# ggRandomForests: Visually Exploring Random Forests

[![active](https://www.repostatus.org/badges/latest/active.svg)](https://www.repostatus.org/badges/latest/active.svg)

[![R-CMD-check](https://github.com/ehrlinger/ggRandomForests/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/ehrlinger/ggRandomForests/actions/workflows/R-CMD-check.yaml)
[![lint](https://github.com/ehrlinger/ggRandomForests/actions/workflows/lint.yaml/badge.svg)](https://github.com/ehrlinger/ggRandomForests/actions/workflows/lint.yaml)
[![pkgdown](https://github.com/ehrlinger/ggRandomForests/actions/workflows/pkgdown.yaml/badge.svg)](https://github.com/ehrlinger/ggRandomForests/actions/workflows/pkgdown.yaml)
[![Codecov test
coverage](https://codecov.io/gh/ehrlinger/ggRandomForests/graph/badge.svg)](https://app.codecov.io/gh/ehrlinger/ggRandomForests)

[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.11526.svg)](https://doi.org/10.5281/zenodo.11526)

![ggRandomForests overview: predicted survival, variable importance, OOB
error, and partial dependence](reference/figures/README-overview.png)

`ggRandomForests` provides `ggplot2`-based diagnostic and exploration
plots for random forests. It reads `rfsrc` fits from
[randomForestSRC::rfsrc()](https://cran.r-project.org/package=randomForestSRC),
`varpro` fits from
[varPro::varpro()](https://cran.r-project.org/package=varPro), and `rhf`
fits from
[randomForestRHF::rhf()](https://cran.r-project.org/package=randomForestRHF),
a random-hazard forest for time-to-event data whose predictor values can
change during follow-up. It also supports `randomForest` fits. Supported
minimum versions are randomForestSRC 3.4.0, varPro 3.1.0, and
randomForestRHF 2.0.0. The package keeps the data step apart from the
figure step, so you can inspect, save, or reuse the tidy object on its
own.

Listed in the [ggplot2 extensions
gallery](https://exts.ggplot2.tidyverse.org/).

## Installation

``` r

# CRAN (stable)
install.packages("ggRandomForests")

# Development version from GitHub
# install.packages("remotes")
remotes::install_github("ehrlinger/ggRandomForests")
```

## Quick start

``` r

library(randomForestSRC)
library(ggRandomForests)

# 1. Fit a forest (regression)
rf <- rfsrc(medv ~ ., data = MASS::Boston, importance = TRUE)

# 2. Check convergence: did the forest grow enough trees?
plot(gg_error(rf))

# 3. Rank predictors by importance
plot(gg_vimp(rf))

# 4. Marginal dependence for top variables
gg_v <- gg_variable(rf)
plot(gg_v, xvar = "lstat")
plot(gg_v, xvar = rf$xvar.names, panel = TRUE, se = FALSE)

# 5. Partial dependence for a single predictor
pv <- plot.variable(rf, xvar.names = "lstat", partial = TRUE, show.plots = FALSE)
pd <- gg_partial(pv)
plot(pd)
```

For survival forests, see the package vignette:

``` r

vignette("ggRandomForests")
```

For Random Hazard Forests with predictors that change during follow-up,
see the RHF vignette:

``` r

vignette("rhf", package = "ggRandomForests")
```

For variable importance with varPro (partial dependence, importance
z-scores, beta importance, individual/local importance, and isolation
forests), see the dedicated vignette:

``` r

vignette("varpro", package = "ggRandomForests")
```

The unsupervised varPro tools,
[`gg_udependent()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_udependent.md),
[`gg_beta_uvarpro()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_beta_uvarpro.md),
and
[`gg_sdependent()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_sdependent.md),
read structure off a
[`varPro::uvarpro()`](https://www.randomforestsrc.org/reference/uvarpro.html)
fit with no outcome. They have their own short vignette:

``` r

vignette("uvarpro", package = "ggRandomForests")
```

## Function reference

Grouped by what you are trying to look at. The first column is the
function you call, the second is what you hand it.

