Package org.tribuo.common.libsvm

Interface SVMType<T extends Output<T>>

All Superinterfaces:
com.oracle.labs.mlrg.olcut.config.Configurable, com.oracle.labs.mlrg.olcut.provenance.Provenancable<com.oracle.labs.mlrg.olcut.provenance.ConfiguredObjectProvenance>, Serializable
All Known Implementing Classes:
SVMAnomalyType, SVMClassificationType, SVMRegressionType
public interface SVMType<T extends Output<T>> extends com.oracle.labs.mlrg.olcut.config.Configurable, com.oracle.labs.mlrg.olcut.provenance.Provenancable<com.oracle.labs.mlrg.olcut.provenance.ConfiguredObjectProvenance>, Serializable
A carrier type for the SVM type. It really wants to be a set of enums with different type parameters, but it's encoded as an interface where each subclass for an Output implementation contains an enum with it's valid values.

LibSVM supported enum values are:

  • C_SVC(0) - Original SVM algorithm.
  • NU_SVC(1) - Original SVM, optimization in dual space.
  • ONE_CLASS(2) - Anomaly detection SVM.
  • EPSILON_SVR(3) - epsilon-insensitive SVR.
  • NU_SVR(4) - nu-SVR, optimization in dual space.

  • Method Summary

    Modifier and Type
    Method
    Description
    int
    getNativeType()
    The LibSVM int id for the algorithm.
    boolean
    isAnomaly()
    Is this an anomaly detection algorithm.
    boolean
    isClassification()
    Is this a classification algorithm.
    boolean
    isNu()
    Is this a nu-SVM.
    boolean
    isRegression()
    Is this a regression algorithm.

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

    postConfig

    Methods inherited from interface com.oracle.labs.mlrg.olcut.provenance.Provenancable

    getProvenance

  • Method Details

    • isClassification

      boolean isClassification()
      Is this a classification algorithm.
      Returns:
      True if it's a classification algorithm.

    • isRegression

      boolean isRegression()
      Is this a regression algorithm.
      Returns:
      True if it's a regression algorithm.

    • isAnomaly

      boolean isAnomaly()
      Is this an anomaly detection algorithm.
      Returns:
      True if it's an anomaly detection algorithm.

    • isNu

      boolean isNu()
      Is this a nu-SVM.
      Returns:
      True if it's a nu-SVM.

    • getNativeType

      int getNativeType()
      The LibSVM int id for the algorithm.
      Returns:
      The int id.