Class ClusteringFactory

java.lang.Object

org.tribuo.clustering.ClusteringFactory

All Implemented Interfaces:

com.oracle.labs.mlrg.olcut.config.Configurable, com.oracle.labs.mlrg.olcut.provenance.Provenancable<OutputFactoryProvenance>, Serializable, OutputFactory<ClusterID>, ProtoSerializable<org.tribuo.protos.core.OutputFactoryProto>

public final class ClusteringFactory
extends Object
implements OutputFactory<ClusterID>

A factory for making ClusterID related classes.

Parses the ClusterID by calling toString on the input then parsing it as an int.

See Also:

• Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static final class	ClusteringFactory.ClusteringFactoryProvenance	Provenance for ClusteringFactory.

Field Summary

Fields

Modifier and Type	Field	Description
static final ClusterID	UNASSIGNED_CLUSTER_ID	The sentinel unassigned cluster id, used when there is no ground truth clustering.

Fields inherited from interface org.tribuo.protos.ProtoSerializable

DESERIALIZATION_METHOD_NAME, PROVENANCE_SERIALIZER

Constructor Summary

Constructors

Constructor	Description
ClusteringFactory()	ClusteringFactory is stateless and immutable, but we need to be able to construct them via the config system.

Method Summary

Modifier and Type	Method	Description
ImmutableOutputInfo<ClusterID>	constructInfoForExternalModel(Map<ClusterID, Integer> mapping)	Unlike the other info types, clustering directly uses the integer IDs as the stored value, so this mapping discards the cluster IDs and just uses the supplied integers.
static ClusteringFactory	deserializeFromProto(int version, String className, com.google.protobuf.Any message)	Deserialization factory.
boolean	equals(Object obj)
MutableOutputInfo<ClusterID>	generateInfo()	Generates the appropriate MutableOutputInfo so the output values can be tracked by a Dataset or other aggregate.
<V> ClusterID	generateOutput(V label)	Generates a ClusterID by calling toString on the input, then calling Integer.parseInt.
Evaluator<ClusterID, ClusteringEvaluation>	getEvaluator()	Gets an Evaluator suitable for measuring performance of predictions for the Output subclass.
OutputFactoryProvenance	getProvenance()
Class<ClusterID>	getTypeWitness()	Gets the output class that this factory supports.
ClusterID	getUnknownOutput()	Returns the singleton unknown output of type T which can be used for prediction time examples.
int	hashCode()
org.tribuo.protos.core.OutputFactoryProto	serialize()	Serializes this object to a protobuf.

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface com.oracle.labs.mlrg.olcut.config.Configurable

postConfig

Methods inherited from interface org.tribuo.OutputFactory

generateOutputs

Field Details

UNASSIGNED_CLUSTER_ID

public static final ClusterID UNASSIGNED_CLUSTER_ID

The sentinel unassigned cluster id, used when there is no ground truth clustering.

Constructor Details

ClusteringFactory

public ClusteringFactory()

ClusteringFactory is stateless and immutable, but we need to be able to construct them via the config system.

Method Details

deserializeFromProto

public static ClusteringFactory deserializeFromProto(int version,
 String className,
 com.google.protobuf.Any message)

Deserialization factory.

Parameters:

version - The serialized object version.

className - The class name.

message - The serialized data.

Returns:

The deserialized object.

serialize

public org.tribuo.protos.core.OutputFactoryProto serialize()

Description copied from interface: ProtoSerializable

Serializes this object to a protobuf.

Specified by:

serialize in interface ProtoSerializable<org.tribuo.protos.core.OutputFactoryProto>

Returns:

The protobuf.

generateOutput

public <V> ClusterID generateOutput(V label)

Generates a ClusterID by calling toString on the input, then calling Integer.parseInt.

Specified by:

generateOutput in interface OutputFactory<ClusterID>

Type Parameters:

V - The type of the input.

Parameters:

label - An input value.

Returns:

A ClusterID representing the data.

getUnknownOutput

public ClusterID getUnknownOutput()

Description copied from interface: OutputFactory

Returns the singleton unknown output of type T which can be used for prediction time examples.

Specified by:

getUnknownOutput in interface OutputFactory<ClusterID>

Returns:

An unknown output.

generateInfo

public MutableOutputInfo<ClusterID> generateInfo()

Description copied from interface: OutputFactory

Generates the appropriate MutableOutputInfo so the output values can be tracked by a Dataset or other aggregate.

Specified by:

generateInfo in interface OutputFactory<ClusterID>

Returns:

The appropriate subclass of MutableOutputInfo initialised to zero.

constructInfoForExternalModel

public ImmutableOutputInfo<ClusterID> constructInfoForExternalModel(Map<ClusterID, Integer> mapping)

Unlike the other info types, clustering directly uses the integer IDs as the stored value, so this mapping discards the cluster IDs and just uses the supplied integers.

Specified by:

constructInfoForExternalModel in interface OutputFactory<ClusterID>

Parameters:

mapping - The mapping to use.

Returns:

An ImmutableOutputInfo for the clustering.

getEvaluator

public Evaluator<ClusterID, ClusteringEvaluation> getEvaluator()

Description copied from interface: OutputFactory

Gets an Evaluator suitable for measuring performance of predictions for the Output subclass.

Evaluator instances are thread safe and immutable, and commonly this is a singleton stored in the OutputFactory implementation.

Specified by:

getEvaluator in interface OutputFactory<ClusterID>

Returns:

An evaluator.

getTypeWitness

public Class<ClusterID> getTypeWitness()

Description copied from interface: OutputFactory

Gets the output class that this factory supports.

Specified by:

getTypeWitness in interface OutputFactory<ClusterID>

Returns:

The output class.

hashCode

public int hashCode()

Overrides:

hashCode in class Object

equals

public boolean equals(Object obj)

Overrides:

equals in class Object

getProvenance

public OutputFactoryProvenance getProvenance()

Specified by:

getProvenance in interface com.oracle.labs.mlrg.olcut.provenance.Provenancable<OutputFactoryProvenance>