Package org.tribuo.regression.impl
Class SkeletalIndependentRegressionTrainer<T>
java.lang.Object
org.tribuo.regression.impl.SkeletalIndependentRegressionTrainer<T>
- All Implemented Interfaces:
com.oracle.labs.mlrg.olcut.config.Configurable
,com.oracle.labs.mlrg.olcut.provenance.Provenancable<TrainerProvenance>
,Trainer<Regressor>
public abstract class SkeletalIndependentRegressionTrainer<T>
extends Object
implements Trainer<Regressor>
Trains n independent binary
Model
s, each of which predicts a single Regressor
.
Generates the SparseVectors once to reduce allocation.
Then wraps it up in an SkeletalIndependentRegressionModel
to provide a Regressor
prediction.
It trains each model sequentially, and could be optimised to train in parallel.
-
Field Summary
Fields inherited from interface org.tribuo.Trainer
DEFAULT_SEED, INCREMENT_INVOCATION_COUNT
-
Constructor Summary
-
Method Summary
Modifier and TypeMethodDescriptionprotected abstract SkeletalIndependentRegressionModel
createModel
(Map<String, T> models, ModelProvenance provenance, ImmutableFeatureMap featureMap, ImmutableOutputInfo<Regressor> outputInfo) Constructs the appropriate subclass ofSkeletalIndependentRegressionModel
for this trainer.int
The number of times this trainer instance has had it's train method invoked.protected abstract String
Returns the class name of the model that this class produces.void
Used by the OLCUT configuration system, and should not be called by external code.void
setInvocationCount
(int invocationCount) Set the internal state of the trainer to the provided number of invocations of the train method.Trains a predictive model using the examples in the given data set.train
(Dataset<Regressor> examples, Map<String, com.oracle.labs.mlrg.olcut.provenance.Provenance> runProvenance) Trains a predictive model using the examples in the given data set.train
(Dataset<Regressor> examples, Map<String, com.oracle.labs.mlrg.olcut.provenance.Provenance> runProvenance, int invocationCount) Trains a predictive model using the examples in the given data set.protected abstract T
trainDimension
(double[] outputs, SparseVector[] features, float[] weights, SplittableRandom rng) Trains a single dimension of the possibly multiple dimensions.protected abstract boolean
useBias()
Returns true if the SparseVector should be constructed with a bias feature.Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
Methods inherited from interface com.oracle.labs.mlrg.olcut.provenance.Provenancable
getProvenance
-
Constructor Details
-
SkeletalIndependentRegressionTrainer
protected SkeletalIndependentRegressionTrainer()for olcut.
-
-
Method Details
-
postConfig
public void postConfig()Used by the OLCUT configuration system, and should not be called by external code.- Specified by:
postConfig
in interfacecom.oracle.labs.mlrg.olcut.config.Configurable
-
train
Description copied from interface:Trainer
Trains a predictive model using the examples in the given data set. -
train
public SkeletalIndependentRegressionModel train(Dataset<Regressor> 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. -
train
public SkeletalIndependentRegressionModel train(Dataset<Regressor> 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 interfaceTrainer<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 toTrainer.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 interfaceTrainer<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 interfaceTrainer<T>
- Parameters:
invocationCount
- the number of invocations of the train method to simulate
-
createModel
protected abstract SkeletalIndependentRegressionModel createModel(Map<String, T> models, ModelProvenance provenance, ImmutableFeatureMap featureMap, ImmutableOutputInfo<Regressor> outputInfo) Constructs the appropriate subclass ofSkeletalIndependentRegressionModel
for this trainer.- Parameters:
models
- The models to use.provenance
- The model provenancefeatureMap
- The feature map.outputInfo
- The regression info.- Returns:
- A subclass of IndependentRegressionModel.
-
trainDimension
protected abstract T trainDimension(double[] outputs, SparseVector[] features, float[] weights, SplittableRandom rng) Trains a single dimension of the possibly multiple dimensions.- Parameters:
outputs
- The regression targets for this dimension.features
- The features.weights
- The example weights.rng
- The RNG to use.- Returns:
- An object representing the model. Should be the same type as that expected by
createModel(java.util.Map<java.lang.String, T>, org.tribuo.provenance.ModelProvenance, org.tribuo.ImmutableFeatureMap, org.tribuo.ImmutableOutputInfo<org.tribuo.regression.Regressor>)
.
-
useBias
protected abstract boolean useBias()Returns true if the SparseVector should be constructed with a bias feature.- Returns:
- True if the trainer needs a bias.
-
getModelClassName
Returns the class name of the model that this class produces.- Returns:
- The class name of the model.
-