GitHub - YCSGP/viRandomForests: Variable importance-weighted Random Forests (viRandomForests) is an R package, which samples features according to their variable importance scores, and then selects the best split from the randomly selected features, to improved prediction accuracy in the presence of weak signals and large noises.

YCSGP / viRandomForests Public

Notifications You must be signed in to change notification settings
Fork 0
Star 0

Variable importance-weighted Random Forests (viRandomForests) is an R package, which samples features according to their variable importance scores, and then selects the best split from the randomly selected features, to improved prediction accuracy in the presence of weak signals and large noises.

0 stars 0 forks Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 1 Commit
readme.txt		readme.txt
viRandomForests-manual.pdf		viRandomForests-manual.pdf
viRandomForests_1.0.tar.gz		viRandomForests_1.0.tar.gz

Repository files navigation

Variable Importance-Weighted Random Forests

This is an R package for variable importance-weighted Random Forests. We modified the original R randomForest package to enable a weighted random feature sampling in Random Forests.

To install the package, type
"install.packages("viRandomForests_1.0.tar.gz")"
in R.

Instructions for functions included in this package can be found in "viRandomForests-manual.pdf".