hex

Class ModelMetricsHGLM.MetricBuilderHGLM<T extends ModelMetricsHGLM.MetricBuilderHGLM<T>>

java.lang.Object

water.Iced<T>

hex.ModelMetrics.MetricBuilder<T>

hex.ModelMetricsSupervised.MetricBuilderSupervised<T>

hex.ModelMetricsHGLM.MetricBuilderHGLM<T>

All Implemented Interfaces:

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

Enclosing class:

ModelMetricsHGLM

public static class ModelMetricsHGLM.MetricBuilderHGLM<T extends ModelMetricsHGLM.MetricBuilderHGLM<T>>
extends ModelMetricsSupervised.MetricBuilderSupervised<T>

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
long	_bad
double	_caic
boolean	_converge
double	_convergence
double	_dfrefe
double[]	_fixef
double	_hlik
int	_iterations
long	_nobs
double	_pbvh
double	_pvh
int[]	_randc
double[]	_ranef
double[]	_sefe
double[]	_sere
double	_sumetadiffsquare
double[]	_summvc1
double[][]	_summvc2
double	_varfix
double[]	_varranef

Fields inherited from class hex.ModelMetricsSupervised.MetricBuilderSupervised

_domain, _nclasses

Fields inherited from class hex.ModelMetrics.MetricBuilder

_count, _customMetric, _sumsqe, _wcount, _work, _wY, _wYY

Constructor Summary

Constructors

Constructor and Description
MetricBuilderHGLM(java.lang.String[] domain)

Method Summary

Modifier and Type	Method and Description
ModelMetrics	makeModelMetrics(Model m, Frame f, Frame adaptedFrame, Frame preds) Having computed a MetricBuilder, this method fills in a ModelMetrics
double[]	perRow(double[] ds, float[] yact, Model m)
void	updateCoeffs(double[] fixedCoeffs, double[] randCoeffs)
void	updateSummVC(double[] VC1, double[][] VC2, int[] randc)

Methods inherited from class hex.ModelMetrics.MetricBuilder

cachePrediction, makePredictionCache, perRow, postGlobal, postGlobal, reduce, reduce, reduceForCV, setCustomMetric, weightedSigma

Methods inherited from class water.Iced

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

Methods inherited from class java.lang.Object

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

Field Detail

_sefe

public double[] _sefe

_sere

public double[] _sere

_varfix

public double _varfix

_varranef

public double[] _varranef

_converge

public boolean _converge

_dfrefe

public double _dfrefe

_summvc1

public double[] _summvc1

_summvc2

public double[][] _summvc2

_hlik

public double _hlik

_pvh

public double _pvh

_pbvh

public double _pbvh

_caic

public double _caic

_bad

public long _bad

_sumetadiffsquare

public double _sumetadiffsquare

_convergence

public double _convergence

_fixef

public double[] _fixef

_ranef

public double[] _ranef

_randc

public int[] _randc

_iterations

public int _iterations

_nobs

public long _nobs

Constructor Detail

MetricBuilderHGLM

public MetricBuilderHGLM(java.lang.String[] domain)

Method Detail

updateCoeffs

public void updateCoeffs(double[] fixedCoeffs,
                         double[] randCoeffs)

updateSummVC

public void updateSummVC(double[] VC1,
                         double[][] VC2,
                         int[] randc)

perRow

public double[] perRow(double[] ds,
                       float[] yact,
                       Model m)

Specified by:

perRow in class ModelMetrics.MetricBuilder<T extends ModelMetricsHGLM.MetricBuilderHGLM<T>>

makeModelMetrics

public ModelMetrics makeModelMetrics(Model m,
                                     Frame f,
                                     Frame adaptedFrame,
                                     Frame preds)

Description copied from class: ModelMetrics.MetricBuilder

Having computed a MetricBuilder, this method fills in a ModelMetrics

Specified by:

makeModelMetrics in class ModelMetrics.MetricBuilder<T extends ModelMetricsHGLM.MetricBuilderHGLM<T>>

Parameters:

m - Model

f - Scored Frame

adaptedFrame - Adapted Frame

preds - Predictions of m on f (optional) @return Filled Model Metrics object