phi: Relevance function.

In UBL: An Implementation of Re-Sampling Approaches to Utility-Based Learning for Both Classification and Regression Tasks

Relevance function.

Description

This function allows to obtain the relevance function values on a set of target variable values given the interpolating points.

Usage

phi(y, control.parms)

Arguments

y	The target variable values of the problem.
control.parms	A named list supplied by the phi.control function with the parameters needed for obtaining the relevance values.

Details

The phi function specifies the regions of interest in the target variable. It does so by performing a Monotone Cubic Spline Interpolation over a set of maximum and minimum relevance points. The notion of relevance can be associated with rarity. Nonetheless, this notion may depend on the domain experts knowledge.

Value

The function returns the relevance values.

Author(s)

Rita Ribeiro [e-mail], Paula Branco [e-mail], and Luis Torgo [e-mail]

References

Ribeiro, R., 2011. Utility-based regression (Doctoral dissertation, PhD thesis, Dep. Computer Science, Faculty of Sciences - University of Porto).

Fritsch, F.N. and Carlson, R.E., 1980. Monotone piecewise cubic interpolation. SIAM Journal on Numerical Analysis, 17(2), pp.238-246.

See Also

phi.control

Examples

# example of a relevance function where the extremes are the important values.
data(morley)
# the target variable
y <- morley$Speed

phiF.args <- phi.control(y,method="extremes",extr.type="both")
y.phi <- phi(y, control.parms=phiF.args)
plot(y, y.phi)

UBL documentation built on Oct. 8, 2023, 1:07 a.m.