Package org.aksw.limes.core.ml.algorithm
Class AMLAlgorithm
- java.lang.Object
-
- org.aksw.limes.core.ml.algorithm.AMLAlgorithm
-
- Direct Known Subclasses:
ActiveMLAlgorithm,SupervisedMLAlgorithm,UnsupervisedMLAlgorithm
public abstract class AMLAlgorithm extends Object
- Author:
- Tommaso Soru (tsoru@informatik.uni-leipzig.de)
-
-
Constructor Summary
Constructors Constructor Description AMLAlgorithm()
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description ActiveMLAlgorithmasActive()SupervisedMLAlgorithmasSupervised()UnsupervisedMLAlgorithmasUnsupervised()ACoreMLAlgorithmgetMl()StringgetName()List<LearningParameter>getParameters()voidinit(List<LearningParameter> lp, ACache source, ACache target)Initialize the ML Algorithm.AMappingpredict(ACache source, ACache target, MLResults mlModel)Predict new links.voidsetMl(ACoreMLAlgorithm ml)voidsetParameter(String par, Object val)
-
-
-
Method Detail
-
getName
public String getName()
- Returns:
- the ML algorithm name
-
getMl
public ACoreMLAlgorithm getMl()
- Returns:
- the associated Core ML algorithm
-
init
public void init(List<LearningParameter> lp, ACache source, ACache target)
Initialize the ML Algorithm.- Parameters:
lp- learning parameterssource- the source cachetarget- the target cache
-
predict
public AMapping predict(ACache source, ACache target, MLResults mlModel)
Predict new links.- Parameters:
source- the source cachetarget- the target cachemlModel- the ML model generated by the learning phase- Returns:
- the predicted mapping
-
asSupervised
public SupervisedMLAlgorithm asSupervised()
- Returns:
- the ML algorithm as supervised-learning algorithm
-
asUnsupervised
public UnsupervisedMLAlgorithm asUnsupervised()
- Returns:
- the ML algorithm as unsupervised-learning algorithm
-
asActive
public ActiveMLAlgorithm asActive()
- Returns:
- the ML algorithm as active-learning algorithm
-
getParameters
public List<LearningParameter> getParameters()
- Returns:
- the learning parameters
-
setMl
public void setMl(ACoreMLAlgorithm ml)
- Parameters:
ml- the core ML algorithm
-
-