ModelMetricsListSchemaV3 (h2o-bindings 3.46.0 API)

java.lang.Object
- water.bindings.pojos.SchemaV3
- - water.bindings.pojos.RequestSchemaV3
  - - water.bindings.pojos.ModelMetricsListSchemaV3

public class ModelMetricsListSchemaV3
extends RequestSchemaV3

Field Summary

Fields
Modifier and Type	Field and Description
`java.lang.String`	`aucType` Set default multinomial AUC type.
`int`	`auucNbins` Set number of bins to calculate AUUC.
`java.lang.String`	`auucType` Set default AUUC type for uplift binomial classification.
`FrameKeyV3`	`backgroundFrame` Specify background frame used as a reference for calculating SHAP.
`int`	`bottomN` Only for predict_contributions function - sort Shapley values and return bottom_n lowest (optional)
`boolean`	`compareAbs` Only for predict_contributions function - sort absolute Shapley values (optional)
`double[]`	`customAuucThresholds` Custom AUUC thresholds (for uplift binomial classification).
`java.lang.String`	`customMetricFunc` Reference to custom evaluation function, format: `language:keyName=funcName`
`int`	`deepFeaturesHiddenLayer` Extract Deep Features for given hidden layer (optional, only for Deep Learning models)
`java.lang.String`	`deepFeaturesHiddenLayerName` Extract Deep Features for given hidden layer by name (optional, only for Deep Water models)
`boolean`	`deviances` Compute the deviances per row (optional, only for classification or regression models)
`FrameKeyV3`	`deviancesFrame` Key for the frame containing per-observation deviances (optional)
`int`	`exemplarIndex` Retrieve all members for a given exemplar (optional, only for Aggregator models)
`boolean`	`featureFrequencies` Retrieve the feature frequencies on paths in trees in tree-based models (optional, only for GBM, DRF and Isolation Forest)
`FrameKeyV3`	`frame` Key of Frame of interest (optional)
`boolean`	`leafNodeAssignment` Return the leaf node assignment (optional, only for DRF/GBM models)
`ModelLeafNodeAssignmentLeafNodeAssignmentType`	`leafNodeAssignmentType` Type of the leaf node assignment (optional, only for DRF/GBM models)
`ModelKeyV3`	`model` Key of Model of interest (optional)
`ModelMetricsBaseV3[]`	`modelMetrics` ModelMetrics
`boolean`	`outputPerReference` If true, return contributions against each background sample (aka reference), i.e.
`boolean`	`outputSpace` If true, transform contributions so that they sum up to the difference in the output space (applicable iff contributions are in link space).
`boolean`	`predictContributions` Predict the feature contributions - Shapley values (optional, only for DRF, GBM and XGBoost models)
`ModelContributionsContributionsOutputFormat`	`predictContributionsOutputFormat` Specify how to output feature contributions in XGBoost - XGBoost by default outputs contributions for 1-hot encoded features, specifying a Compact output format will produce a per-feature contribution
`FrameKeyV3`	`predictionsFrame` Key of predictions frame, if predictions are requested (optional)
`boolean`	`predictStagedProba` Predict the class probabilities at each stage (optional, only for GBM models)
`boolean`	`projectArchetypes` Project GLRM archetypes back into original feature space (optional, only for GLRM models)
`boolean`	`reconstructionError` Compute reconstruction error (optional, only for Deep Learning AutoEncoder models)
`boolean`	`reconstructionErrorPerFeature` Compute reconstruction error per feature (optional, only for Deep Learning AutoEncoder models)
`boolean`	`reconstructTrain` Reconstruct original training frame (optional, only for GLRM models)
`boolean`	`reverseTransform` Reverse transformation applied during training to model output (optional, only for GLRM models)
`boolean`	`rowToTreeAssignment` Return which row is used in which tree (optional, only for GBM models)
`int`	`topN` Only for predict_contributions function - sort Shapley values and return top_n highest (optional)

Fields inherited from class water.bindings.pojos.RequestSchemaV3
_excludeFields

Constructor Summary

Constructors
Constructor and Description

ModelMetricsListSchemaV3()
Public constructor

Constructors
Constructor and Description
`ModelMetricsListSchemaV3()` Public constructor

Method Summary

All Methods Instance Methods Concrete Methods
Modifier and Type Method and Description

java.lang.String toString()
Return the contents of this object as a JSON String.
- Methods inherited from class java.lang.Object
  clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

All Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`java.lang.String`	`toString()` Return the contents of this object as a JSON String.

