Mell {GTbasedIM} | R Documentation |
Mell Function: Subset Data Based on Group Index Conditions
Description
The Mell
function computes equation (1) in page 9 of Davila-Pena et al. (2024)
when the dependency is positive and features are binary. It filters rows from Xdata
and Ydata
based on specific conditions
of features' dependency as defined by index
. It selects rows where the values
of features within the same union, except for those in union ell
, coincide.
Usage
Mell(Xdata, Ydata, index, ell)
Arguments
Xdata |
Matrix. A dataset where rows represent observations and columns represent features. |
Ydata |
Vector. The response variable associated with each row in |
index |
Vector. A grouping vector that assigns each feature in |
ell |
Integer. The index of the union to exclude from the comparison. |
Details
The Mell
function iterates through each row of Xdata
and compares the values of features
within predefined unions (determined by index
). For each union, excluding the one specified
by ell
, the function checks if all feature values in that union coincide.
If this condition is satisfied for all unions except ell
, the row is selected.
Value
A list containing the following components:
- Xdata.ell
A subset of
Xdata
that meets the specified group conditions.- Ydata.ell
The corresponding values from
Ydata
for the selected rows inXdata.ell
.- n.user.ell
The number of selected rows that meet the group condition.
References
Davila-Pena, L., Saavedra-Nieves, A., & Casas-Méndez, B. (2024). On the influence of dependent features in classification problems: a game-theoretic perspective. arXiv preprint. doi:10.48550/arXiv.2408.02481.
Examples
# Example usage from Example 5.2 in Davila-Pena et al. (2024):
library(CoopGame)
n.user <- 16
Xdata <- createBitMatrix(4)[,-5]
Xdata <- rbind(c(0,0,0,0),Xdata)
Ydata <- rep(0,n.user)
Ydata[1+c(10,11,13,14,15)] <- 1
# Scenario 1:
Mell(Xdata = Xdata, Ydata = Ydata, index = c(1,2,3,4), ell = 3)
# Scenario 9:
Mell(Xdata = Xdata, Ydata = Ydata, index = c(1,2,1,2), ell = 2)