chaining

Type Members

1. trait ChainingOneAlgorithm[O, V <: GVector[V], Cz[Y, Z <: GVector[Z]] <: Clusterizable[Y, Z, Cz], GS[X] <: GenSeq[X], Vecto <: VectorizationGenLocal[O, V, Vecto], CM <: ClusteringModelLocal[V], Algorithms <: ClusteringAlgorithmLocal[V, CM]] extends ClusteringSharedTypes

   

   This classe intend to run many algorithms parallely on a local system for medium size datasets, it works for one version of an algorithm with various parameters

   This classe intend to run many algorithms parallely on a local system for medium size datasets, it works for one version of an algorithm with various parameters

   O

   the raw object from which vectorizations came from

   V

   the nature of the working vector

   Cz

   a clusterizable descendant, EasyClusterizable is the basic advise instance

   GS

   the nature of the collection containing Cz[O, V]

   Vecto

   the current vectorization which gives the current Vector nature

   CM

   the clustering model type corresponding to the nature of the given algorithm type

   Algorithms

   the clustering algorith type

2. case class ClusteringChainingLocal[O, V <: GVector[V], Cz[Y, Z <: GVector[Z]] <: Clusterizable[Y, Z, Cz], Vecto[A, B <: GVector[B]] <: VectorizationLocal[A, B, Vecto], GS[X] <: GenSeq[X]](data: GS[Cz[O, V]], chainableID: Int, currentVectorization: Vecto[O, V], clusteringInformations: HMap[ClusteringInformationsMapping] = ...)(implicit ct: ClassTag[Cz[O, V]]) extends ClusteringChaining[O, V, Cz, Vecto[O, V], GS] with Product with Serializable

   

   This classe intend to run many algorithms parallely on a local system for medium size datasets

   This classe intend to run many algorithms parallely on a local system for medium size datasets

   O

   the raw object from which vectorizations came from

   V

   the nature of the working vector

   Cz

   a clusterizable descendant, EasyClusterizable is the basic advise instance

   Vecto

   the current vectorization which gives the current Vector nature

   GS

   the nature of the collection containing Cz[O, V]

   data

   the dataset ideally sorted by Cz's IDs, if not it's done automatically

   chainableID

   the ID of this chainable class

   currentVectorization

   the current vectorization employed

   clusteringInformations

   informations about clustering results

3. final case class LocalClusteringChainingBinary[O, V <: Seq[Int], Cz[Y, Z <: GVector[Z]] <: Clusterizable[Y, Z, Cz], CM <: ClusteringModelLocalBinary[V], Vecto[A, B <: Seq[Int]] <: VectorizationLocalBinary[A, B, Vecto[A, B]], GS[X] <: GenSeq[X], Algorithms[A <: Seq[Int], B <: ClusteringModelLocalBinary[A]] <: ClusteringAlgorithmLocalBinary[A, B]](data: GS[Cz[O, BinaryVector[V]]], isDatasetSortedByID: Boolean, vectorizations: Seq[Vecto[O, V]], algorithms: Seq[Algorithms[V, CM]], modelsKeeper: ModelsKeeper = new ModelsKeeper) extends ChainingOneAlgorithm[O, BinaryVector[V], Cz, GS, Vecto[O, V], CM, Algorithms[V, CM]] with Product with Serializable

   

   This classe intend to run many algorithms parallely on a local system for medium size datasets, it works for one version of an algorithm with various parameters

   This classe intend to run many algorithms parallely on a local system for medium size datasets, it works for one version of an algorithm with various parameters

   O

   the raw object from which vectorizations came from

   V

   the nature of the working vector

   Cz

   a clusterizable descendant, EasyClusterizable is the basic advise instance

   CM

   the clustering model type corresponding to the nature of the given algorithm type

   Vecto

   the current vectorization which gives the current Vector nature

   GS

   the nature of the collection containing Cz[O, V]

   Algorithms

   the clustering algorith type

   data

   the dataset ideally sorted by Cz's IDs, if not it's done automatically

   isDatasetSortedByID

   a neccessary security due to specific algorithm where model is the entire dataset and then require to be aligned with input data

   vectorizations

   vectorizations employed on the algorithms list

   algorithms

   the sequence of algorithms which will be executed at the instantiation of the class

4. final case class LocalClusteringChainingScalar[O, V <: Seq[Double], Cz[Y, Z <: GVector[Z]] <: Clusterizable[Y, Z, Cz], CM <: ClusteringModelLocalScalar[V], Vecto[A, B <: Seq[Double]] <: VectorizationLocalScalar[A, B, Vecto[A, B]], GS[X] <: GenSeq[X], Algorithms[A <: Seq[Double], B <: ClusteringModelLocalScalar[A]] <: ClusteringAlgorithmLocalScalar[A, B]](data: GS[Cz[O, ScalarVector[V]]], isDatasetSortedByID: Boolean, vectorizations: Seq[Vecto[O, V]], algorithms: Seq[Algorithms[V, CM]], modelsKeeper: ModelsKeeper = new ModelsKeeper) extends ChainingOneAlgorithm[O, ScalarVector[V], Cz, GS, Vecto[O, V], CM, Algorithms[V, CM]] with Product with Serializable

   

   This classe intend to run many algorithms parallely on a local system for medium size datasets, it works for one version of an algorithm with various parameters

   This classe intend to run many algorithms parallely on a local system for medium size datasets, it works for one version of an algorithm with various parameters

   O

   the raw object from which vectorizations came from

   V

   the nature of the working vector

   Cz

   a clusterizable descendant, EasyClusterizable is the basic advise instance

   CM

   the clustering model type corresponding to the nature of the given algorithm type

   Vecto

   the current vectorization which gives the current Vector nature

   GS

   the nature of the collection containing Cz[O, V]

   Algorithms

   the clustering algorith type

   data

   the dataset ideally sorted by Cz's IDs, if not it's done automatically

   isDatasetSortedByID

   a neccessary security due to specific algorithm where model is the entire dataset and then require to be aligned with input data

   vectorizations

   vectorizations employed on the algorithms list

   algorithms

   the sequence of algorithms which will be executed at the instantiation of the class