steprfAVIPredictors: Extract names of the selected predictive variables by steprf

In steprf: Stepwise Predictive Variable Selection for Random Forest

Extract names of the selected predictive variables by steprf

Description

This function is to extract names of the selected predictive variables by steprfAVI.

Usage

steprfAVIPredictors(steprf1, trainx)

Arguments

steprf1	a list of output of 'steprf' function.
trainx	a dataframe or matrix contains columns of predictor variables.

Value

A list with the following components: 1) variables.most.accurate: a list of predictive variables contained in the most accurate RF model, 2) PABV: a list of predictive variables with positive contributions to the predictive accuracy of RF models, that is, predictive accuracy boosting variable (PABV), 3) PARV: a list of predictive variables with negative contributions to the predictive accuracy of RF models, that is, predictive accuracy reducing variable, and 4) max.predictive.accuracy: the predictive accuracy of the most accurate RF model.

Author(s)

Jin Li

References

Li, J. (2022). Spatial Predictive Modeling with R. Boca Raton, Chapman and Hall/CRC.

Li, J. (2019). "A critical review of spatial predictive modeling process in environmental sciences with reproducible examples in R." Applied Sciences 9: 2048.

Li, J., Siwabessy, J., Huang, Z., and Nichol, S. (2019). "Developing an optimal spatial predictive model for seabed sand content using machine learning, geostatistics and their hybrid methods." Geosciences 9 (4):180.

Examples

library(spm)
data(petrel)
set.seed(1234)
steprf1 <- steprfAVI(trainx = petrel[, c(1,2, 6:9)], trainy = petrel[, 5],
 nsim = 10, min.n.var = 2)

steprfAVIPredictors(steprf1, trainx = petrel[, c(1,2, 6:9)])

steprf documentation built on June 29, 2022, 5:06 p.m.