- Field Detail
  - model
```
public ModelKeyV3 model
```
    Key of Model of interest (optional)
  - frame
```
public FrameKeyV3 frame
```
    Key of Frame of interest (optional)
  - predictionsFrame
```
@SerializedName(value="predictions_frame")
public FrameKeyV3 predictionsFrame
```
    Key of predictions frame, if predictions are requested (optional)
  - deviancesFrame
```
@SerializedName(value="deviances_frame")
public FrameKeyV3 deviancesFrame
```
    Key for the frame containing per-observation deviances (optional)
  - reconstructionError
```
@SerializedName(value="reconstruction_error")
public boolean reconstructionError
```
    Compute reconstruction error (optional, only for Deep Learning AutoEncoder models)
  - reconstructionErrorPerFeature
```
@SerializedName(value="reconstruction_error_per_feature")
public boolean reconstructionErrorPerFeature
```
    Compute reconstruction error per feature (optional, only for Deep Learning AutoEncoder models)
  - deepFeaturesHiddenLayer
```
@SerializedName(value="deep_features_hidden_layer")
public int deepFeaturesHiddenLayer
```
    Extract Deep Features for given hidden layer (optional, only for Deep Learning models)
  - deepFeaturesHiddenLayerName
```
@SerializedName(value="deep_features_hidden_layer_name")
public java.lang.String deepFeaturesHiddenLayerName
```
    Extract Deep Features for given hidden layer by name (optional, only for Deep Water models)
  - reconstructTrain
```
@SerializedName(value="reconstruct_train")
public boolean reconstructTrain
```
    Reconstruct original training frame (optional, only for GLRM models)
  - projectArchetypes
```
@SerializedName(value="project_archetypes")
public boolean projectArchetypes
```
    Project GLRM archetypes back into original feature space (optional, only for GLRM models)
  - reverseTransform
```
@SerializedName(value="reverse_transform")
public boolean reverseTransform
```
    Reverse transformation applied during training to model output (optional, only for GLRM models)
  - leafNodeAssignment
```
@SerializedName(value="leaf_node_assignment")
public boolean leafNodeAssignment
```
    Return the leaf node assignment (optional, only for DRF/GBM models)
  - leafNodeAssignmentType
```
@SerializedName(value="leaf_node_assignment_type")
public ModelLeafNodeAssignmentLeafNodeAssignmentType leafNodeAssignmentType
```
    Type of the leaf node assignment (optional, only for DRF/GBM models)
  - predictStagedProba
```
@SerializedName(value="predict_staged_proba")
public boolean predictStagedProba
```
    Predict the class probabilities at each stage (optional, only for GBM models)
  - predictContributions
```
@SerializedName(value="predict_contributions")
public boolean predictContributions
```
    Predict the feature contributions - Shapley values (optional, only for DRF, GBM and XGBoost models)
  - rowToTreeAssignment
```
@SerializedName(value="row_to_tree_assignment")
public boolean rowToTreeAssignment
```
    Return which row is used in which tree (optional, only for GBM models)
  - predictContributionsOutputFormat
```
@SerializedName(value="predict_contributions_output_format")
public ModelContributionsContributionsOutputFormat predictContributionsOutputFormat
```
    Specify how to output feature contributions in XGBoost - XGBoost by default outputs contributions for 1-hot encoded features, specifying a Compact output format will produce a per-feature contribution
  - topN
```
@SerializedName(value="top_n")
public int topN
```
    Only for predict_contributions function - sort Shapley values and return top_n highest (optional)
  - bottomN
```
@SerializedName(value="bottom_n")
public int bottomN
```
    Only for predict_contributions function - sort Shapley values and return bottom_n lowest (optional)
  - compareAbs
```
@SerializedName(value="compare_abs")
public boolean compareAbs
```
