object MultipleModelMethod extends Enumeration
Specifying how all the models applicable to a record should be combined.
- Alphabetic
- By Inheritance
- MultipleModelMethod
- Enumeration
- Serializable
- AnyRef
- Any
- Hide All
- Show All
- Public
- Protected
Type Members
- type MultipleModelMethod = Value
- class Val extends Value with Serializable
- Attributes
- protected
- Definition Classes
- Enumeration
- Annotations
- @SerialVersionUID()
- abstract class Value extends Ordered[Value] with Serializable
- Definition Classes
- Enumeration
- Annotations
- @SerialVersionUID()
- class ValueSet extends AbstractSet[Value] with SortedSet[Value] with SortedSetOps[Value, SortedSet, ValueSet] with StrictOptimizedIterableOps[Value, Set, ValueSet] with Serializable
- Definition Classes
- Enumeration
- Annotations
- @SerialVersionUID()
Value Members
- final def !=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
- final def ##: Int
- Definition Classes
- AnyRef → Any
- final def ==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
- final def Value(i: Int, name: String): Value
- Attributes
- protected
- Definition Classes
- Enumeration
- final def Value(name: String): Value
- Attributes
- protected
- Definition Classes
- Enumeration
- final def Value(i: Int): Value
- Attributes
- protected
- Definition Classes
- Enumeration
- final def Value: Value
- Attributes
- protected
- Definition Classes
- Enumeration
- final def apply(x: Int): Value
- Definition Classes
- Enumeration
- final def asInstanceOf[T0]: T0
- Definition Classes
- Any
- val average: Value
selectFirst is applicable to any model type.
selectFirst is applicable to any model type. Simply use the first model for which the predicate in the Segment evaluates to true. selectAll is applicable to any model type. All models for which the predicate in the Segment evaluates to true are evaluated. modelChain is applicable to any model type. During scoring, Segments whose Predicates evaluate to TRUE are executed in the order they appear in the PMML.
For clustering models only majorityVote, weightedMajorityVote, modelChain, selectFirst, or selectAll can be used. In case of majorityVote the cluster ID that was selected by the largest number of models wins. For weightedMajorityVote the weights specified in Segment elements are used, and the cluster ID with highest total weight wins. Cluster affinity for the resulting model combined by majorityVote or weightedMajorityVote is not defined. Note that combining clustering model predictions can produce not very meaningful results because there is no target variable, and the same cluster IDs on different segments can be assigned to very different clusters.
For regression models only average, weightedAverage, median, weightedMedian, sum, weightedSum, modelChain, selectFirst, or selectAll are applicable. The first four methods are applied to the predicted values of all models for which the predicate evaluates to true.
For classification models all the combination methods, except for sum and weightedSum, can be used. For the first six combination methods the models in all segments must have the same target variable. Note that average, weightedAverage, median, weightedMedian, and max are applied to the predicted probabilities of target categories in each of the models used for the case, then the winning category is selected based on the highest combined probability, while majorityVote and weightedMajorityVote use the predicted categories from all applicable models and select the one based on the models' "votes". Predicted probabilities for the final prediction of a classification MiningModel are defined as follows, depending on the combination method:
- majorityVote and weightedMajorityVote: the probabilities are computed as the proportions of the votes or weighted votes for each target category; - average, weightedAverage: the probabilities are computed as the average or weighted average of probabilities of the models used in the prediction; - max: consider the model(s) that have contributed the chosen probability for the winning category. Return their average probabilities; - median, weightedMedian: if the number of models with predicates that resolve to true is odd consider the model(s) that have the chose
- def clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.CloneNotSupportedException]) @IntrinsicCandidate() @native()
- final def eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- def equals(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef → Any
- final def getClass(): Class[_ <: AnyRef]
- Definition Classes
- AnyRef → Any
- Annotations
- @IntrinsicCandidate() @native()
- def hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @IntrinsicCandidate() @native()
- final def isInstanceOf[T0]: Boolean
- Definition Classes
- Any
- val majorityVote: Value
selectFirst is applicable to any model type.
selectFirst is applicable to any model type. Simply use the first model for which the predicate in the Segment evaluates to true. selectAll is applicable to any model type. All models for which the predicate in the Segment evaluates to true are evaluated. modelChain is applicable to any model type. During scoring, Segments whose Predicates evaluate to TRUE are executed in the order they appear in the PMML.
