hex

Class KMeans2.KMeans2Model

java.lang.Object

water.Iced

water.Lockable<Model>

water.Model

hex.KMeans2.KMeans2Model

All Implemented Interfaces:

java.lang.Cloneable, Freezable, Job.Progress

Enclosing class:

KMeans2

public static class KMeans2.KMeans2Model
extends Model
implements Job.Progress

Nested Class Summary

Nested classes/interfaces inherited from class water.Model

Model.ModelCategory

Field Summary

Fields

Modifier and Type	Field and Description
Key	_clustersKey
double	between_cluster_SS
double[]	between_cluster_variances
double[][]	centers
static DocGen.FieldDoc[]	DOC_FIELDS
int	iterations
int	k
int	max_iter
boolean	normalized
long[]	size
double	total_SS
double	total_within_SS
double[]	within_cluster_variances

Fields inherited from class water.Model

_dataKey, _domains, _modelClassDist, _names, _priorClassDist, training_duration_in_ms, training_start_time

Fields inherited from class water.Lockable

_key, _lockers

Constructor Summary

Constructors

Constructor and Description
KMeans2.KMeans2Model(KMeans2 params, Key selfKey, Key dataKey, java.lang.String[] names, java.lang.String[][] domains)

Method Summary

Methods

Modifier and Type	Method and Description
Futures	delete_impl(Futures fs) Remove any Model internal Keys
double	mse() Returns mse for validation set.
float	progress()
protected float[]	score0(Chunk[] chunks, int rowInChunk, double[] tmp, float[] preds) Bulk scoring API for one row.
protected float[]	score0(double[] data, float[] preds) Subclasses implement the scoring logic.

Methods inherited from class water.Model

adapt, calcError, classNames, cm, errStr, get_params, getDomainMapping, getDomainMapping, getModelCategory, getUniqueId, isClassifier, job, missingColumnsType, nclasses, nfeatures, responseName, score, score, score, score, score, score, setModelClassDistribution, start_training, start_training, stop_training, testJavaScoring, toJava, toJava, toJavaDefaultMaxIters, toJavaInit, toJavaInit, toJavaPredictBody, toJavaSuper, varimp

Methods inherited from class water.Lockable

delete_and_lock, delete, delete, delete, delete, is_unlocked, is_wlocked, read_lock, read_lock, unlock_all, unlock, update, write_lock

Methods inherited from class water.Iced

clone, frozenType, init, newInstance, read, toDocField, write, writeJSON, writeJSONFields

Methods inherited from class java.lang.Object

equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

DOC_FIELDS

public static DocGen.FieldDoc[] DOC_FIELDS

centers

@Request.API(help="Cluster centers, always denormalized")
public double[][] centers

total_within_SS

@Request.API(help="Sum of within cluster sum of squares")
public double total_within_SS

between_cluster_SS

@Request.API(help="Between cluster sum of square distances")
public double between_cluster_SS

total_SS

@Request.API(help="Total Sum of squares = total_within_SS + betwen_cluster_SS")
public double total_SS

k

@Request.API(help="Number of clusters")
public int k

size

@Request.API(help="Numbers of observations in each cluster.")
public long[] size

normalized

@Request.API(help="Whether data was normalized")
public boolean normalized

max_iter

@Request.API(help="Maximum number of iterations before stopping")
public int max_iter

iterations

@Request.API(help="Iterations the algorithm ran")
public int iterations

within_cluster_variances

@Request.API(help="Within cluster sum of squares per cluster")
public double[] within_cluster_variances

between_cluster_variances

@Request.API(help="Between Cluster square distances per cluster")
public double[] between_cluster_variances

_clustersKey

@Request.API(help="The row-by-row cluster assignments")
public final Key _clustersKey

Constructor Detail

KMeans2.KMeans2Model

public KMeans2.KMeans2Model(KMeans2 params,
                    Key selfKey,
                    Key dataKey,
                    java.lang.String[] names,
                    java.lang.String[][] domains)

Method Detail

mse

public double mse()

Description copied from class: Model

Returns mse for validation set.

Overrides:

mse in class Model

progress

public float progress()

Specified by:

progress in interface Job.Progress

score0

protected float[] score0(Chunk[] chunks,
             int rowInChunk,
             double[] tmp,
             float[] preds)

Description copied from class: Model

Bulk scoring API for one row. Chunks are all compatible with the model, and expect the last Chunks are for the final distribution and prediction. Default method is to just load the data into the tmp array, then call subclass scoring logic.

Overrides:

score0 in class Model

score0

protected float[] score0(double[] data,
             float[] preds)

Description copied from class: Model

Subclasses implement the scoring logic. The data is pre-loaded into a re-used temp array, in the order the model expects. The predictions are loaded into the re-used temp array, which is also returned.

Specified by:

score0 in class Model

delete_impl

public Futures delete_impl(Futures fs)

Remove any Model internal Keys

Overrides:

delete_impl in class Model