DOMLEM: R6 class representing the DOMLEM algorithm for mixed-type...

Description Details Public fields Methods

Description

The DOMLEM algorithm extracts a minimal set decision rules from an information table.

Details

This class stores methods used in extracting the decision rules. This is an extension of the original DOMLEM algorithm to consider mixed-type attributes.

Public fields

it

the information table to extract the decision rules from

P

the P-attributes

roughSets

the P-lower and P-upper approximations of the class unions

rules

the extracted decision rules

Methods

Public methods


Method new()

Create a new DOMLEM object.

Usage
DOMLEM$new(it, P)
Arguments
it

the infromation table to work on

P

the set of attributes to create the rough sets


Method main()

Main method.

Usage
DOMLEM$main()

Method findRules()

Method to extract a given type of decision rules for a given class union approximation.

Usage
DOMLEM$findRules(approximation, P, t, ruleType)
Arguments
approximation

the class union approximation to cover

P

the set of attributes used for creating the approximations

t

the t-parameter of the class union

ruleType

the type of rule to extract

Returns

the extracted decision rules


Method rulesCover()

Method to calculate the objects covered by a set of rules.

Usage
DOMLEM$rulesCover(it, rules)
Arguments
it

the infromation table to work on

rules

the set of rules

Returns

the covered objects - set of object names


Method addMinimalRules()

Method to add the minimal decision rules to the existing set of rules.

Usage
DOMLEM$addMinimalRules(existingRules, newRules)
Arguments
existingRules

the set of rules to be extended

newRules

the set of rules to be added

Returns

a set of decision rules


Method print()

print method.

Usage
DOMLEM$print()

Method toString()

toString method.

Usage
DOMLEM$toString()

Method clone()

The objects of this class are cloneable with this method.

Usage
DOMLEM$clone(deep = FALSE)
Arguments
deep

Whether to make a deep clone.


jaspeir/NIJ_Tabitha documentation built on June 3, 2020, 12:38 a.m.