hex

Class ModelMetricsBinomial

java.lang.Object

water.Iced<T>

water.Keyed<ModelMetrics>

hex.ModelMetrics

hex.ModelMetricsSupervised

hex.ModelMetricsBinomial

All Implemented Interfaces:

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

Direct Known Subclasses:

ModelMetricsBinomialGeneric, ModelMetricsBinomialGLM

public class ModelMetricsBinomial
extends ModelMetricsSupervised

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	ModelMetricsBinomial.MetricBuilderBinomial<T extends ModelMetricsBinomial.MetricBuilderBinomial<T>>

Nested classes/interfaces inherited from class hex.ModelMetricsSupervised

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

Nested classes/interfaces inherited from class hex.ModelMetrics

ModelMetrics.MetricBuilder<T extends ModelMetrics.MetricBuilder<T>>

Field Summary

Fields

Modifier and Type	Field and Description
AUC2	_auc
GainsLift	_gainsLift
double	_logloss
double	_mean_per_class_error

Fields inherited from class hex.ModelMetricsSupervised

_domain, _sigma

Fields inherited from class hex.ModelMetrics

_custom_metric, _description, _MSE, _nobs, _scoring_time

Fields inherited from class water.Keyed

_key

Constructor Summary

Constructors

Constructor and Description
ModelMetricsBinomial(Model model, Frame frame, long nobs, double mse, java.lang.String[] domain, double sigma, AUC2 auc, double logloss, GainsLift gainsLift, CustomMetric customMetric)

Method Summary

Modifier and Type	Method and Description
AUC2	auc_obj()
double	auc()
double	aucpr()
ConfusionMatrix	cm()
ConfusionMatrix	cm(AUC2.ThresholdCriterion criterion)
GainsLift	gainsLift()
static ModelMetricsBinomial	getFromDKV(Model model, Frame frame)
double	lift_top_group()
double	logloss()
static ModelMetricsBinomial	make(Vec targetClassProbs, Vec actualLabels) Build a Binomial ModelMetrics object from target-class probabilities, from actual labels, and a given domain for both labels (and domain[1] is the target class)
static ModelMetricsBinomial	make(Vec targetClassProbs, Vec actualLabels, java.lang.String[] domain)
static ModelMetricsBinomial	make(Vec targetClassProbs, Vec actualLabels, Vec weights, java.lang.String[] domain) Build a Binomial ModelMetrics object from target-class probabilities, from actual labels, and a given domain for both labels (and domain[1] is the target class)
double	mean_per_class_error()
double	pr_auc()
java.lang.String	toString()

Methods inherited from class hex.ModelMetricsSupervised

r2

Methods inherited from class hex.ModelMetrics

appendToStringMetrics, buildKey, buildKey, calcVarImp, calcVarImp, calcVarImp, calcVarImp, checksum_impl, deepCloneWithDifferentModelAndFrame, defaultModelMetrics, frame, getAllowedMetrics, getMetricFromModel, getMetricFromModelMetric, hr, isForFrame, isForModel, model, mse, residual_degrees_of_freedom, rmse, setModelKey, sortModelsByMetric, sortModelsByMetric, withDescription, withModelAndFrame

Methods inherited from class water.Keyed

checksum_impl, checksum, checksum, getKey, makeSchema, readAll_impl, readAll, remove_impl, remove_impl, remove_self_key_impl, remove, remove, remove, remove, remove, remove, removeQuietly, writeAll_impl, writeAll

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, wait, wait, wait

Field Detail

_auc

public final AUC2 _auc

_logloss

public final double _logloss

_mean_per_class_error

public double _mean_per_class_error

_gainsLift

public final GainsLift _gainsLift

Constructor Detail

ModelMetricsBinomial

public ModelMetricsBinomial(Model model,
                            Frame frame,
                            long nobs,
                            double mse,
                            java.lang.String[] domain,
                            double sigma,
                            AUC2 auc,
                            double logloss,
                            GainsLift gainsLift,
                            CustomMetric customMetric)

Method Detail

getFromDKV

public static ModelMetricsBinomial getFromDKV(Model model,
                                              Frame frame)

toString

public java.lang.String toString()

Overrides:

toString in class ModelMetricsSupervised

logloss

public double logloss()

mean_per_class_error

public double mean_per_class_error()

auc_obj

public AUC2 auc_obj()

Overrides:

auc_obj in class ModelMetrics

cm

public ConfusionMatrix cm()

Overrides:

cm in class ModelMetrics

cm

public ConfusionMatrix cm(AUC2.ThresholdCriterion criterion)

gainsLift

public GainsLift gainsLift()

auc

public double auc()

pr_auc

public double pr_auc()

aucpr

public double aucpr()

lift_top_group

public double lift_top_group()

make

public static ModelMetricsBinomial make(Vec targetClassProbs,
                                        Vec actualLabels)

Build a Binomial ModelMetrics object from target-class probabilities, from actual labels, and a given domain for both labels (and domain[1] is the target class)

Parameters:

targetClassProbs - A Vec containing target class probabilities

actualLabels - A Vec containing the actual labels (can be for fewer labels than what's in domain, since the predictions can be for a small subset of the data)

Returns:

ModelMetrics object

make

public static ModelMetricsBinomial make(Vec targetClassProbs,
                                        Vec actualLabels,
                                        java.lang.String[] domain)

make

public static ModelMetricsBinomial make(Vec targetClassProbs,
                                        Vec actualLabels,
                                        Vec weights,
                                        java.lang.String[] domain)

Build a Binomial ModelMetrics object from target-class probabilities, from actual labels, and a given domain for both labels (and domain[1] is the target class)

Parameters:

targetClassProbs - A Vec containing target class probabilities

actualLabels - A Vec containing the actual labels (can be for fewer labels than what's in domain, since the predictions can be for a small subset of the data)

weights - A Vec containing the observation weights.

domain - The two class labels (domain[0] is the non-target class, domain[1] is the target class, for which probabilities are given)

Returns:

ModelMetrics object