictive model using the examples in the given data set.
      Specified by:
      train in interface Trainer<T extends Output<T>>
      Parameters:
      examples - the data set containing the examples.
      Returns:
      a predictive model that can be used to generate predictions for new examples.

    • train

      public EnsembleModel<T> train(Dataset<T> examples, Map<String,com.oracle.labs.mlrg.olcut.provenance.Provenance> runProvenance)
      Description copied from interface: Trainer
      Trains a predictive model using the examples in the given data set.
      Specified by:
      train in interface Trainer<T extends Output<T>>
      Parameters:
      examples - the data set containing the examples.
      runProvenance - Training run specific provenance (e.g., fold number).
      Returns:
      a predictive model that can be used to generate predictions for new examples.

    • train

      public EnsembleModel<T> train(Dataset<T> examples, Map<String,com.oracle.labs.mlrg.olcut.provenance.Provenance> runProvenance, int invocationCount)
      Description copied from interface: Trainer
      Trains a predictive model using the examples in the given data set.
      Specified by:
      train in interface Trainer<T extends Output<T>>
      Parameters:
      examples - the data set containing the examples.
      runProvenance - Training run specific provenance (e.g., fold number).
      invocationCount - The invocation counter that the trainer should be set to before training, which in most cases alters the state of the RNG inside this trainer. If the value is set to Trainer.INCREMENT_INVOCATION_COUNT then the invocation count is not changed.
      Returns:
      a predictive model that can be used to generate predictions for new examples.

    • trainSingleModel

      protected Model<T> trainSingleModel(Dataset<T> examples, ImmutableFeatureMap featureIDs, ImmutableOutputInfo<T> labelIDs, int randInt, Map<String,com.oracle.labs.mlrg.olcut.provenance.Provenance> runProvenance, int invocationCount)
      Trains a single model.
      Parameters:
      examples - The training dataset.
      featureIDs - The feature domain.
      labelIDs - The output domain.
      randInt - A random int from an rng instance
      runProvenance - Provenance for this instance.
      invocationCount - The invocation count for the inner trainer.
      Returns:
      The trained ensemble member.

    • getInvocationCount

      public int getInvocationCount()
      Description copied from interface: Trainer
      The number of times this trainer instance has had it's train method invoked.

      This is used to determine how many times the trainer's RNG has been accessed to ensure replicability in the random number stream.

      Specified by:
      getInvocationCount in interface Trainer<T extends Output<T>>
      Returns:
      The number of train invocations.

    • setInvocationCount

      public void setInvocationCount(int invocationCount)
      Description copied from interface: Trainer
      Set the internal state of the trainer to the provided number of invocations of the train method.

      This is used when reproducing a Tribuo-trained model by setting the state of the RNG to what it was at when Tribuo trained the original model by simulating invocations of the train method. This method should ALWAYS be overridden, and the default method is purely for compatibility.

      In a future major release this default implementation will be removed.

      Specified by:
      setInvocationCount in interface Trainer<T extends Output<T>>
      Parameters:
      invocationCount - the number of invocations of the train method to simulate

    • getProvenance

      public TrainerProvenance getProvenance()
      Specified by:
      getProvenance in interface com.oracle.labs.mlrg.olcut.provenance.Provenancable<T extends Output<T>>