### The forest itself

| Function | Input | What you get |
|----|----|----|
| [`gg_error()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_error.md) | `rfsrc` / `randomForest` | OOB error vs. number of trees |
| [`gg_vimp()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_vimp.md) | `rfsrc` / `randomForest` | Variable importance ranking |
| [`gg_rfsrc()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_rfsrc.rfsrc.md) | `rfsrc` / `randomForest` | Predicted vs. observed values |
| [`gg_variable()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_variable.md) | `rfsrc` / `randomForest` | Marginal dependence data frame |

### Partial dependence

| Function | Input | What you get |
|----|----|----|
| [`gg_partial()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_partial.md) | `plot.variable` output | Partial dependence (continuous + categorical) |
| [`gg_partial_rfsrc()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_partial_rfsrc.md) | `rfsrc` model | Partial dependence via `partial.rfsrc` |
| [`surv_partial.rfsrc()`](https://ehrlinger.github.io/ggRandomForests/reference/surv_partial.rfsrc.md) | `rfsrc` survival forest | Survival partial dependence, one or more predictors |
| [`quantile_pts()`](https://ehrlinger.github.io/ggRandomForests/reference/quantile_pts.md) | numeric vector | Quantile cut points for coplot panels |

### Survival

| Function | Input | What you get |
|----|----|----|
| [`gg_survival()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_survival.md) | `rfsrc` survival forest, or a data frame | Kaplan–Meier / Nelson–Aalen estimates |
| [`gg_brier()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_brier.md) | `rfsrc` (survival) | Time-resolved Brier score and CRPS |
| [`kaplan()`](https://ehrlinger.github.io/ggRandomForests/reference/kaplan.md) | data frame + interval/censor columns | Nonparametric Kaplan–Meier estimate |
| [`nelson()`](https://ehrlinger.github.io/ggRandomForests/reference/nelson.md) | data frame + interval/censor columns | Nonparametric Nelson–Aalen estimate |

### Classification and ROC

| Function | Input | What you get |
|----|----|----|
| [`gg_roc()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_roc.rfsrc.md) | `rfsrc` / `randomForest` (class) | ROC curve data |
| [`calc_roc()`](https://ehrlinger.github.io/ggRandomForests/reference/calc_roc.rfsrc.md) | `rfsrc` / `randomForest` (class) | The sensitivity/specificity sweep behind [`gg_roc()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_roc.rfsrc.md) |
| [`calc_auc()`](https://ehrlinger.github.io/ggRandomForests/reference/calc_auc.md) | `gg_roc` object | Area under the curve |

### Random Hazard Forests

For time-to-event data with predictors that change during follow-up,
these read an `rhf` fit or a saved tree-size tuning object. A hazard is
the event-risk rate at a particular time.

| Function | Input | What you get |
|----|----|----|
| [`gg_rhf()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_rhf.md) | `rhf` fit | Case-specific hazard or cumulative-hazard curves |
| [`gg_auct()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_auct.md) | `rhf` fit | Time-varying AUC curve for event-risk discrimination |
| [`gg_rhf_importance()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_rhf_importance.md) | `rhf` fit | Variable-priority matrix across time windows |
| [`gg_tune_rhf()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_tune_rhf.md) | `tune.treesize.rhf` object | Inspected tree-size tuning path |

### varPro (variable priority)

These read a `varpro` fit rather than a forest.
[`varPro::varpro()`](https://www.randomforestsrc.org/reference/varpro.html)
is the supervised fit;
[`varPro::uvarpro()`](https://www.randomforestsrc.org/reference/uvarpro.html)
is the unsupervised one, which needs no outcome.

| Function | Input | What you get |
|----|----|----|
| [`gg_varpro()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_varpro.md) | `varpro` fit | Release-rule variable importance |
| [`gg_beta_varpro()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_beta_varpro.md) | `varpro` fit | Per-variable lasso-beta importance |
| [`gg_ivarpro()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_ivarpro.md) | `varpro` fit | Individual (local) variable importance |
| [`gg_partial_varpro()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_partial_varpro.md) | `varpro` fit | Partial dependence (alias: [`gg_partialpro()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_partial_varpro.md)) |
| [`gg_isopro()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_isopro.md) | `isopro` fit | Isolation-forest anomaly scores |
| [`gg_udependent()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_udependent.md) | `uvarpro` fit | Variable dependency graph |
| [`gg_beta_uvarpro()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_beta_uvarpro.md) | `uvarpro` fit | Per-variable lasso-beta importance |
| [`gg_sdependent()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_sdependent.md) | `uvarpro` fit | Signal-variable detection |
| [`varpro_feature_names()`](https://ehrlinger.github.io/ggRandomForests/reference/varpro_feature_names.md) | character vector | Original names behind one-hot encoded features |
| [`varpro_coverage()`](https://ehrlinger.github.io/ggRandomForests/reference/varpro_coverage.md) | `varpro` fit | Share of trees that tested each variable, next to its z |

