hex

Class Model.Output

java.lang.Object

water.Iced

hex.Model.Output

All Implemented Interfaces:

java.io.Externalizable, java.io.Serializable, java.lang.Cloneable, Freezable

Direct Known Subclasses:

SupervisedModel.SupervisedOutput

Enclosing class:

Model<M extends Model<M,P,O>,P extends Model.Parameters,O extends Model.Output>

public abstract static class Model.Output
extends Iced

Model-specific output class. Each model sub-class contains an instance of one of these containing its "output": the pieces of the model needed for scoring. E.g. KMeansModel has a KMeansOutput extending Model.Output which contains the cluster centers. The output also includes the names, domains and other fields which are determined at training time.

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
java.lang.String[][]	_domains Categorical/factor/enum mappings, per column.
Key[]	_model_metrics List of all the associated ModelMetrics objects, so we can delete them when we delete this model.
java.lang.String[]	_names Columns used in the model and are used to match up with scoring data columns.
Job.JobState	_state Job state (CANCELLED, FAILED, DONE).
long	_training_duration_in_ms The duration in mS for model training, again this comes from the Job which needs to split from ModelBuilder.
long	_training_start_time The start time in mS since the epoch for model training, again this comes from the Job which needs to split from ModelBuilder.

Constructor Summary

Constructors

Constructor and Description
Model.Output(ModelBuilder b) Any final prep-work just before model-building starts, but after the user has clicked "go".

Method Summary

Methods

Modifier and Type	Method and Description
protected ModelMetrics	addModelMetrics(ModelMetrics mm)
java.lang.String[]	allNames() The names of all the columns, including the response column (which comes last).
java.lang.String[]	classNames() The names of the levels for an enum (categorical) response column.
Model.ModelCategory	getModelCategory()
boolean	isClassifier() Is this model a classification model? (v.
int	nclasses()
int	nfeatures() Returns number of input features (OK for most unsupervised methods, need to override for supervised!)
java.lang.String	responseName() The name of the response column (which is always the last column).

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

Field Detail

_names

public java.lang.String[] _names

Columns used in the model and are used to match up with scoring data columns. The last name is the response column name (if any).

_domains

public java.lang.String[][] _domains

Categorical/factor/enum mappings, per column. Null for non-enum cols. Columns match the post-init cleanup columns. The last column holds the response col enums for SupervisedModels.

_model_metrics

public Key[] _model_metrics

List of all the associated ModelMetrics objects, so we can delete them when we delete this model.

_state

public Job.JobState _state

Job state (CANCELLED, FAILED, DONE). TODO: Really the whole Job (run-time, etc) but that has to wait until Job is split from ModelBuilder.

_training_start_time

public long _training_start_time

The start time in mS since the epoch for model training, again this comes from the Job which needs to split from ModelBuilder.

_training_duration_in_ms

public long _training_duration_in_ms

The duration in mS for model training, again this comes from the Job which needs to split from ModelBuilder.

Constructor Detail

Model.Output

public Model.Output(ModelBuilder b)

Any final prep-work just before model-building starts, but after the user has clicked "go". E.g., converting a response column to an enum touches the entire column (can be expensive), makes a parallel vec (Key/Data leak management issues), and might throw IAE if there are too many classes.

Method Detail

nfeatures

public int nfeatures()

Returns number of input features (OK for most unsupervised methods, need to override for supervised!)

allNames

public java.lang.String[] allNames()

The names of all the columns, including the response column (which comes last).

responseName

public java.lang.String responseName()

The name of the response column (which is always the last column).

classNames

public java.lang.String[] classNames()

The names of the levels for an enum (categorical) response column.

isClassifier

public boolean isClassifier()

Is this model a classification model? (v. a regression or clustering model)

nclasses

public int nclasses()

getModelCategory

public Model.ModelCategory getModelCategory()

addModelMetrics

protected ModelMetrics addModelMetrics(ModelMetrics mm)