class BisectingKMeansModel extends Serializable with Saveable with Logging
Clustering model produced by BisectingKMeans. The prediction is done level-by-level from the root node to a leaf node, and at each node among its children the closest to the input point is selected.
- Annotations
- @Since( "1.6.0" )
- Source
- BisectingKMeansModel.scala
- Alphabetic
- By Inheritance
- BisectingKMeansModel
- Logging
- Saveable
- Serializable
- Serializable
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Instance Constructors
-
new
BisectingKMeansModel(root: ClusteringTreeNode)
- Annotations
- @Since( "1.6.0" )
Value Members
-
def
clusterCenters: Array[Vector]
Leaf cluster centers.
Leaf cluster centers.
- Annotations
- @Since( "1.6.0" )
-
def
computeCost(data: JavaRDD[Vector]): Double
Java-friendly version of
computeCost()
.Java-friendly version of
computeCost()
.- Annotations
- @Since( "1.6.0" )
-
def
computeCost(data: RDD[Vector]): Double
Computes the sum of squared distances between the input points and their corresponding cluster centers.
Computes the sum of squared distances between the input points and their corresponding cluster centers.
- Annotations
- @Since( "1.6.0" )
-
def
computeCost(point: Vector): Double
Computes the squared distance between the input point and the cluster center it belongs to.
Computes the squared distance between the input point and the cluster center it belongs to.
- Annotations
- @Since( "1.6.0" )
-
val
distanceMeasure: String
- Annotations
- @Since( "2.4.0" )
-
lazy val
k: Int
Number of leaf clusters.
-
def
predict(points: JavaRDD[Vector]): JavaRDD[Integer]
Java-friendly version of
predict()
.Java-friendly version of
predict()
.- Annotations
- @Since( "1.6.0" )
-
def
predict(points: RDD[Vector]): RDD[Int]
Predicts the indices of the clusters that the input points belong to.
Predicts the indices of the clusters that the input points belong to.
- Annotations
- @Since( "1.6.0" )
-
def
predict(point: Vector): Int
Predicts the index of the cluster that the input point belongs to.
Predicts the index of the cluster that the input point belongs to.
- Annotations
- @Since( "1.6.0" )
-
def
save(sc: SparkContext, path: String): Unit
Save this model to the given path.
Save this model to the given path.
This saves:
- human-readable (JSON) model metadata to path/metadata/
- Parquet formatted data to path/data/
The model may be loaded using
Loader.load
.- sc
Spark context used to save model data.
- path
Path specifying the directory in which to save this model. If the directory already exists, this method throws an exception.
- Definition Classes
- BisectingKMeansModel → Saveable
- Annotations
- @Since( "2.0.0" )
-
val
trainingCost: Double
- Annotations
- @Since( "3.0.0" )