    Only for predict_contributions function - sort absolute Shapley values (optional)
  - featureFrequencies
```
@SerializedName(value="feature_frequencies")
public boolean featureFrequencies
```
    Retrieve the feature frequencies on paths in trees in tree-based models (optional, only for GBM, DRF and Isolation Forest)
  - exemplarIndex
```
@SerializedName(value="exemplar_index")
public int exemplarIndex
```
    Retrieve all members for a given exemplar (optional, only for Aggregator models)
  - deviances
```
public boolean deviances
```
    Compute the deviances per row (optional, only for classification or regression models)
  - customMetricFunc
```
@SerializedName(value="custom_metric_func")
public java.lang.String customMetricFunc
```
    Reference to custom evaluation function, format: `language:keyName=funcName`
  - aucType
```
@SerializedName(value="auc_type")
public java.lang.String aucType
```
    Set default multinomial AUC type. Must be one of: "AUTO", "NONE", "MACRO_OVR", "WEIGHTED_OVR", "MACRO_OVO", "WEIGHTED_OVO". Default is "NONE" (optional, only for multinomial classification).
  - auucType
```
@SerializedName(value="auuc_type")
public java.lang.String auucType
```
    Set default AUUC type for uplift binomial classification. Must be one of: "AUTO", "qini", "lift", "gain". Default is "AUTO" (optional, only for uplift binomial classification).
  - customAuucThresholds
```
@SerializedName(value="custom_auuc_thresholds")
public double[] customAuucThresholds
```
    Custom AUUC thresholds (for uplift binomial classification).
  - auucNbins
```
@SerializedName(value="auuc_nbins")
public int auucNbins
```
    Set number of bins to calculate AUUC. Must be -1 or higher than 0. Default is -1 which means 1000 (optional, only for uplift binomial classification).
  - backgroundFrame
```
@SerializedName(value="background_frame")
public FrameKeyV3 backgroundFrame
```
    Specify background frame used as a reference for calculating SHAP.
  - outputSpace
```
@SerializedName(value="output_space")
public boolean outputSpace
```
    If true, transform contributions so that they sum up to the difference in the output space (applicable iff contributions are in link space). Note that this transformation is an approximation and the contributions won't be exact SHAP values.
  - outputPerReference
```
@SerializedName(value="output_per_reference")
public boolean outputPerReference
```
    If true, return contributions against each background sample (aka reference), i.e. phi(feature, x, bg), otherwise return contributions averaged over the background sample (phi(feature, x) = E_{bg} phi(feature, x, bg))
  - modelMetrics
```
@SerializedName(value="model_metrics")
public ModelMetricsBaseV3[] modelMetrics
```
    ModelMetrics
- Constructor Detail
  - ModelMetricsListSchemaV3
```
public ModelMetricsListSchemaV3()
```
    Public constructor
- Method Detail
  - toString
```
public java.lang.String toString()
```
    Return the contents of this object as a JSON String.
    
    Overrides:
    
    toString in class RequestSchemaV3

Class ModelMetricsListSchemaV3

Field Summary

Fields inherited from class water.bindings.pojos.RequestSchemaV3

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Field Detail

model

frame

predictionsFrame

deviancesFrame

reconstructionError

reconstructionErrorPerFeature

deepFeaturesHiddenLayer

deepFeaturesHiddenLayerName

reconstructTrain

projectArchetypes

reverseTransform

leafNodeAssignment

leafNodeAssignmentType

predictStagedProba

predictContributions

rowToTreeAssignment

predictContributionsOutputFormat

topN

bottomN

compareAbs

featureFrequencies

exemplarIndex

deviances

customMetricFunc

aucType

auucType

customAuucThresholds

auucNbins

backgroundFrame

outputSpace

outputPerReference

modelMetrics

Constructor Detail

ModelMetricsListSchemaV3

Method Detail

toString