For clustering models only majorityVote, weightedMajorityVote, modelChain, selectFirst, or selectAll can be used. In case of majorityVote the cluster ID that was selected by the largest number of models wins. For weightedMajorityVote the weights specified in Segment elements are used, and the cluster ID with highest total weight wins. Cluster affinity for the resulting model combined by majorityVote or weightedMajorityVote is not defined. Note that combining clustering model predictions can produce not very meaningful results because there is no target variable, and the same cluster IDs on different segments can be assigned to very different clusters.
For regression models only average, weightedAverage, median, weightedMedian, sum, weightedSum, modelChain, selectFirst, or selectAll are applicable. The first four methods are applied to the predicted values of all models for which the predicate evaluates to true.
For classification models all the combination methods, except for sum and weightedSum, can be used. For the first six combination methods the models in all segments must have the same target variable. Note that average, weightedAverage, median, weightedMedian, and max are applied to the predicted probabilities of target categories in each of the models used for the case, then the winning category is selected based on the highest combined probability, while majorityVote and weightedMajorityVote use the predicted categories from all applicable models and select the one based on the models' "votes". Predicted probabilities for the final prediction of a classification MiningModel are defined as follows, depending on the combination method:
- majorityVote and weightedMajorityVote: the probabilities are computed as the proportions of the votes or weighted votes for each target category; - average, weightedAverage: the probabilities are computed as the average or weighted average of probabilities of the models used in the prediction; - max: consider the model(s) that have contributed the chosen probability for the winning category. Return their average probabilities; - median, weightedMedian: if the number of models with predicates that resolve to true is odd consider the model(s) that have the chose
- val max: Value
selectFirst is applicable to any model type.
selectFirst is applicable to any model type. Simply use the first model for which the predicate in the Segment evaluates to true. selectAll is applicable to any model type. All models for which the predicate in the Segment evaluates to true are evaluated. modelChain is applicable to any model type. During scoring, Segments whose Predicates evaluate to TRUE are executed in the order they appear in the PMML.
For clustering models only majorityVote, weightedMajorityVote, modelChain, selectFirst, or selectAll can be used. In case of majorityVote the cluster ID that was selected by the largest number of models wins. For weightedMajorityVote the weights specified in Segment elements are used, and the cluster ID with highest total weight wins. Cluster affinity for the resulting model combined by majorityVote or weightedMajorityVote is not defined. Note that combining clustering model predictions can produce not very meaningful results because there is no target variable, and the same cluster IDs on different segments can be assigned to very different clusters.
For regression models only average, weightedAverage, median, weightedMedian, sum, weightedSum, modelChain, selectFirst, or selectAll are applicable. The first four methods are applied to the predicted values of all models for which the predicate evaluates to true.
For classification models all the combination methods, except for sum and weightedSum, can be used. For the first six combination methods the models in all segments must have the same target variable. Note that average, weightedAverage, median, weightedMedian, and max are applied to the predicted probabilities of target categories in each of the models used for the case, then the winning category is selected based on the highest combined probability, while majorityVote and weightedMajorityVote use the predicted categories from all applicable models and select the one based on the models' "votes". Predicted probabilities for the final prediction of a classification MiningModel are defined as follows, depending on the combination method:
- majorityVote and weightedMajorityVote: the probabilities are computed as the proportions of the votes or weighted votes for each target category; - average, weightedAverage: the probabilities are computed as the average or weighted average of probabilities of the models used in the prediction; - max: consider the model(s) that have contributed the chosen probability for the winning category. Return their average probabilities; - median, weightedMedian: if the number of models with predicates that resolve to true is odd consider the model(s) that have the chose
- final def maxId: Int
- Definition Classes
- Enumeration
- val median: Value
selectFirst is applicable to any model type.
