hex

Class SupervisedModel<M extends SupervisedModel<M,P,O>,P extends SupervisedModel.SupervisedParameters,O extends SupervisedModel.SupervisedOutput>

java.lang.Object

water.Iced<T>

water.Keyed<T>

water.Lockable<M>

hex.Model<M,P,O>

hex.SupervisedModel<M,P,O>

All Implemented Interfaces:

java.io.Externalizable, java.io.Serializable, java.lang.Cloneable, Freezable<M>

public abstract class SupervisedModel<M extends SupervisedModel<M,P,O>,P extends SupervisedModel.SupervisedParameters,O extends SupervisedModel.SupervisedOutput>
extends Model<M,P,O>

Supervised Model There is a response column used in training.

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	SupervisedModel.SupervisedOutput Output from all Supervised Models, includes class distribution
static class	SupervisedModel.SupervisedParameters Supervised Model Parameters includes a response column, and whether or not rebalancing classes is desirable.

Nested classes/interfaces inherited from class hex.Model

Model.DeepFeatures, Model.Output, Model.Parameters

Field Summary

Fields inherited from class hex.Model

_output, _parms, _warnings

Fields inherited from class water.Lockable

_lockers

Fields inherited from class water.Keyed

_key

Constructor Summary

Constructors

Constructor and Description
SupervisedModel(Key selfKey, P parms, O output)

Method Summary

Methods

Modifier and Type	Method and Description
double	defaultThreshold() Default threshold for assigning class labels to the target class (for binomial models)
double[]	score0(Chunk[] chks, int row_in_chunk, double[] tmp, double[] preds) Bulk scoring API for one row.
protected SB	toJavaPROB(SB sb)

Methods inherited from class hex.Model

adaptTestForTrain, adaptTestForTrain, addMetrics, addWarning, checksum_impl, cleanup_adapt, isSupervised, makeMetricBuilder, remove_impl, score, score, score, score0, scoreImpl, testJavaScoring, toJava, toJava, toJavaCheckTooBig, toJavaInit, toJavaNCLASSES, toJavaPredictBody, toJavaSuper

Methods inherited from class water.Lockable

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

Methods inherited from class water.Keyed

checksum, remove, remove, remove, remove

Methods inherited from class water.Iced

clone, frozenType, read_impl, read, readExternal, readJSON_impl, readJSON, toJsonString, write_impl, write, writeExternal, writeHTML_impl, writeHTML, writeJSON_impl, writeJSON

Methods inherited from class java.lang.Object

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

Constructor Detail

SupervisedModel

public SupervisedModel(Key selfKey,
               P parms,
               O output)

Method Detail

defaultThreshold

public final double defaultThreshold()

Default threshold for assigning class labels to the target class (for binomial models)

Returns:

threshold in 0...1

score0

public double[] score0(Chunk[] chks,
              int row_in_chunk,
              double[] tmp,
              double[] preds)

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<M extends SupervisedModel<M,P,O>,P extends SupervisedModel.SupervisedParameters,O extends SupervisedModel.SupervisedOutput>

toJavaPROB

protected SB toJavaPROB(SB sb)

Overrides:

toJavaPROB in class Model<M extends SupervisedModel<M,P,O>,P extends SupervisedModel.SupervisedParameters,O extends SupervisedModel.SupervisedOutput>