Every data set used in the package has to be in DecisionTable format. Let dt.ex1

be our data set:

R> dt.ex1 <- data.frame(c(1,0,2,1,1,2,2,0), c(0.5,1.2,0.1,1.2,0.4,2.2,1.1,

+ 1.5), c(2,1,0,0,2,0,1,1), c(0,2,1,2,1,1,2,1))

R> colnames(dt.ex1) <- c("a", "b", "c", "d")

the following code showing how to construct DecisionTable of dt.ex1. It should be noted that in case we want to build a decision table, we have to define an index of the decision attribute. However, if we construct an information system, we must omit the decision.attr parameter. The indx.nominal parameter is used to define indexes included as nominal values. We strongly recommend that this parameter is defined by users manually even though we provide a heuristic technique to determine whether they are nominal or continuous values.

R> DecTable.1 <- SF.asDecisionTable(dataset = dt.ex1, decision.attr = 4,

+ indx.nominal = c(1,3:4))

We can see DecTable.1 by typing:

R> print.default(DecTable.1)

$a

[1] 1 0 2 1 1 2 2 0

$b

[1] 0.5 1.2 0.1 1.2 0.4 2.2 1.1 1.5

$c

[1] 2 1 0 0 2 0 1 1

$d

[1] 0 2 1 2 1 1 2 1

attr(,"class")

[1] "DecisionTable" "data.frame"

attr(,"nominal.attrs")

[1] TRUE FALSE TRUE TRUE

attr(,"desc.attrs")

attr(,"desc.attrs")$a

[1] "0" "1" "2"

attr(,"desc.attrs")$b

[1] 0.1 2.2

attr(,"desc.attrs")$c

[1] "0" "1" "2"

attr(,"desc.attrs")$d

[1] "0" "1" "2"

attr(,"decision.attr")

[1] 4