### SHAP

| Function | Input | What you get |
|----|----|----|
| [`gg_shap()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_shap.md) | `rfsrc` / `randomForest` | Shapley additive explanation values |
| [`shap_importance()`](https://ehrlinger.github.io/ggRandomForests/reference/shap_importance.md) | `gg_shap` object | Global importance bar chart |
| [`shap_beeswarm()`](https://ehrlinger.github.io/ggRandomForests/reference/shap_beeswarm.md) | `gg_shap` object | Beeswarm summary plot |
| [`shap_dependence()`](https://ehrlinger.github.io/ggRandomForests/reference/shap_dependence.md) | `gg_shap` object | Dependence plot for one predictor |

Each `gg_*` function has a matching
[`plot()`](https://rdrr.io/r/graphics/plot.default.html) S3 method that
hands back a single plottable object: a `ggplot` you extend with `+`, or
a `patchwork` composite for the multi-panel methods. Every `gg_*` object
also has [`print()`](https://rdrr.io/r/base/print.html) and
[`summary()`](https://rdrr.io/r/base/summary.html) methods:
[`print()`](https://rdrr.io/r/base/print.html) shows a short header at
the REPL rather than dumping every row (use
[`head()`](https://rdrr.io/r/utils/head.html) when you want the rows),
and [`summary()`](https://rdrr.io/r/base/summary.html) gives you a
diagnostics object you can print or keep.

## Why ggRandomForests?

The package is built on one decision: keep the data step and the figure
step apart. The `gg_*` functions pull a tidy data object out of the
forest; the [`plot()`](https://rdrr.io/r/graphics/plot.default.html)
methods turn that object into a `ggplot2` figure. Two things follow from
that split.

First, the data object stands on its own. It carries everything its plot
needs, so you can save it, inspect it, or come back to it later without
keeping the original forest (which can be large) in memory.

Second, you are never locked into the default figure. Because a
[`plot()`](https://rdrr.io/r/graphics/plot.default.html) method returns
a single plottable object (a `ggplot`, or a `patchwork` composite for
the multi-panel methods), you can add layers, swap scales, or apply a
theme; and if the default is not what you want, you can ignore it
entirely and build the figure from the tidy data yourself.

## Recent changes

See [NEWS.md](https://ehrlinger.github.io/ggRandomForests/NEWS.md) for
the full changelog. Recent highlights:

- **v4.0.0 (development)** Random Hazard Forests:
  [`gg_rhf()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_rhf.md)
  for case-specific event-risk curves,
  [`gg_auct()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_auct.md)
  for time-varying discrimination,
  [`gg_rhf_importance()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_rhf_importance.md)
  for variable priority across time windows, and
  [`gg_tune_rhf()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_tune_rhf.md)
  for inspecting a saved tree-size tuning path.
- **v3.5.1**
  [`gg_roc()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_roc.rfsrc.md)
  on an `rfsrc` forest now honors the documented `which_outcome = 0`,
  which had been returning an unusable two-row object;
  [`gg_partial_rfsrc()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_partial_rfsrc.md)
  rejects a non-forest with a real error instead of “argument is of
  length zero”. Also a test-only fix for the `gcc-UBSAN` report filed
  against 3.5.0.
- **v3.5.0** varPro fixes:
  [`plot.gg_varpro()`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_varpro.md)
  no longer draws a phantom “NA” category,
  [`gg_partial_varpro()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_partial_varpro.md)
  warns when you name a variable the fit cannot reach, and
  `scale = "chf"` now honors `xvar.names` instead of computing every
  variable. Vignette figures render with `ragg`, which cut the source
  tarball from 4.7 MB to 2.3 MB.
- **v3.4.0** Unsupervised varPro wrappers
  ([`gg_beta_uvarpro()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_beta_uvarpro.md),
  [`gg_sdependent()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_sdependent.md))
  with their own vignette;
  [`gg_partial_rfsrc()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_partial_rfsrc.md)
  now handles factor predictors correctly.
- **v3.3.0** varPro partial plots default to interpretable scales:
  probability for classification, survival S(τ) for survival.
- **v3.1.0** varPro integration: release-rule importance, partial
  dependence, local importance, anomaly scores, and the dependency
  graph.

