hex

Class ScoreKeeper

java.lang.Object

water.Iced

hex.ScoreKeeper

All Implemented Interfaces:

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

public class ScoreKeeper
extends Iced

Low-weight keeper of scores solely intended for display (either direct or as helper to create scoring history TwoDimTable). Not intended to store large AUC object or ConfusionMatrices, etc.

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	ScoreKeeper.StoppingMetric

Field Summary

Fields

Modifier and Type	Field and Description
double	_AUC
double	_classError
float[]	_hitratio
double	_lift
double	_logloss
double	_mae
double	_mean_per_class_error
double	_mean_residual_deviance
double	_mse
double	_rmse
double	_rmsle

Constructor Summary

Constructors

Constructor and Description
ScoreKeeper()
ScoreKeeper(double mse) Keep score of mean squared error only.
ScoreKeeper(Model m) Keep score for a model using its validation_metrics if available and training_metrics if not.
ScoreKeeper(ModelMetrics mm) Keep score of a given ModelMetrics.

Method Summary

Methods

Modifier and Type	Method and Description
static java.util.Comparator<ScoreKeeper>	comparator(ScoreKeeper.StoppingMetric criterion)
boolean	equals(java.lang.Object that) Compare this ScoreKeeper with that ScoreKeeper
void	fillFrom(ModelMetrics m)
boolean	isEmpty()
static boolean	moreIsBetter(ScoreKeeper.StoppingMetric criterion)
static boolean	stopEarly(ScoreKeeper[] sk, int k, boolean classification, ScoreKeeper.StoppingMetric criterion, double rel_improvement, java.lang.String what, boolean verbose) Based on the given array of ScoreKeeper and stopping criteria should we stop early?
java.lang.String	toString()

Methods inherited from class water.Iced

asBytes, clone, copyOver, frozenType, read, readExternal, readJSON, reloadFromBytes, toJsonString, write, writeExternal, writeJSON

Methods inherited from class java.lang.Object

finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Field Detail

_mean_residual_deviance

public double _mean_residual_deviance

_mse

public double _mse

_rmse

public double _rmse

_mae

public double _mae

_rmsle

public double _rmsle

_logloss

public double _logloss

_AUC

public double _AUC

_classError

public double _classError

_mean_per_class_error

public double _mean_per_class_error

_hitratio

public float[] _hitratio

_lift

public double _lift

Constructor Detail

ScoreKeeper

public ScoreKeeper()

ScoreKeeper

public ScoreKeeper(double mse)

Keep score of mean squared error only.

Parameters:

mse -

ScoreKeeper

public ScoreKeeper(ModelMetrics mm)

Keep score of a given ModelMetrics.

Parameters:

mm - ModelMetrics to keep track of.

ScoreKeeper

public ScoreKeeper(Model m)

Keep score for a model using its validation_metrics if available and training_metrics if not.

Parameters:

m - model for which we should keep score

Method Detail

isEmpty

public boolean isEmpty()

fillFrom

public void fillFrom(ModelMetrics m)

moreIsBetter

public static boolean moreIsBetter(ScoreKeeper.StoppingMetric criterion)

stopEarly

public static boolean stopEarly(ScoreKeeper[] sk,
                int k,
                boolean classification,
                ScoreKeeper.StoppingMetric criterion,
                double rel_improvement,
                java.lang.String what,
                boolean verbose)

Based on the given array of ScoreKeeper and stopping criteria should we stop early?

equals

public boolean equals(java.lang.Object that)

Compare this ScoreKeeper with that ScoreKeeper

Overrides:

equals in class java.lang.Object

Parameters:

that -

Returns:

true if they are equal (up to 1e-6 absolute and relative error, or both contain NaN for the same values)

comparator

public static java.util.Comparator<ScoreKeeper> comparator(ScoreKeeper.StoppingMetric criterion)

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object