selectFirst is applicable to any model type. Simply use the first model for which the predicate in the Segment evaluates to true. selectAll is applicable to any model type. All models for which the predicate in the Segment evaluates to true are evaluated. modelChain is applicable to any model type. During scoring, Segments whose Predicates evaluate to TRUE are executed in the order they appear in the PMML.
For clustering models only majorityVote, weightedMajorityVote, modelChain, selectFirst, or selectAll can be used. In case of majorityVote the cluster ID that was selected by the largest number of models wins. For weightedMajorityVote the weights specified in Segment elements are used, and the cluster ID with highest total weight wins. Cluster affinity for the resulting model combined by majorityVote or weightedMajorityVote is not defined. Note that combining clustering model predictions can produce not very meaningful results because there is no target variable, and the same cluster IDs on different segments can be assigned to very different clusters.
For regression models only average, weightedAverage, median, weightedMedian, sum, weightedSum, modelChain, selectFirst, or selectAll are applicable. The first four methods are applied to the predicted values of all models for which the predicate evaluates to true.
For classification models all the combination methods, except for sum and weightedSum, can be used. For the first six combination methods the models in all segments must have the same target variable. Note that average, weightedAverage, median, weightedMedian, and max are applied to the predicted probabilities of target categories in each of the models used for the case, then the winning category is selected based on the highest combined probability, while majorityVote and weightedMajorityVote use the predicted categories from all applicable models and select the one based on the models' "votes". Predicted probabilities for the final prediction of a classification MiningModel are defined as follows, depending on the combination method:
- majorityVote and weightedMajorityVote: the probabilities are computed as the proportions of the votes or weighted votes for each target category; - average, weightedAverage: the probabilities are computed as the average or weighted average of probabilities of the models used in the prediction; - max: consider the model(s) that have contributed the chosen probability for the winning category. Return their average probabilities; - median, weightedMedian: if the number of models with predicates that resolve to true is odd consider the model(s) that have the chose
- val modelChain: Value
selectFirst is applicable to any model type.
selectFirst is applicable to any model type. Simply use the first model for which the predicate in the Segment evaluates to true. selectAll is applicable to any model type. All models for which the predicate in the Segment evaluates to true are evaluated. modelChain is applicable to any model type. During scoring, Segments whose Predicates evaluate to TRUE are executed in the order they appear in the PMML.
For clustering models only majorityVote, weightedMajorityVote, modelChain, selectFirst, or selectAll can be used. In case of majorityVote the cluster ID that was selected by the largest number of models wins. For weightedMajorityVote the weights specified in Segment elements are used, and the cluster ID with highest total weight wins. Cluster affinity for the resulting model combined by majorityVote or weightedMajorityVote is not defined. Note that combining clustering model predictions can produce not very meaningful results because there is no target variable, and the same cluster IDs on different segments can be assigned to very different clusters.
For regression models only average, weightedAverage, median, weightedMedian, sum, weightedSum, modelChain, selectFirst, or selectAll are applicable. The first four methods are applied to the predicted values of all models for which the predicate evaluates to true.