## References

Breiman, L. (2001). Random forests, *Machine Learning*, 45:5–32.

Ishwaran H. and Kogalur U.B. (2026). *Fast Unified Random Forests for
Survival, Regression, and Classification (RF-SRC).* R package version
3.6.2. <https://cran.r-project.org/package=randomForestSRC>

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.

Lu M. and Ishwaran H. (2024). Model-independent variable selection via
the rule-based variable priority framework. *arXiv preprint*
arXiv:2409.09003. <https://arxiv.org/abs/2409.09003>

Ishwaran H. and Kogalur U.B. (2026). *Model-Independent Variable
Selection via the Rule-Based Variable Priority.* R package version
3.2.0. <https://cran.r-project.org/package=varPro>

Ishwaran H., Hsich E.M., Kogalur U.B. and Lee D.K.K. (2026). Random
Hazard Forests. *arXiv preprint* arXiv:2608.21597.
<https://doi.org/10.48550/arXiv.2608.21597>

Ishwaran H. and Kogalur U.B. (2026). *randomForestRHF: Random Hazard
Forests.* R package version 2.0.0.
<https://cran.r-project.org/package=randomForestRHF>

Liaw A. and Wiener M. (2002). Classification and Regression by
randomForest. *R News* 2(3), 18–22.

Wickham H. (2009). *ggplot2: Elegant Graphics for Data Analysis*.
Springer New York.

# Package index

## Forest Objects

Extract and display data from random forest objects.

- [`gg_rfsrc(`*`<rfsrc>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/gg_rfsrc.rfsrc.md)
  : Predicted response data object

- [`plot(`*`<gg_rfsrc>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_rfsrc.md)
  :

  Predicted response plot from a `gg_rfsrc` object.

## Training Error

Visualize forest convergence and training error.

- [`gg_error()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_error.md)
  : Random forest error trajectory data object

- [`plot(`*`<gg_error>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_error.md)
  :

  Plot a `gg_error` object

## Variable Importance

Assess and plot variable importance (VIMP).

- [`gg_vimp()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_vimp.md)
  : Variable Importance (VIMP) data object

- [`plot(`*`<gg_vimp>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_vimp.md)
  :

  Plot a `gg_vimp` object, extracted variable importance of a
  [`rfsrc`](https://www.randomforestsrc.org//reference/rfsrc.html)
  object

- [`gg_varpro()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_varpro.md)
  : Variable importance data from a varPro model

- [`plot(`*`<gg_varpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_varpro.md)
  :

  Plot a `gg_varpro` variable importance object

- [`gg_beta_varpro()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_beta_varpro.md)
  : Per-variable lasso-beta importance from a varPro fit

- [`plot(`*`<gg_beta_varpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_beta_varpro.md)
  :

  Plot a `gg_beta_varpro` object

- [`gg_beta_uvarpro()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_beta_uvarpro.md)
  : Per-variable lasso-beta importance from an unsupervised varPro fit

- [`plot(`*`<gg_beta_uvarpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_beta_uvarpro.md)
  :

  Plot a `gg_beta_uvarpro` object

- [`gg_udependent()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_udependent.md)
  : Variable dependency graph from a uvarpro model

- [`plot(`*`<gg_udependent>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_udependent.md)
  :

  Plot a `gg_udependent` variable dependency graph

- [`gg_sdependent()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_sdependent.md)
  : Signal-variable detection from an unsupervised varPro fit

- [`plot(`*`<gg_sdependent>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_sdependent.md)
  :

  Plot a `gg_sdependent` object

- [`gg_ivarpro()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_ivarpro.md)
  : Individual (local) variable importance from a varPro fit

- [`plot(`*`<gg_ivarpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_ivarpro.md)
  :

  Plot a `gg_ivarpro` object

## SHAP Analysis

Per-observation additive SHAP explanations for regression and
classification forests.

- [`gg_shap()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_shap.md)
  : SHAP (Shapley additive explanations) data object

- [`plot(`*`<gg_shap>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_shap.md)
  :

  Plot a `gg_shap` object

- [`shap_importance()`](https://ehrlinger.github.io/ggRandomForests/reference/shap_importance.md)
  : SHAP global importance bar chart

- [`shap_beeswarm()`](https://ehrlinger.github.io/ggRandomForests/reference/shap_beeswarm.md)
  : SHAP beeswarm summary plot

- [`shap_dependence()`](https://ehrlinger.github.io/ggRandomForests/reference/shap_dependence.md)
  : SHAP dependence plot

## Anomaly Detection

Score and plot per-observation anomaly scores.

