See: Description
| Interface | Description |
|---|---|
| ClusterShapeGenerator |
Component used to generate a cluster shape in the reduce phase when the cluster center is updated.
|
| CriterionFunction |
Represents a criterion function used to determine if a cluster algorithm has finished during the cluster center update phase at reduce time.
|
| Class | Description |
|---|---|
| ClusterInfo |
Writable class that contains information of a single cluster.
|
| ConvexHullClusterShapeGenerator |
Generates clusters shapes as hexagons
|
| DummyClusterShapeGenerator |
An implementation of
ClusterShapeGenerator that produces no shape. |
| EuclideanDistanceCriterionFunction |
A CriterionFunction implementation based on the uclidian distance between the last two cluster centers.
|
| InitialKPointsGenerator |
Generates the initial k centers used as the input for the KMeans algorithm based on a sample of points from the input data set.
|
| KMeans |
Contains constants, configuration parameter names and utility methods for KMean clusteting
|
| KMeans.KMeansIterationResult |
Holds the result of a cluster iteration.
|
| KMeansCommonMapper<K_IN,V_IN> |
Maps each input record to its closest cluster center.
|
| KMeansCommonReducer |
Processes reduce groups which are composed of records mapped to a cluster.
For each group, it updates a cluster center based on its members locations, determines if the cluster center converges and emits the updated cluster information. |
| KMeansSampler<K,V> |
Samples a dataset to find the initial k cluster centers
|
| PointWritable |
A writable class that holds a point ordinates
|
| SquaredErrorCriterionFunction |
CriterionFunction implementation that uses a squared error criterion function. |
| Enum | Description |
|---|---|
| KMeans.KMeansCounters |
Counters incremented by the KMeans algorithm
|
Copyright © 2017 Oracle and/or its affiliates. All Rights Reserved.