For classification models all the combination methods, except for sum and weightedSum, can be used. For the first six combination methods the models in all segments must have the same target variable. Note that average, weightedAverage, median, weightedMedian, and max are applied to the predicted probabilities of target categories in each of the models used for the case, then the winning category is selected based on the highest combined probability, while majorityVote and weightedMajorityVote use the predicted categories from all applicable models and select the one based on the models' "votes". Predicted probabilities for the final prediction of a classification MiningModel are defined as follows, depending on the combination method:
- majorityVote and weightedMajorityVote: the probabilities are computed as the proportions of the votes or weighted votes for each target category; - average, weightedAverage: the probabilities are computed as the average or weighted average of probabilities of the models used in the prediction; - max: consider the model(s) that have contributed the chosen probability for the winning category. Return their average probabilities; - median, weightedMedian: if the number of models with predicates that resolve to true is odd consider the model(s) that have the chose
- final def ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- var nextId: Int
- Attributes
- protected
- Definition Classes
- Enumeration
- var nextName: Iterator[String]
- Attributes
- protected
- Definition Classes
- Enumeration
- final def notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @IntrinsicCandidate() @native()
- final def notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @IntrinsicCandidate() @native()
- def readResolve(): AnyRef
- Attributes
- protected
- Definition Classes
- Enumeration
- val selectAll: Value
selectFirst is applicable to any model type.
selectFirst is applicable to any model type. Simply use the first model for which the predicate in the Segment evaluates to true. selectAll is applicable to any model type. All models for which the predicate in the Segment evaluates to true are evaluated. modelChain is applicable to any model type. During scoring, Segments whose Predicates evaluate to TRUE are executed in the order they appear in the PMML.
For clustering models only majorityVote, weightedMajorityVote, modelChain, selectFirst, or selectAll can be used. In case of majorityVote the cluster ID that was selected by the largest number of models wins. For weightedMajorityVote the weights specified in Segment elements are used, and the cluster ID with highest total weight wins. Cluster affinity for the resulting model combined by majorityVote or weightedMajorityVote is not defined. Note that combining clustering model predictions can produce not very meaningful results because there is no target variable, and the same cluster IDs on different segments can be assigned to very different clusters.
For regression models only average, weightedAverage, median, weightedMedian, sum, weightedSum, modelChain, selectFirst, or selectAll are applicable. The first four methods are applied to the predicted values of all models for which the predicate evaluates to true.
For classification models all the combination methods, except for sum and weightedSum, can be used. For the first six combination methods the models in all segments must have the same target variable. Note that average, weightedAverage, median, weightedMedian, and max are applied to the predicted probabilities of target categories in each of the models used for the case, then the winning category is selected based on the highest combined probability, while majorityVote and weightedMajorityVote use the predicted categories from all applicable models and select the one based on the models' "votes". Predicted probabilities for the final prediction of a classification MiningModel are defined as follows, depending on the combination method:
- majorityVote and weightedMajorityVote: the probabilities are computed as the proportions of the votes or weighted votes for each target category; - average, weightedAverage: the probabilities are computed as the average or weighted average of probabilities of the models used in the prediction; - max: consider the model(s) that have contributed the chosen probability for the winning category. Return their average probabilities; - median, weightedMedian: if the number of models with predicates that resolve to true is odd consider the model(s) that have the chose
- val selectFirst: Value
selectFirst is applicable to any model type.
selectFirst is applicable to any model type. Simply use the first model for which the predicate in the Segment evaluates to true. selectAll is applicable to any model type. All models for which the predicate in the Segment evaluates to true are evaluated. modelChain is applicable to any model type. During scoring, Segments whose Predicates evaluate to TRUE are executed in the order they appear in the PMML.
For clustering models only majorityVote, weightedMajorityVote, modelChain, selectFirst, or selectAll can be used. In case of majorityVote the cluster ID that was selected by the largest number of models wins. For weightedMajorityVote the weights specified in Segment elements are used, and the cluster ID with highest total weight wins. Cluster affinity for the resulting model combined by majorityVote or weightedMajorityVote is not defined. Note that combining clustering model predictions can produce not very meaningful results because there is no target variable, and the same cluster IDs on different segments can be assigned to very different clusters.
For regression models only average, weightedAverage, median, weightedMedian, sum, weightedSum, modelChain, selectFirst, or selectAll are applicable. The first four methods are applied to the predicted values of all models for which the predicate evaluates to true.