- [`gg_isopro()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_isopro.md)
  : Tidy data from a varPro isolation-forest fit
- [`plot(`*`<gg_isopro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_isopro.md)
  : Plot a varPro isolation-forest anomaly score

## Variable Dependence

Marginal variable dependence plots.

- [`gg_variable()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_variable.md)
  : Marginal variable dependence data object.

- [`plot(`*`<gg_variable>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_variable.md)
  :

  Plot a `gg_variable` object,

## Partial Dependence and Accumulated Local Effects

Marginal-effect plots for individual variables. Partial dependence
averages over the other predictors; accumulated local effects perturb a
predictor only within neighbourhoods of its own observed values, and so
do not extrapolate when predictors are correlated.

- [`gg_partial()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_partial.md)
  : Split partial dependence data into continuous or categorical
  datasets

- [`plot(`*`<gg_partial>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_partial.md)
  :

  Plot a `gg_partial` object

- [`gg_partial_rfsrc()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_partial_rfsrc.md)
  : Partial dependence data from an rfsrc model

- [`plot(`*`<gg_partial_rfsrc>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_partial_rfsrc.md)
  :

  Plot a `gg_partial_rfsrc` object

- [`gg_partial_varpro()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_partial_varpro.md)
  [`gg_partialpro()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_partial_varpro.md)
  : Partial dependence data from a varPro model

- [`plot(`*`<gg_partialpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_partial_varpro.md)
  [`plot(`*`<gg_partial_varpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_partial_varpro.md)
  :

  Plot a `gg_partial_varpro` object

- [`gg_ale_rfsrc()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_ale_rfsrc.md)
  : Accumulated Local Effects (ALE) data from an rfsrc model

- [`plot(`*`<gg_ale_rfsrc>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_ale_rfsrc.md)
  :

  Plot a `gg_ale_rfsrc` object

- [`plot(`*`<gg_ale_interaction>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_ale_interaction.md)
  :

  Plot a `gg_ale_rfsrc` interaction object

## Survival Analysis

Survival curves, ROC, and related diagnostics.

- [`gg_survival()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_survival.md)
  : Nonparametric survival estimates.

- [`plot(`*`<gg_survival>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_survival.md)
  :

  Plot a `gg_survival` object.

- [`gg_roc(`*`<rfsrc>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/gg_roc.rfsrc.md)
  : ROC (Receiver Operating Characteristic) curve data from a
  classification forest.

- [`plot(`*`<gg_roc>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_roc.md)
  :

  ROC plot generic function for a `gg_roc` object.

- [`calc_roc(`*`<rfsrc>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/calc_roc.rfsrc.md)
  : Receiver Operator Characteristic calculator

- [`calc_auc()`](https://ehrlinger.github.io/ggRandomForests/reference/calc_auc.md)
  : Area Under the ROC Curve calculator

- [`surv_partial.rfsrc()`](https://ehrlinger.github.io/ggRandomForests/reference/surv_partial.rfsrc.md)
  : Survival partial dependence data for one or more predictors

- [`kaplan()`](https://ehrlinger.github.io/ggRandomForests/reference/kaplan.md)
  : nonparametric Kaplan-Meier estimates

- [`nelson()`](https://ehrlinger.github.io/ggRandomForests/reference/nelson.md)
  : nonparametric Nelson-Aalen estimates

- [`gg_brier()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_brier.md)
  : Brier score and CRPS for survival forests

- [`plot(`*`<gg_brier>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_brier.md)
  :

  Plot a `gg_brier` object

## Random Hazard Forests

For time-to-event data with predictors that change during follow-up.

