LogicForest (version 2.1.0)

persistence.plot: Plot Persistence of a Variable of Interaction

Description

Plot the persistence of a particular variable or interaction term in a logic forest.

Usage

persistence.plot(fit, preds, PI, title)

Arguments

fit

an object of class logforest.

preds

a numeric value representing the number of predictors in the original data used to construct the logic forest model.

PI

a character string representing the variable or interaction term to be plotted.

title

an optional title for the plot

Value

PI.

Details

Persistence plots can be generated for any variable or interaction term that occurs in a logic forest or LBoost model. Plots can also be generated for variables and interaction terms that do not occur in the model exactly as given in the argument PI assuming that at least one subset match for that variable/interaction exists.

References

Wolf, B.J., Slate, E.H., Hill, E.G. (2010) Logic Forest: An ensemble classifier for discovering logical combinations of binary markers. Bioinformatics.

See Also

vimp.plot, submatch.plot

Examples

data(logforest.fit, LBoost.fit)

#Persistence of the predictor X5 in the logic forest model logforest.fit
persistence.plot(fit=logforest.fit, preds=50, PI="X5",
title="logforest Persistence for X5")
#Same plot for the LBoost model LBoost.fit
persistence.plot(fit=LBoost.fit, preds=50, PI="X5",
                 title="LBoost Persistence for X5")

#Persistence of the interaction term (X4 & X5) in the logic forest model 
#logforest.fit
persistence.plot(fit=logforest.fit, preds=50, PI="X4 & X5",
                 title="logforest Persistence for interaction X4 & X5")

#Same plot for the LBoost model LBoost.fit
persistence.plot(fit=LBoost.fit, preds=50, PI="X4 & X5",  
                 title="LBoost persistence for interaction X4 & X5")