For classification models all the combination methods, except for sum and weightedSum, can be used. For the first six combination methods the models in all segments must have the same target variable. Note that average, weightedAverage, median, weightedMedian, and max are applied to the predicted probabilities of target categories in each of the models used for the case, then the winning category is selected based on the highest combined probability, while majorityVote and weightedMajorityVote use the predicted categories from all applicable models and select the one based on the models' "votes". Predicted probabilities for the final prediction of a classification MiningModel are defined as follows, depending on the combination method:
- majorityVote and weightedMajorityVote: the probabilities are computed as the proportions of the votes or weighted votes for each target category; - average, weightedAverage: the probabilities are computed as the average or weighted average of probabilities of the models used in the prediction; - max: consider the model(s) that have contributed the chosen probability for the winning category. Return their average probabilities; - median, weightedMedian: if the number of models with predicates that resolve to true is odd consider the model(s) that have the chose
- val sum: Value
selectFirst is applicable to any model type.
selectFirst is applicable to any model type. Simply use the first model for which the predicate in the Segment evaluates to true. selectAll is applicable to any model type. All models for which the predicate in the Segment evaluates to true are evaluated. modelChain is applicable to any model type. During scoring, Segments whose Predicates evaluate to TRUE are executed in the order they appear in the PMML.
For clustering models only majorityVote, weightedMajorityVote, modelChain, selectFirst, or selectAll can be used. In case of majorityVote the cluster ID that was selected by the largest number of models wins. For weightedMajorityVote the weights specified in Segment elements are used, and the cluster ID with highest total weight wins. Cluster affinity for the resulting model combined by majorityVote or weightedMajorityVote is not defined. Note that combining clustering model predictions can produce not very meaningful results because there is no target variable, and the same cluster IDs on different segments can be assigned to very different clusters.
For regression models only average, weightedAverage, median, weightedMedian, sum, weightedSum, modelChain, selectFirst, or selectAll are applicable. The first four methods are applied to the predicted values of all models for which the predicate evaluates to true.
For classification models all the combination methods, except for sum and weightedSum, can be used. For the first six combination methods the models in all segments must have the same target variable. Note that average, weightedAverage, median, weightedMedian, and max are applied to the predicted probabilities of target categories in each of the models used for the case, then the winning category is selected based on the highest combined probability, while majorityVote and weightedMajorityVote use the predicted categories from all applicable models and select the one based on the models' "votes". Predicted probabilities for the final prediction of a classification MiningModel are defined as follows, depending on the combination method:
- majorityVote and weightedMajorityVote: the probabilities are computed as the proportions of the votes or weighted votes for each target category; - average, weightedAverage: the probabilities are computed as the average or weighted average of probabilities of the models used in the prediction; - max: consider the model(s) that have contributed the chosen probability for the winning category. Return their average probabilities; - median, weightedMedian: if the number of models with predicates that resolve to true is odd consider the model(s) that have the chose
- def support(mmm: MultipleModelMethod, mf: MiningFunction): Boolean
- final def synchronized[T0](arg0: => T0): T0
- Definition Classes
- AnyRef
- def toString(): String
- Definition Classes
- Enumeration → AnyRef → Any
- def values: ValueSet
- Definition Classes
- Enumeration
- final def wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
- final def wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException]) @native()
- final def wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
- val weightedAverage: Value
selectFirst is applicable to any model type.
selectFirst is applicable to any model type. Simply use the first model for which the predicate in the Segment evaluates to true. selectAll is applicable to any model type. All models for which the predicate in the Segment evaluates to true are evaluated. modelChain is applicable to any model type. During scoring, Segments whose Predicates evaluate to TRUE are executed in the order they appear in the PMML.
