public class ModelMetricsBinomial extends ModelMetricsSupervised
Modifier and Type | Class and Description |
---|---|
static class |
ModelMetricsBinomial.MetricBuilderBinomial<T extends ModelMetricsBinomial.MetricBuilderBinomial<T>> |
ModelMetricsSupervised.MetricBuilderSupervised<T extends ModelMetricsSupervised.MetricBuilderSupervised<T>>
ModelMetrics.MetricBuilder<T extends ModelMetrics.MetricBuilder<T>>
Modifier and Type | Field and Description |
---|---|
AUC2 |
_auc |
GainsLift |
_gainsLift |
double |
_logloss |
double |
_mean_per_class_error |
_domain, _sigma
_custom_metric, _description, _MSE, _nobs, _scoring_time
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) |
Modifier and Type | Method and Description |
---|---|
AUC2 |
auc_obj() |
double |
auc() |
ConfusionMatrix |
cm() |
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)
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() |
java.lang.String |
toString() |
r2
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, sortModelsByMetric, sortModelsByMetric, withDescription, withModelAndFrame
checksum, makeSchema, readAll_impl, readAll, remove_impl, remove, remove, remove, remove, writeAll_impl, writeAll
asBytes, clone, copyOver, frozenType, read, readExternal, readJSON, reloadFromBytes, toJsonString, write, writeExternal, writeJSON
public final AUC2 _auc
public final double _logloss
public final double _mean_per_class_error
public final GainsLift _gainsLift
public ModelMetricsBinomial(Model model, Frame frame, long nobs, double mse, java.lang.String[] domain, double sigma, AUC2 auc, double logloss, GainsLift gainsLift, CustomMetric customMetric)
public static ModelMetricsBinomial getFromDKV(Model model, Frame frame)
public java.lang.String toString()
toString
in class ModelMetricsSupervised
public double logloss()
public double mean_per_class_error()
public AUC2 auc_obj()
auc_obj
in class ModelMetrics
public ConfusionMatrix cm()
cm
in class ModelMetrics
public GainsLift gainsLift()
public double auc()
public double lift_top_group()
public static ModelMetricsBinomial make(Vec targetClassProbs, Vec actualLabels)
targetClassProbs
- A Vec containing target class probabilitiesactualLabels
- 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)public static ModelMetricsBinomial make(Vec targetClassProbs, Vec actualLabels, java.lang.String[] domain)
targetClassProbs
- A Vec containing target class probabilitiesactualLabels
- 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)domain
- The two class labels (domain[0] is the non-target class, domain[1] is the target class, for which probabilities are given)