SAS Namespace Types

Target

Overview

Represents a variable whose values are known in one or more data sets that are available (in training data, for example) but whose values are unknown in one or more future data sets (in a score data set, for example). Data mining models use data from known variables to predict the values of target variables. Used by SAS Enterprise Miner.

Security Inheritance and Enforcement Rules

The following list of associations is used to determine if this object should inherit access controls from another object (inheritance), or if the association is allowed for the object (enforcement). An association will not be created unless the calling user is authorized to update one or both objects involved in the association. For more information about inheritance and enforcement rules, see the SAS Intelligence Platform: Security Administration Guide.

OwningAnalyticColumn

Attributes

Name	Description	Type	Length
Event	The value of interest.	String	32

Inherited Attributes
Name, Id, Desc, MetadataCreated, MetadataUpdated, ChangeState, LockedBy, UsageVersion

Associations

= indicates the resident side of an association, or where the association is persisted for cross-repository associations. If no resident side is indicated, this association may not cross repository boundaries.

Name	Cardinality	Description	Associated Types
FitStatistics Partner: OwningTarget	0 to *	The fit statistics that are associated with this target.	FitStatistic
Models Partner: Targets	0 to *	The models that act upon this target.	MiningResult
OwningAnalyticColumn Partner: TargetInformation	1 to 1	The column that has a role of target.	AnalyticColumn
TextualInformationObjects Partner: Targets	0 to *	Textual information about this target. There would be multiple text objects associated with a target. The roles would be Importance, Interaction, and Profile.	Text ArchiveEntry ArchiveFile Document File SASCatalogEntry TextStore

Inherited Associations
AccessControls/Objects, Changes/Objects, CustomAssociations/OwningObject, Documents/Objects, Extensions/OwningObject, ExternalIdentities/OwningObject, Groups/Members, Implementors/ImplementedObjects, Keywords/Objects, LocalizedAttributes/AssociatedLocalizedObject, Notes/Objects, PrimaryPropertyGroup/AssociatedObject, Prompts/PromptEnabledObject, Properties/AssociatedObject, PropertySets/OwningObject, ReferencedObjects/AssociatedObjects, ResponsibleParties/Objects, SourceTransformations/TransformationSources, SpecSourceTransformations/SourceSpecifications, SpecTargetTransformations/TargetSpecifications, TargetTransformations/TransformationTargets, Timestamps/Objects, Trees/Members, TSObjectNamespace/TSObjects, UsedByPrototypes/UsingPrototype, UsingPrototype/UsedByPrototypes, Variables/AssociatedObject

Attribute Details

Event
Type: String 32
The value of interest. For example, if we want to use column PURCHASE as the binary target to create a predictive model and suppose that there are two values in the target: 0,1 which map to NO and YES using a format. One of the first questions that a min ing tool would ask during model training is what is, "What is the value that is to be modeled. i.e., Is it YES, or is it NO?" If YES is the event, then NO is the non-event, and vice versa.

Association Details

FitStatistics
     Cardinality: 0 to *
     Partner: OwningTarget

The fit statistics that are associated with this target.

Associated Types:
FitStatistic

Models
     Cardinality: 0 to *
     Partner: Targets

The models that act upon this target.

Associated Types:
MiningResult

OwningAnalyticColumn
     Cardinality: 1 to 1
     Partner: TargetInformation

The column that has a role of target.

Associated Types:
AnalyticColumn

TextualInformationObjects
     Cardinality: 0 to *
     Partner: Targets

Textual information about this target. There would be multiple text objects associated with a target. The roles would be Importance, Interaction, and Profile.

Associated Types:
Text, ArchiveEntry, ArchiveFile, Document, File, SASCatalogEntry, TextStore

Top of Page