For clustering models only majorityVote, weightedMajorityVote, modelChain, selectFirst, or selectAll can be used. In case of majorityVote the cluster ID that was selected by the largest number of models wins. For weightedMajorityVote the weights specified in Segment elements are used, and the cluster ID with highest total weight wins. Cluster affinity for the resulting model combined by majorityVote or weightedMajorityVote is not defined. Note that combining clustering model predictions can produce not very meaningful results because there is no target variable, and the same cluster IDs on different segments can be assigned to very different clusters.
For regression models only average, weightedAverage, median, weightedMedian, sum, weightedSum, modelChain, selectFirst, or selectAll are applicable. The first four methods are applied to the predicted values of all models for which the predicate evaluates to true.
For classification models all the combination methods, except for sum and weightedSum, can be used. For the first six combination methods the models in all segments must have the same target variable. Note that average, weightedAverage, median, weightedMedian, and max are applied to the predicted probabilities of target categories in each of the models used for the case, then the winning category is selected based on the highest combined probability, while majorityVote and weightedMajorityVote use the predicted categories from all applicable models and select the one based on the models' "votes". Predicted probabilities for the final prediction of a classification MiningModel are defined as follows, depending on the combination method:
- majorityVote and weightedMajorityVote: the probabilities are computed as the proportions of the votes or weighted votes for each target category; - average, weightedAverage: the probabilities are computed as the average or weighted average of probabilities of the models used in the prediction; - max: consider the model(s) that have contributed the chosen probability for the winning category. Return their average probabilities; - median, weightedMedian: if the number of models with predicates that resolve to true is odd consider the model(s) that have the chose
- val weightedMajorityVote: Value
selectFirst is applicable to any model type.
selectFirst is applicable to any model type. Simply use the first model for which the predicate in the Segment evaluates to true. selectAll is applicable to any model type. All models for which the predicate in the Segment evaluates to true are evaluated. modelChain is applicable to any model type. During scoring, Segments whose Predicates evaluate to TRUE are executed in the order they appear in the PMML.
For clustering models only majorityVote, weightedMajorityVote, modelChain, selectFirst, or selectAll can be used. In case of majorityVote the cluster ID that was selected by the largest number of models wins. For weightedMajorityVote the weights specified in Segment elements are used, and the cluster ID with highest total weight wins. Cluster affinity for the resulting model combined by majorityVote or weightedMajorityVote is not defined. Note that combining clustering model predictions can produce not very meaningful results because there is no target variable, and the same cluster IDs on different segments can be assigned to very different clusters.
For regression models only average, weightedAverage, median, weightedMedian, sum, weightedSum, modelChain, selectFirst, or selectAll are applicable. The first four methods are applied to the predicted values of all models for which the predicate evaluates to true.
For classification models all the combination methods, except for sum and weightedSum, can be used. For the first six combination methods the models in all segments must have the same target variable. Note that average, weightedAverage, median, weightedMedian, and max are applied to the predicted probabilities of target categories in each of the models used for the case, then the winning category is selected based on the highest combined probability, while majorityVote and weightedMajorityVote use the predicted categories from all applicable models and select the one based on the models' "votes". Predicted probabilities for the final prediction of a classification MiningModel are defined as follows, depending on the combination method:
- majorityVote and weightedMajorityVote: the probabilities are computed as the proportions of the votes or weighted votes for each target category; - average, weightedAverage: the probabilities are computed as the average or weighted average of probabilities of the models used in the prediction; - max: consider the model(s) that have contributed the chosen probability for the winning category. Return their average probabilities; - median, weightedMedian: if the number of models with predicates that resolve to true is odd consider the model(s) that have the chose
- val weightedMedian: Value
selectFirst is applicable to any model type.
selectFirst is applicable to any model type. Simply use the first model for which the predicate in the Segment evaluates to true. selectAll is applicable to any model type. All models for which the predicate in the Segment evaluates to true are evaluated. modelChain is applicable to any model type. During scoring, Segments whose Predicates evaluate to TRUE are executed in the order they appear in the PMML.