- [`gg_rhf()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_rhf.md)
  : Tidy hazard and cumulative-hazard curves from a Random Hazard Forest
- [`plot(`*`<gg_rhf>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_rhf.md)
  : Plot Random Hazard Forest hazard / cumulative-hazard curves
- [`gg_auct()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_auct.md)
  : Tidy time-varying AUC from a Random Hazard Forest
- [`plot(`*`<gg_auct>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_auct.md)
  : Plot a time-varying AUC curve
- [`gg_rhf_importance()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_rhf_importance.md)
  : Tidy time-localized variable priority from a Random Hazard Forest
- [`plot(`*`<gg_rhf_importance>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_rhf_importance.md)
  : Plot Random Hazard Forest variable priority over time
- [`gg_tune_rhf()`](https://ehrlinger.github.io/ggRandomForests/reference/gg_tune_rhf.md)
  : Tidy a Random Hazard Forest tuning path
- [`plot(`*`<gg_tune_rhf>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/plot.gg_tune_rhf.md)
  : Plot a Random Hazard Forest tuning path

## S3 Methods

Standard R generics implemented for all gg\_\* data objects.

- [`autoplot(`*`<gg_error>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_vimp>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_rfsrc>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_variable>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_partial>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_partial_rfsrc>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_partialpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_partial_varpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_roc>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_survival>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_brier>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_rhf>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_tune_rhf>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_auct>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_rhf_importance>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_varpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_udependent>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_isopro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_shap>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_ale_rfsrc>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  [`autoplot(`*`<gg_ale_interaction>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/autoplot.gg.md)
  :

  `autoplot` methods for ggRandomForests data objects

- [`print(`*`<gg_beta_uvarpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_sdependent>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_error>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_vimp>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_rfsrc>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_variable>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_partial>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_partial_rfsrc>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_partialpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_partial_varpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_roc>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_survival>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_brier>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_rhf>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_tune_rhf>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_auct>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_rhf_importance>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_udependent>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<summary.gg_udependent>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_varpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_isopro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_beta_varpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_ivarpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_shap>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_ale_rfsrc>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  [`print(`*`<gg_ale_interaction>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/print.gg.md)
  : Print methods for gg\_\* data objects

- [`summary(`*`<gg_beta_uvarpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_sdependent>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`print(`*`<summary.gg>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_error>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_vimp>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_rfsrc>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_variable>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_partial>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_partial_rfsrc>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_partialpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_partial_varpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_roc>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_survival>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_varpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_udependent>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_brier>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_rhf>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_tune_rhf>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_rhf_importance>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_isopro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_beta_varpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_ivarpro>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_auct>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_shap>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_ale_rfsrc>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  [`summary(`*`<gg_ale_interaction>`*`)`](https://ehrlinger.github.io/ggRandomForests/reference/summary.gg.md)
  : Summary methods for gg\_\* data objects

## Utilities

Helper functions used internally and by users.

- [`quantile_pts()`](https://ehrlinger.github.io/ggRandomForests/reference/quantile_pts.md)
  : Quantile-based cut points for coplots
- [`varpro_feature_names()`](https://ehrlinger.github.io/ggRandomForests/reference/varpro_feature_names.md)
  : Recover original variable names from varpro one-hot encoded feature
  names
- [`varpro_coverage()`](https://ehrlinger.github.io/ggRandomForests/reference/varpro_coverage.md)
  : How well a varpro fit tested each variable

## Package

- [`ggRandomForests-package`](https://ehrlinger.github.io/ggRandomForests/reference/ggRandomForests-package.md)
  : ggRandomForests: Visually Exploring Random Forests

# Articles

### Get started

- [Exploring Random Forests with
  ggRandomForests](https://ehrlinger.github.io/ggRandomForests/articles/ggRandomForests.md):

### Tutorials

- [Random Forest Survival Analysis with
  ggRandomForests](https://ehrlinger.github.io/ggRandomForests/articles/ggRandomForests-survival.md):
- [Random Hazard Forests with
  ggRandomForests](https://ehrlinger.github.io/ggRandomForests/articles/rhf.md):
- [Random Forest Regression with
  ggRandomForests](https://ehrlinger.github.io/ggRandomForests/articles/ggRandomForests-regression.md):
- [Random Forest Classification with
  ggRandomForests](https://ehrlinger.github.io/ggRandomForests/articles/ggRandomForests-classification.md):
- [Explaining a forest: five views of a variable's
  effect](https://ehrlinger.github.io/ggRandomForests/articles/explainability.md):
- [Exploring variable importance with
  varPro](https://ehrlinger.github.io/ggRandomForests/articles/varpro.md):
- [varPro on small or sparse
  data](https://ehrlinger.github.io/ggRandomForests/articles/varpro-small-data.md):
- [Variable selection without an outcome: unsupervised
  varPro](https://ehrlinger.github.io/ggRandomForests/articles/uvarpro.md):