hex

Class ModelMetricsSupervised.MetricBuilderSupervised<T extends ModelMetricsSupervised.MetricBuilderSupervised<T>>

java.lang.Object

water.Iced

hex.ModelMetrics.MetricBuilder<T>

hex.ModelMetricsSupervised.MetricBuilderSupervised<T>

All Implemented Interfaces:

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

Direct Known Subclasses:

ModelMetricsBinomial.MetricBuilderBinomial, ModelMetricsMultinomial.MetricBuilderMultinomial, ModelMetricsRegression.MetricBuilderRegression

Enclosing class:

ModelMetricsSupervised

public static class ModelMetricsSupervised.MetricBuilderSupervised<T extends ModelMetricsSupervised.MetricBuilderSupervised<T>>
extends ModelMetrics.MetricBuilder<T>

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
protected java.lang.String[]	_domain
protected int	_nclasses

Fields inherited from class hex.ModelMetrics.MetricBuilder

_count, _sumsqe, _wcount, _work, _wY, _wYY

Constructor Summary

Constructors

Constructor and Description
ModelMetricsSupervised.MetricBuilderSupervised(int nclasses, java.lang.String[] domain)

Method Summary

Methods

Modifier and Type	Method and Description
ModelMetrics	makeModelMetrics(Model m, Frame f, Frame adaptedFrame, Frame preds) Create a model metrics object
double[]	perRow(double[] ds, float[] yact, Model m)

Methods inherited from class hex.ModelMetrics.MetricBuilder

perRow, postGlobal, reduce, weightedSigma

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

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

Field Detail

_domain

protected final java.lang.String[] _domain

_nclasses

protected final int _nclasses

Constructor Detail

ModelMetricsSupervised.MetricBuilderSupervised

public ModelMetricsSupervised.MetricBuilderSupervised(int nclasses,
                                              java.lang.String[] domain)

Method Detail

perRow

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

Specified by:

perRow in class ModelMetrics.MetricBuilder<T extends ModelMetricsSupervised.MetricBuilderSupervised<T>>

makeModelMetrics

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

Create a model metrics object

Specified by:

makeModelMetrics in class ModelMetrics.MetricBuilder<T extends ModelMetricsSupervised.MetricBuilderSupervised<T>>

Parameters:

m - Model

f - Frame

adaptedFrame -

preds - Optional predictions (can be null), only used to compute Gains/Lift table for binomial problems @return