For clustering models only majorityVote, weightedMajorityVote, modelChain, selectFirst, or selectAll can be used. In case of majorityVote the cluster ID that was selected by the largest number of models wins. For weightedMajorityVote the weights specified in Segment elements are used, and the cluster ID with highest total weight wins. Cluster affinity for the resulting model combined by majorityVote or weightedMajorityVote is not defined. Note that combining clustering model predictions can produce not very meaningful results because there is no target variable, and the same cluster IDs on different segments can be assigned to very different clusters.
For regression models only average, weightedAverage, median, weightedMedian, sum, weightedSum, modelChain, selectFirst, or selectAll are applicable. The first four methods are applied to the predicted values of all models for which the predicate evaluates to true.
For classification models all the combination methods, except for sum and weightedSum, can be used. For the first six combination methods the models in all segments must have the same target variable. Note that average, weightedAverage, median, weightedMedian, and max are applied to the predicted probabilities of target categories in each of the models used for the case, then the winning category is selected based on the highest combined probability, while majorityVote and weightedMajorityVote use the predicted categories from all applicable models and select the one based on the models' "votes". Predicted probabilities for the final prediction of a classification MiningModel are defined as follows, depending on the combination method:
- majorityVote and weightedMajorityVote: the probabilities are computed as the proportions of the votes or weighted votes for each target category; - average, weightedAverage: the probabilities are computed as the average or weighted average of probabilities of the models used in the prediction; - max: consider the model(s) that have contributed the chosen probability for the winning category. Return their average probabilities; - median, weightedMedian: if the number of models with predicates that resolve to true is odd consider the model(s) that have the chose
- val weightedSum: Value
selectFirst is applicable to any model type.
selectFirst is applicable to any model type. Simply use the first model for which the predicate in the Segment evaluates to true. selectAll is applicable to any model type. All models for which the predicate in the Segment evaluates to true are evaluated. modelChain is applicable to any model type. During scoring, Segments whose Predicates evaluate to TRUE are executed in the order they appear in the PMML.
For clustering models only majorityVote, weightedMajorityVote, modelChain, selectFirst, or selectAll can be used. In case of majorityVote the cluster ID that was selected by the largest number of models wins. For weightedMajorityVote the weights specified in Segment elements are used, and the cluster ID with highest total weight wins. Cluster affinity for the resulting model combined by majorityVote or weightedMajorityVote is not defined. Note that combining clustering model predictions can produce not very meaningful results because there is no target variable, and the same cluster IDs on different segments can be assigned to very different clusters.
For regression models only average, weightedAverage, median, weightedMedian, sum, weightedSum, modelChain, selectFirst, or selectAll are applicable. The first four methods are applied to the predicted values of all models for which the predicate evaluates to true.
For classification models all the combination methods, except for sum and weightedSum, can be used. For the first six combination methods the models in all segments must have the same target variable. Note that average, weightedAverage, median, weightedMedian, and max are applied to the predicted probabilities of target categories in each of the models used for the case, then the winning category is selected based on the highest combined probability, while majorityVote and weightedMajorityVote use the predicted categories from all applicable models and select the one based on the models' "votes". Predicted probabilities for the final prediction of a classification MiningModel are defined as follows, depending on the combination method:
- majorityVote and weightedMajorityVote: the probabilities are computed as the proportions of the votes or weighted votes for each target category; - average, weightedAverage: the probabilities are computed as the average or weighted average of probabilities of the models used in the prediction; - max: consider the model(s) that have contributed the chosen probability for the winning category. Return their average probabilities; - median, weightedMedian: if the number of models with predicates that resolve to true is odd consider the model(s) that have the chose
- final def withName(s: String): Value
- Definition Classes
- Enumeration
- val x-weightedMedian: Value
- val x-weightedSum: Value
- implicit object ValueOrdering extends Ordering[Value]
- Definition Classes
- Enumeration
Deprecated Value Members
- def finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.Throwable]) @Deprecated
- Deprecated
(Since version 9)