Package org.tribuo.transform

Class TransformTrainer<T extends Output<T>>

java.lang.Object
org.tribuo.transform.TransformTrainer<T>
All Implemented Interfaces:
com.oracle.labs.mlrg.olcut.config.Configurable, com.oracle.labs.mlrg.olcut.provenance.Provenancable<TrainerProvenance>, Trainer<T>
public final class TransformTrainer<T extends Output<T>> extends Object implements Trainer<T>
A Trainer which encapsulates another trainer plus a TransformationMap object to apply to each Dataset before training each Model.

By default transformations only operate on explicit feature values. To include implicit zeros in transformation fitting set includeImplicitZeroFeatures. To convert implicit zeros to explicit zeros before applying the transformations set densify. See org.tribuo.transform for a more detailed discussion of these parameters.

  • Constructor Details

    • TransformTrainer

      public TransformTrainer(Trainer<T> innerTrainer, TransformationMap transformations)
      Creates a trainer which transforms the data before training, and stores the transformers along with the trained model in a TransformedModel.

      Sets observeSparse to false and so this constructor makes a trainer which keeps the data sparse, and does not use the implicit zeros to construct the transformations. Models produced by this trainer will not convert implicit zeros in the feature space to explicit zeros (i.e., densify is false).

      Parameters:
      innerTrainer - The trainer to use.
      transformations - The transformations to apply to the data first.

    • TransformTrainer

      public TransformTrainer(Trainer<T> innerTrainer, TransformationMap transformations, boolean densify)
      Creates a trainer which transforms the data before training, and stores the transformers along with the trained model in a TransformedModel.

      Sets observeSparse to false and so this constructor makes a trainer which keeps the data sparse, and does not use the implicit zeros to construct the transformations.

      Parameters:
      innerTrainer - The trainer to use.
      transformations - The transformations to apply to the data first.
      densify - Convert the implicit zeros in each training and prediction example to explicit zeros before training/prediction.

    • TransformTrainer

      public TransformTrainer(Trainer<T> innerTrainer, TransformationMap transformations, boolean densify, boolean includeImplicitZeroFeatures)
      Creates a trainer which transforms the data before training, and stores the transformers along with the trained model in a TransformedModel.
      Parameters:
      innerTrainer - The trainer to use.
      transformations - The transformations to apply to the data first.
      densify - Convert the implicit zeros in each training and prediction example to explicit zeros before training/prediction.
      includeImplicitZeroFeatures - Use the implicit zero feature values to construct the transformations.

  • Method Details

    • train

      public TransformedModel<T> train(Dataset<T> examples, Map<String,com.oracle.labs.mlrg.olcut.provenance.Provenance> instanceProvenance)
      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.
      instanceProvenance - Training run specific provenance (e.g., fold number).
      Returns:
      a predictive model that can be used to generate predictions for new examples.

    • train

      public TransformedModel<T> train(Dataset<T> examples, Map<String,com.oracle.labs.mlrg.olcut.provenance.Provenance> instanceProvenance, 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.
      instanceProvenance - 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.

    • 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>>