nodeHarvest: Node Harvest for Regression and Classification

Node harvest is a simple interpretable tree-like estimator for high-dimensional regression and classification. A few nodes are selected from an initially large ensemble of nodes, each associated with a positive weight. New observations can fall into one or several nodes and predictions are the weighted average response across all these groups. The package offers visualization of the estimator. Predictions can return the nodes a new observation fell into, along with the mean response of training observations in each node, offering a simple explanation of the prediction.

Author
Nicolai Meinshausen
Date of publication
2015-06-12 23:29:00
Maintainer
Nicolai Meinshausen <meinshausen@stat.math.ethz.ch>
License
GPL-3
Version
0.7-3
URLs

View on CRAN

Man pages

BostonHousing
BostonHousing
nodeHarvest
Node Harvest
plot.nodeHarvest
plot method for Node Harvest objects
predict.nodeHarvest
predict method for Node Harvest objects

Files in this package

nodeHarvest
nodeHarvest/NAMESPACE
nodeHarvest/data
nodeHarvest/data/BostonHousing.rda
nodeHarvest/R
nodeHarvest/R/print.nodeHarvest.R
nodeHarvest/R/getw.R
nodeHarvest/R/getsamples.R
nodeHarvest/R/predict.nodeHarvest.R
nodeHarvest/R/nodeHarvest.R
nodeHarvest/R/makepostree.R
nodeHarvest/R/plot.nodeHarvest.R
nodeHarvest/R/getRULES.R
nodeHarvest/R/dectobin.R
nodeHarvest/R/getI.R
nodeHarvest/R/adjustmeans.R
nodeHarvest/R/makeRules.R
nodeHarvest/R/is.inf.R
nodeHarvest/R/drawtext.R
nodeHarvest/MD5
nodeHarvest/DESCRIPTION
nodeHarvest/man
nodeHarvest/man/BostonHousing.Rd
nodeHarvest/man/predict.nodeHarvest.Rd
nodeHarvest/man/nodeHarvest.Rd
nodeHarvest/man/plot.nodeHarvest.Rd