RoughSets (version 1.0-0)

FS.permutation.heuristic.reduct.RST: The permutation heuristic algorithm for determining a reduct

Description

It is a function implementing the permutation heuristic approach based on RST.

Usage

FS.permutation.heuristic.reduct.RST(decision.table,
    permutation = NULL, decisionIdx = ncol(decision.table),
    ...)

Arguments

decision.table

a "DecisionTable" class representing the decision table. See SF.asDecisionTable.

permutation

a value representing whether we will randomize the conditional attributes or not. The values of this parameter are NULL as default one and FALSE.

decisionIdx

an index of decision attribute. The default value is the last column of decision table.

...

other parameters.

Value

• A class "FeatureSubset" that contains the following components:
  • reduct: a list representing a single reduct. In this case, it could be a superreduct or just a subset of features.
  • type.method: a string representing the type of method which is"permutation.heuristic".
  • type.task: a string showing the type of task which is"feature selection".
  • model: a string representing the type of model. In this case, it is"RST"which means rough set theory.

Details

Basically there are two processes in this algorithm which are

• generating feature subset as superreduct: In this step, we choose a subset of attributes by evaluating the discernibility relation of pairs of objects.
• eliminating feature subset to obtain a reduct: we iterate over the superreduct resulting from the previous process. Then, an attribute that isdispensablein the subset is eliminated along iteration.

The detail of the algorithm can be seen in (A. Janusz and D. Slezak, 2012).

Additionally, SF.applyDecTable has been provided to generate new decision table.

References

A. Janusz and D. Slezak, "Utilization of Attribute Clustering Methods for Scalable Computation of Reducts from High-Dimensional Data" Proceedings of Federated Conference on Computer Science and Information Systems - FedCSIS, p. 295 - 302 (2012).

See Also

FS.quickreduct.RST and FS.reduct.computation.

Examples

###################################################
## Example 1: Generate reduct and new decision table
###################################################
data(RoughSetData)
decision.table <- RoughSetData$hiring.dt

## generate single reduct
res.1 <- FS.permutation.heuristic.reduct.RST(decision.table,  permutation = NULL,
                        decisionIdx = 5)

## generate new decision table according to the reduct
new.decTable <- SF.applyDecTable(decision.table, res.1)