Skip to contents

Predicted response data object

Source: R/gg_rfsrc.R
gg_rfsrc.rfsrc.Rd

Extracts the predicted response values from the rfsrc object, and formats data for plotting the response using plot.gg_rfsrc.

Usage

# S3 method for class 'rfsrc'
gg_rfsrc(object, oob = TRUE, by, ...)

Arguments

object

rfsrc object

oob

boolean, should we return the oob prediction , or the full forest prediction.

by

stratifying variable in the training dataset, defaults to NULL

...

extra arguments

Value

gg_rfsrc object

Details

surv_type ("surv", "chf", "mortality", "hazard") for survival forests

oob boolean, should we return the oob prediction , or the full forest prediction.

See also

plot.gg_rfsrc rfsrc plot.rfsrc gg_survival

#' @examples ## ———————————————————— ## classification example ## ———————————————————— ## ——– iris data rfsrc_iris <- rfsrc(Species ~ ., data = iris) gg_dta<- gg_rfsrc(rfsrc_iris)

plot(gg_dta)

## ———————————————————— ## Regression example ## ————————————————————

## ——– air quality data rfsrc_airq <- rfsrc(Ozone ~ ., data = airquality, na.action = "na.impute") gg_dta<- gg_rfsrc(rfsrc_airq)

plot(gg_dta)

## ——– Boston data data(Boston, package = "MASS") Boston$chas <- as.logical(Boston$chas) rfsrc_boston <- rfsrc(medv ~ ., data = Boston, forest = TRUE, importance = TRUE, tree.err = TRUE, save.memory = TRUE)

plot(gg_rfsrc(rfsrc_boston))

### randomForest example data(Boston, package="MASS") rf_boston <- randomForest::randomForest(medv ~ ., data = Boston) plot(gg_rfsrc(rf_boston))

## ——– mtcars data rfsrc_mtcars <- rfsrc(mpg ~ ., data = mtcars) gg_dta<- gg_rfsrc(rfsrc_mtcars)

plot(gg_dta)

## ———————————————————— ## Survival example ## ———————————————————— ## ——– veteran data ## randomized trial of two treatment regimens for lung cancer data(veteran, package = "randomForestSRC") rfsrc_veteran <- rfsrc(Surv(time, status) ~ ., data = veteran, ntree = 100)

gg_dta <- gg_rfsrc(rfsrc_veteran) plot(gg_dta)

gg_dta <- gg_rfsrc(rfsrc_veteran, conf.int=.95) plot(gg_dta)

gg_dta <- gg_rfsrc(rfsrc_veteran, by="trt") plot(gg_dta)

## ——– pbc data ## We don't run this because of bootstrap confidence limits # We need to create this dataset data(pbc, package = "randomForestSRC",) # For whatever reason, the age variable is in days... makes no sense to me #Convert age to years pbc$age <- pbc$age / 364.24

pbc$years <- pbc$days / 364.24 pbc <- pbc[, -which(colnames(pbc) == "days")] pbc$treatment <- as.numeric(pbc$treatment) pbc$treatment[which(pbc$treatment == 1)] <- "DPCA" pbc$treatment[which(pbc$treatment == 2)] <- "placebo" pbc$treatment <- factor(pbc$treatment) dta_train <- pbc[-which(is.na(pbc$treatment)), ] # Create a test set from the remaining patients pbc_test <- pbc[which(is.na(pbc$treatment)), ]

#======== # build the forest: rfsrc_pbc <- randomForestSRC::rfsrc( Surv(years, status) ~ ., dta_train, nsplit = 10, na.action = "na.impute", forest = TRUE, importance = TRUE, save.memory = TRUE ) gg_dta <- gg_rfsrc(rfsrc_pbc) plot(gg_dta)

gg_dta <- gg_rfsrc(rfsrc_pbc, conf.int=.95) plot(gg_dta)

gg_dta <- gg_rfsrc(rfsrc_pbc, by="treatment") plot(gg_dta)