associations-class: Class associations - A Set of Associations

Description

The associations class is a virtual class which is extended to represent mining result (e.g., sets of itemsets or rules). The class provides accessors for the quality slot and a method for sorting the associations.

Arguments

Objects from the Class

A virtual class: No objects may be created from it.

Slots

quality:: a data.frame for quality measures (e.g., interest measures as support or confidence). Each quality measure is a named vector with the same length as the number of elements in the set of associations and each vector element belongs to the association with the same index.
info:: a list which is used to store algorithm specific mining information. Typically it contains a least the elements "data" (name of the transaction data set), "ntransactions" (length of the data set), "support" (the minimum support used for mining).

Methods

info<-: signature(x = "associations"); replaces the info list.
info: signature(x = "associations"); returns the info list.
items: signature(x = "associations"); dummy method. This method has to be implemented by all subclasses of associations and return the items which make up each association as an object of class itemMatrix.
labels: signature(object = "associations"); dummy method. This method has to be implemented by all subclasses of associations and return a vector of length(object) of labels for the elements in the association.
length: signature(x = "associations"); dummy method. This method has to be implemented by all subclasses of associations and return the number of elements in the association.
quality<-: signature(x = "associations"); replaces the quality data.frame. The lengths of the vectors in the data.frame have to equal the number of associations in the set.
quality: signature(x = "associations"); returns the quality data.frame.
show: signature(object = "associations")

Subclasses

itemsets-class, rules-class

Details

The implementations of associations store itemsets (e.g., the LHS and RHS of a rule) as objects of class itemMatrix (i.e., sparse binary matrices). Quality measures (e.g., support) are stored in a data.frame accessible via method quality.

Associations can store multisets with duplicated elements. Duplicated elements can result from combining several sets of associations. Use unique to remove duplicate associations.