generateTupelData {impimp}

Tuple representation

Description

Generating a tuple representation of a data.frame with imprecise observations

Usage

generateTupelData(data, constraints = NULL)

Arguments

data

a data.frame object, with potentially imprecise entries; see 'Note'.

constraints

a list of so-called logical constraints or fixed zeros. Each element must be an object of class "impimp_event". See 'Details'.

Details

By specifying constraints one can exlude combinations of imputed values which are deemed impossible, so called ‘logical constraints’ or ‘fixed zeros’.

Value

A list of length NROW(data) of data.frames for the observation within the original data.frame.

Each such data.frame contains the precise observations which are compatible with its imprecise representation.

Note

No sanity check is performed on whether data actually contains imprecise observations or is in the form for denoting imprecision throughoutly used in the impimp-package. A warning is triggered if it is not of class "impimp".

See Also

impimp, impimp_event for sepcifying the constraints

Examples

A <- data.frame(x1 = c(1,0), x2 = c(0,0),
                y1 = c(1,0), y2 = c(2,2))
B <- data.frame(x1 = c(1,1,0), x2 = c(0,0,0),
                z1 = c(0,1,1), z2 = c(0,1,2))
AimpB <- impimp(A, B, method = "domain")

## no constraints
generateTupelData(AimpB)

## (y1,z1) = (0,0) as constraint
generateTupelData(AimpB, list(impimp_event(y1 = 0, z1 = 0)))


data(iris)
generateTupelData(iris) # emits a warning