ggRandomForests is a utility package for randomForestSRC
(Iswaran et.al. 2014, 2008, 2007) for survival, regression and
classification forests and uses the ggplot2 (Wickham 2009) package for plotting results.
ggRandomForests is structured to extract data objects from the random forest
and provides S3 functions for printing and plotting these objects.The randomForestSRC package provides a unified treatment of Breiman's (2001) random
forests for a variety of data settings. Regression and
classification forests are grown when the response is numeric or categorical
(factor) while survival and competing risk forests (Ishwaran et al. 2008, 2012)
are grown for right-censored survival data.
Many of the figures created by the ggRandomForests package are also available
directly from within the randomForestSRC package. However, ggRandomForests offers the
following advantages:
ggRandomForestcontains functions that
operate on either therandomForestSRC::rfsrcforest object directly, or on
the output fromrandomForestSRCpost processing functions (i.e.plot.variable,var.select,find.interaction) to
generate intermediateggRandomForestsdata objects. S3 functions are provide to
further process these objects and plot results using theggplot2graphics package.
Alternatively, users can use these data objects for additional custom plotting or
analysis operations.ggplot2objects to meet users specific
needs and requirements.ggplot2for plotting. We chose to use theggplot2package
for our figures to allow users flexibility in modifying the figures to their liking. Each S3
plot function returns either a singleggplot2object, or alistofggplot2objects, allowing users to use additionalggplot2functions or themes
to modify and customise the figures to their liking.The ggRandomForests package contains the following data functions:
gg_rfsrc: randomForest[SRC] predictions.gg_error: randomForest[SRC] convergence rate based on the OOB error rate.gg_roc: ROC curves for randomForest classification models.gg_vimp: Variable Importance ranking for variable selection.gg_minimal_depth: Minimal Depth ranking for variable selection
(Ishwaran et.al. 2010).gg_minimal_vimp: Comparing Minimal Depth and VIMP rankings for variable
selection.gg_interaction: Minimal Depth interaction detection (Ishwaran et.al. 2010)gg_variable: Marginal variable dependence.gg_partial: Partial (risk adjusted) variable dependence.gg_partial_coplot: Partial variable conditional dependence
(computationally expensive).gg_survival: Kaplan-Meier/Nelson-Aalon hazard analysis.Each of these data functions has an associated S3 plot function that returns ggplot2 objects, either
individually or as a list, which can be further customised using standard ggplot2 commands.
Ishwaran H. and Kogalur U.B. (2014). Random Forests for Survival, Regression and Classification (RF-SRC), R package version 1.5.5.12.
Ishwaran H. and Kogalur U.B. (2007). Random survival forests for R. R News 7(2), 25--31.
Ishwaran H., Kogalur U.B., Blackstone E.H. and Lauer M.S. (2008). Random survival forests. Ann. Appl. Statist. 2(3), 841--860.
Ishwaran, H., U. B. Kogalur, E. Z. Gorodeski, A. J. Minn, and M. S. Lauer (2010). High-dimensional variable selection for survival data. J. Amer. Statist. Assoc. 105, 205-217.
Ishwaran, H. (2007). Variable importance in binary regression trees and forests. Electronic J. Statist., 1, 519-537.
Wickham, H. ggplot2: elegant graphics for data analysis. Springer New York, 2009.